Coverage report: 15%

Files Functions Classes

coverage.py v7.6.9, created at 2026-03-12 02:21 +0800

File function statements missing excluded coverage
src/flag_gems/__init__.py torch_ge 1 1 0 0%
src/flag_gems/__init__.py enable 3 0 0 100%
src/flag_gems/__init__.py only_enable 6 2 0 67%
src/flag_gems/__init__.py use_gems.__init__ 7 0 0 100%
src/flag_gems/__init__.py use_gems.__enter__ 3 0 0 100%
src/flag_gems/__init__.py use_gems.__exit__ 9 0 0 100%
src/flag_gems/__init__.py use_gems.experimental_ops 2 2 0 0%
src/flag_gems/__init__.py all_registered_ops 1 1 0 0%
src/flag_gems/__init__.py all_registered_keys 1 1 0 0%
src/flag_gems/__init__.py (no function) 40 1 0 98%
src/flag_gems/config.py load_enable_config_from_yaml 19 10 0 47%
src/flag_gems/config.py get_default_enable_config 9 9 0 0%
src/flag_gems/config.py resolve_user_setting 18 3 0 83%
src/flag_gems/config.py (no function) 31 11 2 65%
src/flag_gems/experimental_ops/__init__.py (no function) 2 0 0 100%
src/flag_gems/experimental_ops/_adaptive_avg_pool3d.py adaptive_avg_pool3d_kernel 55 55 0 0%
src/flag_gems/experimental_ops/_adaptive_avg_pool3d.py _normalize_output_size_3d 7 7 0 0%
src/flag_gems/experimental_ops/_adaptive_avg_pool3d.py _prepare_5d_input 5 5 0 0%
src/flag_gems/experimental_ops/_adaptive_avg_pool3d.py _launch_adaptive_avg_pool3d_kernel 10 10 0 0%
src/flag_gems/experimental_ops/_adaptive_avg_pool3d.py _adaptive_avg_pool3d 9 9 0 0%
src/flag_gems/experimental_ops/_adaptive_avg_pool3d.py _adaptive_avg_pool3d_out 18 18 0 0%
src/flag_gems/experimental_ops/_adaptive_avg_pool3d.py (no function) 10 10 0 0%
src/flag_gems/experimental_ops/_functional_sym_constrain_range_for_size.py _functional_sym_constrain_range_for_size_kernel 6 6 0 0%
src/flag_gems/experimental_ops/_functional_sym_constrain_range_for_size.py _functional_sym_constrain_range_for_size 18 18 0 0%
src/flag_gems/experimental_ops/_functional_sym_constrain_range_for_size.py (no function) 6 6 0 0%
src/flag_gems/experimental_ops/_log_softmax_backward_data.py _log_softmax_bwd_kernel 22 22 0 0%
src/flag_gems/experimental_ops/_log_softmax_backward_data.py _normalize_dim 3 3 0 0%
src/flag_gems/experimental_ops/_log_softmax_backward_data.py _choose_block_size 4 4 0 0%
src/flag_gems/experimental_ops/_log_softmax_backward_data.py _log_softmax_backward_data_impl 24 24 0 0%
src/flag_gems/experimental_ops/_log_softmax_backward_data.py _log_softmax_backward_data 1 1 0 0%
src/flag_gems/experimental_ops/_log_softmax_backward_data.py _log_softmax_backward_data_out 3 3 0 0%
src/flag_gems/experimental_ops/_log_softmax_backward_data.py (no function) 11 11 0 0%
src/flag_gems/experimental_ops/_safe_softmax.py _safe_softmax 14 14 0 0%
src/flag_gems/experimental_ops/_safe_softmax.py _safe_softmax 29 29 0 0%
src/flag_gems/experimental_ops/_safe_softmax.py _safe_softmax._next_pow2 3 3 0 0%
src/flag_gems/experimental_ops/_safe_softmax.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/_unsafe_view.py _copy_1d_kernel 6 6 0 0%
src/flag_gems/experimental_ops/_unsafe_view.py _infer_view_size 36 36 0 0%
src/flag_gems/experimental_ops/_unsafe_view.py _launch_copy_kernel 7 7 0 0%
src/flag_gems/experimental_ops/_unsafe_view.py _unsafe_view 6 6 0 0%
src/flag_gems/experimental_ops/_unsafe_view.py _unsafe_view_out 12 12 0 0%
src/flag_gems/experimental_ops/_unsafe_view.py (no function) 9 9 0 0%
src/flag_gems/experimental_ops/_upsample_nearest_exact1d.py _upsample_nearest_exact1d_kernel 20 20 0 0%
src/flag_gems/experimental_ops/_upsample_nearest_exact1d.py _parse_size_1d 9 9 0 0%
src/flag_gems/experimental_ops/_upsample_nearest_exact1d.py _parse_scale_1d 7 7 0 0%
src/flag_gems/experimental_ops/_upsample_nearest_exact1d.py _compute_out_w 5 5 0 0%
src/flag_gems/experimental_ops/_upsample_nearest_exact1d.py _launch_upsample_nearest_exact1d_kernel 14 14 0 0%
src/flag_gems/experimental_ops/_upsample_nearest_exact1d.py _extract_io_and_params 30 30 0 0%
src/flag_gems/experimental_ops/_upsample_nearest_exact1d.py _prepare_out_tensor 9 9 0 0%
src/flag_gems/experimental_ops/_upsample_nearest_exact1d.py _upsample_nearest_exact1d 5 5 0 0%
src/flag_gems/experimental_ops/_upsample_nearest_exact1d.py _upsample_nearest_exact1d_out 9 9 0 0%
src/flag_gems/experimental_ops/_upsample_nearest_exact1d.py _upsample_nearest_exact1d_vec 5 5 0 0%
src/flag_gems/experimental_ops/_upsample_nearest_exact1d.py (no function) 15 15 0 0%
src/flag_gems/experimental_ops/abs.py _abs_kernel_real 7 7 0 0%
src/flag_gems/experimental_ops/abs.py _abs_kernel_complex 9 9 0 0%
src/flag_gems/experimental_ops/abs.py _ensure_cuda_tensor 5 5 0 0%
src/flag_gems/experimental_ops/abs.py _complex_abs_out_dtype 7 7 0 0%
src/flag_gems/experimental_ops/abs.py _launch_abs_real 6 6 0 0%
src/flag_gems/experimental_ops/abs.py _launch_abs_complex 13 13 0 0%
src/flag_gems/experimental_ops/abs.py abs 13 13 0 0%
src/flag_gems/experimental_ops/abs.py abs_out 28 28 0 0%
src/flag_gems/experimental_ops/abs.py (no function) 13 13 0 0%
src/flag_gems/experimental_ops/abs_.py abs_ 7 7 0 0%
src/flag_gems/experimental_ops/abs_.py abs_ 18 18 0 0%
src/flag_gems/experimental_ops/abs_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/absolute.py _absolute_kernel 9 9 0 0%
src/flag_gems/experimental_ops/absolute.py _absolute_complex_kernel 9 9 0 0%
src/flag_gems/experimental_ops/absolute.py absolute 12 12 0 0%
src/flag_gems/experimental_ops/absolute.py absolute_out 15 15 0 0%
src/flag_gems/experimental_ops/absolute.py (no function) 9 9 0 0%
src/flag_gems/experimental_ops/absolute_.py absolute_ 7 7 0 0%
src/flag_gems/experimental_ops/absolute_.py absolute_ 20 20 0 0%
src/flag_gems/experimental_ops/absolute_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/addcdiv.py addcdiv_kernel 10 10 0 0%
src/flag_gems/experimental_ops/addcdiv.py _prepare_addcdiv_tensors 10 10 0 0%
src/flag_gems/experimental_ops/addcdiv.py _launch_addcdiv 11 11 0 0%
src/flag_gems/experimental_ops/addcdiv.py addcdiv 4 4 0 0%
src/flag_gems/experimental_ops/addcdiv.py addcdiv_out 17 17 0 0%
src/flag_gems/experimental_ops/addcdiv.py (no function) 9 9 0 0%
src/flag_gems/experimental_ops/addcmul_.py addcmul_ 13 13 0 0%
src/flag_gems/experimental_ops/addcmul_.py addcmul_ 40 40 0 0%
src/flag_gems/experimental_ops/addcmul_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/alias_copy.py _alias_copy_kernel 6 6 0 0%
src/flag_gems/experimental_ops/alias_copy.py alias_copy 16 16 0 0%
src/flag_gems/experimental_ops/alias_copy.py alias_copy_out 17 17 0 0%
src/flag_gems/experimental_ops/alias_copy.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/amin.py amin_reduce_last_kernel 12 12 0 0%
src/flag_gems/experimental_ops/amin.py _prod 1 1 0 0%
src/flag_gems/experimental_ops/amin.py _parse_dims 15 15 0 0%
src/flag_gems/experimental_ops/amin.py _amin_impl 58 58 0 0%
src/flag_gems/experimental_ops/amin.py amin 14 14 0 0%
src/flag_gems/experimental_ops/amin.py amin_out 23 23 0 0%
src/flag_gems/experimental_ops/amin.py (no function) 12 12 0 0%
src/flag_gems/experimental_ops/arccosh.py arccosh_kernel 10 10 0 0%
src/flag_gems/experimental_ops/arccosh.py arccosh 8 8 0 0%
src/flag_gems/experimental_ops/arccosh.py arccosh_out 13 13 0 0%
src/flag_gems/experimental_ops/arccosh.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/arcsinh.py arcsinh_kernel 10 10 0 0%
src/flag_gems/experimental_ops/arcsinh.py _ensure_cuda_tensor 6 6 0 0%
src/flag_gems/experimental_ops/arcsinh.py _arcsinh_impl 22 22 0 0%
src/flag_gems/experimental_ops/arcsinh.py arcsinh 1 1 0 0%
src/flag_gems/experimental_ops/arcsinh.py arcsinh_out 1 1 0 0%
src/flag_gems/experimental_ops/arcsinh.py (no function) 9 9 0 0%
src/flag_gems/experimental_ops/arcsinh_.py arcsinh_ 11 11 0 0%
src/flag_gems/experimental_ops/arcsinh_.py arcsinh_ 12 12 0 0%
src/flag_gems/experimental_ops/arcsinh_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/arctanh.py arctanh_kernel 10 10 0 0%
src/flag_gems/experimental_ops/arctanh.py _launch_arctanh 16 16 0 0%
src/flag_gems/experimental_ops/arctanh.py arctanh 3 3 0 0%
src/flag_gems/experimental_ops/arctanh.py arctanh_out 2 2 0 0%
src/flag_gems/experimental_ops/arctanh.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/arctanh_.py arctanh_ 17 17 0 0%
src/flag_gems/experimental_ops/arctanh_.py arctanh_ 19 19 0 0%
src/flag_gems/experimental_ops/arctanh_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/asinh_.py asinh_ 11 11 0 0%
src/flag_gems/experimental_ops/asinh_.py asinh_ 27 27 0 0%
src/flag_gems/experimental_ops/asinh_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/atanh_.py atanh_ 11 11 0 0%
src/flag_gems/experimental_ops/atanh_.py atanh_ 16 16 0 0%
src/flag_gems/experimental_ops/atanh_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/celu.py celu_kernel 9 9 0 0%
src/flag_gems/experimental_ops/celu.py _parse_alpha 8 8 0 0%
src/flag_gems/experimental_ops/celu.py celu 15 15 0 0%
src/flag_gems/experimental_ops/celu.py celu_out 27 27 0 0%
src/flag_gems/experimental_ops/celu.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/celu_.py celu_ 11 11 0 0%
src/flag_gems/experimental_ops/celu_.py celu_ 6 6 0 0%
src/flag_gems/experimental_ops/celu_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/copy_.py _tl_dtype_from_torch 19 19 0 0%
src/flag_gems/experimental_ops/copy_.py _copy_kernel 7 7 0 0%
src/flag_gems/experimental_ops/copy_.py _fill_kernel 6 6 0 0%
src/flag_gems/experimental_ops/copy_.py _launch_copy_tensor 8 8 0 0%
src/flag_gems/experimental_ops/copy_.py _launch_fill_scalar 10 10 0 0%
src/flag_gems/experimental_ops/copy_.py copy_ 7 7 0 0%
src/flag_gems/experimental_ops/copy_.py copy__Tensor 1 1 0 0%
src/flag_gems/experimental_ops/copy_.py copy__int 1 1 0 0%
src/flag_gems/experimental_ops/copy_.py copy__float 1 1 0 0%
src/flag_gems/experimental_ops/copy_.py (no function) 14 14 0 0%
src/flag_gems/experimental_ops/cos_.py cos_ 9 9 0 0%
src/flag_gems/experimental_ops/cos_.py cos_ 12 12 0 0%
src/flag_gems/experimental_ops/cos_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/cosh_.py cosh_ 10 10 0 0%
src/flag_gems/experimental_ops/cosh_.py cosh_ 15 15 0 0%
src/flag_gems/experimental_ops/cosh_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/deg2rad.py deg2rad_kernel 7 7 0 0%
src/flag_gems/experimental_ops/deg2rad.py _launch_deg2rad_kernel 7 7 0 0%
src/flag_gems/experimental_ops/deg2rad.py deg2rad 21 21 0 0%
src/flag_gems/experimental_ops/deg2rad.py deg2rad_out 31 31 0 0%
src/flag_gems/experimental_ops/deg2rad.py (no function) 9 9 0 0%
src/flag_gems/experimental_ops/deg2rad_.py deg2rad_ 8 8 0 0%
src/flag_gems/experimental_ops/deg2rad_.py deg2rad_ 19 19 0 0%
src/flag_gems/experimental_ops/deg2rad_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/diag.py _diag_extract_kernel 7 7 0 0%
src/flag_gems/experimental_ops/diag.py _diag_write_kernel 7 7 0 0%
src/flag_gems/experimental_ops/diag.py diag 34 34 0 0%
src/flag_gems/experimental_ops/diag.py diag_out 55 55 0 0%
src/flag_gems/experimental_ops/diag.py (no function) 9 9 0 0%
src/flag_gems/experimental_ops/digamma_.py digamma_ 27 27 0 0%
src/flag_gems/experimental_ops/digamma_.py digamma_ 20 20 0 0%
src/flag_gems/experimental_ops/digamma_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/elu.py elu_kernel 11 11 0 0%
src/flag_gems/experimental_ops/elu.py _parse_elu_args 22 22 0 0%
src/flag_gems/experimental_ops/elu.py _parse_elu_args._get_scalar 5 5 0 0%
src/flag_gems/experimental_ops/elu.py _launch_elu_kernel 12 12 0 0%
src/flag_gems/experimental_ops/elu.py elu 4 4 0 0%
src/flag_gems/experimental_ops/elu.py elu_out 5 5 0 0%
src/flag_gems/experimental_ops/elu.py (no function) 9 9 0 0%
src/flag_gems/experimental_ops/erf_.py erf_ 14 14 0 0%
src/flag_gems/experimental_ops/erf_.py erf_ 22 22 0 0%
src/flag_gems/experimental_ops/erf_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/erfinv.py erfinv_kernel 44 44 0 0%
src/flag_gems/experimental_ops/erfinv.py _launch_erfinv_kernel 7 7 0 0%
src/flag_gems/experimental_ops/erfinv.py erfinv 8 8 0 0%
src/flag_gems/experimental_ops/erfinv.py erfinv_out 11 11 0 0%
src/flag_gems/experimental_ops/erfinv.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/erfinv_.py erfinv_ 27 27 0 0%
src/flag_gems/experimental_ops/erfinv_.py erfinv_ 12 12 0 0%
src/flag_gems/experimental_ops/erfinv_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/exp2.py exp2_kernel 7 7 0 0%
src/flag_gems/experimental_ops/exp2.py exp2 11 11 0 0%
src/flag_gems/experimental_ops/exp2.py exp2_out 17 17 0 0%
src/flag_gems/experimental_ops/exp2.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/exp2_.py exp2_ 10 10 0 0%
src/flag_gems/experimental_ops/exp2_.py exp2_ 13 13 0 0%
src/flag_gems/experimental_ops/exp2_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/exp_.py exp_ 9 9 0 0%
src/flag_gems/experimental_ops/exp_.py exp_ 16 16 0 0%
src/flag_gems/experimental_ops/exp_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/expand.py expand 13 13 0 0%
src/flag_gems/experimental_ops/expand.py expand 48 48 0 0%
src/flag_gems/experimental_ops/expand.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/eye.py eye_kernel 11 11 0 0%
src/flag_gems/experimental_ops/eye.py _eye_impl 28 28 0 0%
src/flag_gems/experimental_ops/eye.py eye 1 1 0 0%
src/flag_gems/experimental_ops/eye.py eye_m 1 1 0 0%
src/flag_gems/experimental_ops/eye.py eye_out 1 1 0 0%
src/flag_gems/experimental_ops/eye.py eye_m_out 1 1 0 0%
src/flag_gems/experimental_ops/eye.py (no function) 10 10 0 0%
src/flag_gems/experimental_ops/fft_ifftshift.py fft_ifftshift 26 26 0 0%
src/flag_gems/experimental_ops/fft_ifftshift.py fft_ifftshift 42 42 0 0%
src/flag_gems/experimental_ops/fft_ifftshift.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/fix.py _fix_trunc_kernel 11 11 0 0%
src/flag_gems/experimental_ops/fix.py _copy_kernel 6 6 0 0%
src/flag_gems/experimental_ops/fix.py _launch_fix_kernel 9 9 0 0%
src/flag_gems/experimental_ops/fix.py fix 5 5 0 0%
src/flag_gems/experimental_ops/fix.py fix_out 5 5 0 0%
src/flag_gems/experimental_ops/fix.py (no function) 10 10 0 0%
src/flag_gems/experimental_ops/fix_.py fix_ 15 15 0 0%
src/flag_gems/experimental_ops/fix_.py fix_ 17 17 0 0%
src/flag_gems/experimental_ops/fix_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/floor_.py floor_ 15 15 0 0%
src/flag_gems/experimental_ops/floor_.py floor_ 22 22 0 0%
src/flag_gems/experimental_ops/floor_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/fmin.py fmin_kernel 8 8 0 0%
src/flag_gems/experimental_ops/fmin.py _to_tensor 8 8 0 0%
src/flag_gems/experimental_ops/fmin.py _prepare_inputs 21 21 0 0%
src/flag_gems/experimental_ops/fmin.py fmin 13 13 0 0%
src/flag_gems/experimental_ops/fmin.py fmin_out 23 23 0 0%
src/flag_gems/experimental_ops/fmin.py (no function) 9 9 0 0%
src/flag_gems/experimental_ops/frac.py frac_kernel 20 20 0 0%
src/flag_gems/experimental_ops/frac.py _launch_frac 20 20 0 0%
src/flag_gems/experimental_ops/frac.py frac 3 3 0 0%
src/flag_gems/experimental_ops/frac.py frac_out 4 4 0 0%
src/flag_gems/experimental_ops/frac.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/gelu_.py gelu_ 35 35 0 0%
src/flag_gems/experimental_ops/gelu_.py gelu_ 32 32 0 0%
src/flag_gems/experimental_ops/gelu_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/glu.py glu_kernel 23 23 0 0%
src/flag_gems/experimental_ops/glu.py _normalize_dim 6 6 0 0%
src/flag_gems/experimental_ops/glu.py _check_dtype_supported 2 2 0 0%
src/flag_gems/experimental_ops/glu.py _glu_launch 32 32 0 0%
src/flag_gems/experimental_ops/glu.py glu 1 1 0 0%
src/flag_gems/experimental_ops/glu.py glu_out 3 3 0 0%
src/flag_gems/experimental_ops/glu.py (no function) 11 11 0 0%
src/flag_gems/experimental_ops/hardshrink.py hardshrink_kernel 9 9 0 0%
src/flag_gems/experimental_ops/hardshrink.py _hardshrink_launch 9 9 0 0%
src/flag_gems/experimental_ops/hardshrink.py hardshrink 4 4 0 0%
src/flag_gems/experimental_ops/hardshrink.py hardshrink_out 14 14 0 0%
src/flag_gems/experimental_ops/hardshrink.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/hardsigmoid.py hardsigmoid_kernel 10 10 0 0%
src/flag_gems/experimental_ops/hardsigmoid.py hardsigmoid 6 6 0 0%
src/flag_gems/experimental_ops/hardsigmoid.py hardsigmoid_out 6 6 0 0%
src/flag_gems/experimental_ops/hardsigmoid.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/hardsigmoid_.py hardsigmoid_ 10 10 0 0%
src/flag_gems/experimental_ops/hardsigmoid_.py hardsigmoid_ 20 20 0 0%
src/flag_gems/experimental_ops/hardsigmoid_.py hardsigmoid_.launch 5 5 0 0%
src/flag_gems/experimental_ops/hardsigmoid_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/hardswish.py hardswish_kernel 14 14 0 0%
src/flag_gems/experimental_ops/hardswish.py _launch_hardswish 5 5 0 0%
src/flag_gems/experimental_ops/hardswish.py _parse_input_tensor 7 7 0 0%
src/flag_gems/experimental_ops/hardswish.py _parse_out_tensor 5 5 0 0%
src/flag_gems/experimental_ops/hardswish.py _ensure_cuda_tensor 4 4 0 0%
src/flag_gems/experimental_ops/hardswish.py _hardswish_impl 20 20 0 0%
src/flag_gems/experimental_ops/hardswish.py hardswish 2 2 0 0%
src/flag_gems/experimental_ops/hardswish.py hardswish_out 4 4 0 0%
src/flag_gems/experimental_ops/hardswish.py (no function) 13 13 0 0%
src/flag_gems/experimental_ops/hardswish_.py hardswish_ 13 13 0 0%
src/flag_gems/experimental_ops/hardswish_.py hardswish_ 22 22 0 0%
src/flag_gems/experimental_ops/hardswish_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/hardtanh.py hardtanh_kernel 11 11 0 0%
src/flag_gems/experimental_ops/hardtanh.py _launch_hardtanh 10 10 0 0%
src/flag_gems/experimental_ops/hardtanh.py hardtanh 6 6 0 0%
src/flag_gems/experimental_ops/hardtanh.py hardtanh_out 14 14 0 0%
src/flag_gems/experimental_ops/hardtanh.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/hardtanh_.py hardtanh_ 10 10 0 0%
src/flag_gems/experimental_ops/hardtanh_.py hardtanh_ 34 34 0 0%
src/flag_gems/experimental_ops/hardtanh_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/heaviside.py _heaviside_kernel 12 12 0 0%
src/flag_gems/experimental_ops/heaviside.py heaviside 11 11 0 0%
src/flag_gems/experimental_ops/heaviside.py heaviside_out 23 23 0 0%
src/flag_gems/experimental_ops/heaviside.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/heaviside_.py heaviside_ 11 11 0 0%
src/flag_gems/experimental_ops/heaviside_.py heaviside_ 17 17 0 0%
src/flag_gems/experimental_ops/heaviside_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/huber_loss.py huber_loss_element_kernel 12 12 0 0%
src/flag_gems/experimental_ops/huber_loss.py reduce_sum_kernel 8 8 0 0%
src/flag_gems/experimental_ops/huber_loss.py _normalize_reduction 14 14 0 0%
src/flag_gems/experimental_ops/huber_loss.py huber_loss 23 23 0 0%
src/flag_gems/experimental_ops/huber_loss.py huber_loss_out 35 35 0 0%
src/flag_gems/experimental_ops/huber_loss.py (no function) 10 10 0 0%
src/flag_gems/experimental_ops/hypot.py _torch_dtype_to_triton 9 9 0 0%
src/flag_gems/experimental_ops/hypot.py _hypot_kernel 17 17 0 0%
src/flag_gems/experimental_ops/hypot.py _infer_hypot_out_dtype 5 5 0 0%
src/flag_gems/experimental_ops/hypot.py _launch_hypot_kernel 13 13 0 0%
src/flag_gems/experimental_ops/hypot.py hypot 12 12 0 0%
src/flag_gems/experimental_ops/hypot.py hypot_out 10 10 0 0%
src/flag_gems/experimental_ops/hypot.py (no function) 10 10 0 0%
src/flag_gems/experimental_ops/hypot_.py hypot_ 11 11 0 0%
src/flag_gems/experimental_ops/hypot_.py hypot_ 38 38 0 0%
src/flag_gems/experimental_ops/hypot_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/i0.py i0_kernel 16 16 0 0%
src/flag_gems/experimental_ops/i0.py _launch_i0 19 19 0 0%
src/flag_gems/experimental_ops/i0.py i0 6 6 0 0%
src/flag_gems/experimental_ops/i0.py i0_out 8 8 0 0%
src/flag_gems/experimental_ops/i0.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/i0_.py i0_ 16 16 0 0%
src/flag_gems/experimental_ops/i0_.py i0_ 21 21 0 0%
src/flag_gems/experimental_ops/i0_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/im2col.py im2col_kernel 32 32 0 0%
src/flag_gems/experimental_ops/im2col.py _parse_2tuple 5 5 0 0%
src/flag_gems/experimental_ops/im2col.py _compute_output_dims 3 3 0 0%
src/flag_gems/experimental_ops/im2col.py _launch_im2col_kernel 15 15 0 0%
src/flag_gems/experimental_ops/im2col.py im2col 18 18 0 0%
src/flag_gems/experimental_ops/im2col.py im2col_out 31 31 0 0%
src/flag_gems/experimental_ops/im2col.py (no function) 10 10 0 0%
src/flag_gems/experimental_ops/leaky_relu.py _leaky_relu_kernel 9 9 0 0%
src/flag_gems/experimental_ops/leaky_relu.py _launch_leaky_relu_kernel 14 14 0 0%
src/flag_gems/experimental_ops/leaky_relu.py leaky_relu 2 2 0 0%
src/flag_gems/experimental_ops/leaky_relu.py leaky_relu_out 3 3 0 0%
src/flag_gems/experimental_ops/leaky_relu.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/leaky_relu_.py leaky_relu_ 7 7 0 0%
src/flag_gems/experimental_ops/leaky_relu_.py leaky_relu_ 30 30 0 0%
src/flag_gems/experimental_ops/leaky_relu_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/lift.py _copy_kernel 6 6 0 0%
src/flag_gems/experimental_ops/lift.py lift 10 10 0 0%
src/flag_gems/experimental_ops/lift.py lift_out 15 15 0 0%
src/flag_gems/experimental_ops/lift.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/lift_fresh_copy.py _copy_kernel 6 6 0 0%
src/flag_gems/experimental_ops/lift_fresh_copy.py lift_fresh_copy 19 19 0 0%
src/flag_gems/experimental_ops/lift_fresh_copy.py lift_fresh_copy_out 19 19 0 0%
src/flag_gems/experimental_ops/lift_fresh_copy.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/log10_.py log10_ 9 9 0 0%
src/flag_gems/experimental_ops/log10_.py log10_ 22 22 0 0%
src/flag_gems/experimental_ops/log10_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/log1p_.py log1p_ 9 9 0 0%
src/flag_gems/experimental_ops/log1p_.py log1p_ 20 20 0 0%
src/flag_gems/experimental_ops/log1p_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/log2_.py log2_ 10 10 0 0%
src/flag_gems/experimental_ops/log2_.py log2_ 20 20 0 0%
src/flag_gems/experimental_ops/log2_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/log_.py log_ 9 9 0 0%
src/flag_gems/experimental_ops/log_.py log_ 18 18 0 0%
src/flag_gems/experimental_ops/log_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/logaddexp.py logaddexp_kernel 14 14 0 0%
src/flag_gems/experimental_ops/logaddexp.py _ensure_cuda_tensor 3 3 0 0%
src/flag_gems/experimental_ops/logaddexp.py _common_float_dtype 4 4 0 0%
src/flag_gems/experimental_ops/logaddexp.py _launch_logaddexp_kernel 10 10 0 0%
src/flag_gems/experimental_ops/logaddexp.py logaddexp 16 16 0 0%
src/flag_gems/experimental_ops/logaddexp.py logaddexp_out 13 13 0 0%
src/flag_gems/experimental_ops/logaddexp.py (no function) 10 10 0 0%
src/flag_gems/experimental_ops/logaddexp2.py logaddexp2_kernel 12 12 0 0%
src/flag_gems/experimental_ops/logaddexp2.py _broadcast_and_check 6 6 0 0%
src/flag_gems/experimental_ops/logaddexp2.py _choose_out_dtype 7 7 0 0%
src/flag_gems/experimental_ops/logaddexp2.py _launch_kernel 5 5 0 0%
src/flag_gems/experimental_ops/logaddexp2.py logaddexp2 10 10 0 0%
src/flag_gems/experimental_ops/logaddexp2.py logaddexp2_out 18 18 0 0%
src/flag_gems/experimental_ops/logaddexp2.py (no function) 10 10 0 0%
src/flag_gems/experimental_ops/logical_xor_.py logical_xor_ 10 10 0 0%
src/flag_gems/experimental_ops/logical_xor_.py logical_xor_ 24 24 0 0%
src/flag_gems/experimental_ops/logical_xor_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/logit.py logit_kernel 11 11 0 0%
src/flag_gems/experimental_ops/logit.py _to_triton_dtype 7 7 0 0%
src/flag_gems/experimental_ops/logit.py _logit_impl 50 50 0 0%
src/flag_gems/experimental_ops/logit.py logit 1 1 0 0%
src/flag_gems/experimental_ops/logit.py logit_out 3 3 0 0%
src/flag_gems/experimental_ops/logit.py (no function) 9 9 0 0%
src/flag_gems/experimental_ops/logit_.py logit_ 24 24 0 0%
src/flag_gems/experimental_ops/logit_.py logit_ 30 30 0 0%
src/flag_gems/experimental_ops/logit_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/margin_ranking_loss.py margin_ranking_loss 13 13 0 0%
src/flag_gems/experimental_ops/margin_ranking_loss.py margin_ranking_loss 48 48 0 0%
src/flag_gems/experimental_ops/margin_ranking_loss.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/masked_scatter.py _masked_scatter_count_kernel 8 8 0 0%
src/flag_gems/experimental_ops/masked_scatter.py _masked_scatter_apply_kernel 15 15 0 0%
src/flag_gems/experimental_ops/masked_scatter.py _launch_masked_scatter 40 40 0 0%
src/flag_gems/experimental_ops/masked_scatter.py masked_scatter 1 1 0 0%
src/flag_gems/experimental_ops/masked_scatter.py masked_scatter_out 1 1 0 0%
src/flag_gems/experimental_ops/masked_scatter.py (no function) 10 10 0 0%
src/flag_gems/experimental_ops/masked_select.py _masked_select_count_kernel 7 7 0 0%
src/flag_gems/experimental_ops/masked_select.py _masked_select_scatter_kernel 12 12 0 0%
src/flag_gems/experimental_ops/masked_select.py _prepare_broadcast_flatten 7 7 0 0%
src/flag_gems/experimental_ops/masked_select.py masked_select 22 22 0 0%
src/flag_gems/experimental_ops/masked_select.py masked_select_out 27 27 0 0%
src/flag_gems/experimental_ops/masked_select.py (no function) 10 10 0 0%
src/flag_gems/experimental_ops/maximum.py maximum_kernel 28 28 0 0%
src/flag_gems/experimental_ops/maximum.py _as_tensor_on_device 3 3 0 0%
src/flag_gems/experimental_ops/maximum.py _broadcast_to_common 2 2 0 0%
src/flag_gems/experimental_ops/maximum.py _pad_shape_strides 9 9 0 0%
src/flag_gems/experimental_ops/maximum.py _launch_maximum_kernel 14 14 0 0%
src/flag_gems/experimental_ops/maximum.py maximum 18 18 0 0%
src/flag_gems/experimental_ops/maximum.py maximum_out 16 16 0 0%
src/flag_gems/experimental_ops/maximum.py (no function) 13 13 0 0%
src/flag_gems/experimental_ops/mse_loss.py _mse_elemwise_kernel 9 9 0 0%
src/flag_gems/experimental_ops/mse_loss.py _mse_reduce_kernel 11 11 0 0%
src/flag_gems/experimental_ops/mse_loss.py _parse_reduction 12 12 0 0%
src/flag_gems/experimental_ops/mse_loss.py _ensure_supported_dtype 2 2 0 0%
src/flag_gems/experimental_ops/mse_loss.py _launch_mse_elemwise 4 4 0 0%
src/flag_gems/experimental_ops/mse_loss.py _launch_mse_reduce 5 5 0 0%
src/flag_gems/experimental_ops/mse_loss.py mse_loss 32 32 0 0%
src/flag_gems/experimental_ops/mse_loss.py mse_loss_out 46 46 0 0%
src/flag_gems/experimental_ops/mse_loss.py (no function) 13 13 0 0%
src/flag_gems/experimental_ops/multiply.py _multiply_tt_kernel 7 7 0 0%
src/flag_gems/experimental_ops/multiply.py _multiply_ts_kernel 6 6 0 0%
src/flag_gems/experimental_ops/multiply.py _broadcast_shape 1 1 0 0%
src/flag_gems/experimental_ops/multiply.py _result_dtype_for 3 3 0 0%
src/flag_gems/experimental_ops/multiply.py _ensure_cuda_device 2 2 0 0%
src/flag_gems/experimental_ops/multiply.py _launch_tt 5 5 0 0%
src/flag_gems/experimental_ops/multiply.py _launch_ts 5 5 0 0%
src/flag_gems/experimental_ops/multiply.py _multiply_impl 42 42 0 0%
src/flag_gems/experimental_ops/multiply.py multiply_Tensor 1 1 0 0%
src/flag_gems/experimental_ops/multiply.py multiply_Scalar 1 1 0 0%
src/flag_gems/experimental_ops/multiply.py multiply_out 1 1 0 0%
src/flag_gems/experimental_ops/multiply.py (no function) 17 17 0 0%
src/flag_gems/experimental_ops/mv.py mv_kernel 11 11 0 0%
src/flag_gems/experimental_ops/mv.py _launch_mv_kernel 4 4 0 0%
src/flag_gems/experimental_ops/mv.py mv 16 16 0 0%
src/flag_gems/experimental_ops/mv.py mv_out 19 19 0 0%
src/flag_gems/experimental_ops/mv.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/native_dropout_backward.py _native_dropout_backward_kernel 8 8 0 0%
src/flag_gems/experimental_ops/native_dropout_backward.py _launch_native_dropout_backward 17 17 0 0%
src/flag_gems/experimental_ops/native_dropout_backward.py native_dropout_backward 2 2 0 0%
src/flag_gems/experimental_ops/native_dropout_backward.py native_dropout_backward_out 2 2 0 0%
src/flag_gems/experimental_ops/native_dropout_backward.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/neg_.py neg__kernel 7 7 0 0%
src/flag_gems/experimental_ops/neg_.py neg_ 19 19 0 0%
src/flag_gems/experimental_ops/neg_.py (no function) 6 6 0 0%
src/flag_gems/experimental_ops/negative.py negative_kernel 6 6 0 0%
src/flag_gems/experimental_ops/negative.py _launch_negative 12 12 0 0%
src/flag_gems/experimental_ops/negative.py negative 3 3 0 0%
src/flag_gems/experimental_ops/negative.py negative_out 2 2 0 0%
src/flag_gems/experimental_ops/negative.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/negative_.py negative_ 7 7 0 0%
src/flag_gems/experimental_ops/negative_.py negative_ 11 11 0 0%
src/flag_gems/experimental_ops/negative_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/permute.py permute_kernel 15 15 0 0%
src/flag_gems/experimental_ops/permute.py permute 43 43 0 0%
src/flag_gems/experimental_ops/permute.py (no function) 6 6 0 0%
src/flag_gems/experimental_ops/permute_copy.py permute_copy_kernel 20 20 0 0%
src/flag_gems/experimental_ops/permute_copy.py _normalize_dims 15 15 0 0%
src/flag_gems/experimental_ops/permute_copy.py _launch_permute_copy 28 28 0 0%
src/flag_gems/experimental_ops/permute_copy.py permute_copy 1 1 0 0%
src/flag_gems/experimental_ops/permute_copy.py permute_copy_out 1 1 0 0%
src/flag_gems/experimental_ops/permute_copy.py (no function) 9 9 0 0%
src/flag_gems/experimental_ops/pixel_shuffle.py pixel_shuffle_kernel 35 35 0 0%
src/flag_gems/experimental_ops/pixel_shuffle.py _check_and_get_shapes_strides 13 13 0 0%
src/flag_gems/experimental_ops/pixel_shuffle.py _launch_pixel_shuffle_kernel 9 9 0 0%
src/flag_gems/experimental_ops/pixel_shuffle.py pixel_shuffle 8 8 0 0%
src/flag_gems/experimental_ops/pixel_shuffle.py pixel_shuffle_out 12 12 0 0%
src/flag_gems/experimental_ops/pixel_shuffle.py (no function) 9 9 0 0%
src/flag_gems/experimental_ops/pixel_unshuffle.py pixel_unshuffle_kernel 28 28 0 0%
src/flag_gems/experimental_ops/pixel_unshuffle.py _launch_pixel_unshuffle_kernel 18 18 0 0%
src/flag_gems/experimental_ops/pixel_unshuffle.py pixel_unshuffle 12 12 0 0%
src/flag_gems/experimental_ops/pixel_unshuffle.py pixel_unshuffle_out 16 16 0 0%
src/flag_gems/experimental_ops/pixel_unshuffle.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/prelu.py prelu 12 12 0 0%
src/flag_gems/experimental_ops/prelu.py prelu 40 40 0 0%
src/flag_gems/experimental_ops/prelu.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/rad2deg_.py rad2deg__kernel 7 7 0 0%
src/flag_gems/experimental_ops/rad2deg_.py rad2deg_ 23 23 0 0%
src/flag_gems/experimental_ops/rad2deg_.py (no function) 6 6 0 0%
src/flag_gems/experimental_ops/reciprocal.py reciprocal_kernel 8 8 0 0%
src/flag_gems/experimental_ops/reciprocal.py _reciprocal_impl 19 19 0 0%
src/flag_gems/experimental_ops/reciprocal.py reciprocal 7 7 0 0%
src/flag_gems/experimental_ops/reciprocal.py reciprocal_out 13 13 0 0%
src/flag_gems/experimental_ops/reciprocal.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/reciprocal_.py reciprocal_ 7 7 0 0%
src/flag_gems/experimental_ops/reciprocal_.py reciprocal_ 10 10 0 0%
src/flag_gems/experimental_ops/reciprocal_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/reflection_pad1d.py _reflection_pad1d_kernel 14 14 0 0%
src/flag_gems/experimental_ops/reflection_pad1d.py _copy_rows_kernel 7 7 0 0%
src/flag_gems/experimental_ops/reflection_pad1d.py _launch_reflection_pad1d 41 41 0 0%
src/flag_gems/experimental_ops/reflection_pad1d.py reflection_pad1d 1 1 0 0%
src/flag_gems/experimental_ops/reflection_pad1d.py reflection_pad1d_out 1 1 0 0%
src/flag_gems/experimental_ops/reflection_pad1d.py (no function) 11 11 0 0%
src/flag_gems/experimental_ops/relu.py relu_kernel 11 11 0 0%
src/flag_gems/experimental_ops/relu.py relu 22 22 0 0%
src/flag_gems/experimental_ops/relu.py (no function) 6 6 0 0%
src/flag_gems/experimental_ops/relu6.py relu6 8 8 0 0%
src/flag_gems/experimental_ops/relu6.py relu6 11 11 0 0%
src/flag_gems/experimental_ops/relu6.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/relu_.py relu_ 8 8 0 0%
src/flag_gems/experimental_ops/relu_.py relu_ 13 13 0 0%
src/flag_gems/experimental_ops/relu_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/replication_pad1d.py replication_pad1d_kernel 15 15 0 0%
src/flag_gems/experimental_ops/replication_pad1d.py _launch_replication_pad1d_kernel 34 34 0 0%
src/flag_gems/experimental_ops/replication_pad1d.py replication_pad1d 11 11 0 0%
src/flag_gems/experimental_ops/replication_pad1d.py replication_pad1d_out 8 8 0 0%
src/flag_gems/experimental_ops/replication_pad1d.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/replication_pad2d.py replication_pad2d_kernel 28 28 0 0%
src/flag_gems/experimental_ops/replication_pad2d.py _prepare_dims_and_out 25 25 0 0%
src/flag_gems/experimental_ops/replication_pad2d.py _launch_replication_pad2d_kernel 12 12 0 0%
src/flag_gems/experimental_ops/replication_pad2d.py replication_pad2d 2 2 0 0%
src/flag_gems/experimental_ops/replication_pad2d.py replication_pad2d_out 2 2 0 0%
src/flag_gems/experimental_ops/replication_pad2d.py (no function) 9 9 0 0%
src/flag_gems/experimental_ops/replication_pad3d.py replication_pad3d_kernel 25 25 0 0%
src/flag_gems/experimental_ops/replication_pad3d.py _normalize_3d_pad 3 3 0 0%
src/flag_gems/experimental_ops/replication_pad3d.py _get_5d_shape_and_strides 13 13 0 0%
src/flag_gems/experimental_ops/replication_pad3d.py _launch_replication_pad3d_kernel 19 19 0 0%
src/flag_gems/experimental_ops/replication_pad3d.py replication_pad3d 11 11 0 0%
src/flag_gems/experimental_ops/replication_pad3d.py replication_pad3d_out 13 13 0 0%
src/flag_gems/experimental_ops/replication_pad3d.py (no function) 10 10 0 0%
src/flag_gems/experimental_ops/rmsnorm.py rmsnorm 22 22 0 0%
src/flag_gems/experimental_ops/rmsnorm.py rmsnorm 17 17 0 0%
src/flag_gems/experimental_ops/rmsnorm.py rmsnorm.next_pow2 1 1 0 0%
src/flag_gems/experimental_ops/rmsnorm.py (no function) 7 0 0 100%
src/flag_gems/experimental_ops/rrelu_with_noise_backward.py rrelu_with_noise_backward_kernel 17 17 0 0%
src/flag_gems/experimental_ops/rrelu_with_noise_backward.py _launch_rrelu_with_noise_backward 13 13 0 0%
src/flag_gems/experimental_ops/rrelu_with_noise_backward.py rrelu_with_noise_backward 2 2 0 0%
src/flag_gems/experimental_ops/rrelu_with_noise_backward.py rrelu_with_noise_backward_out 1 1 0 0%
src/flag_gems/experimental_ops/rrelu_with_noise_backward.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/rsqrt_.py rsqrt_ 9 9 0 0%
src/flag_gems/experimental_ops/rsqrt_.py rsqrt_ 22 22 0 0%
src/flag_gems/experimental_ops/rsqrt_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/selu.py selu_kernel 15 15 0 0%
src/flag_gems/experimental_ops/selu.py selu 21 21 0 0%
src/flag_gems/experimental_ops/selu.py (no function) 6 6 0 0%
src/flag_gems/experimental_ops/selu_.py selu_ 11 11 0 0%
src/flag_gems/experimental_ops/selu_.py selu_ 21 21 0 0%
src/flag_gems/experimental_ops/selu_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/sgn.py sgn_real_kernel 10 10 0 0%
src/flag_gems/experimental_ops/sgn.py sgn_complex_kernel 16 16 0 0%
src/flag_gems/experimental_ops/sgn.py _sgn_impl 16 16 0 0%
src/flag_gems/experimental_ops/sgn.py sgn 5 5 0 0%
src/flag_gems/experimental_ops/sgn.py sgn_out 3 3 0 0%
src/flag_gems/experimental_ops/sgn.py (no function) 10 10 0 0%
src/flag_gems/experimental_ops/sgn_.py sgn_ 11 11 0 0%
src/flag_gems/experimental_ops/sgn_.py sgn_ 19 19 0 0%
src/flag_gems/experimental_ops/sgn_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/sigmoid.py sigmoid_kernel 9 9 0 0%
src/flag_gems/experimental_ops/sigmoid.py _sigmoid_common 26 26 0 0%
src/flag_gems/experimental_ops/sigmoid.py sigmoid 1 1 0 0%
src/flag_gems/experimental_ops/sigmoid.py sigmoid_out 1 1 0 0%
src/flag_gems/experimental_ops/sigmoid.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/sigmoid_.py sigmoid_ 15 15 0 0%
src/flag_gems/experimental_ops/sigmoid_.py sigmoid_ 15 15 0 0%
src/flag_gems/experimental_ops/sigmoid_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/sign.py sign_kernel 9 9 0 0%
src/flag_gems/experimental_ops/sign.py _launch_sign_kernel 5 5 0 0%
src/flag_gems/experimental_ops/sign.py sign 5 5 0 0%
src/flag_gems/experimental_ops/sign.py sign_out 10 10 0 0%
src/flag_gems/experimental_ops/sign.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/silu.py silu_kernel 11 11 0 0%
src/flag_gems/experimental_ops/silu.py _silu_impl 26 26 0 0%
src/flag_gems/experimental_ops/silu.py silu 7 7 0 0%
src/flag_gems/experimental_ops/silu.py silu_out 12 12 0 0%
src/flag_gems/experimental_ops/silu.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/silu_.py silu_ 9 9 0 0%
src/flag_gems/experimental_ops/silu_.py silu_ 20 20 0 0%
src/flag_gems/experimental_ops/silu_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/sin_.py sin_ 9 9 0 0%
src/flag_gems/experimental_ops/sin_.py sin_ 20 20 0 0%
src/flag_gems/experimental_ops/sin_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/sinc.py sinc_kernel_fp32 9 9 0 0%
src/flag_gems/experimental_ops/sinc.py sinc 8 8 0 0%
src/flag_gems/experimental_ops/sinc.py sinc_out 7 7 0 0%
src/flag_gems/experimental_ops/sinc.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/sinc_.py sinc_ 15 15 0 0%
src/flag_gems/experimental_ops/sinc_.py sinc_ 10 10 0 0%
src/flag_gems/experimental_ops/sinc_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/sinh_.py sinh_ 9 9 0 0%
src/flag_gems/experimental_ops/sinh_.py sinh_ 22 22 0 0%
src/flag_gems/experimental_ops/sinh_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/slice_backward.py _slice_backward_scatter_kernel 19 19 0 0%
src/flag_gems/experimental_ops/slice_backward.py _normalize_slice_params 22 22 0 0%
src/flag_gems/experimental_ops/slice_backward.py _launch_slice_backward_kernel 17 17 0 0%
src/flag_gems/experimental_ops/slice_backward.py slice_backward 3 3 0 0%
src/flag_gems/experimental_ops/slice_backward.py slice_backward_out 6 6 0 0%
src/flag_gems/experimental_ops/slice_backward.py (no function) 9 9 0 0%
src/flag_gems/experimental_ops/slice_scatter.py _copy_kernel 6 6 0 0%
src/flag_gems/experimental_ops/slice_scatter.py _slice_scatter_kernel 18 18 0 0%
src/flag_gems/experimental_ops/slice_scatter.py _normalize_slice_params 16 16 0 0%
src/flag_gems/experimental_ops/slice_scatter.py _slice_scatter_impl 31 31 0 0%
src/flag_gems/experimental_ops/slice_scatter.py slice_scatter 2 2 0 0%
src/flag_gems/experimental_ops/slice_scatter.py slice_scatter_out 3 3 0 0%
src/flag_gems/experimental_ops/slice_scatter.py (no function) 11 11 0 0%
src/flag_gems/experimental_ops/smooth_l1_loss.py smooth_l1_elementwise_kernel 13 13 0 0%
src/flag_gems/experimental_ops/smooth_l1_loss.py _normalize_reduction 13 13 0 0%
src/flag_gems/experimental_ops/smooth_l1_loss.py _parse_smooth_l1_args 17 17 0 0%
src/flag_gems/experimental_ops/smooth_l1_loss.py _parse_smooth_l1_args.maybe_set_reduction 9 9 0 0%
src/flag_gems/experimental_ops/smooth_l1_loss.py _parse_smooth_l1_args.maybe_set_beta 6 6 0 0%
src/flag_gems/experimental_ops/smooth_l1_loss.py _launch_smooth_l1_elementwise 6 6 0 0%
src/flag_gems/experimental_ops/smooth_l1_loss.py _prepare_tensors_for_elementwise 14 14 0 0%
src/flag_gems/experimental_ops/smooth_l1_loss.py smooth_l1_loss 15 15 0 0%
src/flag_gems/experimental_ops/smooth_l1_loss.py smooth_l1_loss_out 45 45 0 0%
src/flag_gems/experimental_ops/smooth_l1_loss.py (no function) 11 11 0 0%
src/flag_gems/experimental_ops/soft_margin_loss.py _soft_margin_loss_elementwise_kernel 12 12 0 0%
src/flag_gems/experimental_ops/soft_margin_loss.py _soft_margin_loss_sum_kernel 14 14 0 0%
src/flag_gems/experimental_ops/soft_margin_loss.py _normalize_reduction 14 14 0 0%
src/flag_gems/experimental_ops/soft_margin_loss.py _check_tensors 11 11 0 0%
src/flag_gems/experimental_ops/soft_margin_loss.py soft_margin_loss 23 23 0 0%
src/flag_gems/experimental_ops/soft_margin_loss.py soft_margin_loss_out 36 36 0 0%
src/flag_gems/experimental_ops/soft_margin_loss.py (no function) 11 11 0 0%
src/flag_gems/experimental_ops/softplus.py softplus_kernel 12 12 0 0%
src/flag_gems/experimental_ops/softplus.py _softplus_launch 10 10 0 0%
src/flag_gems/experimental_ops/softplus.py _parse_softplus_args 19 19 0 0%
src/flag_gems/experimental_ops/softplus.py softplus 6 6 0 0%
src/flag_gems/experimental_ops/softplus.py softplus_out 13 13 0 0%
src/flag_gems/experimental_ops/softplus.py (no function) 9 9 0 0%
src/flag_gems/experimental_ops/softshrink.py softshrink_kernel 13 13 0 0%
src/flag_gems/experimental_ops/softshrink.py _check_supported_dtype 2 2 0 0%
src/flag_gems/experimental_ops/softshrink.py _launch_softshrink_kernel 6 6 0 0%
src/flag_gems/experimental_ops/softshrink.py softshrink 7 7 0 0%
src/flag_gems/experimental_ops/softshrink.py softshrink_out 17 17 0 0%
src/flag_gems/experimental_ops/softshrink.py (no function) 9 9 0 0%
src/flag_gems/experimental_ops/special_i0e.py _special_i0e_kernel 18 18 0 0%
src/flag_gems/experimental_ops/special_i0e.py _run_special_i0e_kernel 13 13 0 0%
src/flag_gems/experimental_ops/special_i0e.py special_i0e 2 2 0 0%
src/flag_gems/experimental_ops/special_i0e.py special_i0e_out 4 4 0 0%
src/flag_gems/experimental_ops/special_i0e.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/special_i1.py special_i1_kernel 33 33 0 0%
src/flag_gems/experimental_ops/special_i1.py _launch_special_i1 9 9 0 0%
src/flag_gems/experimental_ops/special_i1.py special_i1 7 7 0 0%
src/flag_gems/experimental_ops/special_i1.py special_i1_out 11 11 0 0%
src/flag_gems/experimental_ops/special_i1.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/special_xlog1py.py _xlog1py_kernel 8 8 0 0%
src/flag_gems/experimental_ops/special_xlog1py.py _ensure_cuda_tensor 5 5 0 0%
src/flag_gems/experimental_ops/special_xlog1py.py _prepare_inputs 7 7 0 0%
src/flag_gems/experimental_ops/special_xlog1py.py _launch_xlog1py 3 3 0 0%
src/flag_gems/experimental_ops/special_xlog1py.py special_xlog1py 6 6 0 0%
src/flag_gems/experimental_ops/special_xlog1py.py special_xlog1py_other_scalar 8 8 0 0%
src/flag_gems/experimental_ops/special_xlog1py.py special_xlog1py_self_scalar 8 8 0 0%
src/flag_gems/experimental_ops/special_xlog1py.py special_xlog1py_out 9 9 0 0%
src/flag_gems/experimental_ops/special_xlog1py.py special_xlog1py_self_scalar_out 11 11 0 0%
src/flag_gems/experimental_ops/special_xlog1py.py special_xlog1py_other_scalar_out 11 11 0 0%
src/flag_gems/experimental_ops/special_xlog1py.py (no function) 14 14 0 0%
src/flag_gems/experimental_ops/t_copy.py t_copy_2d_kernel 11 11 0 0%
src/flag_gems/experimental_ops/t_copy.py copy_1d_strided_kernel 8 8 0 0%
src/flag_gems/experimental_ops/t_copy.py _launch_t_copy_kernel 22 22 0 0%
src/flag_gems/experimental_ops/t_copy.py t_copy_out 2 2 0 0%
src/flag_gems/experimental_ops/t_copy.py t_copy 11 11 0 0%
src/flag_gems/experimental_ops/t_copy.py (no function) 10 10 0 0%
src/flag_gems/experimental_ops/take.py take_kernel 10 10 0 0%
src/flag_gems/experimental_ops/take.py _launch_take 8 8 0 0%
src/flag_gems/experimental_ops/take.py take 4 4 0 0%
src/flag_gems/experimental_ops/take.py take_out 9 9 0 0%
src/flag_gems/experimental_ops/take.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/threshold.py threshold_kernel 7 7 0 0%
src/flag_gems/experimental_ops/threshold.py _coerce_scalars_for_dtype 10 10 0 0%
src/flag_gems/experimental_ops/threshold.py threshold 11 11 0 0%
src/flag_gems/experimental_ops/threshold.py threshold_out 19 19 0 0%
src/flag_gems/experimental_ops/threshold.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/threshold_.py threshold_ 9 9 0 0%
src/flag_gems/experimental_ops/threshold_.py threshold_ 18 18 0 0%
src/flag_gems/experimental_ops/threshold_.py (no function) 7 7 0 0%
src/flag_gems/experimental_ops/trace.py trace_kernel 31 31 0 0%
src/flag_gems/experimental_ops/trace.py _dtype_to_code 4 4 0 0%
src/flag_gems/experimental_ops/trace.py _launch_trace_kernel 12 12 0 0%
src/flag_gems/experimental_ops/trace.py trace 3 3 0 0%
src/flag_gems/experimental_ops/trace.py trace_out 2 2 0 0%
src/flag_gems/experimental_ops/trace.py (no function) 9 9 0 0%
src/flag_gems/experimental_ops/tril.py _tril_kernel 12 12 0 0%
src/flag_gems/experimental_ops/tril.py _launch_tril_kernel 17 17 0 0%
src/flag_gems/experimental_ops/tril.py tril 2 2 0 0%
src/flag_gems/experimental_ops/tril.py tril_out 4 4 0 0%
src/flag_gems/experimental_ops/tril.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/triu.py triu_kernel 15 15 0 0%
src/flag_gems/experimental_ops/triu.py _check_supported_dtype 2 2 0 0%
src/flag_gems/experimental_ops/triu.py _launch_triu_kernel 34 34 0 0%
src/flag_gems/experimental_ops/triu.py triu 3 3 0 0%
src/flag_gems/experimental_ops/triu.py triu_out 10 10 0 0%
src/flag_gems/experimental_ops/triu.py (no function) 9 9 0 0%
src/flag_gems/experimental_ops/trunc.py trunc_kernel 21 21 0 0%
src/flag_gems/experimental_ops/trunc.py _dtype_code 11 11 0 0%
src/flag_gems/experimental_ops/trunc.py _launch_trunc 9 9 0 0%
src/flag_gems/experimental_ops/trunc.py trunc 16 16 0 0%
src/flag_gems/experimental_ops/trunc.py trunc_out 19 19 0 0%
src/flag_gems/experimental_ops/trunc.py (no function) 9 9 0 0%
src/flag_gems/experimental_ops/unsqueeze.py unsqueeze_kernel 17 17 0 0%
src/flag_gems/experimental_ops/unsqueeze.py unsqueeze 22 22 0 0%
src/flag_gems/experimental_ops/unsqueeze.py (no function) 6 6 0 0%
src/flag_gems/experimental_ops/unsqueeze_copy.py _unsqueeze_copy_kernel 21 21 0 0%
src/flag_gems/experimental_ops/unsqueeze_copy.py _launch_unsqueeze_copy 10 10 0 0%
src/flag_gems/experimental_ops/unsqueeze_copy.py unsqueeze_copy 8 8 0 0%
src/flag_gems/experimental_ops/unsqueeze_copy.py unsqueeze_copy_out 13 13 0 0%
src/flag_gems/experimental_ops/unsqueeze_copy.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/upsample_nearest1d.py _upsample_nearest1d_kernel 17 17 0 0%
src/flag_gems/experimental_ops/upsample_nearest1d.py _upsample_nearest1d_impl 39 39 0 0%
src/flag_gems/experimental_ops/upsample_nearest1d.py upsample_nearest1d 1 1 0 0%
src/flag_gems/experimental_ops/upsample_nearest1d.py upsample_nearest1d_vec 1 1 0 0%
src/flag_gems/experimental_ops/upsample_nearest1d.py upsample_nearest1d_out 2 2 0 0%
src/flag_gems/experimental_ops/upsample_nearest1d.py (no function) 10 10 0 0%
src/flag_gems/experimental_ops/upsample_nearest3d.py upsample_nearest3d_kernel 22 22 0 0%
src/flag_gems/experimental_ops/upsample_nearest3d.py _ensure_5d_input 3 3 0 0%
src/flag_gems/experimental_ops/upsample_nearest3d.py _normalize_output_size 10 10 0 0%
src/flag_gems/experimental_ops/upsample_nearest3d.py _normalize_scale_factors 7 7 0 0%
src/flag_gems/experimental_ops/upsample_nearest3d.py _compute_out_size_and_kernel_scales 21 21 0 0%
src/flag_gems/experimental_ops/upsample_nearest3d.py _launch_upsample_nearest3d 11 11 0 0%
src/flag_gems/experimental_ops/upsample_nearest3d.py upsample_nearest3d 9 9 0 0%
src/flag_gems/experimental_ops/upsample_nearest3d.py upsample_nearest3d_vec 9 9 0 0%
src/flag_gems/experimental_ops/upsample_nearest3d.py upsample_nearest3d_out 16 16 0 0%
src/flag_gems/experimental_ops/upsample_nearest3d.py (no function) 13 13 0 0%
src/flag_gems/experimental_ops/xlogy.py xlogy_kernel 10 10 0 0%
src/flag_gems/experimental_ops/xlogy.py _ensure_tensor_on_device 3 3 0 0%
src/flag_gems/experimental_ops/xlogy.py _prepare_tensors 31 31 0 0%
src/flag_gems/experimental_ops/xlogy.py _launch_xlogy 11 11 0 0%
src/flag_gems/experimental_ops/xlogy.py xlogy_Tensor 1 1 0 0%
src/flag_gems/experimental_ops/xlogy.py xlogy_Scalar_Other 1 1 0 0%
src/flag_gems/experimental_ops/xlogy.py xlogy_Scalar_Self 1 1 0 0%
src/flag_gems/experimental_ops/xlogy.py xlogy_OutTensor 1 1 0 0%
src/flag_gems/experimental_ops/xlogy.py xlogy_OutScalar_Self 1 1 0 0%
src/flag_gems/experimental_ops/xlogy.py xlogy_OutScalar_Other 1 1 0 0%
src/flag_gems/experimental_ops/xlogy.py (no function) 14 14 0 0%
src/flag_gems/experimental_ops/xlogy_.py xlogy_inplace_tensor_kernel 12 12 0 0%
src/flag_gems/experimental_ops/xlogy_.py xlogy_inplace_scalar_kernel 11 11 0 0%
src/flag_gems/experimental_ops/xlogy_.py _ensure_supported_dtype 2 2 0 0%
src/flag_gems/experimental_ops/xlogy_.py _ensure_cuda_contiguous 4 4 0 0%
src/flag_gems/experimental_ops/xlogy_.py xlogy__Tensor 22 22 0 0%
src/flag_gems/experimental_ops/xlogy_.py xlogy__Scalar_Other 15 15 0 0%
src/flag_gems/experimental_ops/xlogy_.py (no function) 11 11 0 0%
src/flag_gems/experimental_ops/zero.py zero_kernel 7 7 0 0%
src/flag_gems/experimental_ops/zero.py _launch_zero_kernel 10 10 0 0%
src/flag_gems/experimental_ops/zero.py zero 11 11 0 0%
src/flag_gems/experimental_ops/zero.py zero_out 7 7 0 0%
src/flag_gems/experimental_ops/zero.py (no function) 8 8 0 0%
src/flag_gems/experimental_ops/zeros_like.py _fill_zero_kernel 6 6 0 0%
src/flag_gems/experimental_ops/zeros_like.py _torch_dtype_to_triton_dtype 21 21 0 0%
src/flag_gems/experimental_ops/zeros_like.py _launch_fill_zero 12 12 0 0%
src/flag_gems/experimental_ops/zeros_like.py zeros_like 14 14 0 0%
src/flag_gems/experimental_ops/zeros_like.py zeros_like_out 17 17 0 0%
src/flag_gems/experimental_ops/zeros_like.py (no function) 9 9 0 0%
src/flag_gems/fused/FLA/__init__.py (no function) 3 0 0 100%
src/flag_gems/fused/FLA/chunk.py chunk_gated_delta_rule_fwd 10 10 0 0%
src/flag_gems/fused/FLA/chunk.py (no function) 9 0 0 100%
src/flag_gems/fused/FLA/chunk_delta_h.py chunk_gated_delta_rule_fwd_kernel_h_blockdim64 134 134 0 0%
src/flag_gems/fused/FLA/chunk_delta_h.py chunk_gated_delta_rule_fwd_h 14 14 0 0%
src/flag_gems/fused/FLA/chunk_delta_h.py chunk_gated_delta_rule_fwd_h.grid 1 1 0 0%
src/flag_gems/fused/FLA/chunk_delta_h.py (no function) 14 0 0 100%
src/flag_gems/fused/FLA/chunk_o.py chunk_fwd_kernel_o 42 42 0 0%
src/flag_gems/fused/FLA/chunk_o.py chunk_fwd_o 11 11 0 0%
src/flag_gems/fused/FLA/chunk_o.py chunk_fwd_o.grid 1 1 0 0%
src/flag_gems/fused/FLA/chunk_o.py (no function) 15 0 0 100%
src/flag_gems/fused/FLA/chunk_scaled_dot_kkt.py chunk_scaled_dot_kkt_fwd_kernel 26 26 0 0%
src/flag_gems/fused/FLA/chunk_scaled_dot_kkt.py chunk_scaled_dot_kkt_fwd 8 8 0 0%
src/flag_gems/fused/FLA/chunk_scaled_dot_kkt.py (no function) 12 0 0 100%
src/flag_gems/fused/FLA/cumsum.py chunk_local_cumsum_scalar_kernel 18 18 0 0%
src/flag_gems/fused/FLA/cumsum.py chunk_local_cumsum_vector_kernel 19 19 0 0%
src/flag_gems/fused/FLA/cumsum.py chunk_local_cumsum_scalar 11 11 0 0%
src/flag_gems/fused/FLA/cumsum.py chunk_local_cumsum_vector 11 11 0 0%
src/flag_gems/fused/FLA/cumsum.py chunk_local_cumsum_vector.grid 1 1 0 0%
src/flag_gems/fused/FLA/cumsum.py chunk_local_cumsum 9 9 0 0%
src/flag_gems/fused/FLA/cumsum.py (no function) 21 0 0 100%
src/flag_gems/fused/FLA/fused_recurrent.py fused_recurrent_gated_delta_rule_fwd_sp_for_qwen3_next_kernel 63 63 0 0%
src/flag_gems/fused/FLA/fused_recurrent.py fused_recurrent_gated_delta_rule_fwd_kernel 70 70 0 0%
src/flag_gems/fused/FLA/fused_recurrent.py fused_recurrent_gated_delta_rule_fwd 27 27 0 0%
src/flag_gems/fused/FLA/fused_recurrent.py (no function) 13 0 0 100%
src/flag_gems/fused/FLA/index.py prepare_lens 1 1 0 0%
src/flag_gems/fused/FLA/index.py prepare_chunk_indices 2 2 0 0%
src/flag_gems/fused/FLA/index.py prepare_chunk_offsets 1 1 0 0%
src/flag_gems/fused/FLA/index.py (no function) 9 0 0 100%
src/flag_gems/fused/FLA/solve_tril.py solve_tril_16x16_kernel 29 29 0 0%
src/flag_gems/fused/FLA/solve_tril.py merge_16x16_to_32x32_inverse_kernel 48 48 0 0%
src/flag_gems/fused/FLA/solve_tril.py merge_16x16_to_64x64_inverse_kernel 107 107 0 0%
src/flag_gems/fused/FLA/solve_tril.py solve_tril 14 14 0 0%
src/flag_gems/fused/FLA/solve_tril.py (no function) 28 0 0 100%
src/flag_gems/fused/FLA/triton_ops_helper.py get_exp 1 0 0 100%
src/flag_gems/fused/FLA/triton_ops_helper.py (no function) 14 6 0 57%
src/flag_gems/fused/FLA/utils.py _detect_nvidia_hopper 5 1 0 80%
src/flag_gems/fused/FLA/utils.py tensor_cache 5 0 0 100%
src/flag_gems/fused/FLA/utils.py tensor_cache.wrapper 10 10 0 0%
src/flag_gems/fused/FLA/utils.py input_guard 3 0 0 100%
src/flag_gems/fused/FLA/utils.py input_guard.wrapper 17 0 0 100%
src/flag_gems/fused/FLA/utils.py check_shared_mem 10 2 0 80%
src/flag_gems/fused/FLA/utils.py (no function) 18 0 0 100%
src/flag_gems/fused/FLA/wy_fast.py recompute_w_u_fwd_kernel 27 27 0 0%
src/flag_gems/fused/FLA/wy_fast.py recompute_w_u_fwd 11 11 0 0%
src/flag_gems/fused/FLA/wy_fast.py (no function) 11 0 0 100%
src/flag_gems/fused/__init__.py (no function) 27 0 0 100%
src/flag_gems/fused/apply_repetition_penalties.py _repetition_penalty_kernel 16 16 0 0%
src/flag_gems/fused/apply_repetition_penalties.py apply_repetition_penalties 12 0 0 100%
src/flag_gems/fused/apply_repetition_penalties.py (no function) 6 0 0 100%
src/flag_gems/fused/concat_and_cache_mla.py concat_and_cache_mla_kernel 35 35 0 0%
src/flag_gems/fused/concat_and_cache_mla.py ConcatAndCacheMla.forward 26 4 0 85%
src/flag_gems/fused/concat_and_cache_mla.py concat_and_cache_mla 2 0 0 100%
src/flag_gems/fused/concat_and_cache_mla.py (no function) 17 0 0 100%
src/flag_gems/fused/cross_entropy_loss.py celoss_indices_kernel 32 32 0 0%
src/flag_gems/fused/cross_entropy_loss.py celoss_probability_kernel 35 35 0 0%
src/flag_gems/fused/cross_entropy_loss.py celoss_indices_smooth_kernel 44 44 0 0%
src/flag_gems/fused/cross_entropy_loss.py celoss_indices_bwd 36 36 0 0%
src/flag_gems/fused/cross_entropy_loss.py celoss_probability_bwd 48 48 0 0%
src/flag_gems/fused/cross_entropy_loss.py celoss_indices_smooth_bwd 48 48 0 0%
src/flag_gems/fused/cross_entropy_loss.py sum_and_scale 25 25 0 0%
src/flag_gems/fused/cross_entropy_loss.py CrossEntropyLoss.forward 46 0 0 100%
src/flag_gems/fused/cross_entropy_loss.py CrossEntropyLoss.backward 18 18 0 0%
src/flag_gems/fused/cross_entropy_loss.py cross_entropy_loss 1 0 0 100%
src/flag_gems/fused/cross_entropy_loss.py (no function) 43 0 0 100%
src/flag_gems/fused/cutlass_scaled_mm.py get_sm_version_num 2 0 0 100%
src/flag_gems/fused/cutlass_scaled_mm.py get_block_wise_smm_configs 2 0 0 100%
src/flag_gems/fused/cutlass_scaled_mm.py grouped_launch 8 8 0 0%
src/flag_gems/fused/cutlass_scaled_mm.py _block_wise_smm_kernel 27 27 0 0%
src/flag_gems/fused/cutlass_scaled_mm.py _block_wise_128_smm_launcher 7 7 0 0%
src/flag_gems/fused/cutlass_scaled_mm.py _pertensor_or_pertoken_smm_kernel 58 58 0 0%
src/flag_gems/fused/cutlass_scaled_mm.py _pertensor_or_pertoken_smm_launcher 9 9 0 0%
src/flag_gems/fused/cutlass_scaled_mm.py dispatch_scaled_mm 20 20 0 0%
src/flag_gems/fused/cutlass_scaled_mm.py cutlass_scaled_mm_sm90 1 1 0 0%
src/flag_gems/fused/cutlass_scaled_mm.py cutlass_scaled_mm_sm120 1 1 0 0%
src/flag_gems/fused/cutlass_scaled_mm.py cutlass_scaled_mm_sm100 1 1 0 0%
src/flag_gems/fused/cutlass_scaled_mm.py cutlass_scaled_mm_sm89 1 1 0 0%
src/flag_gems/fused/cutlass_scaled_mm.py cutlass_scaled_mm_sm80 1 1 0 0%
src/flag_gems/fused/cutlass_scaled_mm.py cutlass_scaled_mm_sm75 1 1 0 0%
src/flag_gems/fused/cutlass_scaled_mm.py cutlass_scaled_mm 22 22 0 0%
src/flag_gems/fused/cutlass_scaled_mm.py (no function) 30 0 0 100%
src/flag_gems/fused/flash_mla.py flash_mla_attn_kernel 63 63 0 0%
src/flag_gems/fused/flash_mla.py flash_mla 29 9 0 69%
src/flag_gems/fused/flash_mla.py (no function) 15 0 0 100%
src/flag_gems/fused/fused_add_rms_norm.py fused_add_rms_norm_kernel 17 17 0 0%
src/flag_gems/fused/fused_add_rms_norm.py fused_add_rms_norm 11 0 0 100%
src/flag_gems/fused/fused_add_rms_norm.py (no function) 12 0 0 100%
src/flag_gems/fused/fused_moe.py write_zeros_to_output 5 5 0 0%
src/flag_gems/fused/fused_moe.py fused_moe_kernel 62 62 0 0%
src/flag_gems/fused/fused_moe.py get_default_config 32 32 0 0%
src/flag_gems/fused/fused_moe.py invoke_fused_moe_triton_kernel 18 18 0 0%
src/flag_gems/fused/fused_moe.py _apply_silu_and_mul 3 3 0 0%
src/flag_gems/fused/fused_moe.py fused_experts_impl 26 26 0 0%
src/flag_gems/fused/fused_moe.py (no function) 17 0 0 100%
src/flag_gems/fused/geglu.py geglu_kernel 13 13 0 0%
src/flag_gems/fused/geglu.py dgeglu_kernel 21 21 0 0%
src/flag_gems/fused/geglu.py geglu 8 0 0 100%
src/flag_gems/fused/geglu.py dgeglu 9 0 0 100%
src/flag_gems/fused/geglu.py (no function) 17 0 0 100%
src/flag_gems/fused/gelu_and_mul.py gelu_none_and_mul_kernel 4 4 0 0%
src/flag_gems/fused/gelu_and_mul.py gelu_none_and_mul_grad_kernel 8 8 0 0%
src/flag_gems/fused/gelu_and_mul.py gelu_tanh_and_mul_kernel 3 3 0 0%
src/flag_gems/fused/gelu_and_mul.py gelu_tanh_and_mul_grad_kernel 13 13 0 0%
src/flag_gems/fused/gelu_and_mul.py GeluAndMul.forward 8 1 0 88%
src/flag_gems/fused/gelu_and_mul.py GeluAndMul.backward 6 6 0 0%
src/flag_gems/fused/gelu_and_mul.py gelu_and_mul 1 0 0 100%
src/flag_gems/fused/gelu_and_mul.py (no function) 27 0 0 100%
src/flag_gems/fused/grouped_topk.py topk_with_k2_triton 18 18 0 0%
src/flag_gems/fused/grouped_topk.py group_idx_and_topk_triton 64 64 0 0%
src/flag_gems/fused/grouped_topk.py grouped_topk 40 40 0 0%
src/flag_gems/fused/grouped_topk.py (no function) 8 0 0 100%
src/flag_gems/fused/instance_norm.py prev_multiple_of 1 1 0 0%
src/flag_gems/fused/instance_norm.py instance_norm_persistent_kernel 20 20 0 0%
src/flag_gems/fused/instance_norm.py instance_norm_persistent_kernel_multiline 22 22 0 0%
src/flag_gems/fused/instance_norm.py instance_norm_loop_kernel 49 49 0 0%
src/flag_gems/fused/instance_norm.py instance_norm_use_running_stats_kernel 17 17 0 0%
src/flag_gems/fused/instance_norm.py update_running_stats_kernel 19 19 0 0%
src/flag_gems/fused/instance_norm.py instance_norm_backward_kernel 39 39 0 0%
src/flag_gems/fused/instance_norm.py weight_bias_backward_kernel 27 27 0 0%
src/flag_gems/fused/instance_norm.py InstanceNorm.forward 48 0 0 100%
src/flag_gems/fused/instance_norm.py InstanceNorm.backward 19 19 0 0%
src/flag_gems/fused/instance_norm.py instance_norm 1 0 0 100%
src/flag_gems/fused/instance_norm.py (no function) 46 0 0 100%
src/flag_gems/fused/moe_align_block_size.py ceil_div 1 0 0 100%
src/flag_gems/fused/moe_align_block_size.py round_up 1 1 0 0%
src/flag_gems/fused/moe_align_block_size.py moe_align_block_size_stage1_tle 25 25 0 0%
src/flag_gems/fused/moe_align_block_size.py moe_align_block_size_stage1 13 13 0 0%
src/flag_gems/fused/moe_align_block_size.py moe_align_block_size_stage2_vec 5 5 0 0%
src/flag_gems/fused/moe_align_block_size.py moe_align_block_size_stage2 6 6 0 0%
src/flag_gems/fused/moe_align_block_size.py moe_align_block_size_stage3 9 9 0 0%
src/flag_gems/fused/moe_align_block_size.py moe_align_block_size_stage4 13 13 0 0%
src/flag_gems/fused/moe_align_block_size.py moe_align_block_size_triton 19 1 0 95%
src/flag_gems/fused/moe_align_block_size.py moe_align_block_size 12 12 0 0%
src/flag_gems/fused/moe_align_block_size.py (no function) 27 1 0 96%
src/flag_gems/fused/moe_sum.py moe_sum_kernel 15 15 0 0%
src/flag_gems/fused/moe_sum.py moe_sum 5 0 0 100%
src/flag_gems/fused/moe_sum.py (no function) 7 0 0 100%
src/flag_gems/fused/outer.py Outer.forward 9 0 0 100%
src/flag_gems/fused/outer.py Outer.backward 6 6 0 0%
src/flag_gems/fused/outer.py outer 1 0 0 100%
src/flag_gems/fused/outer.py (no function) 10 0 0 100%
src/flag_gems/fused/reglu.py dreglu_kernel 19 19 0 0%
src/flag_gems/fused/reglu.py reglu_kernel 13 13 0 0%
src/flag_gems/fused/reglu.py reglu 17 4 0 76%
src/flag_gems/fused/reglu.py dreglu 11 1 0 91%
src/flag_gems/fused/reglu.py (no function) 18 0 0 100%
src/flag_gems/fused/reshape_and_cache.py reshape_and_cache_kernel 20 20 0 0%
src/flag_gems/fused/reshape_and_cache.py reshape_and_cache 11 0 0 100%
src/flag_gems/fused/reshape_and_cache.py (no function) 10 0 0 100%
src/flag_gems/fused/reshape_and_cache_flash.py reshape_and_cache_flash_kernel 17 17 0 0%
src/flag_gems/fused/reshape_and_cache_flash.py reshape_and_cache_flash 15 2 0 87%
src/flag_gems/fused/reshape_and_cache_flash.py (no function) 12 0 0 100%
src/flag_gems/fused/rotary_embedding.py apply_rotary_pos_emb_kernel 42 42 0 0%
src/flag_gems/fused/rotary_embedding.py apply_rotary_pos_emb_inplace_kernel 38 38 0 0%
src/flag_gems/fused/rotary_embedding.py apply_rotary_pos_emb 32 4 0 88%
src/flag_gems/fused/rotary_embedding.py (no function) 16 0 0 100%
src/flag_gems/fused/rwkv_ka_fusion.py rwkv_ka_fusion_kernel 19 19 0 0%
src/flag_gems/fused/rwkv_ka_fusion.py rwkv_ka_fusion 12 2 0 83%
src/flag_gems/fused/rwkv_ka_fusion.py (no function) 6 0 0 100%
src/flag_gems/fused/rwkv_mm_sparsity.py rwkv_mm_sparsity_kernel 14 14 0 0%
src/flag_gems/fused/rwkv_mm_sparsity.py rwkv_mm_sparsity 10 0 0 100%
src/flag_gems/fused/rwkv_mm_sparsity.py (no function) 6 0 0 100%
src/flag_gems/fused/silu_and_mul.py silu_and_mul_kernel 3 3 0 0%
src/flag_gems/fused/silu_and_mul.py silu_and_mul_grad_kernel 7 7 0 0%
src/flag_gems/fused/silu_and_mul.py SiluAndMul.forward 3 0 0 100%
src/flag_gems/fused/silu_and_mul.py SiluAndMul.backward 3 3 0 0%
src/flag_gems/fused/silu_and_mul.py silu_and_mul 1 0 0 100%
src/flag_gems/fused/silu_and_mul.py silu_and_mul_out 2 2 0 0%
src/flag_gems/fused/silu_and_mul.py (no function) 18 0 0 100%
src/flag_gems/fused/skip_layernorm.py skip_layer_norm_kernel 20 20 0 0%
src/flag_gems/fused/skip_layernorm.py SkipLayerNorm.forward 13 0 0 100%
src/flag_gems/fused/skip_layernorm.py skip_layer_norm 1 0 0 100%
src/flag_gems/fused/skip_layernorm.py (no function) 16 0 0 100%
src/flag_gems/fused/swiglu.py swiglu_kernel 13 13 0 0%
src/flag_gems/fused/swiglu.py dswiglu_kernel 20 20 0 0%
src/flag_gems/fused/swiglu.py swiglu 12 2 0 83%
src/flag_gems/fused/swiglu.py dswiglu 10 0 0 100%
src/flag_gems/fused/swiglu.py (no function) 17 0 0 100%
src/flag_gems/fused/topk_softmax.py topk_gating_softmax_kernel 24 24 0 0%
src/flag_gems/fused/topk_softmax.py topk_softmax 21 21 0 0%
src/flag_gems/fused/topk_softmax.py (no function) 6 0 0 100%
src/flag_gems/fused/weight_norm.py weight_norm_except_dim_kernel 29 29 0 0%
src/flag_gems/fused/weight_norm.py weight_norm_except_dim_bwd_kernel 32 32 0 0%
src/flag_gems/fused/weight_norm.py weight_norm_except_dim 9 9 0 0%
src/flag_gems/fused/weight_norm.py weight_norm_except_dim_backward 9 9 0 0%
src/flag_gems/fused/weight_norm.py WeightNorm.forward 10 10 0 0%
src/flag_gems/fused/weight_norm.py WeightNorm.backward 7 7 0 0%
src/flag_gems/fused/weight_norm.py weight_norm 1 1 0 0%
src/flag_gems/fused/weight_norm.py (no function) 27 0 0 100%
src/flag_gems/logging_utils.py LogOncePerLocationFilter.__init__ 2 2 0 0%
src/flag_gems/logging_utils.py LogOncePerLocationFilter.filter 5 5 0 0%
src/flag_gems/logging_utils.py _remove_file_handlers 7 0 0 100%
src/flag_gems/logging_utils.py setup_flaggems_logging 14 1 0 93%
src/flag_gems/logging_utils.py teardown_flaggems_logging 2 0 0 100%
src/flag_gems/logging_utils.py (no function) 8 0 0 100%
src/flag_gems/modules/__init__.py (no function) 5 0 0 100%
src/flag_gems/modules/activation.py gems_silu_and_mul 2 2 0 0%
src/flag_gems/modules/activation.py GemsSiluAndMul.__init__ 1 1 0 0%
src/flag_gems/modules/activation.py GemsSiluAndMul.forward 1 1 0 0%
src/flag_gems/modules/activation.py (no function) 11 0 0 100%
src/flag_gems/modules/normalization.py gems_rms_forward 13 13 0 0%
src/flag_gems/modules/normalization.py GemsRMSNorm.__init__ 11 11 0 0%
src/flag_gems/modules/normalization.py GemsRMSNorm.reset_parameters 2 2 0 0%
src/flag_gems/modules/normalization.py GemsRMSNorm.forward 1 1 0 0%
src/flag_gems/modules/normalization.py GemsRMSNorm.extra_repr 1 1 0 0%
src/flag_gems/modules/normalization.py (no function) 21 0 0 100%
src/flag_gems/modules/rotary_embedding.py gems_rope_forward 8 8 0 0%
src/flag_gems/modules/rotary_embedding.py GemsRope.__init__ 8 8 0 0%
src/flag_gems/modules/rotary_embedding.py GemsRope._compute_inv_freq 1 1 0 0%
src/flag_gems/modules/rotary_embedding.py GemsRope._set_cos_sin_cache 5 5 0 0%
src/flag_gems/modules/rotary_embedding.py GemsRope.forward 3 3 0 0%
src/flag_gems/modules/rotary_embedding.py yarn_find_correction_dim 1 1 0 0%
src/flag_gems/modules/rotary_embedding.py yarn_find_correction_range 3 3 0 0%
src/flag_gems/modules/rotary_embedding.py yarn_get_mscale 3 3 0 0%
src/flag_gems/modules/rotary_embedding.py yarn_linear_ramp_mask 5 5 0 0%
src/flag_gems/modules/rotary_embedding.py GemsDeepseekYarnRoPE.__init__ 7 7 0 0%
src/flag_gems/modules/rotary_embedding.py GemsDeepseekYarnRoPE._compute_inv_freq 6 6 0 0%
src/flag_gems/modules/rotary_embedding.py GemsDeepseekYarnRoPE._set_cos_sin_cache 6 6 0 0%
src/flag_gems/modules/rotary_embedding.py (no function) 23 0 0 100%
src/flag_gems/ops/__init__.py (no function) 173 0 0 100%
src/flag_gems/ops/abs.py abs_func 1 1 0 0%
src/flag_gems/ops/abs.py abs 2 0 0 100%
src/flag_gems/ops/abs.py abs_ 3 0 0 100%
src/flag_gems/ops/abs.py (no function) 10 0 0 100%
src/flag_gems/ops/acos.py acos_kernel 1 1 0 0%
src/flag_gems/ops/acos.py acos 3 0 0 100%
src/flag_gems/ops/acos.py (no function) 10 0 0 100%
src/flag_gems/ops/add.py add_func 1 1 0 0%
src/flag_gems/ops/add.py add_func_tensor_scalar 1 1 0 0%
src/flag_gems/ops/add.py add_func_scalar_tensor 1 1 0 0%
src/flag_gems/ops/add.py add 10 2 0 80%
src/flag_gems/ops/add.py add_ 8 2 0 75%
src/flag_gems/ops/add.py (no function) 16 0 0 100%
src/flag_gems/ops/addcdiv.py addcdiv_kernel 1 1 0 0%
src/flag_gems/ops/addcdiv.py addcdiv 5 0 0 100%
src/flag_gems/ops/addcdiv.py (no function) 9 0 0 100%
src/flag_gems/ops/addcmul.py addcmul_forward 1 1 0 0%
src/flag_gems/ops/addcmul.py addcmul 8 5 0 38%
src/flag_gems/ops/addcmul.py (no function) 9 0 0 100%
src/flag_gems/ops/addmm.py addmm_kernel 23 23 0 0%
src/flag_gems/ops/addmm.py addmm 12 0 0 100%
src/flag_gems/ops/addmm.py addmm_out 14 1 0 93%
src/flag_gems/ops/addmm.py (no function) 15 0 0 100%
src/flag_gems/ops/addmv.py addmv_kernel 20 20 0 0%
src/flag_gems/ops/addmv.py addmv 10 0 0 100%
src/flag_gems/ops/addmv.py addmv_out 12 1 0 92%
src/flag_gems/ops/addmv.py (no function) 15 0 0 100%
src/flag_gems/ops/addr.py addr_kernel 16 16 0 0%
src/flag_gems/ops/addr.py addr 17 3 0 82%
src/flag_gems/ops/addr.py (no function) 11 0 0 100%
src/flag_gems/ops/all.py reduce_all 1 1 0 0%
src/flag_gems/ops/all.py all_kernel_dim 14 14 0 0%
src/flag_gems/ops/all.py all_kernel_1 8 8 0 0%
src/flag_gems/ops/all.py all_kernel_2 6 6 0 0%
src/flag_gems/ops/all.py all 11 0 0 100%
src/flag_gems/ops/all.py all_dim 19 3 0 84%
src/flag_gems/ops/all.py all_dims 19 1 0 95%
src/flag_gems/ops/all.py (no function) 25 0 0 100%
src/flag_gems/ops/amax.py amax_kernel_1 9 9 0 0%
src/flag_gems/ops/amax.py amax_kernel_2 7 7 0 0%
src/flag_gems/ops/amax.py amax_kernel 17 17 0 0%
src/flag_gems/ops/amax.py amax 37 17 0 54%
src/flag_gems/ops/amax.py (no function) 22 0 0 100%
src/flag_gems/ops/angle.py angle_func 3 3 0 0%
src/flag_gems/ops/angle.py angle_float_and_int 5 5 0 0%
src/flag_gems/ops/angle.py angle 7 0 0 100%
src/flag_gems/ops/angle.py (no function) 15 0 0 100%
src/flag_gems/ops/any.py reduce_any 1 1 0 0%
src/flag_gems/ops/any.py any_kernel_dim 14 14 0 0%
src/flag_gems/ops/any.py any_kernel_1 8 8 0 0%
src/flag_gems/ops/any.py any_kernel_2 6 6 0 0%
src/flag_gems/ops/any.py any 11 0 0 100%
src/flag_gems/ops/any.py any_dim 19 3 0 84%
src/flag_gems/ops/any.py any_dims 19 1 0 95%
src/flag_gems/ops/any.py (no function) 25 0 0 100%
src/flag_gems/ops/arange.py arange_func 7 7 0 0%
src/flag_gems/ops/arange.py arange_start 16 2 0 88%
src/flag_gems/ops/arange.py arange 1 0 0 100%
src/flag_gems/ops/arange.py (no function) 14 0 0 100%
src/flag_gems/ops/argmax.py argmax_kernel_1 12 12 0 0%
src/flag_gems/ops/argmax.py argmax_kernel_2 9 9 0 0%
src/flag_gems/ops/argmax.py argmax_kernel_non_inner 34 34 0 0%
src/flag_gems/ops/argmax.py argmax_kernel_inner 37 37 0 0%
src/flag_gems/ops/argmax.py argmax 45 0 0 100%
src/flag_gems/ops/argmax.py (no function) 26 0 0 100%
src/flag_gems/ops/argmin.py argmin_kernel_1 12 12 0 0%
src/flag_gems/ops/argmin.py argmin_kernel_2 9 9 0 0%
src/flag_gems/ops/argmin.py heur_block_n 1 1 0 0%
src/flag_gems/ops/argmin.py argmin_kernel_opt_k1 17 17 0 0%
src/flag_gems/ops/argmin.py argmin_split_K_kernel_merged 24 24 0 0%
src/flag_gems/ops/argmin.py argmin_kernel 22 22 0 0%
src/flag_gems/ops/argmin.py argmin 45 4 0 91%
src/flag_gems/ops/argmin.py (no function) 31 0 0 100%
src/flag_gems/ops/atan.py atan_kernel 1 1 0 0%
src/flag_gems/ops/atan.py atan 3 0 0 100%
src/flag_gems/ops/atan.py atan_ 3 0 0 100%
src/flag_gems/ops/atan.py (no function) 11 0 0 100%
src/flag_gems/ops/attention.py _attn_fwd_inner 51 51 0 0%
src/flag_gems/ops/attention.py _attn_fwd 35 35 0 0%
src/flag_gems/ops/attention.py _attn_bwd_preprocess 8 8 0 0%
src/flag_gems/ops/attention.py _attn_bwd_dkdv 32 32 0 0%
src/flag_gems/ops/attention.py _attn_bwd_dq 26 26 0 0%
src/flag_gems/ops/attention.py _attn_bwd 61 61 0 0%
src/flag_gems/ops/attention.py scaled_dot_product_attention_forward 32 8 0 75%
src/flag_gems/ops/attention.py scaled_dot_product_attention_backward 36 36 0 0%
src/flag_gems/ops/attention.py ScaleDotProductAttention.forward 7 0 0 100%
src/flag_gems/ops/attention.py ScaleDotProductAttention.backward 6 6 0 0%
src/flag_gems/ops/attention.py scaled_dot_product_attention 1 0 0 100%
src/flag_gems/ops/attention.py flash_attention_forward 33 13 0 61%
src/flag_gems/ops/attention.py maybe_contiguous 1 0 0 100%
src/flag_gems/ops/attention.py flash_attn_varlen_func 25 8 0 68%
src/flag_gems/ops/attention.py (no function) 45 0 0 100%
src/flag_gems/ops/avg_pool2d.py pool2d_output_size 8 1 0 88%
src/flag_gems/ops/avg_pool2d.py avg_pool2d_forward_kernel 33 33 0 0%
src/flag_gems/ops/avg_pool2d.py avg_pool2d_backward_kernel 44 44 0 0%
src/flag_gems/ops/avg_pool2d.py _parse_pool_params 18 4 0 78%
src/flag_gems/ops/avg_pool2d.py avg_pool2d 15 2 0 87%
src/flag_gems/ops/avg_pool2d.py avg_pool2d_backward 14 2 0 86%
src/flag_gems/ops/avg_pool2d.py (no function) 18 0 0 100%
src/flag_gems/ops/baddbmm.py baddbmm_kernel 63 63 0 0%
src/flag_gems/ops/baddbmm.py BaddbmmFunction.forward 17 0 0 100%
src/flag_gems/ops/baddbmm.py BaddbmmFunction.backward 12 12 0 0%
src/flag_gems/ops/baddbmm.py compute_bias_grad 8 8 0 0%
src/flag_gems/ops/baddbmm.py compute_A_grad 10 10 0 0%
src/flag_gems/ops/baddbmm.py compute_B_grad 10 10 0 0%
src/flag_gems/ops/baddbmm.py baddbmm 1 0 0 100%
src/flag_gems/ops/baddbmm.py (no function) 25 0 0 100%
src/flag_gems/ops/batch_norm.py make_3d_for_bn 5 0 0 100%
src/flag_gems/ops/batch_norm.py batch_norm_forward_kernel 54 54 0 0%
src/flag_gems/ops/batch_norm.py batch_norm_backward_kernel 45 45 0 0%
src/flag_gems/ops/batch_norm.py batch_norm 11 0 0 100%
src/flag_gems/ops/batch_norm.py batch_norm_backward 16 1 0 94%
src/flag_gems/ops/batch_norm.py (no function) 23 0 0 100%
src/flag_gems/ops/bitwise_and.py bitwise_and_func 1 1 0 0%
src/flag_gems/ops/bitwise_and.py bitwise_and_tensor 2 0 0 100%
src/flag_gems/ops/bitwise_and.py bitwise_and_tensor_ 2 0 0 100%
src/flag_gems/ops/bitwise_and.py bitwise_and_func_scalar 1 1 0 0%
src/flag_gems/ops/bitwise_and.py bitwise_and_scalar 2 0 0 100%
src/flag_gems/ops/bitwise_and.py bitwise_and_scalar_ 2 0 0 100%
src/flag_gems/ops/bitwise_and.py bitwise_and_scalar_tensor 2 0 0 100%
src/flag_gems/ops/bitwise_and.py (no function) 15 0 0 100%
src/flag_gems/ops/bitwise_left_shift.py bitwise_left_shift_kernel 1 1 0 0%
src/flag_gems/ops/bitwise_left_shift.py bitwise_left_shift 2 2 0 0%
src/flag_gems/ops/bitwise_left_shift.py (no function) 8 0 0 100%
src/flag_gems/ops/bitwise_not.py bitwise_not_func 1 1 0 0%
src/flag_gems/ops/bitwise_not.py bitwise_not 2 0 0 100%
src/flag_gems/ops/bitwise_not.py bitwise_not_ 3 0 0 100%
src/flag_gems/ops/bitwise_not.py (no function) 9 0 0 100%
src/flag_gems/ops/bitwise_or.py bitwise_or_func 1 1 0 0%
src/flag_gems/ops/bitwise_or.py bitwise_or_tensor 2 0 0 100%
src/flag_gems/ops/bitwise_or.py bitwise_or_tensor_ 2 0 0 100%
src/flag_gems/ops/bitwise_or.py bitwise_or_func_scalar 1 1 0 0%
src/flag_gems/ops/bitwise_or.py bitwise_or_scalar 2 0 0 100%
src/flag_gems/ops/bitwise_or.py bitwise_or_scalar_ 2 0 0 100%
src/flag_gems/ops/bitwise_or.py bitwise_or_scalar_tensor 2 0 0 100%
src/flag_gems/ops/bitwise_or.py (no function) 15 0 0 100%
src/flag_gems/ops/bitwise_right_shift.py bitwise_right_shift_kernel 1 1 0 0%
src/flag_gems/ops/bitwise_right_shift.py bitwise_right_shift 1 1 0 0%
src/flag_gems/ops/bitwise_right_shift.py (no function) 8 0 0 100%
src/flag_gems/ops/bmm.py bmm_kernel 58 58 0 0%
src/flag_gems/ops/bmm.py bmm 10 0 0 100%
src/flag_gems/ops/bmm.py bmm_out 9 0 0 100%
src/flag_gems/ops/bmm.py (no function) 16 0 0 100%
src/flag_gems/ops/cat.py cat_copy_func_kernel_4 31 31 0 0%
src/flag_gems/ops/cat.py cat 69 4 0 94%
src/flag_gems/ops/cat.py (no function) 9 0 0 100%
src/flag_gems/ops/ceil.py ceil_func 1 1 0 0%
src/flag_gems/ops/ceil.py ceil 2 0 0 100%
src/flag_gems/ops/ceil.py ceil_out 5 1 0 80%
src/flag_gems/ops/ceil.py ceil_ 3 0 0 100%
src/flag_gems/ops/ceil.py (no function) 11 0 0 100%
src/flag_gems/ops/celu.py celu_forward_kernel 1 1 0 0%
src/flag_gems/ops/celu.py celu 2 0 0 100%
src/flag_gems/ops/celu.py celu_ 2 0 0 100%
src/flag_gems/ops/celu.py (no function) 10 0 0 100%
src/flag_gems/ops/clamp.py clamp_func_tensor 1 1 0 0%
src/flag_gems/ops/clamp.py clamp_func_min_tensor 1 1 0 0%
src/flag_gems/ops/clamp.py clamp_func_max_tensor 1 1 0 0%
src/flag_gems/ops/clamp.py clamp_tensor 8 1 0 88%
src/flag_gems/ops/clamp.py clamp_tensor_ 8 1 0 88%
src/flag_gems/ops/clamp.py clamp_func 1 1 0 0%
src/flag_gems/ops/clamp.py clamp_func_min 1 1 0 0%
src/flag_gems/ops/clamp.py clamp_func_max 1 1 0 0%
src/flag_gems/ops/clamp.py clamp_min 4 4 0 0%
src/flag_gems/ops/clamp.py clamp_min_ 4 4 0 0%
src/flag_gems/ops/clamp.py clamp 8 1 0 88%
src/flag_gems/ops/clamp.py clamp_ 8 1 0 88%
src/flag_gems/ops/clamp.py (no function) 29 0 0 100%
src/flag_gems/ops/contiguous.py contiguous 6 6 0 0%
src/flag_gems/ops/contiguous.py (no function) 5 0 0 100%
src/flag_gems/ops/conv1d.py conv1d 22 3 0 86%
src/flag_gems/ops/conv1d.py (no function) 5 0 0 100%
src/flag_gems/ops/conv2d.py conv2d_output_size 1 0 0 100%
src/flag_gems/ops/conv2d.py conv2d_forward_kernel 36 36 0 0%
src/flag_gems/ops/conv2d.py conv2d_backward_kernel_weight 28 28 0 0%
src/flag_gems/ops/conv2d.py Conv2d.forward 35 0 0 100%
src/flag_gems/ops/conv2d.py Conv2d.backward 38 38 0 0%
src/flag_gems/ops/conv2d.py conv2d 17 1 0 94%
src/flag_gems/ops/conv2d.py (no function) 23 0 0 100%
src/flag_gems/ops/conv3d.py conv3d_output_size 1 0 0 100%
src/flag_gems/ops/conv3d.py conv3d_forward_kernel 41 41 0 0%
src/flag_gems/ops/conv3d.py conv3d 47 4 0 91%
src/flag_gems/ops/conv3d.py (no function) 15 0 0 100%
src/flag_gems/ops/conv_depthwise2d.py _conv_depthwise2d 6 6 0 0%
src/flag_gems/ops/conv_depthwise2d.py (no function) 4 0 0 100%
src/flag_gems/ops/copy.py _copy_kernel 1 1 0 0%
src/flag_gems/ops/copy.py _can_use_triton 9 3 0 67%
src/flag_gems/ops/copy.py _expand_like 3 0 0 100%
src/flag_gems/ops/copy.py copy 4 4 0 0%
src/flag_gems/ops/copy.py copy_ 29 12 0 59%
src/flag_gems/ops/copy.py (no function) 14 0 0 100%
src/flag_gems/ops/cos.py cos_func 1 1 0 0%
src/flag_gems/ops/cos.py cos 2 0 0 100%
src/flag_gems/ops/cos.py cos_ 3 0 0 100%
src/flag_gems/ops/cos.py (no function) 10 0 0 100%
src/flag_gems/ops/count_nonzero.py count_nonzero_kernel_1 8 8 0 0%
src/flag_gems/ops/count_nonzero.py count_nonzero_kernel 10 10 0 0%
src/flag_gems/ops/count_nonzero.py count_nonzero_combin_kernel_1 9 9 0 0%
src/flag_gems/ops/count_nonzero.py count_nonzero_combin_kernel 9 9 0 0%
src/flag_gems/ops/count_nonzero.py count_nonzero 36 0 0 100%
src/flag_gems/ops/count_nonzero.py (no function) 23 0 0 100%
src/flag_gems/ops/cummax.py tl_cummax 1 1 0 0%
src/flag_gems/ops/cummax.py tl_max_tie_break_right 1 1 0 0%
src/flag_gems/ops/cummax.py add_base_max_kernel 16 16 0 0%
src/flag_gems/ops/cummax.py scan_part_max_kernel 27 27 0 0%
src/flag_gems/ops/cummax.py scan_then_fan_col 17 5 0 71%
src/flag_gems/ops/cummax.py scan_part_max_abc_kernel 34 34 0 0%
src/flag_gems/ops/cummax.py add_base_max_abc_kernel 24 24 0 0%
src/flag_gems/ops/cummax.py scan_then_fan 17 5 0 71%
src/flag_gems/ops/cummax.py scan_part_max_abc_loop_kernel 39 39 0 0%
src/flag_gems/ops/cummax.py scan_then_fan_loop 7 0 0 100%
src/flag_gems/ops/cummax.py cummax 24 1 0 96%
src/flag_gems/ops/cummax.py (no function) 35 0 0 100%
src/flag_gems/ops/cummin.py tl_cummin 1 1 0 0%
src/flag_gems/ops/cummin.py tl_min_tie_break_right 1 1 0 0%
src/flag_gems/ops/cummin.py add_base_min_kernel 16 16 0 0%
src/flag_gems/ops/cummin.py scan_part_min_kernel 27 27 0 0%
src/flag_gems/ops/cummin.py scan_then_fan_col 17 5 0 71%
src/flag_gems/ops/cummin.py scan_part_min_abc_kernel 34 34 0 0%
src/flag_gems/ops/cummin.py add_base_min_abc_kernel 24 24 0 0%
src/flag_gems/ops/cummin.py scan_then_fan 17 5 0 71%
src/flag_gems/ops/cummin.py scan_part_min_abc_loop_kernel 39 39 0 0%
src/flag_gems/ops/cummin.py scan_then_fan_loop 7 0 0 100%
src/flag_gems/ops/cummin.py cummin 24 1 0 96%
src/flag_gems/ops/cummin.py (no function) 35 0 0 100%
src/flag_gems/ops/cumsum.py get_num_sms 1 0 0 100%
src/flag_gems/ops/cumsum.py get_scan_accum_type 5 5 0 0%
src/flag_gems/ops/cumsum.py scan_part_sum_kernel 16 16 0 0%
src/flag_gems/ops/cumsum.py add_base_sum_kernel 10 10 0 0%
src/flag_gems/ops/cumsum.py scan_part_sum_abc_kernel 23 23 0 0%
src/flag_gems/ops/cumsum.py add_base_sum_abc_kernel 18 18 0 0%
src/flag_gems/ops/cumsum.py scan_then_fan_col 12 12 0 0%
src/flag_gems/ops/cumsum.py scan_then_fan 12 0 0 100%
src/flag_gems/ops/cumsum.py cumsum_wrapper 22 0 0 100%
src/flag_gems/ops/cumsum.py reduce_then_scan_row 18 0 0 100%
src/flag_gems/ops/cumsum.py reduce_then_scan_block_sum_kernel_row 13 13 0 0%
src/flag_gems/ops/cumsum.py reduce_then_scan_root_scan_kernel_row 7 7 0 0%
src/flag_gems/ops/cumsum.py reduce_then_scan_block_scan_kernel_row 13 13 0 0%
src/flag_gems/ops/cumsum.py cumsum 2 0 0 100%
src/flag_gems/ops/cumsum.py cumsum_out 2 2 0 0%
src/flag_gems/ops/cumsum.py normed_cumsum_kernel 9 9 0 0%
src/flag_gems/ops/cumsum.py block_cumsum_kernel 35 35 0 0%
src/flag_gems/ops/cumsum.py block_update_kernel 22 22 0 0%
src/flag_gems/ops/cumsum.py normed_cumsum 37 13 0 65%
src/flag_gems/ops/cumsum.py (no function) 51 0 0 100%
src/flag_gems/ops/diag.py diag_1d_to_2d_kernel 10 10 0 0%
src/flag_gems/ops/diag.py diag_2d_to_1d_kernel 9 9 0 0%
src/flag_gems/ops/diag.py diag_1d_to_2d 9 0 0 100%
src/flag_gems/ops/diag.py diag_2d_to_1d 14 0 0 100%
src/flag_gems/ops/diag.py diag 6 1 0 83%
src/flag_gems/ops/diag.py (no function) 14 0 0 100%
src/flag_gems/ops/diag_embed.py copy_func 1 1 0 0%
src/flag_gems/ops/diag_embed.py diag_embed 19 0 0 100%
src/flag_gems/ops/diag_embed.py (no function) 9 0 0 100%
src/flag_gems/ops/diagonal.py copy_func 1 1 0 0%
src/flag_gems/ops/diagonal.py diagonal_backward 5 5 0 0%
src/flag_gems/ops/diagonal.py (no function) 9 0 0 100%
src/flag_gems/ops/div.py true_div_func 1 1 0 0%
src/flag_gems/ops/div.py true_div_func_tensor_scalar 1 1 0 0%
src/flag_gems/ops/div.py true_div_func_scalar_tensor 1 1 0 0%
src/flag_gems/ops/div.py true_divide 8 1 0 88%
src/flag_gems/ops/div.py true_divide_out 8 5 0 38%
src/flag_gems/ops/div.py true_divide_ 4 0 0 100%
src/flag_gems/ops/div.py trunc_div_func 1 1 0 0%
src/flag_gems/ops/div.py trunc_div_func_tensor_scalar 1 1 0 0%
src/flag_gems/ops/div.py trunc_div_func_scalar_tensor 1 1 0 0%
src/flag_gems/ops/div.py trunc_divide 8 5 0 38%
src/flag_gems/ops/div.py trunc_divide_ 4 1 0 75%
src/flag_gems/ops/div.py _int_floordiv 4 4 0 0%
src/flag_gems/ops/div.py _float_floordiv 14 14 0 0%
src/flag_gems/ops/div.py floor_div_func 3 3 0 0%
src/flag_gems/ops/div.py floor_div_func_tensor_scalar 3 3 0 0%
src/flag_gems/ops/div.py floor_div_func_scalar_tensor 3 3 0 0%
src/flag_gems/ops/div.py floor_divide 8 5 0 38%
src/flag_gems/ops/div.py floor_divide_ 4 1 0 75%
src/flag_gems/ops/div.py div_mode 8 3 0 62%
src/flag_gems/ops/div.py div_mode_ 8 3 0 62%
src/flag_gems/ops/div.py _remainder 4 4 0 0%
src/flag_gems/ops/div.py rem_tt 1 1 0 0%
src/flag_gems/ops/div.py rem_ts 1 1 0 0%
src/flag_gems/ops/div.py rem_st 1 1 0 0%
src/flag_gems/ops/div.py remainder 8 5 0 38%
src/flag_gems/ops/div.py remainder_ 4 1 0 75%
src/flag_gems/ops/div.py (no function) 60 0 0 100%
src/flag_gems/ops/dot.py dot_kernel 8 8 0 0%
src/flag_gems/ops/dot.py dot_kernel_1 8 8 0 0%
src/flag_gems/ops/dot.py dot_kernel_2 6 6 0 0%
src/flag_gems/ops/dot.py dot 22 10 0 55%
src/flag_gems/ops/dot.py (no function) 19 0 0 100%
src/flag_gems/ops/dropout.py dropout_forward_kernel 38 38 0 0%
src/flag_gems/ops/dropout.py dropout_backward_kernel 6 6 0 0%
src/flag_gems/ops/dropout.py dropout 21 6 0 71%
src/flag_gems/ops/dropout.py dropout_backward 8 0 0 100%
src/flag_gems/ops/dropout.py (no function) 17 0 0 100%
src/flag_gems/ops/elu.py elu_forward_kernel 1 1 0 0%
src/flag_gems/ops/elu.py elu_backward_kernel_with_self 3 3 0 0%
src/flag_gems/ops/elu.py elu_backward_kernel_with_result 2 2 0 0%
src/flag_gems/ops/elu.py elu 2 0 0 100%
src/flag_gems/ops/elu.py elu_ 2 0 0 100%
src/flag_gems/ops/elu.py elu_backward 4 0 0 100%
src/flag_gems/ops/elu.py (no function) 17 0 0 100%
src/flag_gems/ops/embedding.py embedding_kernel 9 9 0 0%
src/flag_gems/ops/embedding.py indice_freq_kernel 6 6 0 0%
src/flag_gems/ops/embedding.py embedding_backward_kernel 18 18 0 0%
src/flag_gems/ops/embedding.py embedding_grad_scale_kernel 12 12 0 0%
src/flag_gems/ops/embedding.py embedding 11 0 0 100%
src/flag_gems/ops/embedding.py embedding_backward 20 0 0 100%
src/flag_gems/ops/embedding.py (no function) 22 0 0 100%
src/flag_gems/ops/eq.py eq_func 1 1 0 0%
src/flag_gems/ops/eq.py eq 6 3 0 50%
src/flag_gems/ops/eq.py eq_func_scalar 1 1 0 0%
src/flag_gems/ops/eq.py eq_scalar 2 0 0 100%
src/flag_gems/ops/eq.py equal 5 1 0 80%
src/flag_gems/ops/eq.py (no function) 18 0 0 100%
src/flag_gems/ops/erf.py erf_func 2 2 0 0%
src/flag_gems/ops/erf.py erf 2 0 0 100%
src/flag_gems/ops/erf.py erf_ 2 0 0 100%
src/flag_gems/ops/erf.py (no function) 10 0 0 100%
src/flag_gems/ops/exp.py exp_func 1 1 0 0%
src/flag_gems/ops/exp.py exp 2 0 0 100%
src/flag_gems/ops/exp.py exp_ 2 0 0 100%
src/flag_gems/ops/exp.py exp_out 2 0 0 100%
src/flag_gems/ops/exp.py (no function) 11 0 0 100%
src/flag_gems/ops/exp2.py exp2_func 1 1 0 0%
src/flag_gems/ops/exp2.py exp2 2 0 0 100%
src/flag_gems/ops/exp2.py exp2_ 2 0 0 100%
src/flag_gems/ops/exp2.py (no function) 10 0 0 100%
src/flag_gems/ops/exponential_.py safe_fast_log_f32 8 8 0 0%
src/flag_gems/ops/exponential_.py safe_fast_log_f64 8 8 0 0%
src/flag_gems/ops/exponential_.py paste_u64 1 1 0 0%
src/flag_gems/ops/exponential_.py transform_exponential_f32_precise 2 2 0 0%
src/flag_gems/ops/exponential_.py transform_exponential_f32_fast 2 2 0 0%
src/flag_gems/ops/exponential_.py transform_exponential_f64 2 2 0 0%
src/flag_gems/ops/exponential_.py fused_exponential_kernel_f32 22 22 0 0%
src/flag_gems/ops/exponential_.py fused_exponential_kernel_f64 18 18 0 0%
src/flag_gems/ops/exponential_.py exponential_ 25 7 0 72%
src/flag_gems/ops/exponential_.py (no function) 32 1 0 97%
src/flag_gems/ops/eye.py eye 13 2 0 85%
src/flag_gems/ops/eye.py (no function) 8 0 0 100%
src/flag_gems/ops/eye_m.py eye_kernel 10 10 0 0%
src/flag_gems/ops/eye_m.py eye_m 13 2 0 85%
src/flag_gems/ops/eye_m.py (no function) 12 0 0 100%
src/flag_gems/ops/fill.py fill_scalar_func 1 1 0 0%
src/flag_gems/ops/fill.py fill_tensor_func 1 1 0 0%
src/flag_gems/ops/fill.py fill_scalar 4 0 0 100%
src/flag_gems/ops/fill.py fill_tensor 8 2 0 75%
src/flag_gems/ops/fill.py fill_tensor_ 8 2 0 75%
src/flag_gems/ops/fill.py fill_scalar_ 4 0 0 100%
src/flag_gems/ops/fill.py (no function) 17 0 0 100%
src/flag_gems/ops/flash_api.py CHECK_DEVICE 1 0 0 100%
src/flag_gems/ops/flash_api.py fwd_params.__init__ 57 0 0 100%
src/flag_gems/ops/flash_api.py fwd_params.args 1 0 0 100%
src/flag_gems/ops/flash_api.py mha_varlan_fwd 154 23 0 85%
src/flag_gems/ops/flash_api.py mha_fwd 102 9 0 91%
src/flag_gems/ops/flash_api.py mha_fwd.splits_heuristic 7 0 0 100%
src/flag_gems/ops/flash_api.py mha_fwd.dispatch 33 1 0 97%
src/flag_gems/ops/flash_api.py (no function) 18 0 0 100%
src/flag_gems/ops/flash_kernel.py u64_to_lohi 1 1 0 0%
src/flag_gems/ops/flash_kernel.py u64_from_lohi 1 1 0 0%
src/flag_gems/ops/flash_kernel.py philox_ 21 21 0 0%
src/flag_gems/ops/flash_kernel.py apply_dropout_mask 4 4 0 0%
src/flag_gems/ops/flash_kernel.py apply_dropout 13 13 0 0%
src/flag_gems/ops/flash_kernel.py apply_alibi 7 7 0 0%
src/flag_gems/ops/flash_kernel.py apply_mask 11 11 0 0%
src/flag_gems/ops/flash_kernel.py softmax_rescale 12 12 0 0%
src/flag_gems/ops/flash_kernel.py apply_softcap 3 3 0 0%
src/flag_gems/ops/flash_kernel.py block_m_splitkv_heuristic 1 0 0 100%
src/flag_gems/ops/flash_kernel.py block_n_splitkv_heuristic 1 0 0 100%
src/flag_gems/ops/flash_kernel.py is_even_mn 5 0 0 100%
src/flag_gems/ops/flash_kernel.py block_m_splitkv_heuristic_spec_args 1 0 0 100%
src/flag_gems/ops/flash_kernel.py block_n_splitkv_heuristic_spec_args 1 0 0 100%
src/flag_gems/ops/flash_kernel.py is_even_mn_spec_args 5 0 0 100%
src/flag_gems/ops/flash_kernel.py keep 4 0 0 100%
src/flag_gems/ops/flash_kernel.py prune_fwd_configs 4 0 0 100%
src/flag_gems/ops/flash_kernel.py flash_fwd_kernel_heur_block_k 1 0 0 100%
src/flag_gems/ops/flash_kernel.py flash_fwd_kernel 159 159 0 0%
src/flag_gems/ops/flash_kernel.py flash_fwd_bh_parallel_kernel 1 1 0 0%
src/flag_gems/ops/flash_kernel.py flash_fwd_splitkv_kernel_heur_block_k 1 0 0 100%
src/flag_gems/ops/flash_kernel.py flash_fwd_splitkv_kernel 111 111 0 0%
src/flag_gems/ops/flash_kernel.py flash_fwd_splitkv_combine_kernel 23 23 0 0%
src/flag_gems/ops/flash_kernel.py virtual_to_cache 6 6 0 0%
src/flag_gems/ops/flash_kernel.py load_from_kvcache 13 13 0 0%
src/flag_gems/ops/flash_kernel.py flash_varlen_fwd_kernel 92 92 0 0%
src/flag_gems/ops/flash_kernel.py (no function) 53 0 0 100%
src/flag_gems/ops/flip.py copy_func 1 1 0 0%
src/flag_gems/ops/flip.py flip 21 0 0 100%
src/flag_gems/ops/flip.py (no function) 10 0 0 100%
src/flag_gems/ops/full.py check_dtype 8 1 0 88%
src/flag_gems/ops/full.py full_func 1 1 0 0%
src/flag_gems/ops/full.py full_func_scalar 1 1 0 0%
src/flag_gems/ops/full.py full 14 1 0 93%
src/flag_gems/ops/full.py (no function) 17 0 0 100%
src/flag_gems/ops/full_like.py full_like 11 0 0 100%
src/flag_gems/ops/full_like.py (no function) 5 0 0 100%
src/flag_gems/ops/gather.py generate_imports 10 0 0 100%
src/flag_gems/ops/gather.py generate_gather_kernel 41 0 0 100%
src/flag_gems/ops/gather.py generate_gather_wrapper 25 0 0 100%
src/flag_gems/ops/gather.py generate_code 5 0 0 100%
src/flag_gems/ops/gather.py GatherFunction.__init__ 2 0 0 100%
src/flag_gems/ops/gather.py GatherFunction.__call__ 14 0 0 100%
src/flag_gems/ops/gather.py GatherFunction.arg_key 1 0 0 100%
src/flag_gems/ops/gather.py gather 8 0 0 100%
src/flag_gems/ops/gather.py gather_backward 3 3 0 0%
src/flag_gems/ops/gather.py (no function) 21 0 0 100%
src/flag_gems/ops/ge.py ge_func 1 1 0 0%
src/flag_gems/ops/ge.py ge 2 0 0 100%
src/flag_gems/ops/ge.py ge_func_scalar 1 1 0 0%
src/flag_gems/ops/ge.py ge_scalar 2 0 0 100%
src/flag_gems/ops/ge.py (no function) 13 0 0 100%
src/flag_gems/ops/gelu.py gelu_none 3 3 0 0%
src/flag_gems/ops/gelu.py gelu_tanh 3 3 0 0%
src/flag_gems/ops/gelu.py gelu_backward_none 6 6 0 0%
src/flag_gems/ops/gelu.py gelu_backward_tanh 5 5 0 0%
src/flag_gems/ops/gelu.py gelu 5 0 0 100%
src/flag_gems/ops/gelu.py gelu_backward 5 0 0 100%
src/flag_gems/ops/gelu.py gelu_ 5 0 0 100%
src/flag_gems/ops/gelu.py (no function) 24 0 0 100%
src/flag_gems/ops/get_scheduler_metadata.py tile_size_fwd_sm8x 50 50 0 0%
src/flag_gems/ops/get_scheduler_metadata.py tile_size_fwd_sm90 26 26 0 0%
src/flag_gems/ops/get_scheduler_metadata.py get_optimal_block_mn 8 8 0 0%
src/flag_gems/ops/get_scheduler_metadata.py round_up_headdim 11 11 0 0%
src/flag_gems/ops/get_scheduler_metadata.py round_up_headdimv 11 11 0 0%
src/flag_gems/ops/get_scheduler_metadata.py get_pagedkv_tma 7 7 0 0%
src/flag_gems/ops/get_scheduler_metadata.py use_one_mma_wg 5 5 0 0%
src/flag_gems/ops/get_scheduler_metadata.py should_pack_gqa 6 6 0 0%
src/flag_gems/ops/get_scheduler_metadata.py should_pack_gqa.round_up 1 1 0 0%
src/flag_gems/ops/get_scheduler_metadata.py get_num_splits 17 17 0 0%
src/flag_gems/ops/get_scheduler_metadata.py _vllm_num_splits_heuristic 20 20 0 0%
src/flag_gems/ops/get_scheduler_metadata.py _prepare_pass1_kernel 33 33 0 0%
src/flag_gems/ops/get_scheduler_metadata.py _prepare_pass2_kernel 12 12 0 0%
src/flag_gems/ops/get_scheduler_metadata.py get_pack_gqa 7 7 0 0%
src/flag_gems/ops/get_scheduler_metadata.py get_scheduler_metadata 94 94 0 0%
src/flag_gems/ops/get_scheduler_metadata.py (no function) 24 0 0 100%
src/flag_gems/ops/glu.py glu_kernel 3 3 0 0%
src/flag_gems/ops/glu.py glu_backward_kernel 4 4 0 0%
src/flag_gems/ops/glu.py glu 5 0 0 100%
src/flag_gems/ops/glu.py glu_backward 7 0 0 100%
src/flag_gems/ops/glu.py (no function) 15 0 0 100%
src/flag_gems/ops/groupnorm.py group_norm_kernel 29 29 0 0%
src/flag_gems/ops/groupnorm.py group_norm_backward_kernel 37 37 0 0%
src/flag_gems/ops/groupnorm.py weight_bias_backward_kernel 21 21 0 0%
src/flag_gems/ops/groupnorm.py group_norm 12 0 0 100%
src/flag_gems/ops/groupnorm.py group_norm_backward 20 1 0 95%
src/flag_gems/ops/groupnorm.py (no function) 20 0 0 100%
src/flag_gems/ops/gt.py gt_func 1 1 0 0%
src/flag_gems/ops/gt.py gt 2 0 0 100%
src/flag_gems/ops/gt.py gt_func_scalar 1 1 0 0%
src/flag_gems/ops/gt.py gt_scalar 2 0 0 100%
src/flag_gems/ops/gt.py (no function) 13 0 0 100%
src/flag_gems/ops/hstack.py hstack_copy_func_kernel_4 31 31 0 0%
src/flag_gems/ops/hstack.py hstack 66 3 0 95%
src/flag_gems/ops/hstack.py (no function) 9 0 0 100%
src/flag_gems/ops/index.py get_max_rank_shape 13 13 0 0%
src/flag_gems/ops/index.py broadcast_indices 3 3 0 0%
src/flag_gems/ops/index.py generate_imports 10 0 0 100%
src/flag_gems/ops/index.py generate_index_kernel 65 0 0 100%
src/flag_gems/ops/index.py generate_index_wrapper 37 0 0 100%
src/flag_gems/ops/index.py generate_code 10 1 0 90%
src/flag_gems/ops/index.py IndexFunction.__init__ 2 0 0 100%
src/flag_gems/ops/index.py IndexFunction.__call__ 16 0 0 100%
src/flag_gems/ops/index.py IndexFunction.arg_key 7 1 0 86%
src/flag_gems/ops/index.py index 98 5 0 95%
src/flag_gems/ops/index.py (no function) 20 0 0 100%
src/flag_gems/ops/index_add.py generate_imports 6 0 0 100%
src/flag_gems/ops/index_add.py generate_index_add_kernel 43 0 0 100%
src/flag_gems/ops/index_add.py parameter_for_wrapper 13 0 0 100%
src/flag_gems/ops/index_add.py generate_destination_passing_wrapper 21 0 0 100%
src/flag_gems/ops/index_add.py generate_code 6 0 0 100%
src/flag_gems/ops/index_add.py IndexAddFunction.__init__ 2 0 0 100%
src/flag_gems/ops/index_add.py IndexAddFunction.__call__ 14 0 0 100%
src/flag_gems/ops/index_add.py IndexAddFunction.arg_key 3 0 0 100%
src/flag_gems/ops/index_add.py index_add 15 0 0 100%
src/flag_gems/ops/index_add.py index_add_ 14 0 0 100%
src/flag_gems/ops/index_add.py (no function) 20 0 0 100%
src/flag_gems/ops/index_put.py get_max_rank_shape 13 0 0 100%
src/flag_gems/ops/index_put.py broadcast_indices 3 0 0 100%
src/flag_gems/ops/index_put.py generate_imports 10 0 0 100%
src/flag_gems/ops/index_put.py generate_index_put_kernel 62 0 0 100%
src/flag_gems/ops/index_put.py generate_index_put_wrapper 37 0 0 100%
src/flag_gems/ops/index_put.py generate_code 10 1 0 90%
src/flag_gems/ops/index_put.py IndexPutFunction.__init__ 2 0 0 100%
src/flag_gems/ops/index_put.py IndexPutFunction.__call__ 16 0 0 100%
src/flag_gems/ops/index_put.py IndexPutFunction.arg_key 7 1 0 86%
src/flag_gems/ops/index_put.py index_put 26 3 0 88%
src/flag_gems/ops/index_put.py index_put_ 25 3 0 88%
src/flag_gems/ops/index_put.py (no function) 21 0 0 100%
src/flag_gems/ops/index_select.py index_select_kernel 15 15 0 0%
src/flag_gems/ops/index_select.py index_select 22 1 0 95%
src/flag_gems/ops/index_select.py (no function) 13 0 0 100%
src/flag_gems/ops/isclose.py isclose_func 13 13 0 0%
src/flag_gems/ops/isclose.py isclose 13 5 0 62%
src/flag_gems/ops/isclose.py allclose 2 0 0 100%
src/flag_gems/ops/isclose.py (no function) 17 2 0 88%
src/flag_gems/ops/isfinite.py isfinite_func 1 1 0 0%
src/flag_gems/ops/isfinite.py isfinite 4 1 0 75%
src/flag_gems/ops/isfinite.py (no function) 15 2 0 87%
src/flag_gems/ops/isin.py launch_arg 1 0 0 100%
src/flag_gems/ops/isin.py isin_by_comparation_impl 16 16 0 0%
src/flag_gems/ops/isin.py isin_by_comparation_kernel 5 5 0 0%
src/flag_gems/ops/isin.py isin_by_comparation 20 7 0 65%
src/flag_gems/ops/isin.py isin_by_search_impl 16 16 0 0%
src/flag_gems/ops/isin.py isin_by_search_kernel 5 5 0 0%
src/flag_gems/ops/isin.py isin_by_search 27 4 0 85%
src/flag_gems/ops/isin.py isin 14 0 0 100%
src/flag_gems/ops/isin.py (no function) 26 0 0 100%
src/flag_gems/ops/isinf.py isinf_func 1 1 0 0%
src/flag_gems/ops/isinf.py isinf 2 0 0 100%
src/flag_gems/ops/isinf.py (no function) 10 0 0 100%
src/flag_gems/ops/isnan.py isnan_func 1 1 0 0%
src/flag_gems/ops/isnan.py isnan 2 0 0 100%
src/flag_gems/ops/isnan.py (no function) 10 0 0 100%
src/flag_gems/ops/kron.py prepare_tensor_for_kron 23 3 0 87%
src/flag_gems/ops/kron.py calculate_indices 13 0 0 100%
src/flag_gems/ops/kron.py kron_kernel_for_batch_size_1 21 21 0 0%
src/flag_gems/ops/kron.py kron_kernel 26 26 0 0%
src/flag_gems/ops/kron.py calculate_batch_indices_kernel 13 13 0 0%
src/flag_gems/ops/kron.py kron 55 2 0 96%
src/flag_gems/ops/kron.py (no function) 20 0 0 100%
src/flag_gems/ops/layernorm.py prev_multiple_of 1 1 0 0%
src/flag_gems/ops/layernorm.py layer_norm_persistent_kernel 20 20 0 0%
src/flag_gems/ops/layernorm.py layer_norm_persistent_kernel_multiline 23 23 0 0%
src/flag_gems/ops/layernorm.py layer_norm_loop_kernel 54 54 0 0%
src/flag_gems/ops/layernorm.py layer_norm_backward_kernel 41 41 0 0%
src/flag_gems/ops/layernorm.py weight_bias_backward_kernel 23 23 0 0%
src/flag_gems/ops/layernorm.py layer_norm 22 0 0 100%
src/flag_gems/ops/layernorm.py layer_norm_backward 23 1 0 96%
src/flag_gems/ops/layernorm.py (no function) 34 0 0 100%
src/flag_gems/ops/le.py le_func 1 1 0 0%
src/flag_gems/ops/le.py le 2 0 0 100%
src/flag_gems/ops/le.py le_func_scalar 1 1 0 0%
src/flag_gems/ops/le.py le_scalar 2 0 0 100%
src/flag_gems/ops/le.py (no function) 13 0 0 100%
src/flag_gems/ops/lerp.py lerp_tensor_kernel 1 1 0 0%
src/flag_gems/ops/lerp.py lerp_scalar_kernel_head 1 1 0 0%
src/flag_gems/ops/lerp.py lerp_scalar_kernel_tail 1 1 0 0%
src/flag_gems/ops/lerp.py lerp_tensor 3 0 0 100%
src/flag_gems/ops/lerp.py lerp_tensor_ 2 0 0 100%
src/flag_gems/ops/lerp.py lerp_scalar 5 1 0 80%
src/flag_gems/ops/lerp.py lerp_scalar_ 4 1 0 75%
src/flag_gems/ops/lerp.py (no function) 18 0 0 100%
src/flag_gems/ops/linspace.py linspace_kernel 8 8 0 0%
src/flag_gems/ops/linspace.py linspace 15 2 0 87%
src/flag_gems/ops/linspace.py (no function) 11 0 0 100%
src/flag_gems/ops/log.py log_func 1 1 0 0%
src/flag_gems/ops/log.py log 2 0 0 100%
src/flag_gems/ops/log.py (no function) 9 0 0 100%
src/flag_gems/ops/log_sigmoid.py log_sigmoid_forward 1 1 0 0%
src/flag_gems/ops/log_sigmoid.py log_sigmoid 2 0 0 100%
src/flag_gems/ops/log_sigmoid.py (no function) 9 0 0 100%
src/flag_gems/ops/log_softmax.py log_softmax_kernel 26 26 0 0%
src/flag_gems/ops/log_softmax.py log_softmax_backward_kernel 23 23 0 0%
src/flag_gems/ops/log_softmax.py log_softmax 17 1 0 94%
src/flag_gems/ops/log_softmax.py log_softmax_backward 14 0 0 100%
src/flag_gems/ops/log_softmax.py (no function) 18 0 0 100%
src/flag_gems/ops/logical_and.py logical_and_func 1 1 0 0%
src/flag_gems/ops/logical_and.py logical_and 2 0 0 100%
src/flag_gems/ops/logical_and.py logical_and_func_ 1 1 0 0%
src/flag_gems/ops/logical_and.py logical_and_ 3 0 0 100%
src/flag_gems/ops/logical_and.py (no function) 13 0 0 100%
src/flag_gems/ops/logical_not.py logical_not_func 1 1 0 0%
src/flag_gems/ops/logical_not.py logical_not 2 0 0 100%
src/flag_gems/ops/logical_not.py (no function) 9 0 0 100%
src/flag_gems/ops/logical_or.py logical_or_func 1 1 0 0%
src/flag_gems/ops/logical_or.py logical_or 2 0 0 100%
src/flag_gems/ops/logical_or.py logical_or_ 3 0 0 100%
src/flag_gems/ops/logical_or.py (no function) 10 0 0 100%
src/flag_gems/ops/logical_xor.py logical_xor_func 1 1 0 0%
src/flag_gems/ops/logical_xor.py logical_xor 2 0 0 100%
src/flag_gems/ops/logical_xor.py (no function) 9 0 0 100%
src/flag_gems/ops/logspace.py logspace_kernel 6 6 0 0%
src/flag_gems/ops/logspace.py logspace 19 3 0 84%
src/flag_gems/ops/logspace.py (no function) 12 0 0 100%
src/flag_gems/ops/lt.py lt_func 1 1 0 0%
src/flag_gems/ops/lt.py lt 2 0 0 100%
src/flag_gems/ops/lt.py lt_func_scalar 1 1 0 0%
src/flag_gems/ops/lt.py lt_scalar 2 0 0 100%
src/flag_gems/ops/lt.py (no function) 13 0 0 100%
src/flag_gems/ops/masked_fill.py masked_fill_kernel 2 2 0 0%
src/flag_gems/ops/masked_fill.py masked_fill 9 0 0 100%
src/flag_gems/ops/masked_fill.py masked_fill_ 11 0 0 100%
src/flag_gems/ops/masked_fill.py (no function) 11 0 0 100%
src/flag_gems/ops/masked_scatter.py masked_scatter_single_pass_kernel 9 9 0 0%
src/flag_gems/ops/masked_scatter.py mask_part_sum_kernel 24 24 0 0%
src/flag_gems/ops/masked_scatter.py masked_scatter_kernel 22 22 0 0%
src/flag_gems/ops/masked_scatter.py masked_scatter_impl 24 2 0 92%
src/flag_gems/ops/masked_scatter.py masked_scatter 13 3 0 77%
src/flag_gems/ops/masked_scatter.py masked_scatter_ 10 1 0 90%
src/flag_gems/ops/masked_scatter.py (no function) 20 0 0 100%
src/flag_gems/ops/masked_select.py masked_select_single_pass_kernel 7 7 0 0%
src/flag_gems/ops/masked_select.py masked_select_single_pass 8 3 0 62%
src/flag_gems/ops/masked_select.py mask_part_sum_kernel 24 24 0 0%
src/flag_gems/ops/masked_select.py write_back_kernel 20 20 0 0%
src/flag_gems/ops/masked_select.py masked_select 27 0 0 100%
src/flag_gems/ops/masked_select.py (no function) 19 0 0 100%
src/flag_gems/ops/max.py max_kernel_1 9 9 0 0%
src/flag_gems/ops/max.py max_kernel_2 7 7 0 0%
src/flag_gems/ops/max.py heur_block_n 1 1 0 0%
src/flag_gems/ops/max.py max_kernel 23 23 0 0%
src/flag_gems/ops/max.py max 13 0 0 100%
src/flag_gems/ops/max.py max_dim 19 0 0 100%
src/flag_gems/ops/max.py (no function) 25 0 0 100%
src/flag_gems/ops/max_pool2d_with_indices.py max_pool2d_output_size 8 1 0 88%
src/flag_gems/ops/max_pool2d_with_indices.py max_pool2d_forward_kernel 34 34 0 0%
src/flag_gems/ops/max_pool2d_with_indices.py max_pool2d_backward_kernel 31 31 0 0%
src/flag_gems/ops/max_pool2d_with_indices.py _parse_pool_params 12 3 0 75%
src/flag_gems/ops/max_pool2d_with_indices.py _parse_pool_params._parse_param 7 2 0 71%
src/flag_gems/ops/max_pool2d_with_indices.py max_pool2d_with_indices 14 1 0 93%
src/flag_gems/ops/max_pool2d_with_indices.py max_pool2d_backward 16 1 0 94%
src/flag_gems/ops/max_pool2d_with_indices.py (no function) 19 0 0 100%
src/flag_gems/ops/maximum.py maximum_kernel 4 4 0 0%
src/flag_gems/ops/maximum.py maximum 3 0 0 100%
src/flag_gems/ops/maximum.py (no function) 11 0 0 100%
src/flag_gems/ops/mean.py mean_kernel_1 11 11 0 0%
src/flag_gems/ops/mean.py mean_kernel_2 10 10 0 0%
src/flag_gems/ops/mean.py mean 14 0 0 100%
src/flag_gems/ops/mean.py mean_dim_kernel_non_inner 29 29 0 0%
src/flag_gems/ops/mean.py mean_dim_kernel_inner 27 27 0 0%
src/flag_gems/ops/mean.py mean_dim_kernel 17 17 0 0%
src/flag_gems/ops/mean.py mean_dim_comm 51 9 0 82%
src/flag_gems/ops/mean.py mean_dim 2 0 0 100%
src/flag_gems/ops/mean.py (no function) 32 0 0 100%
src/flag_gems/ops/min.py min_kernel_1 9 9 0 0%
src/flag_gems/ops/min.py min_kernel_2 7 7 0 0%
src/flag_gems/ops/min.py heur_block_n 1 1 0 0%
src/flag_gems/ops/min.py min_kernel 23 23 0 0%
src/flag_gems/ops/min.py min 12 0 0 100%
src/flag_gems/ops/min.py min_dim 19 0 0 100%
src/flag_gems/ops/min.py (no function) 25 0 0 100%
src/flag_gems/ops/minimum.py minimum_kernel 4 4 0 0%
src/flag_gems/ops/minimum.py minimum 3 0 0 100%
src/flag_gems/ops/minimum.py (no function) 11 0 0 100%
src/flag_gems/ops/mm.py prev_multiple_of 1 1 0 0%
src/flag_gems/ops/mm.py mm_kernel_general 38 38 0 0%
src/flag_gems/ops/mm.py get_higher_dtype 9 7 0 22%
src/flag_gems/ops/mm.py general_mm 5 0 0 100%
src/flag_gems/ops/mm.py streamk_scenario 2 0 0 100%
src/flag_gems/ops/mm.py mm 14 2 0 86%
src/flag_gems/ops/mm.py mm_out 11 11 0 0%
src/flag_gems/ops/mm.py (no function) 24 0 0 100%
src/flag_gems/ops/mm_streamk.py prev_multiple_of 1 1 0 0%
src/flag_gems/ops/mm_streamk.py swizzle_tile 8 8 0 0%
src/flag_gems/ops/mm_streamk.py linear_tile 4 4 0 0%
src/flag_gems/ops/mm_streamk.py mac_loop 51 51 0 0%
src/flag_gems/ops/mm_streamk.py first_wave 39 39 0 0%
src/flag_gems/ops/mm_streamk.py first_wave_for_bf16 47 47 0 0%
src/flag_gems/ops/mm_streamk.py classic_mm 30 30 0 0%
src/flag_gems/ops/mm_streamk.py streamk_mm 29 2 0 93%
src/flag_gems/ops/mm_streamk.py (no function) 25 0 0 100%
src/flag_gems/ops/mse_loss.py kernel_1 14 14 0 0%
src/flag_gems/ops/mse_loss.py kernel_2 6 6 0 0%
src/flag_gems/ops/mse_loss.py func 1 1 0 0%
src/flag_gems/ops/mse_loss.py mse_loss 16 0 0 100%
src/flag_gems/ops/mse_loss.py (no function) 24 0 0 100%
src/flag_gems/ops/mul.py mul_func 1 1 0 0%
src/flag_gems/ops/mul.py mul_func_scalar 1 1 0 0%
src/flag_gems/ops/mul.py mul 8 1 0 88%
src/flag_gems/ops/mul.py mul_ 4 0 0 100%
src/flag_gems/ops/mul.py (no function) 13 0 0 100%
src/flag_gems/ops/multinomial.py multinomial_with_replacement 16 16 0 0%
src/flag_gems/ops/multinomial.py multinomial 24 0 0 100%
src/flag_gems/ops/multinomial.py (no function) 12 0 0 100%
src/flag_gems/ops/mv.py mv_kernel 17 17 0 0%
src/flag_gems/ops/mv.py mv 8 0 0 100%
src/flag_gems/ops/mv.py (no function) 14 0 0 100%
src/flag_gems/ops/nan_to_num.py nan_to_num_func 7 7 0 0%
src/flag_gems/ops/nan_to_num.py nan_to_num 8 0 0 100%
src/flag_gems/ops/nan_to_num.py (no function) 11 0 0 100%
src/flag_gems/ops/ne.py ne_func 1 1 0 0%
src/flag_gems/ops/ne.py ne 2 0 0 100%
src/flag_gems/ops/ne.py ne_func_scalar 1 1 0 0%
src/flag_gems/ops/ne.py ne_scalar 2 0 0 100%
src/flag_gems/ops/ne.py (no function) 13 0 0 100%
src/flag_gems/ops/neg.py neg_func 1 1 0 0%
src/flag_gems/ops/neg.py neg 2 0 0 100%
src/flag_gems/ops/neg.py neg_ 2 0 0 100%
src/flag_gems/ops/neg.py (no function) 9 0 0 100%
src/flag_gems/ops/nllloss.py nll_loss_forward_kernel 27 27 0 0%
src/flag_gems/ops/nllloss.py nll_loss_backward_kernel 18 18 0 0%
src/flag_gems/ops/nllloss.py nll_loss2d_forward_kernel 31 31 0 0%
src/flag_gems/ops/nllloss.py nll_loss2d_backward_kernel 21 21 0 0%
src/flag_gems/ops/nllloss.py nll_loss_forward 27 0 0 100%
src/flag_gems/ops/nllloss.py nll_loss_backward 11 11 0 0%
src/flag_gems/ops/nllloss.py nll_loss2d_forward 27 0 0 100%
src/flag_gems/ops/nllloss.py nll_loss2d_backward 11 11 0 0%
src/flag_gems/ops/nllloss.py (no function) 23 0 0 100%
src/flag_gems/ops/nonzero.py nonzero_kernel 12 12 0 0%
src/flag_gems/ops/nonzero.py nonzero 20 1 0 95%
src/flag_gems/ops/nonzero.py (no function) 14 0 0 100%
src/flag_gems/ops/normal.py transform_func_tensor_tensor 1 1 0 0%
src/flag_gems/ops/normal.py transform_func_tensor_float 1 1 0 0%
src/flag_gems/ops/normal.py transform_func_float_tensor 1 1 0 0%
src/flag_gems/ops/normal.py transform_func_float_float 1 1 0 0%
src/flag_gems/ops/normal.py normal_distribution 9 0 0 100%
src/flag_gems/ops/normal.py normal_tensor_tensor 5 0 0 100%
src/flag_gems/ops/normal.py normal_tensor_float 5 0 0 100%
src/flag_gems/ops/normal.py normal_float_tensor 5 0 0 100%
src/flag_gems/ops/normal.py normal_ 6 0 0 100%
src/flag_gems/ops/normal.py (no function) 27 0 0 100%
src/flag_gems/ops/one_hot.py one_hot 27 6 0 78%
src/flag_gems/ops/one_hot.py (no function) 5 0 0 100%
src/flag_gems/ops/ones.py ones_kernel 5 5 0 0%
src/flag_gems/ops/ones.py ones 12 1 0 92%
src/flag_gems/ops/ones.py (no function) 14 0 0 100%
src/flag_gems/ops/ones_like.py ones_like 11 0 0 100%
src/flag_gems/ops/ones_like.py (no function) 7 0 0 100%
src/flag_gems/ops/pad.py parameter_for_wrapper 6 0 0 100%
src/flag_gems/ops/pad.py parameter_for_wrapper_out 9 0 0 100%
src/flag_gems/ops/pad.py parameter_ref_for_wrapper 9 0 0 100%
src/flag_gems/ops/pad.py output_ref_for_wrapper 1 0 0 100%
src/flag_gems/ops/pad.py generate_imports 12 0 0 100%
src/flag_gems/ops/pad.py generate_functional_padding_wrapper 29 0 0 100%
src/flag_gems/ops/pad.py generate_destination_passing_padding_wrapper 52 0 0 100%
src/flag_gems/ops/pad.py generate_pad_kernel 85 0 0 100%
src/flag_gems/ops/pad.py generate_code 7 0 0 100%
src/flag_gems/ops/pad.py PadFunction.__init__ 2 0 0 100%
src/flag_gems/ops/pad.py PadFunction.__call__ 14 0 0 100%
src/flag_gems/ops/pad.py PadFunction.arg_key 3 0 0 100%
src/flag_gems/ops/pad.py pad 20 0 0 100%
src/flag_gems/ops/pad.py constant_pad_nd 1 1 0 0%
src/flag_gems/ops/pad.py (no function) 24 0 0 100%
src/flag_gems/ops/per_token_group_quant_fp8.py _per_token_group_quant_fp8 17 17 0 0%
src/flag_gems/ops/per_token_group_quant_fp8.py _per_token_group_quant_fp8_colmajor 17 17 0 0%
src/flag_gems/ops/per_token_group_quant_fp8.py per_token_group_quant_fp8 21 3 0 86%
src/flag_gems/ops/per_token_group_quant_fp8.py (no function) 14 1 0 93%
src/flag_gems/ops/polar.py polar_kernel 3 3 0 0%
src/flag_gems/ops/polar.py polar 4 0 0 100%
src/flag_gems/ops/polar.py (no function) 10 0 0 100%
src/flag_gems/ops/pow.py pow_func 1 1 0 0%
src/flag_gems/ops/pow.py pow_tensor_tensor 2 0 0 100%
src/flag_gems/ops/pow.py pow_tensor_tensor_ 2 0 0 100%
src/flag_gems/ops/pow.py pow_func_tensor_scalar 1 1 0 0%
src/flag_gems/ops/pow.py pow_tensor_scalar 2 0 0 100%
src/flag_gems/ops/pow.py pow_tensor_scalar_ 2 0 0 100%
src/flag_gems/ops/pow.py pow_func_scalar_tensor 1 1 0 0%
src/flag_gems/ops/pow.py pow_scalar 2 0 0 100%
src/flag_gems/ops/pow.py (no function) 20 0 0 100%
src/flag_gems/ops/prod.py reduce_mul 1 1 0 0%
src/flag_gems/ops/prod.py prod_kernel_mid 8 8 0 0%
src/flag_gems/ops/prod.py prod_kernel_result 6 6 0 0%
src/flag_gems/ops/prod.py prod 13 0 0 100%
src/flag_gems/ops/prod.py heur_block_n 1 1 0 0%
src/flag_gems/ops/prod.py prod_kernel 15 15 0 0%
src/flag_gems/ops/prod.py prod_dim 17 0 0 100%
src/flag_gems/ops/prod.py (no function) 25 0 0 100%
src/flag_gems/ops/quantile.py heur_block_q 1 0 0 100%
src/flag_gems/ops/quantile.py heur_block_n 9 3 0 67%
src/flag_gems/ops/quantile.py quantile_kernel 28 28 0 0%
src/flag_gems/ops/quantile.py quantile_bitonic_kernel 37 37 0 0%
src/flag_gems/ops/quantile.py quantile 56 17 0 70%
src/flag_gems/ops/quantile.py (no function) 22 0 0 100%
src/flag_gems/ops/rand.py rand_kernel 20 20 0 0%
src/flag_gems/ops/rand.py rand 13 2 0 85%
src/flag_gems/ops/rand.py (no function) 15 0 0 100%
src/flag_gems/ops/rand_like.py rand_like 13 0 0 100%
src/flag_gems/ops/rand_like.py (no function) 9 0 0 100%
src/flag_gems/ops/randn.py high_precision_fast_sin_cos 18 18 0 0%
src/flag_gems/ops/randn.py pair_uniform_to_normal_fast 5 5 0 0%
src/flag_gems/ops/randn.py randn_kernel 22 22 0 0%
src/flag_gems/ops/randn.py randn 13 2 0 85%
src/flag_gems/ops/randn.py (no function) 19 0 0 100%
src/flag_gems/ops/randn_like.py randn_like 13 0 0 100%
src/flag_gems/ops/randn_like.py (no function) 9 0 0 100%
src/flag_gems/ops/randperm.py _get_iinfo_val 21 21 0 0%
src/flag_gems/ops/randperm.py bitonic_sortbykey_kernel 13 13 0 0%
src/flag_gems/ops/randperm.py radix_type_convert 15 15 0 0%
src/flag_gems/ops/randperm.py digit_hist_kernel 19 19 0 0%
src/flag_gems/ops/randperm.py radix_sortbykey_scatter_kernel 45 45 0 0%
src/flag_gems/ops/randperm.py duplicate_keys_shuffle_kernel 20 20 0 0%
src/flag_gems/ops/randperm.py sort_by_key 54 0 0 100%
src/flag_gems/ops/randperm.py randperm 37 10 0 73%
src/flag_gems/ops/randperm.py (no function) 42 0 0 100%
src/flag_gems/ops/reciprocal.py reciprocal_func 1 1 0 0%
src/flag_gems/ops/reciprocal.py reciprocal 2 0 0 100%
src/flag_gems/ops/reciprocal.py reciprocal_ 2 0 0 100%
src/flag_gems/ops/reciprocal.py (no function) 10 0 0 100%
src/flag_gems/ops/relu.py relu_forward 1 1 0 0%
src/flag_gems/ops/relu.py relu_backward 1 1 0 0%
src/flag_gems/ops/relu.py relu 3 0 0 100%
src/flag_gems/ops/relu.py relu_ 3 0 0 100%
src/flag_gems/ops/relu.py (no function) 13 0 0 100%
src/flag_gems/ops/repeat.py parameter_for_wrapper 4 0 0 100%
src/flag_gems/ops/repeat.py parameter_for_wrapper_out 4 0 0 100%
src/flag_gems/ops/repeat.py parameter_ref_for_wrapper 4 0 0 100%
src/flag_gems/ops/repeat.py output_ref_for_wrapper 1 0 0 100%
src/flag_gems/ops/repeat.py generate_imports 13 0 0 100%
src/flag_gems/ops/repeat.py generate_functional_repeat_wrapper 38 0 0 100%
src/flag_gems/ops/repeat.py generate_destination_passing_repeat_wrapper 48 2 0 96%
src/flag_gems/ops/repeat.py generate_repeat_kernel 89 0 0 100%
src/flag_gems/ops/repeat.py generate_code 5 0 0 100%
src/flag_gems/ops/repeat.py RepeatFunction.__init__ 2 0 0 100%
src/flag_gems/ops/repeat.py RepeatFunction.__call__ 15 0 0 100%
src/flag_gems/ops/repeat.py RepeatFunction.arg_key 2 0 0 100%
src/flag_gems/ops/repeat.py repeat 3 0 0 100%
src/flag_gems/ops/repeat.py (no function) 23 0 0 100%
src/flag_gems/ops/repeat_interleave.py copy_func 1 1 0 0%
src/flag_gems/ops/repeat_interleave.py repeat_interleave_self_int 25 3 0 88%
src/flag_gems/ops/repeat_interleave.py repeat_interleave_tensor_kernel 11 11 0 0%
src/flag_gems/ops/repeat_interleave.py repeat_interleave_tensor 11 0 0 100%
src/flag_gems/ops/repeat_interleave.py repeat_interleave_self_tensor 18 6 0 67%
src/flag_gems/ops/repeat_interleave.py (no function) 17 0 0 100%
src/flag_gems/ops/resolve_conj.py resolve_conj_kernel_1d 13 13 0 0%
src/flag_gems/ops/resolve_conj.py resolve_conj_kernel_2d_strided 15 15 0 0%
src/flag_gems/ops/resolve_conj.py resolve_conj_kernel_large_2d 16 16 0 0%
src/flag_gems/ops/resolve_conj.py resolve_conj_triton 39 39 0 0%
src/flag_gems/ops/resolve_conj.py resolve_conj 6 3 0 50%
src/flag_gems/ops/resolve_conj.py (no function) 13 0 0 100%
src/flag_gems/ops/resolve_neg.py resolve_neg 2 0 0 100%
src/flag_gems/ops/resolve_neg.py (no function) 5 0 0 100%
src/flag_gems/ops/rms_norm.py rms_norm_kernel 15 15 0 0%
src/flag_gems/ops/rms_norm.py rms_norm_grad_dx_kernel 17 17 0 0%
src/flag_gems/ops/rms_norm.py rms_norm_grad_dw_kernel 18 18 0 0%
src/flag_gems/ops/rms_norm.py rms_norm_forward 12 0 0 100%
src/flag_gems/ops/rms_norm.py rms_norm_backward 20 20 0 0%
src/flag_gems/ops/rms_norm.py RmsNorm.forward 5 0 0 100%
src/flag_gems/ops/rms_norm.py RmsNorm.backward 5 5 0 0%
src/flag_gems/ops/rms_norm.py rms_norm 1 0 0 100%
src/flag_gems/ops/rms_norm.py (no function) 26 0 0 100%
src/flag_gems/ops/rsqrt.py rsqrt_func 1 1 0 0%
src/flag_gems/ops/rsqrt.py rsqrt 2 0 0 100%
src/flag_gems/ops/rsqrt.py rsqrt_ 2 0 0 100%
src/flag_gems/ops/rsqrt.py (no function) 10 0 0 100%
src/flag_gems/ops/scaled_softmax.py scaled_softmax_forward_kernel 40 40 0 0%
src/flag_gems/ops/scaled_softmax.py scaled_softmax_forward 13 0 0 100%
src/flag_gems/ops/scaled_softmax.py scaled_softmax_forward.grid 3 0 0 100%
src/flag_gems/ops/scaled_softmax.py scaled_softmax_backward_kernel 34 34 0 0%
src/flag_gems/ops/scaled_softmax.py scaled_softmax_backward 14 0 0 100%
src/flag_gems/ops/scaled_softmax.py scaled_softmax_backward.grid 3 0 0 100%
src/flag_gems/ops/scaled_softmax.py (no function) 15 0 0 100%
src/flag_gems/ops/scatter.py generate_imports 10 0 0 100%
src/flag_gems/ops/scatter.py generate_scatter_kernel 116 0 0 100%
src/flag_gems/ops/scatter.py parameter_for_wrapper 11 0 0 100%
src/flag_gems/ops/scatter.py generate_destination_passing_wrapper 39 0 0 100%
src/flag_gems/ops/scatter.py generate_code 6 0 0 100%
src/flag_gems/ops/scatter.py ScatterFunction.__init__ 2 0 0 100%
src/flag_gems/ops/scatter.py ScatterFunction.__call__ 14 0 0 100%
src/flag_gems/ops/scatter.py ScatterFunction.arg_key 3 0 0 100%
src/flag_gems/ops/scatter.py scatter 15 1 0 93%
src/flag_gems/ops/scatter.py scatter_ 14 0 0 100%
src/flag_gems/ops/scatter.py (no function) 21 0 0 100%
src/flag_gems/ops/scatter_add_.py scatter_add_kernel_1 12 12 0 0%
src/flag_gems/ops/scatter_add_.py generate_imports 10 0 0 100%
src/flag_gems/ops/scatter_add_.py generate_scatter_kernel 76 0 0 100%
src/flag_gems/ops/scatter_add_.py parameter_for_wrapper 9 0 0 100%
src/flag_gems/ops/scatter_add_.py generate_destination_passing_wrapper 33 0 0 100%
src/flag_gems/ops/scatter_add_.py generate_code 6 0 0 100%
src/flag_gems/ops/scatter_add_.py ScatterFunction.__init__ 2 0 0 100%
src/flag_gems/ops/scatter_add_.py ScatterFunction.__call__ 14 0 0 100%
src/flag_gems/ops/scatter_add_.py ScatterFunction.arg_key 3 0 0 100%
src/flag_gems/ops/scatter_add_.py scatter_add_0 15 0 0 100%
src/flag_gems/ops/scatter_add_.py clip_tensor_to_shape 4 4 0 0%
src/flag_gems/ops/scatter_add_.py scatter_add_1 24 24 0 0%
src/flag_gems/ops/scatter_add_.py scatter_add_ 19 6 0 68%
src/flag_gems/ops/scatter_add_.py (no function) 28 0 0 100%
src/flag_gems/ops/select_scatter.py select_scatter_kernel 14 14 0 0%
src/flag_gems/ops/select_scatter.py select_scatter 22 0 0 100%
src/flag_gems/ops/select_scatter.py (no function) 9 0 0 100%
src/flag_gems/ops/sigmoid.py sigmoid_forward 2 2 0 0%
src/flag_gems/ops/sigmoid.py sigmoid_backward_kernel 3 3 0 0%
src/flag_gems/ops/sigmoid.py sigmoid 3 0 0 100%
src/flag_gems/ops/sigmoid.py sigmoid_backward 3 0 0 100%
src/flag_gems/ops/sigmoid.py sigmoid_ 3 0 0 100%
src/flag_gems/ops/sigmoid.py (no function) 15 0 0 100%
src/flag_gems/ops/silu.py silu_forward 3 3 0 0%
src/flag_gems/ops/silu.py silu_backward_kernel 5 5 0 0%
src/flag_gems/ops/silu.py silu 3 0 0 100%
src/flag_gems/ops/silu.py silu_backward 3 0 0 100%
src/flag_gems/ops/silu.py silu_ 3 0 0 100%
src/flag_gems/ops/silu.py (no function) 15 0 0 100%
src/flag_gems/ops/sin.py sin_func 1 1 0 0%
src/flag_gems/ops/sin.py sin 2 0 0 100%
src/flag_gems/ops/sin.py sin_ 3 0 0 100%
src/flag_gems/ops/sin.py (no function) 10 0 0 100%
src/flag_gems/ops/slice_scatter.py slice_scatter_kernel 15 15 0 0%
src/flag_gems/ops/slice_scatter.py slice_scatter 27 1 0 96%
src/flag_gems/ops/slice_scatter.py (no function) 9 0 0 100%
src/flag_gems/ops/softmax.py softmax_kernel_non_inner 37 37 0 0%
src/flag_gems/ops/softmax.py next_multiple_of 1 1 0 0%
src/flag_gems/ops/softmax.py prev_multiple_of 1 1 0 0%
src/flag_gems/ops/softmax.py softmax_kernel_inner 48 48 0 0%
src/flag_gems/ops/softmax.py softmax_backward_kernel_non_inner 33 33 0 0%
src/flag_gems/ops/softmax.py softmax_backward_kernel_inner 32 32 0 0%
src/flag_gems/ops/softmax.py softmax 20 1 0 95%
src/flag_gems/ops/softmax.py softmax_backward 17 0 0 100%
src/flag_gems/ops/softmax.py (no function) 33 0 0 100%
src/flag_gems/ops/softplus.py softplus_forward 5 5 0 0%
src/flag_gems/ops/softplus.py softplus 3 0 0 100%
src/flag_gems/ops/softplus.py (no function) 9 0 0 100%
src/flag_gems/ops/sort.py unwrap_if_constexpr 1 1 0 0%
src/flag_gems/ops/sort.py get_int_t 3 3 0 0%
src/flag_gems/ops/sort.py one_zeros 2 2 0 0%
src/flag_gems/ops/sort.py zero_ones 2 2 0 0%
src/flag_gems/ops/sort.py uint_to_uint 2 2 0 0%
src/flag_gems/ops/sort.py int_to_uint 11 11 0 0%
src/flag_gems/ops/sort.py floating_to_uint 14 14 0 0%
src/flag_gems/ops/sort.py convert_to_uint_preverse_order 7 7 0 0%
src/flag_gems/ops/sort.py compute_global_hist_kernel 23 23 0 0%
src/flag_gems/ops/sort.py sweep 43 43 0 0%
src/flag_gems/ops/sort.py radix_sort 35 0 0 100%
src/flag_gems/ops/sort.py sort_kernel 15 15 0 0%
src/flag_gems/ops/sort.py sort 2 0 0 100%
src/flag_gems/ops/sort.py sort_stable 17 0 0 100%
src/flag_gems/ops/sort.py (no function) 33 0 0 100%
src/flag_gems/ops/sqrt.py sqrt_func 1 1 0 0%
src/flag_gems/ops/sqrt.py sqrt 2 0 0 100%
src/flag_gems/ops/sqrt.py sqrt_ 3 0 0 100%
src/flag_gems/ops/sqrt.py (no function) 10 0 0 100%
src/flag_gems/ops/stack.py stack_copy_func_kernel_4 31 31 0 0%
src/flag_gems/ops/stack.py stack 46 3 0 93%
src/flag_gems/ops/stack.py (no function) 9 0 0 100%
src/flag_gems/ops/std.py _std_map_kernel 8 8 0 0%
src/flag_gems/ops/std.py _std_reduce_kernel 17 17 0 0%
src/flag_gems/ops/std.py _std_fused_dim_kernel 30 30 0 0%
src/flag_gems/ops/std.py std 40 5 0 88%
src/flag_gems/ops/std.py (no function) 15 0 0 100%
src/flag_gems/ops/sub.py sub_func 1 1 0 0%
src/flag_gems/ops/sub.py sub_func_tensor_scalar 1 1 0 0%
src/flag_gems/ops/sub.py sub_func_scalar_tensor 1 1 0 0%
src/flag_gems/ops/sub.py sub 8 1 0 88%
src/flag_gems/ops/sub.py sub_ 4 0 0 100%
src/flag_gems/ops/sub.py (no function) 16 0 0 100%
src/flag_gems/ops/sum.py sum_kernel_1 11 11 0 0%
src/flag_gems/ops/sum.py sum_kernel_2 9 9 0 0%
src/flag_gems/ops/sum.py sum 17 0 0 100%
src/flag_gems/ops/sum.py sum_out 15 15 0 0%
src/flag_gems/ops/sum.py sum_dim_kernel_non_inner 27 27 0 0%
src/flag_gems/ops/sum.py sum_dim_kernel_inner 25 25 0 0%
src/flag_gems/ops/sum.py sum_dim_kernel 16 16 0 0%
src/flag_gems/ops/sum.py sum_dim_comm 48 19 0 60%
src/flag_gems/ops/sum.py sum_dim 2 0 0 100%
src/flag_gems/ops/sum.py sum_dim_out 2 2 0 0%
src/flag_gems/ops/sum.py (no function) 34 0 0 100%
src/flag_gems/ops/tan.py tan_func 2 2 0 0%
src/flag_gems/ops/tan.py tan 2 0 0 100%
src/flag_gems/ops/tan.py tan_ 3 0 0 100%
src/flag_gems/ops/tan.py (no function) 10 0 0 100%
src/flag_gems/ops/tanh.py tanh_kernel 1 1 0 0%
src/flag_gems/ops/tanh.py tanh_backward_kernel 2 2 0 0%
src/flag_gems/ops/tanh.py tanh 3 0 0 100%
src/flag_gems/ops/tanh.py tanh_backward 3 0 0 100%
src/flag_gems/ops/tanh.py tanh_ 3 0 0 100%
src/flag_gems/ops/tanh.py (no function) 16 0 0 100%
src/flag_gems/ops/threshold.py threshold_kernel 1 1 0 0%
src/flag_gems/ops/threshold.py threshold_backward_kernel 1 1 0 0%
src/flag_gems/ops/threshold.py threshold 3 0 0 100%
src/flag_gems/ops/threshold.py threshold_backward 3 0 0 100%
src/flag_gems/ops/threshold.py (no function) 13 0 0 100%
src/flag_gems/ops/tile.py parameter_for_wrapper 4 0 0 100%
src/flag_gems/ops/tile.py parameter_for_wrapper_out 4 0 0 100%
src/flag_gems/ops/tile.py parameter_ref_for_wrapper 4 0 0 100%
src/flag_gems/ops/tile.py output_ref_for_wrapper 1 0 0 100%
src/flag_gems/ops/tile.py generate_imports 13 0 0 100%
src/flag_gems/ops/tile.py generate_functional_tile_wrapper 42 0 0 100%
src/flag_gems/ops/tile.py generate_destination_passing_tile_wrapper 48 2 0 96%
src/flag_gems/ops/tile.py generate_tile_kernel 89 0 0 100%
src/flag_gems/ops/tile.py generate_code 5 0 0 100%
src/flag_gems/ops/tile.py TileFunction.__init__ 2 0 0 100%
src/flag_gems/ops/tile.py TileFunction.__call__ 15 0 0 100%
src/flag_gems/ops/tile.py TileFunction.arg_key 2 0 0 100%
src/flag_gems/ops/tile.py tile 3 0 0 100%
src/flag_gems/ops/tile.py (no function) 23 0 0 100%
src/flag_gems/ops/to.py _to_copy_func 1 1 0 0%
src/flag_gems/ops/to.py _resolve_dtype 5 2 0 60%
src/flag_gems/ops/to.py _resolve_device 3 0 0 100%
src/flag_gems/ops/to.py _normalize_memory_format 3 0 0 100%
src/flag_gems/ops/to.py _allocate_preserve_format 3 0 0 100%
src/flag_gems/ops/to.py to_copy 17 3 0 82%
src/flag_gems/ops/to.py (no function) 15 0 0 100%
src/flag_gems/ops/topk.py _get_finfo_val 12 12 0 0%
src/flag_gems/ops/topk.py _get_iinfo_val 3 3 0 0%
src/flag_gems/ops/topk.py topk_stage1_kernel 22 22 0 0%
src/flag_gems/ops/topk.py _compare_and_swap 41 41 0 0%
src/flag_gems/ops/topk.py _bitonic_merge 9 9 0 0%
src/flag_gems/ops/topk.py argsort 5 5 0 0%
src/flag_gems/ops/topk.py topk_stage2_kernel 14 14 0 0%
src/flag_gems/ops/topk.py topk 30 1 0 97%
src/flag_gems/ops/topk.py (no function) 47 2 0 96%
src/flag_gems/ops/trace.py trace_kernel 21 21 0 0%
src/flag_gems/ops/trace.py trace 23 2 0 91%
src/flag_gems/ops/trace.py (no function) 11 0 0 100%
src/flag_gems/ops/triu.py triu_kernel 12 12 0 0%
src/flag_gems/ops/triu.py triu_batch_kernel 14 14 0 0%
src/flag_gems/ops/triu.py _check_batch_contiguous 18 10 0 44%
src/flag_gems/ops/triu.py triu 15 0 0 100%
src/flag_gems/ops/triu.py triu_ 27 0 0 100%
src/flag_gems/ops/triu.py (no function) 20 0 0 100%
src/flag_gems/ops/unfold_backward.py _unfold_backward_kernel 14 14 0 0%
src/flag_gems/ops/unfold_backward.py unfold_backward 23 2 0 91%
src/flag_gems/ops/unfold_backward.py (no function) 8 0 0 100%
src/flag_gems/ops/uniform.py uniform_kernel 20 20 0 0%
src/flag_gems/ops/uniform.py uniform_ 8 0 0 100%
src/flag_gems/ops/uniform.py (no function) 13 0 0 100%
src/flag_gems/ops/unique.py simple_unique_flat_kernel 16 16 0 0%
src/flag_gems/ops/unique.py output_counts_flat_impl 9 9 0 0%
src/flag_gems/ops/unique.py output_counts_flat_kernel 5 5 0 0%
src/flag_gems/ops/unique.py quick_output_flat_impl 11 11 0 0%
src/flag_gems/ops/unique.py quick_output_flat_kernel 5 5 0 0%
src/flag_gems/ops/unique.py local_quick_unique_flat_impl 18 18 0 0%
src/flag_gems/ops/unique.py local_quick_unique_flat_kernel 5 5 0 0%
src/flag_gems/ops/unique.py global_quick_unique_flat_impl 20 20 0 0%
src/flag_gems/ops/unique.py global_quick_unique_flat_kernel 8 8 0 0%
src/flag_gems/ops/unique.py sorted_quick_unique_flat 36 0 0 100%
src/flag_gems/ops/unique.py local_ne_flat_impl 11 11 0 0%
src/flag_gems/ops/unique.py local_ne_flat_kernel 5 5 0 0%
src/flag_gems/ops/unique.py global_cumsum_flat_impl 25 25 0 0%
src/flag_gems/ops/unique.py global_cumsum_flat_kernel 8 8 0 0%
src/flag_gems/ops/unique.py sorted_indices_unique_flat 30 0 0 100%
src/flag_gems/ops/unique.py simple_unique_flat 20 0 0 100%
src/flag_gems/ops/unique.py _unique2 9 0 0 100%
src/flag_gems/ops/unique.py (no function) 43 0 0 100%
src/flag_gems/ops/upsample_bicubic2d_aa.py upsample_bicubic2d_aa_kernel 97 97 0 0%
src/flag_gems/ops/upsample_bicubic2d_aa.py general_interpolate_bicubic2d_aa_kernel 42 42 0 0%
src/flag_gems/ops/upsample_bicubic2d_aa.py bicubic_reciprocal_scale 7 2 0 71%
src/flag_gems/ops/upsample_bicubic2d_aa.py _upsample_bicubic2d_aa 14 0 0 100%
src/flag_gems/ops/upsample_bicubic2d_aa.py (no function) 18 0 0 100%
src/flag_gems/ops/upsample_linear1d.py upsample_linear1d_kernel 21 21 0 0%
src/flag_gems/ops/upsample_linear1d.py upsample_linear1d 20 2 0 90%
src/flag_gems/ops/upsample_linear1d.py (no function) 9 0 0 100%
src/flag_gems/ops/upsample_nearest1d.py upsample_nearest1d_kernel 22 22 0 0%
src/flag_gems/ops/upsample_nearest1d.py upsample_nearest1d 15 1 0 93%
src/flag_gems/ops/upsample_nearest1d.py (no function) 14 0 0 100%
src/flag_gems/ops/upsample_nearest2d.py upsample_nearest2d_kernel 26 26 0 0%
src/flag_gems/ops/upsample_nearest2d.py upsample_nearest2d 18 2 0 89%
src/flag_gems/ops/upsample_nearest2d.py (no function) 14 0 0 100%
src/flag_gems/ops/var_mean.py welford_func 7 7 0 0%
src/flag_gems/ops/var_mean.py var_mean_welford_kernel 25 25 0 0%
src/flag_gems/ops/var_mean.py var_mean_kernel_1 14 14 0 0%
src/flag_gems/ops/var_mean.py var_mean_kernel_2 12 12 0 0%
src/flag_gems/ops/var_mean.py var_mean 34 1 0 97%
src/flag_gems/ops/var_mean.py (no function) 23 0 0 100%
src/flag_gems/ops/vdot.py compute_vdot 12 12 0 0%
src/flag_gems/ops/vdot.py vdot_kernel_complex 19 19 0 0%
src/flag_gems/ops/vdot.py reduce_kernel_complex 10 10 0 0%
src/flag_gems/ops/vdot.py dot_kernel 12 12 0 0%
src/flag_gems/ops/vdot.py reduce_kernel 6 6 0 0%
src/flag_gems/ops/vdot.py dot_kernel_fp32 7 7 0 0%
src/flag_gems/ops/vdot.py vdot 46 0 0 100%
src/flag_gems/ops/vdot.py (no function) 28 0 0 100%
src/flag_gems/ops/vector_norm.py l2_norm_kernel 14 14 0 0%
src/flag_gems/ops/vector_norm.py l2_norm_kernel_1 8 8 0 0%
src/flag_gems/ops/vector_norm.py l2_norm_kernel_2 6 6 0 0%
src/flag_gems/ops/vector_norm.py max_norm_kernel 14 14 0 0%
src/flag_gems/ops/vector_norm.py max_norm_kernel_1 8 8 0 0%
src/flag_gems/ops/vector_norm.py max_norm_kernel_2 6 6 0 0%
src/flag_gems/ops/vector_norm.py min_norm_kernel 14 14 0 0%
src/flag_gems/ops/vector_norm.py min_norm_kernel_1 8 8 0 0%
src/flag_gems/ops/vector_norm.py min_norm_kernel_2 6 6 0 0%
src/flag_gems/ops/vector_norm.py l0_norm_kernel 14 14 0 0%
src/flag_gems/ops/vector_norm.py l0_norm_kernel_1 9 9 0 0%
src/flag_gems/ops/vector_norm.py l0_norm_kernel_2 6 6 0 0%
src/flag_gems/ops/vector_norm.py v_norm_kernel 14 14 0 0%
src/flag_gems/ops/vector_norm.py l1_norm_kernel_1 8 8 0 0%
src/flag_gems/ops/vector_norm.py l1_norm_kernel_2 6 6 0 0%
src/flag_gems/ops/vector_norm.py vector_norm 56 5 0 91%
src/flag_gems/ops/vector_norm.py (no function) 62 0 0 100%
src/flag_gems/ops/vstack.py vstack_kernel 20 20 0 0%
src/flag_gems/ops/vstack.py vstack 42 0 0 100%
src/flag_gems/ops/vstack.py (no function) 14 0 0 100%
src/flag_gems/ops/weightnorm.py weight_norm_kernel_last 21 21 0 0%
src/flag_gems/ops/weightnorm.py weight_norm_kernel_first 21 21 0 0%
src/flag_gems/ops/weightnorm.py weight_norm_bwd_kernel_last 26 26 0 0%
src/flag_gems/ops/weightnorm.py weight_norm_bwd_kernel_first 26 26 0 0%
src/flag_gems/ops/weightnorm.py weight_norm_interface 18 0 0 100%
src/flag_gems/ops/weightnorm.py weight_norm_interface_backward 20 20 0 0%
src/flag_gems/ops/weightnorm.py (no function) 28 0 0 100%
src/flag_gems/ops/where.py where_inner 1 1 0 0%
src/flag_gems/ops/where.py where_self_out 28 0 0 100%
src/flag_gems/ops/where.py where_self 2 0 0 100%
src/flag_gems/ops/where.py where_scalar_self 2 0 0 100%
src/flag_gems/ops/where.py where_scalar_other 2 0 0 100%
src/flag_gems/ops/where.py (no function) 13 0 0 100%
src/flag_gems/ops/zeros.py zeros_kernel 5 5 0 0%
src/flag_gems/ops/zeros.py zeros 11 1 0 91%
src/flag_gems/ops/zeros.py zero_ 6 0 0 100%
src/flag_gems/ops/zeros.py (no function) 13 0 0 100%
src/flag_gems/ops/zeros_like.py zeros_like 11 0 0 100%
src/flag_gems/ops/zeros_like.py (no function) 7 0 0 100%
src/flag_gems/patches/__init__.py (no function) 3 0 0 100%
src/flag_gems/patches/patch_util.py _try_import_vllm_extension 5 1 0 80%
src/flag_gems/patches/patch_util.py _is_op_registered 5 2 0 60%
src/flag_gems/patches/patch_util.py _ensure_vllm_library_exists 11 5 0 55%
src/flag_gems/patches/patch_util.py _define_op_if_not_exists 5 2 0 60%
src/flag_gems/patches/patch_util.py patch_module_method 5 5 0 0%
src/flag_gems/patches/patch_util.py patch_vllm_lib 6 6 0 0%
src/flag_gems/patches/patch_util.py (no function) 22 0 0 100%
src/flag_gems/patches/patch_vllm_all.py custom_gems_rms_forward_cuda 2 2 0 0%
src/flag_gems/patches/patch_vllm_all.py custom_gems_rope_forward_cuda 23 23 0 0%
src/flag_gems/patches/patch_vllm_all.py custom_gems_silu_and_mul 4 4 0 0%
src/flag_gems/patches/patch_vllm_all.py custom_gems_write_to_paged_cache 2 2 0 0%
src/flag_gems/patches/patch_vllm_all.py custom_gems_flash_mla_forward 16 16 0 0%
src/flag_gems/patches/patch_vllm_all.py custom_gems_flash_attention_impl_forward 32 32 0 0%
src/flag_gems/patches/patch_vllm_all.py custom_silu_and_mul 3 3 0 0%
src/flag_gems/patches/patch_vllm_all.py custom_moe_align_block_size 1 1 0 0%
src/flag_gems/patches/patch_vllm_all.py custom_moe_grouped_topk 2 2 0 0%
src/flag_gems/patches/patch_vllm_all.py custom_topk_softmax 1 1 0 0%
src/flag_gems/patches/patch_vllm_all.py custom_moe_sum 2 2 0 0%
src/flag_gems/patches/patch_vllm_all.py custom_apply_repetition_penalties 1 1 0 0%
src/flag_gems/patches/patch_vllm_all.py custom_get_scheduler_metadata 1 1 0 0%
src/flag_gems/patches/patch_vllm_all.py custom_per_token_group_fp8_quant 5 5 0 0%
src/flag_gems/patches/patch_vllm_all.py custom_cutlass_scaled_mm 1 1 0 0%
src/flag_gems/patches/patch_vllm_all.py custom_concat_and_cache_mla 1 1 0 0%
src/flag_gems/patches/patch_vllm_all.py custom_gems_flashattn_mla_forward_decode 17 17 0 0%
src/flag_gems/patches/patch_vllm_all.py patch_vllm_vit_to_attn 5 5 0 0%
src/flag_gems/patches/patch_vllm_all.py patch_vllm_vit_to_attn._seqlens_to_cu_seqlens 2 2 0 0%
src/flag_gems/patches/patch_vllm_all.py patch_vllm_vit_to_attn._torch_sdpa_wrapper_gems 13 13 0 0%
src/flag_gems/patches/patch_vllm_all.py patch_vllm_vit_to_attn._wrapped_vit_xformers_attn_wrapper 4 4 0 0%
src/flag_gems/patches/patch_vllm_all.py apply_gems_patches_to_vllm 22 22 0 0%
src/flag_gems/patches/patch_vllm_all.py (no function) 25 0 0 100%
src/flag_gems/runtime/__init__.py get_tuned_config 1 0 0 100%
src/flag_gems/runtime/__init__.py get_heuristic_config 1 0 0 100%
src/flag_gems/runtime/__init__.py replace_customized_ops 15 10 0 33%
src/flag_gems/runtime/__init__.py (no function) 13 0 0 100%
src/flag_gems/runtime/backend/__init__.py BackendArchEvent.__new__ 3 0 0 100%
src/flag_gems/runtime/backend/__init__.py BackendArchEvent.__init__ 12 0 0 100%
src/flag_gems/runtime/backend/__init__.py BackendArchEvent.get_functions_from_module 1 0 0 100%
src/flag_gems/runtime/backend/__init__.py BackendArchEvent.get_heuristics_configs 10 5 0 50%
src/flag_gems/runtime/backend/__init__.py BackendArchEvent.get_autotune_configs 2 0 0 100%
src/flag_gems/runtime/backend/__init__.py BackendArchEvent.get_arch 17 5 0 71%
src/flag_gems/runtime/backend/__init__.py BackendArchEvent._get_supported_archs 10 0 0 100%
src/flag_gems/runtime/backend/__init__.py BackendArchEvent.get_supported_archs 1 1 0 0%
src/flag_gems/runtime/backend/__init__.py BackendArchEvent.get_arch_module 5 0 0 100%
src/flag_gems/runtime/backend/__init__.py BackendArchEvent.get_arch_ops 17 7 0 59%
src/flag_gems/runtime/backend/__init__.py import_vendor_extra_lib 15 9 0 40%
src/flag_gems/runtime/backend/__init__.py get_codegen_result 7 2 0 71%
src/flag_gems/runtime/backend/__init__.py gen_torch_tensor_attr_res 3 3 0 0%
src/flag_gems/runtime/backend/__init__.py set_tl_extra_backend_module 5 0 0 100%
src/flag_gems/runtime/backend/__init__.py get_tl_extra_backend_module 1 0 0 100%
src/flag_gems/runtime/backend/__init__.py set_torch_backend_device_fn 5 1 0 80%
src/flag_gems/runtime/backend/__init__.py get_torch_backend_device_fn 1 0 0 100%
src/flag_gems/runtime/backend/__init__.py gen_torch_device_object 6 0 0 100%
src/flag_gems/runtime/backend/__init__.py get_vendor_module 6 0 0 100%
src/flag_gems/runtime/backend/__init__.py get_vendor_module.get_module 4 0 0 100%
src/flag_gems/runtime/backend/__init__.py get_vendor_info 4 0 0 100%
src/flag_gems/runtime/backend/__init__.py get_vendor_infos 9 0 0 100%
src/flag_gems/runtime/backend/__init__.py get_current_device_extend_op 11 1 0 91%
src/flag_gems/runtime/backend/__init__.py get_curent_device_unused_op 2 2 0 0%
src/flag_gems/runtime/backend/__init__.py get_heuristic_config 7 3 0 57%
src/flag_gems/runtime/backend/__init__.py get_tune_config 2 0 0 100%
src/flag_gems/runtime/backend/__init__.py (no function) 51 0 0 100%
src/flag_gems/runtime/backend/_aipu/__init__.py (no function) 6 0 0 100%
src/flag_gems/runtime/backend/_aipu/fused/__init__.py (no function) 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py simple_elementwise_blocksize_heur 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py argmax_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py argmax_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py argmin_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py argmin_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py bmm_heur_divisible_m 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py bmm_heur_divisible_n 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py bmm_heur_divisible_k 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py dropout_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py dropout_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py exponential_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py exponential_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py gather_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py gather_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py index_select_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py index_select_heur_block_n 2 2 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py mm_heur_even_k 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py rand_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py rand_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py randn_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py randn_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py softmax_heur_tile_k 11 11 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py softmax_heur_tile_n_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py softmax_heur_one_tile_per_cta 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py softmax_heur_num_warps_non_inner 6 6 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py softmax_heur_tile_n_inner 3 3 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py softmax_heur_num_warps_inner 6 6 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py softmax_heur_tile_n_bwd_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py softmax_heur_tile_m 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py uniform_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py uniform_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py var_mean_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py upsample_nearest2d_SAME_H 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py upsample_nearest2d_SAME_W 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py batch_norm_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py batch_norm_heur_block_n 3 3 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py vdot_heur_block_size 6 6 0 0%
src/flag_gems/runtime/backend/_aipu/heuristics_config_utils.py (no function) 39 39 0 0%
src/flag_gems/runtime/backend/_aipu/ops/__init__.py (no function) 3 3 0 0%
src/flag_gems/runtime/backend/_aipu/ops/cumsum.py scan_part_sum_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_aipu/ops/cumsum.py add_base_sum_kernel 10 10 0 0%
src/flag_gems/runtime/backend/_aipu/ops/cumsum.py scan_part_sum_abc_kernel 23 23 0 0%
src/flag_gems/runtime/backend/_aipu/ops/cumsum.py add_base_sum_abc_kernel 18 18 0 0%
src/flag_gems/runtime/backend/_aipu/ops/cumsum.py scan_then_fan_col 12 12 0 0%
src/flag_gems/runtime/backend/_aipu/ops/cumsum.py scan_then_fan 12 12 0 0%
src/flag_gems/runtime/backend/_aipu/ops/cumsum.py cumsum_wrapper 22 22 0 0%
src/flag_gems/runtime/backend/_aipu/ops/cumsum.py cumsum 2 2 0 0%
src/flag_gems/runtime/backend/_aipu/ops/cumsum.py cumsum_out 2 2 0 0%
src/flag_gems/runtime/backend/_aipu/ops/cumsum.py normed_cumsum_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_aipu/ops/cumsum.py block_cumsum_kernel 35 35 0 0%
src/flag_gems/runtime/backend/_aipu/ops/cumsum.py block_update_kernel 22 22 0 0%
src/flag_gems/runtime/backend/_aipu/ops/cumsum.py normed_cumsum 37 37 0 0%
src/flag_gems/runtime/backend/_aipu/ops/cumsum.py (no function) 38 38 0 0%
src/flag_gems/runtime/backend/_aipu/ops/multinomial.py multinomial_with_replacement 16 16 0 0%
src/flag_gems/runtime/backend/_aipu/ops/multinomial.py multinomial 24 24 0 0%
src/flag_gems/runtime/backend/_aipu/ops/multinomial.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_amd/__init__.py (no function) 4 0 0 100%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py simple_elementwise_blocksize_heur 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py argmax_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py argmax_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py argmin_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py argmin_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py bmm_heur_divisible_m 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py bmm_heur_divisible_n 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py bmm_heur_divisible_k 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py dropout_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py dropout_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py exponential_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py exponential_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py gather_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py gather_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py index_select_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py index_select_heur_block_n 2 2 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py mm_heur_even_k 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py rand_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py rand_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py randn_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py randn_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py softmax_heur_tile_k 11 11 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py softmax_heur_tile_n_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py softmax_heur_one_tile_per_cta 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py softmax_heur_num_warps_non_inner 6 6 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py softmax_heur_tile_n_inner 3 3 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py softmax_heur_num_warps_inner 6 6 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py softmax_heur_tile_n_bwd_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py softmax_heur_tile_m 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py uniform_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py uniform_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py var_mean_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py upsample_nearest2d_SAME_H 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py upsample_nearest2d_SAME_W 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py upsample_nearest2d_USE_INT32_IDX 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py batch_norm_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py batch_norm_heur_block_n 3 3 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py vdot_heur_block_size 6 6 0 0%
src/flag_gems/runtime/backend/_amd/heuristics_config_utils.py (no function) 41 41 0 0%
src/flag_gems/runtime/backend/_amd/ops/__init__.py (no function) 0 0 0 100%
src/flag_gems/runtime/backend/_arm/__init__.py (no function) 4 4 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py argmax_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py argmax_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py argmin_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py argmin_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py bmm_heur_divisible_m 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py bmm_heur_divisible_n 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py bmm_heur_divisible_k 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py dropout_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py dropout_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py exponential_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py exponential_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py gather_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py gather_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py index_select_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py index_select_heur_block_n 2 2 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py mm_heur_even_k 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py rand_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py rand_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py randn_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py randn_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py softmax_heur_tile_k 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py softmax_heur_tile_n_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py softmax_heur_one_tile_per_cta 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py softmax_heur_num_warps_non_inner 6 6 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py softmax_heur_tile_n_inner 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py softmax_heur_num_warps_inner 6 6 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py softmax_heur_tile_n_bwd_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py softmax_heur_tile_m 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py uniform_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py uniform_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py var_mean_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py upsample_nearest2d_SAME_H 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py upsample_nearest2d_SAME_W 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py batch_norm_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py batch_norm_heur_block_n 3 3 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py vdot_heur_block_size 6 6 0 0%
src/flag_gems/runtime/backend/_arm/heuristics_config_utils.py (no function) 38 38 0 0%
src/flag_gems/runtime/backend/_arm/ops/__init__.py (no function) 3 3 0 0%
src/flag_gems/runtime/backend/_arm/ops/add.py add_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_arm/ops/add.py add 6 6 0 0%
src/flag_gems/runtime/backend/_arm/ops/add.py (no function) 6 6 0 0%
src/flag_gems/runtime/backend/_arm/ops/gelu.py gelu_none 3 3 0 0%
src/flag_gems/runtime/backend/_arm/ops/gelu.py gelu_tanh 2 2 0 0%
src/flag_gems/runtime/backend/_arm/ops/gelu.py gelu_backward_none 6 6 0 0%
src/flag_gems/runtime/backend/_arm/ops/gelu.py gelu_backward_tanh 5 5 0 0%
src/flag_gems/runtime/backend/_arm/ops/gelu.py Gelu.forward 7 7 0 0%
src/flag_gems/runtime/backend/_arm/ops/gelu.py Gelu.backward 7 7 0 0%
src/flag_gems/runtime/backend/_arm/ops/gelu.py gelu 2 2 0 0%
src/flag_gems/runtime/backend/_arm/ops/gelu.py (no function) 28 28 0 0%
src/flag_gems/runtime/backend/_ascend/__init__.py get_triton_extra_name 8 3 0 62%
src/flag_gems/runtime/backend/_ascend/__init__.py (no function) 6 0 0 100%
src/flag_gems/runtime/backend/_ascend/fused/__init__.py (no function) 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/fused/cross_entropy_loss.py celoss_indices_kernel 33 33 0 0%
src/flag_gems/runtime/backend/_ascend/fused/cross_entropy_loss.py celoss_probability_kernel 35 35 0 0%
src/flag_gems/runtime/backend/_ascend/fused/cross_entropy_loss.py celoss_indices_smooth_kernel 45 45 0 0%
src/flag_gems/runtime/backend/_ascend/fused/cross_entropy_loss.py celoss_indices_bwd 37 37 0 0%
src/flag_gems/runtime/backend/_ascend/fused/cross_entropy_loss.py celoss_probability_bwd 48 48 0 0%
src/flag_gems/runtime/backend/_ascend/fused/cross_entropy_loss.py celoss_indices_smooth_bwd 49 49 0 0%
src/flag_gems/runtime/backend/_ascend/fused/cross_entropy_loss.py sum_and_scale 25 25 0 0%
src/flag_gems/runtime/backend/_ascend/fused/cross_entropy_loss.py CrossEntropyLoss.forward 46 46 0 0%
src/flag_gems/runtime/backend/_ascend/fused/cross_entropy_loss.py CrossEntropyLoss.backward 18 18 0 0%
src/flag_gems/runtime/backend/_ascend/fused/cross_entropy_loss.py cross_entropy_loss 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/fused/cross_entropy_loss.py (no function) 43 43 0 0%
src/flag_gems/runtime/backend/_ascend/fused/fused_add_rms_norm.py fused_add_rms_norm_kernel 23 23 0 0%
src/flag_gems/runtime/backend/_ascend/fused/fused_add_rms_norm.py fused_add_rms_norm 11 11 0 0%
src/flag_gems/runtime/backend/_ascend/fused/fused_add_rms_norm.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_ascend/fused/rotary_embedding.py rotary_embedding_rw_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/fused/rotary_embedding.py rotary_embedding_siso_kernel 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/fused/rotary_embedding.py apply_rotary_pos_emb 23 23 0 0%
src/flag_gems/runtime/backend/_ascend/fused/rotary_embedding.py apply_rotary_pos_emb.torch_rotary_embedding 22 22 0 0%
src/flag_gems/runtime/backend/_ascend/fused/rotary_embedding.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_ascend/fused/skip_layernorm.py skip_layer_norm_kernel 30 30 0 0%
src/flag_gems/runtime/backend/_ascend/fused/skip_layernorm.py SkipLayerNorm.forward 13 13 0 0%
src/flag_gems/runtime/backend/_ascend/fused/skip_layernorm.py skip_layer_norm 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/fused/skip_layernorm.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py argmax_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py argmax_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py argmax_heur_tile_k 2 2 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py argmax_heur_tile_n_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py argmax_heur_one_tile_per_cta 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py argmin_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py argmin_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py bmm_heur_divisible_m 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py bmm_heur_divisible_n 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py bmm_heur_divisible_k 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py dropout_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py dropout_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py exponential_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py exponential_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py gather_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py gather_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py index_select_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py index_select_heur_block_n 2 2 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py mm_heur_even_k 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py rand_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py rand_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py randn_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py randn_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py softmax_heur_tile_k 11 11 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py softmax_heur_tile_n_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py softmax_heur_one_tile_per_cta 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py softmax_heur_num_warps_non_inner 6 6 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py softmax_heur_tile_n_inner 3 3 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py softmax_heur_num_warps_inner 6 6 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py softmax_heur_tile_n_bwd_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py softmax_heur_tile_m 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py uniform_heur_block 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py uniform_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py var_mean_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py upsample_nearest2d_SAME_H 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py upsample_nearest2d_SAME_W 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py batch_norm_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py batch_norm_heur_block_n 3 3 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py vdot_heur_block_size 6 6 0 0%
src/flag_gems/runtime/backend/_ascend/heuristics_config_utils.py (no function) 41 41 0 0%
src/flag_gems/runtime/backend/_ascend/ops/__init__.py (no function) 63 63 0 0%
src/flag_gems/runtime/backend/_ascend/ops/addmm.py addmm_kernel 24 24 0 0%
src/flag_gems/runtime/backend/_ascend/ops/addmm.py addmm 13 13 0 0%
src/flag_gems/runtime/backend/_ascend/ops/addmm.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/all.py reduce_all 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/all.py all_kernel_dim 19 19 0 0%
src/flag_gems/runtime/backend/_ascend/ops/all.py all_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_ascend/ops/all.py all_kernel_2 6 6 0 0%
src/flag_gems/runtime/backend/_ascend/ops/all.py all 11 11 0 0%
src/flag_gems/runtime/backend/_ascend/ops/all.py all_dim 22 22 0 0%
src/flag_gems/runtime/backend/_ascend/ops/all.py all_dims 19 19 0 0%
src/flag_gems/runtime/backend/_ascend/ops/all.py all_dims.grid 3 3 0 0%
src/flag_gems/runtime/backend/_ascend/ops/all.py (no function) 25 25 0 0%
src/flag_gems/runtime/backend/_ascend/ops/amax.py amax_kernel_1 9 9 0 0%
src/flag_gems/runtime/backend/_ascend/ops/amax.py amax_kernel_2 7 7 0 0%
src/flag_gems/runtime/backend/_ascend/ops/amax.py amax_kernel 22 22 0 0%
src/flag_gems/runtime/backend/_ascend/ops/amax.py amax 40 40 0 0%
src/flag_gems/runtime/backend/_ascend/ops/amax.py (no function) 22 22 0 0%
src/flag_gems/runtime/backend/_ascend/ops/angle.py angle_func 3 3 0 0%
src/flag_gems/runtime/backend/_ascend/ops/angle.py angle_float_and_int 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/ops/angle.py angle 7 7 0 0%
src/flag_gems/runtime/backend/_ascend/ops/angle.py (no function) 21 21 0 0%
src/flag_gems/runtime/backend/_ascend/ops/any.py reduce_any 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/any.py any_kernel_dim 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/any.py any_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_ascend/ops/any.py any_kernel_2 6 6 0 0%
src/flag_gems/runtime/backend/_ascend/ops/any.py any 11 11 0 0%
src/flag_gems/runtime/backend/_ascend/ops/any.py any_dim 22 22 0 0%
src/flag_gems/runtime/backend/_ascend/ops/any.py any_dims 19 19 0 0%
src/flag_gems/runtime/backend/_ascend/ops/any.py (no function) 25 25 0 0%
src/flag_gems/runtime/backend/_ascend/ops/arange.py arange_func 7 7 0 0%
src/flag_gems/runtime/backend/_ascend/ops/arange.py arange_start 16 16 0 0%
src/flag_gems/runtime/backend/_ascend/ops/arange.py arange 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/arange.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/argmax.py argmax_kernel_1 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/argmax.py argmax_kernel_2 9 9 0 0%
src/flag_gems/runtime/backend/_ascend/ops/argmax.py argmax_kernel_non_inner 34 34 0 0%
src/flag_gems/runtime/backend/_ascend/ops/argmax.py argmax_kernel 22 22 0 0%
src/flag_gems/runtime/backend/_ascend/ops/argmax.py argmax 45 45 0 0%
src/flag_gems/runtime/backend/_ascend/ops/argmax.py (no function) 26 26 0 0%
src/flag_gems/runtime/backend/_ascend/ops/argmin.py argmin_kernel_1 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/argmin.py argmin_kernel_2 9 9 0 0%
src/flag_gems/runtime/backend/_ascend/ops/argmin.py argmin_kernel 22 22 0 0%
src/flag_gems/runtime/backend/_ascend/ops/argmin.py argmin 36 36 0 0%
src/flag_gems/runtime/backend/_ascend/ops/argmin.py (no function) 22 22 0 0%
src/flag_gems/runtime/backend/_ascend/ops/bmm.py bmm_kernel 37 37 0 0%
src/flag_gems/runtime/backend/_ascend/ops/bmm.py bmm 10 10 0 0%
src/flag_gems/runtime/backend/_ascend/ops/bmm.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cat.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cat.py cat 28 28 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cat.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/count_nonzero.py count_nonzero_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_ascend/ops/count_nonzero.py count_nonzero_kernel 15 15 0 0%
src/flag_gems/runtime/backend/_ascend/ops/count_nonzero.py count_nonzero_combin_kernel_1 9 9 0 0%
src/flag_gems/runtime/backend/_ascend/ops/count_nonzero.py count_nonzero_combin_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_ascend/ops/count_nonzero.py count_nonzero 36 36 0 0%
src/flag_gems/runtime/backend/_ascend/ops/count_nonzero.py count_nonzero.grid 3 3 0 0%
src/flag_gems/runtime/backend/_ascend/ops/count_nonzero.py (no function) 23 23 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cumsum.py get_scan_accum_type 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cumsum.py scan_part_sum_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cumsum.py add_base_sum_kernel 10 10 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cumsum.py scan_part_sum_abc_kernel 23 23 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cumsum.py add_base_sum_abc_kernel 18 18 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cumsum.py scan_then_fan_col 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cumsum.py scan_then_fan 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cumsum.py cumsum_wrapper 22 22 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cumsum.py reduce_then_scan_row 15 15 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cumsum.py reduce_then_scan_block_sum_kernel_row 13 13 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cumsum.py reduce_then_scan_root_scan_kernel_row 7 7 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cumsum.py reduce_then_scan_block_scan_kernel_row 13 13 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cumsum.py cumsum 2 2 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cumsum.py cumsum_out 2 2 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cumsum.py normed_cumsum_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cumsum.py block_cumsum_kernel 35 35 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cumsum.py block_update_kernel 22 22 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cumsum.py normed_cumsum 36 36 0 0%
src/flag_gems/runtime/backend/_ascend/ops/cumsum.py (no function) 49 49 0 0%
src/flag_gems/runtime/backend/_ascend/ops/diag.py diag_1d_to_2d_kernel 10 10 0 0%
src/flag_gems/runtime/backend/_ascend/ops/diag.py diag_2d_to_1d_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_ascend/ops/diag.py diag_1d_to_2d 9 9 0 0%
src/flag_gems/runtime/backend/_ascend/ops/diag.py diag_2d_to_1d 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/diag.py diag 6 6 0 0%
src/flag_gems/runtime/backend/_ascend/ops/diag.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/diag_embed.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/diag_embed.py diag_embed 19 19 0 0%
src/flag_gems/runtime/backend/_ascend/ops/diag_embed.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_ascend/ops/diagonal.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/diagonal.py diagonal_backward 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/ops/diagonal.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_ascend/ops/dot.py dot_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_ascend/ops/dot.py dot_kernel_1 13 13 0 0%
src/flag_gems/runtime/backend/_ascend/ops/dot.py dot_kernel_2 8 8 0 0%
src/flag_gems/runtime/backend/_ascend/ops/dot.py dot 24 24 0 0%
src/flag_gems/runtime/backend/_ascend/ops/dot.py (no function) 19 19 0 0%
src/flag_gems/runtime/backend/_ascend/ops/embedding.py embedding_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_ascend/ops/embedding.py indice_freq_kernel 7 7 0 0%
src/flag_gems/runtime/backend/_ascend/ops/embedding.py embedding_backward_kernel 18 18 0 0%
src/flag_gems/runtime/backend/_ascend/ops/embedding.py embedding_grad_scale_kernel 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/embedding.py Embedding.forward 18 18 0 0%
src/flag_gems/runtime/backend/_ascend/ops/embedding.py Embedding.backward 18 18 0 0%
src/flag_gems/runtime/backend/_ascend/ops/embedding.py embedding 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/embedding.py (no function) 27 27 0 0%
src/flag_gems/runtime/backend/_ascend/ops/exponential_.py fused_exponential_kernel 41 41 0 0%
src/flag_gems/runtime/backend/_ascend/ops/exponential_.py paste_u64 3 3 0 0%
src/flag_gems/runtime/backend/_ascend/ops/exponential_.py transform_exponential 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/ops/exponential_.py exponential_ 18 18 0 0%
src/flag_gems/runtime/backend/_ascend/ops/exponential_.py exponential_.grid_fn 3 3 0 0%
src/flag_gems/runtime/backend/_ascend/ops/exponential_.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_ascend/ops/fill.py fill_scalar_kernel 7 7 0 0%
src/flag_gems/runtime/backend/_ascend/ops/fill.py fill_tensor_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_ascend/ops/fill.py fill_tensor 13 13 0 0%
src/flag_gems/runtime/backend/_ascend/ops/fill.py fill_scalar 9 9 0 0%
src/flag_gems/runtime/backend/_ascend/ops/fill.py fill_tensor_ 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/fill.py fill_scalar_ 8 8 0 0%
src/flag_gems/runtime/backend/_ascend/ops/fill.py (no function) 18 18 0 0%
src/flag_gems/runtime/backend/_ascend/ops/flip.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/flip.py flip 21 21 0 0%
src/flag_gems/runtime/backend/_ascend/ops/flip.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/full.py check_dtype 8 8 0 0%
src/flag_gems/runtime/backend/_ascend/ops/full.py full_func 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/full.py full_func_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/full.py full 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/full.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_ascend/ops/full_like.py full_like 11 11 0 0%
src/flag_gems/runtime/backend/_ascend/ops/full_like.py (no function) 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/ops/gather.py compute_base_offset 10 10 0 0%
src/flag_gems/runtime/backend/_ascend/ops/gather.py _gather_flat_kernel_fixed 8 8 0 0%
src/flag_gems/runtime/backend/_ascend/ops/gather.py gather_flat_fixed 13 13 0 0%
src/flag_gems/runtime/backend/_ascend/ops/gather.py _gather_high_perf_kernel 10 10 0 0%
src/flag_gems/runtime/backend/_ascend/ops/gather.py gather_high_perf 8 8 0 0%
src/flag_gems/runtime/backend/_ascend/ops/gather.py gather 9 9 0 0%
src/flag_gems/runtime/backend/_ascend/ops/gather.py gather_backward 3 3 0 0%
src/flag_gems/runtime/backend/_ascend/ops/gather.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_ascend/ops/groupnorm.py group_norm_backward_kernel 37 37 0 0%
src/flag_gems/runtime/backend/_ascend/ops/groupnorm.py weight_bias_backward_kernel 29 29 0 0%
src/flag_gems/runtime/backend/_ascend/ops/groupnorm.py group_norm_kernel 49 49 0 0%
src/flag_gems/runtime/backend/_ascend/ops/groupnorm.py group_norm 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/groupnorm.py group_norm_backward 20 20 0 0%
src/flag_gems/runtime/backend/_ascend/ops/groupnorm.py (no function) 21 21 0 0%
src/flag_gems/runtime/backend/_ascend/ops/hstack.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/hstack.py hstack 30 30 0 0%
src/flag_gems/runtime/backend/_ascend/ops/hstack.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/index.py index_kernel_func 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/index.py index_wrapper 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/index.py get_max_rank_shape 10 10 0 0%
src/flag_gems/runtime/backend/_ascend/ops/index.py broadcast_indices 3 3 0 0%
src/flag_gems/runtime/backend/_ascend/ops/index.py index 8 8 0 0%
src/flag_gems/runtime/backend/_ascend/ops/index.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/index_add.py generate_imports 7 7 0 0%
src/flag_gems/runtime/backend/_ascend/ops/index_add.py generate_index_add_kernel 44 44 0 0%
src/flag_gems/runtime/backend/_ascend/ops/index_add.py parameter_for_wrapper 13 13 0 0%
src/flag_gems/runtime/backend/_ascend/ops/index_add.py generate_destination_passing_wrapper 22 22 0 0%
src/flag_gems/runtime/backend/_ascend/ops/index_add.py generate_code 6 6 0 0%
src/flag_gems/runtime/backend/_ascend/ops/index_add.py IndexAddFunction.__init__ 2 2 0 0%
src/flag_gems/runtime/backend/_ascend/ops/index_add.py IndexAddFunction.__call__ 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/index_add.py IndexAddFunction.arg_key 3 3 0 0%
src/flag_gems/runtime/backend/_ascend/ops/index_add.py index_add 15 15 0 0%
src/flag_gems/runtime/backend/_ascend/ops/index_add.py (no function) 19 19 0 0%
src/flag_gems/runtime/backend/_ascend/ops/index_select.py index_select_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/index_select.py index_select 22 22 0 0%
src/flag_gems/runtime/backend/_ascend/ops/index_select.py index_select.grid 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/ops/index_select.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_ascend/ops/isin.py launch_arg 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/isin.py isin_by_comparation_impl 18 18 0 0%
src/flag_gems/runtime/backend/_ascend/ops/isin.py isin_by_comparation_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/ops/isin.py isin_by_comparation 20 20 0 0%
src/flag_gems/runtime/backend/_ascend/ops/isin.py isin_by_search_impl 16 16 0 0%
src/flag_gems/runtime/backend/_ascend/ops/isin.py isin_by_search_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/ops/isin.py isin_by_search 27 27 0 0%
src/flag_gems/runtime/backend/_ascend/ops/isin.py isin 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/isin.py (no function) 26 26 0 0%
src/flag_gems/runtime/backend/_ascend/ops/linspace.py linspace_kernel 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/linspace.py linspace 19 19 0 0%
src/flag_gems/runtime/backend/_ascend/ops/linspace.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_ascend/ops/log_softmax.py log_softmax_kernel 26 26 0 0%
src/flag_gems/runtime/backend/_ascend/ops/log_softmax.py log_softmax_backward_kernel 23 23 0 0%
src/flag_gems/runtime/backend/_ascend/ops/log_softmax.py log_softmax 17 17 0 0%
src/flag_gems/runtime/backend/_ascend/ops/log_softmax.py log_softmax_backward 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/log_softmax.py (no function) 19 19 0 0%
src/flag_gems/runtime/backend/_ascend/ops/masked_fill.py masked_fill_kernel 13 13 0 0%
src/flag_gems/runtime/backend/_ascend/ops/masked_fill.py masked_fill_kernel_self 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/masked_fill.py masked_fill 17 17 0 0%
src/flag_gems/runtime/backend/_ascend/ops/masked_fill.py masked_fill_ 18 18 0 0%
src/flag_gems/runtime/backend/_ascend/ops/masked_fill.py (no function) 18 18 0 0%
src/flag_gems/runtime/backend/_ascend/ops/masked_select.py masked_select_kernel 7 7 0 0%
src/flag_gems/runtime/backend/_ascend/ops/masked_select.py masked_select 15 15 0 0%
src/flag_gems/runtime/backend/_ascend/ops/masked_select.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/max.py max_kernel_1 9 9 0 0%
src/flag_gems/runtime/backend/_ascend/ops/max.py max_kernel_2 7 7 0 0%
src/flag_gems/runtime/backend/_ascend/ops/max.py heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/max.py max_kernel 26 26 0 0%
src/flag_gems/runtime/backend/_ascend/ops/max.py max 13 13 0 0%
src/flag_gems/runtime/backend/_ascend/ops/max.py max_dim 21 21 0 0%
src/flag_gems/runtime/backend/_ascend/ops/max.py max_dim.grid 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/ops/max.py (no function) 25 25 0 0%
src/flag_gems/runtime/backend/_ascend/ops/mean.py mean_kernel_1 13 13 0 0%
src/flag_gems/runtime/backend/_ascend/ops/mean.py mean 9 9 0 0%
src/flag_gems/runtime/backend/_ascend/ops/mean.py mean_dim_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/mean.py mean_dim 23 23 0 0%
src/flag_gems/runtime/backend/_ascend/ops/mean.py (no function) 19 19 0 0%
src/flag_gems/runtime/backend/_ascend/ops/min.py min_kernel_1 9 9 0 0%
src/flag_gems/runtime/backend/_ascend/ops/min.py min_kernel_2 7 7 0 0%
src/flag_gems/runtime/backend/_ascend/ops/min.py heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/min.py min_kernel 26 26 0 0%
src/flag_gems/runtime/backend/_ascend/ops/min.py min 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/min.py min_dim 21 21 0 0%
src/flag_gems/runtime/backend/_ascend/ops/min.py (no function) 25 25 0 0%
src/flag_gems/runtime/backend/_ascend/ops/mm.py mm_kernel 35 35 0 0%
src/flag_gems/runtime/backend/_ascend/ops/mm.py get_higher_dtype 9 9 0 0%
src/flag_gems/runtime/backend/_ascend/ops/mm.py mm 16 16 0 0%
src/flag_gems/runtime/backend/_ascend/ops/mm.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_ascend/ops/multinomial.py multinomial_with_replacement 16 16 0 0%
src/flag_gems/runtime/backend/_ascend/ops/multinomial.py multinomial 25 25 0 0%
src/flag_gems/runtime/backend/_ascend/ops/multinomial.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_ascend/ops/ones.py ones_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/ops/ones.py ones 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/ones.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_ascend/ops/ones_like.py ones_like 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/ones_like.py (no function) 8 8 0 0%
src/flag_gems/runtime/backend/_ascend/ops/outer.py early_config_prune 11 11 0 0%
src/flag_gems/runtime/backend/_ascend/ops/outer.py outer_kernel 25 25 0 0%
src/flag_gems/runtime/backend/_ascend/ops/outer.py outer_ 7 7 0 0%
src/flag_gems/runtime/backend/_ascend/ops/outer.py Outer.forward 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/ops/outer.py Outer.backward 6 6 0 0%
src/flag_gems/runtime/backend/_ascend/ops/outer.py outer 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/outer.py (no function) 19 19 0 0%
src/flag_gems/runtime/backend/_ascend/ops/polar.py polar_kernel 3 3 0 0%
src/flag_gems/runtime/backend/_ascend/ops/polar.py polar 4 4 0 0%
src/flag_gems/runtime/backend/_ascend/ops/polar.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/pow.py pow_func 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/pow.py pow_tensor_tensor 2 2 0 0%
src/flag_gems/runtime/backend/_ascend/ops/pow.py pow_tensor_tensor_ 2 2 0 0%
src/flag_gems/runtime/backend/_ascend/ops/pow.py pow_func_tensor_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/pow.py pow_tensor_scalar 2 2 0 0%
src/flag_gems/runtime/backend/_ascend/ops/pow.py pow_tensor_scalar_ 2 2 0 0%
src/flag_gems/runtime/backend/_ascend/ops/pow.py pow_func_scalar_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/pow.py pow_scalar 2 2 0 0%
src/flag_gems/runtime/backend/_ascend/ops/pow.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_ascend/ops/randperm.py _get_iinfo_val 21 21 0 0%
src/flag_gems/runtime/backend/_ascend/ops/randperm.py bitonic_sortbykey_kernel 13 13 0 0%
src/flag_gems/runtime/backend/_ascend/ops/randperm.py radix_type_convert 18 18 0 0%
src/flag_gems/runtime/backend/_ascend/ops/randperm.py digit_hist_kernel 19 19 0 0%
src/flag_gems/runtime/backend/_ascend/ops/randperm.py radix_sortbykey_scatter_kernel 48 48 0 0%
src/flag_gems/runtime/backend/_ascend/ops/randperm.py duplicate_keys_shuffle_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_ascend/ops/randperm.py sort_by_key 55 55 0 0%
src/flag_gems/runtime/backend/_ascend/ops/randperm.py randperm 37 37 0 0%
src/flag_gems/runtime/backend/_ascend/ops/randperm.py (no function) 42 42 0 0%
src/flag_gems/runtime/backend/_ascend/ops/repeat_interleave.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/repeat_interleave.py repeat_interleave_self_int 25 25 0 0%
src/flag_gems/runtime/backend/_ascend/ops/repeat_interleave.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_ascend/ops/resolve_neg.py get_npu_properties 2 2 0 0%
src/flag_gems/runtime/backend/_ascend/ops/resolve_neg.py resolve_neg_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_ascend/ops/resolve_neg.py resolve_neg 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/resolve_neg.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_ascend/ops/rms_norm.py rms_norm_kernel 18 18 0 0%
src/flag_gems/runtime/backend/_ascend/ops/rms_norm.py rms_norm_grad_dx_kernel 27 27 0 0%
src/flag_gems/runtime/backend/_ascend/ops/rms_norm.py rms_norm_grad_dw_kernel 18 18 0 0%
src/flag_gems/runtime/backend/_ascend/ops/rms_norm.py RmsNorm.forward 15 15 0 0%
src/flag_gems/runtime/backend/_ascend/ops/rms_norm.py RmsNorm.backward 22 22 0 0%
src/flag_gems/runtime/backend/_ascend/ops/rms_norm.py rms_norm 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/rms_norm.py (no function) 24 24 0 0%
src/flag_gems/runtime/backend/_ascend/ops/select_scatter.py select_scatter_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/select_scatter.py select_scatter 22 22 0 0%
src/flag_gems/runtime/backend/_ascend/ops/select_scatter.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_ascend/ops/slice_scatter.py copy 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/slice_scatter.py slice_scatter 22 22 0 0%
src/flag_gems/runtime/backend/_ascend/ops/slice_scatter.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/softmax.py softmax_kernel_non_inner 37 37 0 0%
src/flag_gems/runtime/backend/_ascend/ops/softmax.py next_multiple_of 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/softmax.py prev_multiple_of 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/softmax.py softmax_kernel_inner 48 48 0 0%
src/flag_gems/runtime/backend/_ascend/ops/softmax.py softmax_backward_kernel_non_inner 29 29 0 0%
src/flag_gems/runtime/backend/_ascend/ops/softmax.py softmax_backward_kernel_inner 27 27 0 0%
src/flag_gems/runtime/backend/_ascend/ops/softmax.py softmax 20 20 0 0%
src/flag_gems/runtime/backend/_ascend/ops/softmax.py softmax_backward 17 17 0 0%
src/flag_gems/runtime/backend/_ascend/ops/softmax.py (no function) 33 33 0 0%
src/flag_gems/runtime/backend/_ascend/ops/sort.py sort_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_ascend/ops/sort.py sort 21 21 0 0%
src/flag_gems/runtime/backend/_ascend/ops/sort.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_ascend/ops/stack.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/stack.py stack 23 23 0 0%
src/flag_gems/runtime/backend/_ascend/ops/stack.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/threshold.py threshold_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/threshold.py threshold_backward_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/threshold.py threshold 3 3 0 0%
src/flag_gems/runtime/backend/_ascend/ops/threshold.py threshold_backward 3 3 0 0%
src/flag_gems/runtime/backend/_ascend/ops/threshold.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_ascend/ops/triu.py triu_kernel 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/triu.py triu_batch_kernel 21 21 0 0%
src/flag_gems/runtime/backend/_ascend/ops/triu.py triu 20 20 0 0%
src/flag_gems/runtime/backend/_ascend/ops/triu.py (no function) 19 19 0 0%
src/flag_gems/runtime/backend/_ascend/ops/unique.py simple_unique_flat_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_ascend/ops/unique.py output_counts_flat_impl 9 9 0 0%
src/flag_gems/runtime/backend/_ascend/ops/unique.py output_counts_flat_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/ops/unique.py quick_output_flat_impl 11 11 0 0%
src/flag_gems/runtime/backend/_ascend/ops/unique.py quick_output_flat_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/ops/unique.py local_quick_unique_flat_impl 21 21 0 0%
src/flag_gems/runtime/backend/_ascend/ops/unique.py local_quick_unique_flat_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/ops/unique.py global_quick_unique_flat_impl 28 28 0 0%
src/flag_gems/runtime/backend/_ascend/ops/unique.py global_quick_unique_flat_kernel 10 10 0 0%
src/flag_gems/runtime/backend/_ascend/ops/unique.py sorted_quick_unique_flat 33 33 0 0%
src/flag_gems/runtime/backend/_ascend/ops/unique.py local_ne_flat_impl 18 18 0 0%
src/flag_gems/runtime/backend/_ascend/ops/unique.py local_ne_flat_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/ops/unique.py global_cumsum_flat_impl 37 37 0 0%
src/flag_gems/runtime/backend/_ascend/ops/unique.py global_cumsum_flat_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_ascend/ops/unique.py sorted_indices_unique_flat 27 27 0 0%
src/flag_gems/runtime/backend/_ascend/ops/unique.py simple_unique_flat 20 20 0 0%
src/flag_gems/runtime/backend/_ascend/ops/unique.py _unique2 10 10 0 0%
src/flag_gems/runtime/backend/_ascend/ops/unique.py (no function) 45 45 0 0%
src/flag_gems/runtime/backend/_ascend/ops/upsample_nearest2d.py upsample_nearest2d_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_ascend/ops/upsample_nearest2d.py upsample_nearest2d 18 18 0 0%
src/flag_gems/runtime/backend/_ascend/ops/upsample_nearest2d.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_ascend/ops/var_mean.py welford_func 7 7 0 0%
src/flag_gems/runtime/backend/_ascend/ops/var_mean.py var_mean_welford_kernel 30 30 0 0%
src/flag_gems/runtime/backend/_ascend/ops/var_mean.py var_mean_welford_kernel_simple 27 27 0 0%
src/flag_gems/runtime/backend/_ascend/ops/var_mean.py var_mean_kernel_1 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/var_mean.py var_mean_kernel_2 16 16 0 0%
src/flag_gems/runtime/backend/_ascend/ops/var_mean.py var_mean 34 34 0 0%
src/flag_gems/runtime/backend/_ascend/ops/var_mean.py (no function) 27 27 0 0%
src/flag_gems/runtime/backend/_ascend/ops/vector_norm.py l2_norm_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/vector_norm.py l2_norm_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_ascend/ops/vector_norm.py l2_norm_kernel_2 9 9 0 0%
src/flag_gems/runtime/backend/_ascend/ops/vector_norm.py max_norm_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/vector_norm.py max_norm_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_ascend/ops/vector_norm.py max_norm_kernel_2 6 6 0 0%
src/flag_gems/runtime/backend/_ascend/ops/vector_norm.py min_norm_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/vector_norm.py min_norm_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_ascend/ops/vector_norm.py min_norm_kernel_2 6 6 0 0%
src/flag_gems/runtime/backend/_ascend/ops/vector_norm.py l0_norm_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/vector_norm.py l0_norm_kernel_1 9 9 0 0%
src/flag_gems/runtime/backend/_ascend/ops/vector_norm.py l0_norm_kernel_2 6 6 0 0%
src/flag_gems/runtime/backend/_ascend/ops/vector_norm.py v_norm_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/vector_norm.py l1_norm_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_ascend/ops/vector_norm.py l1_norm_kernel_2 6 6 0 0%
src/flag_gems/runtime/backend/_ascend/ops/vector_norm.py vector_norm 57 57 0 0%
src/flag_gems/runtime/backend/_ascend/ops/vector_norm.py (no function) 66 66 0 0%
src/flag_gems/runtime/backend/_ascend/ops/vstack.py vstack_kernel 24 24 0 0%
src/flag_gems/runtime/backend/_ascend/ops/vstack.py vstack 42 42 0 0%
src/flag_gems/runtime/backend/_ascend/ops/vstack.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_ascend/ops/where.py where_inner 1 1 0 0%
src/flag_gems/runtime/backend/_ascend/ops/where.py where_self_out 28 28 0 0%
src/flag_gems/runtime/backend/_ascend/ops/where.py where_self 2 2 0 0%
src/flag_gems/runtime/backend/_ascend/ops/where.py where_scalar_self 2 2 0 0%
src/flag_gems/runtime/backend/_ascend/ops/where.py where_scalar_other 2 2 0 0%
src/flag_gems/runtime/backend/_ascend/ops/where.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_ascend/ops/zeros.py zeros_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_ascend/ops/zeros.py zeros 13 13 0 0%
src/flag_gems/runtime/backend/_ascend/ops/zeros.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_ascend/ops/zeros_like.py zeros_like 13 13 0 0%
src/flag_gems/runtime/backend/_ascend/ops/zeros_like.py (no function) 7 7 0 0%
src/flag_gems/runtime/backend/_ascend/utils/__init__.py (no function) 8 0 0 100%
src/flag_gems/runtime/backend/_cambricon/__init__.py (no function) 18 16 0 11%
src/flag_gems/runtime/backend/_cambricon/fused/__init__.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/cross_entropy_loss.py softmax_forward_kernel 42 42 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/cross_entropy_loss.py max_kernel 22 22 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/cross_entropy_loss.py softmax_forward_with_max_kernel 24 24 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/cross_entropy_loss.py nllloss_without_weight_kernel 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/cross_entropy_loss.py nllloss_with_weight_kernel 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/cross_entropy_loss.py celoss_probability_kernel 35 35 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/cross_entropy_loss.py celoss_indices_smooth_kernel 44 44 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/cross_entropy_loss.py single_celoss_indice_bwd 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/cross_entropy_loss.py config_prune 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/cross_entropy_loss.py celoss_indice_bwd_with_saved_sum_kernel 41 41 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/cross_entropy_loss.py celoss_probability_bwd 48 48 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/cross_entropy_loss.py celoss_indices_smooth_bwd 48 48 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/cross_entropy_loss.py CrossEntropyLoss.forward 62 62 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/cross_entropy_loss.py CrossEntropyLoss.forward.get_result 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/cross_entropy_loss.py CrossEntropyLoss.backward 23 23 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/cross_entropy_loss.py cross_entropy_loss 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/cross_entropy_loss.py (no function) 60 60 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/flash_mla.py flash_mla_attn_kernel 63 63 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/flash_mla.py flash_mla 29 29 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/flash_mla.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/fused_add_rms_norm.py get_configs 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/fused_add_rms_norm.py fused_add_rms_norm_kernel 33 33 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/fused_add_rms_norm.py fused_add_rms_norm 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/fused_add_rms_norm.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/gelu_and_mul.py gelu_none_and_mul_kernel 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/gelu_and_mul.py gelu_none_and_mul_grad_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/gelu_and_mul.py gelu_tanh_and_mul_kernel 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/gelu_and_mul.py gelu_tanh_and_mul_grad_kernel 13 13 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/gelu_and_mul.py GeluAndMul.forward 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/gelu_and_mul.py GeluAndMul.backward 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/gelu_and_mul.py gelu_and_mul 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/gelu_and_mul.py (no function) 27 27 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/outer.py early_config_prune 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/outer.py outer_kernel 25 25 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/outer.py outer_ 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/outer.py Outer.forward 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/outer.py Outer.backward 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/outer.py outer 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/outer.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/silu_and_mul.py silu_and_mul_kernel 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/silu_and_mul.py silu_and_mul_grad_kernel 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/silu_and_mul.py SiluAndMul.forward 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/silu_and_mul.py SiluAndMul.backward 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/silu_and_mul.py silu_and_mul 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/silu_and_mul.py silu_and_mul_out 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/silu_and_mul.py (no function) 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/skip_layernorm.py cfggen_middle_n 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/skip_layernorm.py skip_layer_norm_middle_n_kernel 29 29 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/skip_layernorm.py cfggen 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/skip_layernorm.py skip_layer_norm_kernel 37 37 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/skip_layernorm.py SkipLayerNorm.forward 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/skip_layernorm.py skip_layer_norm 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/skip_layernorm.py (no function) 24 24 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/weight_norm.py weight_norm_except_dim_kernel 29 29 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/weight_norm.py weight_norm_except_dim_bwd_kernel 32 32 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/weight_norm.py weight_norm_except_dim 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/weight_norm.py weight_norm_except_dim_backward 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/weight_norm.py WeightNorm.forward 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/weight_norm.py WeightNorm.backward 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/weight_norm.py weight_norm 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/fused/weight_norm.py (no function) 27 27 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py argmax_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py argmax_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py argmin_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py argmin_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py bmm_heur_divisible_m 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py bmm_heur_divisible_n 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py bmm_heur_divisible_k 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py dropout_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py exponential_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py exponential_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py gather_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py gather_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py index_select_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py index_select_heur_block_n 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py mm_heur_even_k 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py rand_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py randn_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py softmax_heur_tile_k 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py softmax_heur_tile_mode_non_inner 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py softmax_heur_tile_mode_inner 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py uniform_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py uniform_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py upsample_nearest2d_SAME_H 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py upsample_nearest2d_SAME_W 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py vdot_heur_block_size 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py linspace_heur_inner_block_size 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py simple_elementwise_blocksize_heur 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/heuristics_config_utils.py (no function) 31 31 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/__init__.py (no function) 139 139 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/abs.py abs_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/abs.py abs 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/abs.py abs_ 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/abs.py (no function) 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/acos.py acos_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/acos.py acos 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/acos.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/add.py add_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/add.py add_func_tensor_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/add.py add_func_scalar_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/add.py add 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/add.py add_ 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/add.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/addcdiv.py addcdiv_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/addcdiv.py addcdiv 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/addcdiv.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/addcmul.py addcmul_forward 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/addcmul.py addcmul 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/addcmul.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/addmm.py addmm_kernel 37 37 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/addmm.py addmm 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/addmm.py addmm_out 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/addmm.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/all.py reduce_all 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/all.py all_kernel_dim 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/all.py all_kernel_1 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/all.py all 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/all.py all_dim 19 19 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/all.py all_dims 19 19 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/all.py (no function) 22 22 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/amax.py amax_kernel_once 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/amax.py amax_kernel_1 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/amax.py amax_kernel_opt 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/amax.py amax_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/amax.py amax 50 50 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/amax.py (no function) 26 26 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/any.py reduce_any 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/any.py any_kernel_dim 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/any.py any_kernel_1 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/any.py any 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/any.py any_dim 19 19 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/any.py any_dims 19 19 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/any.py (no function) 22 22 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/arange.py arange_func 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/arange.py arange_start 16 16 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/arange.py arange 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/arange.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/argmax.py cfggen_reduce_op 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/argmax.py argmax_kernel_once 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/argmax.py argmax_kernel_1 24 24 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/argmax.py argmax_kernel_2 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/argmax.py argmax_kernel 22 22 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/argmax.py argmax 47 47 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/argmax.py (no function) 27 27 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/atan.py atan_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/atan.py atan 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/atan.py atan_ 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/atan.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/attention.py _attn_fwd_inner 49 49 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/attention.py _attn_fwd 35 35 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/attention.py _attn_bwd_preprocess 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/attention.py _attn_bwd_dkdv 32 32 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/attention.py _attn_bwd_dq 26 26 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/attention.py _attn_bwd 61 61 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/attention.py scaled_dot_product_attention_forward 32 32 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/attention.py scaled_dot_product_attention_backward 36 36 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/attention.py ScaleDotProductAttention.forward 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/attention.py ScaleDotProductAttention.backward 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/attention.py scaled_dot_product_attention 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/attention.py flash_attention_forward 33 33 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/attention.py maybe_contiguous 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/attention.py flash_attn_varlen_func 25 25 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/attention.py (no function) 45 45 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/avg_pool2d.py pool2d_output_size 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/avg_pool2d.py limit_grid 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/avg_pool2d.py avg_pool2d_forward_kernel 40 40 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/avg_pool2d.py avg_pool2d_backward_kernel 51 51 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/avg_pool2d.py _parse_pool_params 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/avg_pool2d.py avg_pool2d 16 16 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/avg_pool2d.py avg_pool2d.grid 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/avg_pool2d.py avg_pool2d_backward 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/avg_pool2d.py avg_pool2d_backward.grid 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/avg_pool2d.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_and.py bitwise_and_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_and.py bitwise_and_tensor 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_and.py bitwise_and_tensor_ 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_and.py bitwise_and_func_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_and.py bitwise_and_scalar 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_and.py bitwise_and_scalar_ 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_and.py bitwise_and_scalar_tensor 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_and.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_left_shift.py bitwise_left_shift_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_left_shift.py bitwise_left_shift 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_left_shift.py (no function) 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_not.py bitwise_not_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_not.py bitwise_not 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_not.py bitwise_not_ 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_not.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_or.py bitwise_or_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_or.py bitwise_or_tensor 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_or.py bitwise_or_tensor_ 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_or.py bitwise_or_func_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_or.py bitwise_or_scalar 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_or.py bitwise_or_scalar_ 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_or.py bitwise_or_scalar_tensor 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_or.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_right_shift.py bitwise_right_shift_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_right_shift.py bitwise_right_shift 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bitwise_right_shift.py (no function) 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bmm.py bmm_kernel 58 58 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bmm.py bmm 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bmm.py bmm_out 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/bmm.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cat.py CatKernelGenerator.__init__ 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cat.py CatKernelGenerator.__init 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cat.py CatKernelGenerator.__call__ 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cat.py CatKernelGenerator.gen_imports 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cat.py CatKernelGenerator.gen_wrapper 22 22 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cat.py CatKernelGenerator.gen_decorators 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cat.py CatKernelGenerator.gen_kernel 47 47 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cat.py CatKernelGenerator.gen_kernel_args 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cat.py CatKernelGenerator.codegen 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cat.py cat 52 52 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cat.py (no function) 22 22 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/ceil.py ceil_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/ceil.py ceil 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/ceil.py ceil_out 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/ceil.py ceil_ 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/ceil.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/celu.py celu_forward_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/celu.py celu 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/celu.py celu_ 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/celu.py (no function) 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/clamp.py clamp_func_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/clamp.py clamp_func_min_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/clamp.py clamp_func_max_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/clamp.py clamp_tensor 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/clamp.py clamp_tensor_ 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/clamp.py clamp_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/clamp.py clamp_func_min 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/clamp.py clamp_func_max 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/clamp.py clamp_min 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/clamp.py clamp_min_ 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/clamp.py clamp 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/clamp.py clamp_ 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/clamp.py (no function) 29 29 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/contiguous.py contiguous 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/contiguous.py (no function) 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/copy.py _copy_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/copy.py _can_use_triton 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/copy.py _expand_like 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/copy.py copy 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/copy.py copy_ 29 29 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/copy.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cos.py cos_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cos.py cos 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cos.py cos_ 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cos.py (no function) 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/count_nonzero.py count_nonzero_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/count_nonzero.py count_nonzero_kernel 27 27 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/count_nonzero.py count_nonzero_combin_kernel_1 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/count_nonzero.py count_nonzero_combin_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/count_nonzero.py count_nonzero 36 36 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/count_nonzero.py (no function) 24 24 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cummin.py tl_cummin 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cummin.py tl_min_tie_break_right 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cummin.py add_base_min_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cummin.py scan_part_min_kernel 27 27 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cummin.py scan_then_fan_col 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cummin.py scan_part_min_abc_kernel 34 34 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cummin.py add_base_min_abc_kernel 24 24 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cummin.py scan_then_fan 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cummin.py scan_part_min_abc_loop_kernel 39 39 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cummin.py scan_then_fan_loop 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cummin.py cummin 24 24 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cummin.py (no function) 35 35 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cumsum.py cumsum_blelloch_impl 28 28 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cumsum.py config_prune 31 31 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cumsum.py cumsum_blelloch 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cumsum.py get_reduction_dim_block_size 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cumsum.py config_prune_mid 24 24 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cumsum.py cumsum_kernel_mid 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cumsum.py cumsum_kernel_result 19 19 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cumsum.py cumsum_wrapper 30 30 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cumsum.py cumsum 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cumsum.py cumsum_out 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cumsum.py normed_cumsum_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cumsum.py block_cumsum_kernel 35 35 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cumsum.py block_update_kernel 22 22 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cumsum.py normed_cumsum 37 37 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/cumsum.py (no function) 47 47 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/diag.py diag_1d_to_2d_kernel 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/diag.py diag_2d_to_1d_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/diag.py diag_1d_to_2d 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/diag.py diag_2d_to_1d 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/diag.py diag 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/diag.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/diag_embed.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/diag_embed.py diag_embed 19 19 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/diag_embed.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/diagonal.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/diagonal.py diagonal_backward 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/diagonal.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py true_div_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py true_div_func_tensor_scalar 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py true_div_func_scalar_tensor 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py true_divide 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py true_divide_out 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py true_divide_ 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py trunc_div_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py trunc_div_func_tensor_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py trunc_div_func_scalar_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py trunc_divide 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py trunc_divide_ 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py _int_floordiv 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py _float_floordiv 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py floor_div_func 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py floor_div_func_tensor_scalar 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py floor_div_func_scalar_tensor 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py floor_divide 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py floor_divide_ 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py div_mode 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py div_mode_ 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py _remainder 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py rem_tt 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py rem_ts 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py rem_st 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py remainder 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py remainder_ 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/div.py (no function) 64 64 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/dropout.py dropout_forward_kernel 24 24 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/dropout.py dropout_backward_kernel 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/dropout.py dropout 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/dropout.py dropout_backward 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/dropout.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/elu.py elu_forward_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/elu.py elu_backward_kernel_with_self 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/elu.py elu_backward_kernel_with_result 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/elu.py elu 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/elu.py elu_ 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/elu.py elu_backward 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/elu.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/embedding.py indice_freq_kernel 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/embedding.py embedding_backward_kernel 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/embedding.py embedding_grad_scale_kernel 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/embedding.py embedding 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/embedding.py embedding_backward 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/embedding.py (no function) 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/eq.py eq_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/eq.py eq 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/eq.py eq_func_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/eq.py eq_scalar 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/eq.py equal 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/eq.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/erf.py erf_func 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/erf.py erf 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/erf.py erf_ 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/erf.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/exp.py exp_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/exp.py exp 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/exp.py exp_ 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/exp.py exp_out 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/exp.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/exp2.py exp2_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/exp2.py exp2 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/exp2.py exp2_ 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/exp2.py (no function) 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/exponential_.py fused_exponential_kernel 25 25 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/exponential_.py paste_u64 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/exponential_.py transform_exponential 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/exponential_.py exponential_ 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/exponential_.py (no function) 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/fill.py fill_scalar_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/fill.py fill_tensor_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/fill.py fill_tensor 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/fill.py fill_scalar 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/fill.py fill_tensor_ 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/fill.py fill_scalar_ 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/fill.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/flip.py FlipKernelCode.__init__ 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/flip.py FlipKernelCode.__init 32 32 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/flip.py FlipKernelCode.__imports 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/flip.py FlipKernelCode.__wrapper 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/flip.py FlipKernelCode.__config 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/flip.py FlipKernelCode.__kernel_flip_2d 96 96 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/flip.py FlipKernelCode.__kernel 75 75 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/flip.py FlipKernelCode.__gen_code 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/flip.py FlipKernelCode.__kernel_args 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/flip.py FlipKernelCode.__call__ 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/flip.py flip 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/flip.py (no function) 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/full.py full_tensor_kernel 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/full.py full_scalar_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/full.py check_dtype 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/full.py full 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/full.py (no function) 22 22 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/full_like.py full_like 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/full_like.py (no function) 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gather.py generate_imports 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gather.py generate_gather_kernel 45 45 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gather.py parameter_for_wrapper 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gather.py generate_gather_wrapper 28 28 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gather.py generate_code 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gather.py GatherFunction.__init__ 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gather.py GatherFunction.__call__ 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gather.py GatherFunction.arg_key 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gather.py gather 13 13 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gather.py gather_backward 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gather.py (no function) 22 22 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/ge.py ge_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/ge.py ge 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/ge.py ge_func_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/ge.py ge_scalar 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/ge.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gelu.py gelu_none 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gelu.py gelu_tanh 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gelu.py gelu_backward_none 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gelu.py gelu_backward_tanh 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gelu.py gelu 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gelu.py gelu_backward 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gelu.py gelu_ 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gelu.py (no function) 24 24 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/glu.py glu_kernel 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/glu.py glu_backward_kernel 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/glu.py glu 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/glu.py glu_backward 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/glu.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/groupnorm.py group_norm_kernel_opt_prune 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/groupnorm.py group_norm_kernel_opt 67 67 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/groupnorm.py group_norm_backward_kernel_opt_prune 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/groupnorm.py group_norm_backward_kernel_opt 58 58 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/groupnorm.py weight_bias_backward_kernel_opt_prune 26 26 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/groupnorm.py weight_bias_backward_kernel_opt 91 91 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/groupnorm.py group_norm 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/groupnorm.py group_norm_backward 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/groupnorm.py (no function) 26 26 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gt.py gt_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gt.py gt 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gt.py gt_func_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gt.py gt_scalar 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/gt.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/hstack.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/hstack.py hstack 37 37 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/hstack.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_add.py cfggen 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_add.py index_add_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_add.py index_add 25 25 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_add.py generate_imports 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_add.py generate_index_add_kernel 43 43 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_add.py parameter_for_wrapper 13 13 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_add.py generate_destination_passing_wrapper 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_add.py generate_code 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_add.py IndexAddFunction.__init__ 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_add.py IndexAddFunction.__call__ 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_add.py IndexAddFunction.arg_key 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_add.py index_add_ 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_add.py (no function) 28 28 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_select.py get_max_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_select.py config_prune 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_select.py ld_st_1 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_select.py one_batch_index_select_kernel 25 25 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_select.py config_prune 29 29 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_select.py ld_st_2 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_select.py multi_batch_index_select_kernel 31 31 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_select.py index_select 27 27 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_select.py index_select.grid_fn 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/index_select.py (no function) 25 25 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isclose.py isclose_func 13 13 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isclose.py isclose 13 13 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isclose.py allclose 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isclose.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isfinite.py isfinite_func 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isfinite.py isfinite 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isfinite.py (no function) 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isin.py launch_arg 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isin.py isin_by_comparation_impl 16 16 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isin.py isin_by_comparation_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isin.py isin_by_comparation 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isin.py isin_by_search_impl 16 16 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isin.py isin_by_search_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isin.py isin_by_search 27 27 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isin.py isin 13 13 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isin.py (no function) 24 24 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isinf.py isinf_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isinf.py isinf 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isinf.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isnan.py isnan_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isnan.py isnan 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/isnan.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/kron.py prepare_tensor_for_kron 23 23 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/kron.py calculate_indices 13 13 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/kron.py kron_kernel 32 32 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/kron.py kron 39 39 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/kron.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/layernorm.py layer_norm_kernel_middle_n 32 32 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/layernorm.py config_prune 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/layernorm.py cfggen 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/layernorm.py layer_norm_kernel_non_inner 30 30 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/layernorm.py layer_norm_kernel_inner 37 37 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/layernorm.py prune_in_wb_config 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/layernorm.py input_backward_kernel 45 45 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/layernorm.py weight_bias_backward_kernel 28 28 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/layernorm.py cfggen_bw_middle_n 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/layernorm.py pre_hook 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/layernorm.py layer_norm_backward_kernel_middle_n 45 45 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/layernorm.py layer_norm 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/layernorm.py layer_norm_backward 35 35 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/layernorm.py (no function) 44 44 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/le.py le_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/le.py le 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/le.py le_func_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/le.py le_scalar 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/le.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/linspace.py linspace_kernel 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/linspace.py linspace 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/linspace.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log.py log_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log.py log 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_sigmoid.py log_sigmoid_forward 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_sigmoid.py log_sigmoid 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_sigmoid.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_softmax.py align 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_softmax.py config_prune1 46 46 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_softmax.py log_softmax_tile_mode_for_non_inner 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_softmax.py log_softmax_kernel_non_inner 58 58 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_softmax.py config_prune2 45 45 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_softmax.py log_softmax_tile_mode_for_inner 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_softmax.py log_softmax_kernel_inner 64 64 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_softmax.py log_softmax_kernel_inner_k_partial_stats 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_softmax.py log_softmax_kernel_inner_k_merge_stats 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_softmax.py log_softmax_kernel_inner_k_write_logsoftmax 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_softmax.py config_prune3 46 46 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_softmax.py log_softmax_backward_kernel_non_inner 44 44 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_softmax.py nram_usage_for_backward_inner 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_softmax.py config_prune4 24 24 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_softmax.py log_softmax_backward_kernel_inner 43 43 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_softmax.py log_softmax 37 37 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_softmax.py log_softmax_backward 19 19 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/log_softmax.py (no function) 48 48 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/logical_and.py logical_and_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/logical_and.py logical_and 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/logical_and.py logical_and_func_ 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/logical_and.py logical_and_ 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/logical_and.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/logical_not.py logical_not_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/logical_not.py logical_not 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/logical_not.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/logical_or.py logical_or_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/logical_or.py logical_or 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/logical_or.py logical_or_ 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/logical_or.py (no function) 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/logical_xor.py logical_xor_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/logical_xor.py logical_xor 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/logical_xor.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/logspace.py logspace_kernel 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/logspace.py logspace 19 19 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/logspace.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/lt.py lt_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/lt.py lt 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/lt.py lt_func_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/lt.py lt_scalar 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/lt.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/masked_fill.py masked_fill_kernel 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/masked_fill.py masked_fill_kernel_self 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/masked_fill.py masked_fill 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/masked_fill.py masked_fill.gridfn 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/masked_fill.py masked_fill_ 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/masked_fill.py (no function) 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/masked_select.py masked_select_kernel 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/masked_select.py get_out_kernel 23 23 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/masked_select.py masked_select 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/masked_select.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max.py max_kernel_float_once 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max.py max_kernel_float 19 19 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max.py max_kernel_int 19 19 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max.py max_kernel_int64_1 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max.py max_kernel_int64_2 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max.py heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max.py max_kernel 25 25 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max.py max 23 23 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max.py max_dim 22 22 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max.py (no function) 40 40 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max_pool2d_with_indices.py max_pool2d_output_size 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max_pool2d_with_indices.py limit_grid 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max_pool2d_with_indices.py max_pool2d_forward_kernel 41 41 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max_pool2d_with_indices.py max_pool2d_backward_kernel 38 38 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max_pool2d_with_indices.py _parse_pool_params 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max_pool2d_with_indices.py _parse_pool_params._parse_param 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max_pool2d_with_indices.py max_pool2d_with_indices 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max_pool2d_with_indices.py max_pool2d_with_indices.grid 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max_pool2d_with_indices.py max_pool2d_backward 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max_pool2d_with_indices.py max_pool2d_backward.grid 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/max_pool2d_with_indices.py (no function) 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/maximum.py maximum_kernel 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/maximum.py maximum 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/maximum.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/mean.py mean_kernel_1 13 13 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/mean.py mean 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/mean.py mean_dim_kernel 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/mean.py mean_dim 23 23 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/mean.py (no function) 19 19 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/min.py min_kernel_float_once 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/min.py min_kernel_float 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/min.py min_kernel_int 19 19 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/min.py min_kernel_int64_1 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/min.py min_kernel_int64_2 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/min.py heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/min.py min_kernel 22 22 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/min.py min 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/min.py min_dim 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/min.py (no function) 40 40 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/minimum.py minimum_kernel 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/minimum.py minimum 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/minimum.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/mm.py mm_kernel 39 39 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/mm.py get_higher_dtype 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/mm.py mm 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/mm.py mm_out 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/mm.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/mul.py mul_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/mul.py mul_func_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/mul.py mul 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/mul.py mul_ 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/mul.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/multinomial.py multinomial_with_replacement 25 25 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/multinomial.py multinomial 25 25 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/multinomial.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/mv.py config_prune 19 19 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/mv.py mv_kernel 23 23 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/mv.py mv 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/mv.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/ne.py ne_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/ne.py ne 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/ne.py ne_func_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/ne.py ne_scalar 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/ne.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/neg.py neg_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/neg.py neg 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/neg.py neg_ 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/neg.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/nonzero.py nonzero_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/nonzero.py nonzero 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/nonzero.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/normal.py transform_func_tensor_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/normal.py transform_func_tensor_float 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/normal.py transform_func_float_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/normal.py transform_func_float_float 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/normal.py normal_distribution 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/normal.py normal_tensor_tensor 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/normal.py normal_tensor_float 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/normal.py normal_float_tensor 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/normal.py normal_ 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/normal.py (no function) 28 28 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/ones.py ones_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/ones.py ones 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/ones.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/ones_like.py ones_like 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/ones_like.py (no function) 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pad.py parameter_for_wrapper 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pad.py parameter_for_wrapper_out 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pad.py parameter_ref_for_wrapper 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pad.py output_ref_for_wrapper 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pad.py generate_imports 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pad.py generate_functional_padding_wrapper 29 29 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pad.py generate_destination_passing_padding_wrapper 52 52 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pad.py generate_pad_kernel 85 85 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pad.py generate_code 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pad.py PadFunction.__init__ 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pad.py PadFunction.__call__ 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pad.py PadFunction.arg_key 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pad.py pad_1d_constant_kernel 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pad.py pad_2d_constant_kernel 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pad.py pad 49 49 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pad.py constant_pad_nd 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pad.py (no function) 36 36 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/per_token_group_quant_fp8.py _per_token_group_quant_fp8 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/per_token_group_quant_fp8.py _per_token_group_quant_fp8_colmajor 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/per_token_group_quant_fp8.py per_token_group_quant_fp8 23 23 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/per_token_group_quant_fp8.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pow.py pow_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pow.py pow_tensor_tensor 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pow.py pow_tensor_tensor_ 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pow.py pow_func_tensor_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pow.py pow_func_tensor_scalar_int 23 23 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pow.py pow_tensor_scalar 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pow.py pow_tensor_scalar_ 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pow.py pow_func_scalar_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pow.py pow_scalar 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/pow.py (no function) 24 24 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/prod.py reduce_mul 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/prod.py prod_kernel_mid 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/prod.py prod_kernel_result 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/prod.py prod 13 13 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/prod.py heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/prod.py prod_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/prod.py prod_dim 19 19 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/prod.py (no function) 26 26 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/quantile.py _compare_and_swap 41 41 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/quantile.py _bitonic_merge 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/quantile.py argsort 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/quantile.py heur_block_q 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/quantile.py heur_block_n 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/quantile.py quantile_kernel 28 28 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/quantile.py quantile_bitonic_kernel 40 40 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/quantile.py quantile 56 56 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/quantile.py (no function) 36 36 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/rand.py rand_kernel 19 19 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/rand.py rand 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/rand.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/rand_like.py rand_like 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/rand_like.py (no function) 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/randn.py randn_kernel 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/randn.py randn 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/randn.py (no function) 26 26 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/randn_like.py randn_like 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/randn_like.py (no function) 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/randperm.py _compare_and_swap 41 41 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/randperm.py _bitonic_merge 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/randperm.py argsort 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/randperm.py _get_iinfo_val 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/randperm.py bitonic_sortbykey_kernel 13 13 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/randperm.py radix_type_convert 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/randperm.py digit_hist_kernel 19 19 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/randperm.py radix_sortbykey_scatter_kernel 45 45 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/randperm.py duplicate_keys_shuffle_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/randperm.py sort_by_key 54 54 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/randperm.py randperm 37 37 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/randperm.py (no function) 50 50 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/reciprocal.py reciprocal_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/reciprocal.py reciprocal 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/reciprocal.py reciprocal_ 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/reciprocal.py (no function) 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/relu.py relu_forward 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/relu.py relu_backward 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/relu.py relu 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/relu.py relu_ 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/relu.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat.py parameter_for_wrapper 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat.py parameter_for_wrapper_out 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat.py parameter_ref_for_wrapper 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat.py output_ref_for_wrapper 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat.py generate_imports 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat.py generate_functional_repeat_wrapper 38 38 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat.py generate_destination_passing_repeat_wrapper 48 48 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat.py generate_repeat_kernel 89 89 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat.py generate_code 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat.py RepeatFunction.__init__ 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat.py RepeatFunction.__call__ 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat.py RepeatFunction.arg_key 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat.py repeat_2d_kernel 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat.py repeat 24 24 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat.py (no function) 31 31 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat_interleave.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat_interleave.py repeat_interleave_self_int_forward 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat_interleave.py RepeatInterleaveSelfIntFn.forward 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat_interleave.py RepeatInterleaveSelfIntFn.backward 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat_interleave.py repeat_interleave_self_int 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat_interleave.py repeat_interleave_tensor_kernel 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat_interleave.py repeat_interleave_tensor 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat_interleave.py repeat_interleave_self_tensor 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/repeat_interleave.py (no function) 22 22 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/resolve_conj.py conj_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/resolve_conj.py resolve_conj 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/resolve_conj.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/resolve_neg.py resolve_neg 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/resolve_neg.py (no function) 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/rms_norm.py rms_norm_forward 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/rms_norm.py rms_norm_backward 24 24 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/rms_norm.py rms_norm_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/rms_norm.py rms_norm_kernel_C_split 23 23 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/rms_norm.py rms_norm_grad_dx_kernel 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/rms_norm.py rms_norm_grad_dx_kernel_C_split 34 34 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/rms_norm.py rms_norm_grad_dw_kernel 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/rms_norm.py RmsNorm.forward 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/rms_norm.py RmsNorm.backward 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/rms_norm.py rms_norm 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/rms_norm.py (no function) 35 35 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/rsqrt.py rsqrt_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/rsqrt.py rsqrt 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/rsqrt.py rsqrt_ 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/rsqrt.py (no function) 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/scatter.py generate_imports 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/scatter.py generate_scatter_kernel 65 65 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/scatter.py parameter_for_wrapper 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/scatter.py generate_destination_passing_wrapper 34 34 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/scatter.py generate_code 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/scatter.py ScatterFunction.__init__ 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/scatter.py ScatterFunction.__call__ 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/scatter.py ScatterFunction.arg_key 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/scatter.py scatter 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/scatter.py scatter_ 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/scatter.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/select_scatter.py select_scatter_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/select_scatter.py select_scatter 22 22 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/select_scatter.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sigmoid.py sigmoid_forward 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sigmoid.py sigmoid_backward_kernel 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sigmoid.py sigmoid 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sigmoid.py sigmoid_backward 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sigmoid.py sigmoid_ 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sigmoid.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/silu.py silu_forward 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/silu.py silu_backward_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/silu.py silu 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/silu.py silu_backward 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/silu.py silu_ 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/silu.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sin.py sin_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sin.py sin 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sin.py sin_ 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sin.py (no function) 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/slice_scatter.py slice_scatter_kernel 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/slice_scatter.py slice_scatter 27 27 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/slice_scatter.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softmax.py align 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softmax.py config_prune1 45 45 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softmax.py softmax_tile_mode_for_non_inner 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softmax.py softmax_kernel_non_inner 58 58 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softmax.py config_prune2 44 44 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softmax.py softmax_tile_mode_for_inner 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softmax.py softmax_kernel_inner 60 60 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softmax.py softmax_kernel_inner_k_partial_stats 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softmax.py softmax_kernel_inner_k_merge_stats 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softmax.py softmax_kernel_inner_k_write_softmax 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softmax.py nram_usage_for_backward_non_inner 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softmax.py config_prune3 25 25 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softmax.py softmax_backward_kernel_non_inner 45 45 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softmax.py config_prune4 44 44 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softmax.py softmax_backward_kernel_inner 44 44 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softmax.py softmax 37 37 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softmax.py softmax_backward 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softmax.py (no function) 48 48 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softplus.py softplus_forward 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softplus.py softplus 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/softplus.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sort.py unwrap_if_constexpr 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sort.py get_int_t 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sort.py one_zeros 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sort.py zero_ones 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sort.py uint_to_uint 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sort.py int_to_uint 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sort.py floating_to_uint 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sort.py convert_to_uint_preverse_order 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sort.py compute_global_hist_kernel 26 26 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sort.py sweep 45 45 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sort.py radix_sort 47 47 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sort.py sort 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sort.py sort_stable 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sort.py (no function) 28 28 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sqrt.py sqrt_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sqrt.py sqrt 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sqrt.py sqrt_ 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sqrt.py (no function) 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/stack.py get_dtype_size 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/stack.py StackKernelCode.__init__ 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/stack.py StackKernelCode.__imports 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/stack.py StackKernelCode.__wrapper 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/stack.py StackKernelCode.__config 13 13 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/stack.py StackKernelCode.__kernel 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/stack.py StackKernelCode.__kernel.add_indent 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/stack.py StackKernelCode.__gen_code 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/stack.py StackKernelCode.__call__ 22 22 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/stack.py stack 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/stack.py (no function) 23 23 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sub.py sub_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sub.py sub_func_tensor_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sub.py sub_func_scalar_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sub.py sub 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sub.py sub_ 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sub.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sum.py sum_kernel_1 16 16 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sum.py sum_kernel 23 23 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sum.py sum 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sum.py sum_out 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sum.py sum_dim 30 30 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sum.py sum_dim_out 29 29 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/sum.py (no function) 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tan.py tan_func 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tan.py tan 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tan.py tan_ 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tan.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tanh.py tanh_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tanh.py tanh_backward_kernel 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tanh.py tanh 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tanh.py tanh_backward 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tanh.py tanh_ 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tanh.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tile.py parameter_for_wrapper 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tile.py parameter_for_wrapper_out 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tile.py parameter_ref_for_wrapper 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tile.py output_ref_for_wrapper 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tile.py generate_imports 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tile.py generate_functional_tile_wrapper 42 42 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tile.py generate_destination_passing_tile_wrapper 48 48 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tile.py generate_tile_kernel 89 89 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tile.py generate_code 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tile.py TileFunction.__init__ 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tile.py TileFunction.__call__ 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tile.py TileFunction.arg_key 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tile.py tile_2d_kernel 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tile.py tile 23 23 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/tile.py (no function) 31 31 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/to.py _to_copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/to.py _resolve_dtype 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/to.py _resolve_device 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/to.py _normalize_memory_format 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/to.py _allocate_preserve_format 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/to.py to_copy 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/to.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/topk.py _get_finfo_val 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/topk.py _get_iinfo_val 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/topk.py get_topk_bubble_res 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/topk.py topk_cfggen 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/topk.py topk_config_prune 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/topk.py topk_bubble_kernel 30 30 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/topk.py topk 37 37 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/topk.py topk.grid_fn 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/topk.py (no function) 37 37 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/triu.py triu_kernel 30 30 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/triu.py triu_batch_kernel 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/triu.py _check_batch_contiguous 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/triu.py triu 19 19 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/triu.py triu_ 35 35 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/triu.py (no function) 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/uniform.py uniform_kernel 19 19 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/uniform.py uniform_ 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/uniform.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/unique.py get_ne_kernel 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/unique.py get_unique_out_kernel 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/unique.py get_output_counts_kernel 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/unique.py sorted_unique_flat 27 27 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/unique.py _unique2 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/unique.py (no function) 19 19 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/upsample_nearest2d.py upsample_nearest2d_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/upsample_nearest2d.py configs2 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/upsample_nearest2d.py upsample_nearest2d_kernel_opt 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/upsample_nearest2d.py upsample_nearest2d_kernel_opt_tile_h 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/upsample_nearest2d.py upsample_nearest2d 26 26 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/upsample_nearest2d.py (no function) 22 22 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/var_mean.py welford_func 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/var_mean.py var_mean_welford_kernel 29 29 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/var_mean.py prune_varmean_config 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/var_mean.py var_mean_kernel_1 33 33 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/var_mean.py var_mean_kernel_2 13 13 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/var_mean.py var_mean 34 34 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/var_mean.py (no function) 26 26 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vector_norm.py l2_norm_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vector_norm.py l2_norm_kernel_1 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vector_norm.py l2_norm_kernel_2 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vector_norm.py max_norm_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vector_norm.py max_norm_kernel_1 19 19 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vector_norm.py min_norm_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vector_norm.py min_norm_kernel_1 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vector_norm.py l0_norm_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vector_norm.py l0_norm_kernel_1 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vector_norm.py v_norm_kernel 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vector_norm.py l1_norm_kernel_1 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vector_norm.py l1_norm_kernel_2 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vector_norm.py vector_norm 52 52 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vector_norm.py (no function) 62 62 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vstack.py VstackKernelCode.__init__ 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vstack.py VstackKernelCode.__init 24 24 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vstack.py VstackKernelCode.__imports 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vstack.py VstackKernelCode.__wrapper 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vstack.py VstackKernelCode.__config 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vstack.py VstackKernelCode.__kernel 89 89 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vstack.py VstackKernelCode.__gen_code 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vstack.py VstackKernelCode.__kernel_args 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vstack.py VstackKernelCode.__call__ 16 16 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vstack.py vstack 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/vstack.py (no function) 22 22 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/weightnorm.py weight_norm_kernel_last 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/weightnorm.py config_prune_for_first 32 32 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/weightnorm.py tile_mode_for_first 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/weightnorm.py weight_norm_kernel_first 50 50 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/weightnorm.py weight_norm_bwd_kernel_last 24 24 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/weightnorm.py weight_norm_bwd_kernel_first 24 24 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/weightnorm.py weight_norm_interface 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/weightnorm.py weight_norm_interface_backward 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/weightnorm.py (no function) 33 33 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/where.py where_inner 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/where.py where_self_out 28 28 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/where.py where_self 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/where.py where_scalar_self 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/where.py where_scalar_other 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/where.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/zeros.py zeros_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/zeros.py zeros 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/zeros.py zero_ 6 6 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/zeros.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/zeros_like.py zeros_like 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/ops/zeros_like.py (no function) 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/__init__.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py _type_name 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py _check_typed_list 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py _check_sized_list 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py _tuple_content 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py _cs 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py _broadcast_vec 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py FunctionSchema.__init__ 41 41 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py FunctionSchema.canonicalize_promotion_methods 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py FunctionSchema.num_inputs 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py FunctionSchema.num_outputs 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py FunctionSchema.is_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py FunctionSchema.input_type 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py FunctionSchema.output_type 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py FunctionSchema.num_input_tensors 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py FunctionSchema.num_output_tensors 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py FunctionSchema.num_non_tensor_args 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py FunctionSchema.signature 16 16 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py FunctionSchema._compute_input_id 10 10 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py FunctionSchema.input_index 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py FunctionSchema.__str__ 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py KernelGenerator.__init__ 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py KernelGenerator.gen_import_function 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py KernelGenerator.gen_config_prune 31 31 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py KernelGenerator.gen_decorators 80 80 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py KernelGenerator.input_name 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py KernelGenerator.output_name 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py KernelGenerator.gen_signature 47 47 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py KernelGenerator.gen_signature_1d_tile 35 35 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py KernelGenerator.gen_num_tiles 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py KernelGenerator.gen_body_for_0d 17 17 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py KernelGenerator.gen_body_one_tile_per_cta_with_bptr 82 82 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py KernelGenerator.gen_body_gsl_with_bptr 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py KernelGenerator.gen_body_one_tile_per_cta_without_bptr 33 33 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py KernelGenerator.gen_body_gsl_without_bptr 8 8 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py KernelGenerator.codegen_nd_tile_with_bptr 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py KernelGenerator.codegen_nd_tile_without_bptr 21 21 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py KernelGenerator.codegen_nd_tile 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py KernelGenerator.gen_body_one_tile_per_cta_1d_tile 27 27 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py KernelGenerator.gen_body_gsl_1d_tile 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py KernelGenerator.codegen_1d_tile 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py WrapperGenerator.__init__ 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py WrapperGenerator.input_name 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py WrapperGenerator.output_name 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py WrapperGenerator.gen_signature 14 14 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py WrapperGenerator.gen_docstring 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py WrapperGenerator.gen_same_shape_check 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py WrapperGenerator.gen_fallback_bptr 15 15 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py WrapperGenerator.gen_task_partition 35 35 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py WrapperGenerator.gen_task_partition_1d 31 31 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py WrapperGenerator.gen_kernel_launch 63 63 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py WrapperGenerator.gen_kernel_launch_1d 36 36 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py WrapperGenerator.gen_return 2 2 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py WrapperGenerator.codegen_nd_tile 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py WrapperGenerator.codegen_1d_tile 11 11 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py ModuleGenerator.__init__ 3 3 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py ModuleGenerator.generate_imports 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py ModuleGenerator.codegen 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py PointwiseDynamicFunction.__init__ 7 7 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py PointwiseDynamicFunction.__call__ 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py PointwiseDynamicFunction.use_fast_path 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py PointwiseDynamicFunction.prepare_args 49 49 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py PointwiseDynamicFunction._unwrap 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py PointwiseDynamicFunction.instantiate 20 20 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py pointwise_dynamic 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py pointwise_dynamic.decorator 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/pointwise_dynamic.py (no function) 91 91 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/reduce_utils.py cfggen_reduce_op 1 1 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/reduce_utils.py cfggen_reduce_op2 4 4 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/reduce_utils.py count_divisible_by_2 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/reduce_utils.py next_power_of_two 5 5 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/reduce_utils.py prune_reduce_config 18 18 0 0%
src/flag_gems/runtime/backend/_cambricon/utils/reduce_utils.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_enflame/__init__.py (no function) 15 9 0 40%
src/flag_gems/runtime/backend/_enflame/fused/__init__.py (no function) 21 21 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py argmax_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py argmax_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py argmin_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py argmin_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py dropout_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py dropout_heur_num_warps 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py exponential_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py exponential_heur_num_warps 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py gather_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py gather_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py index_select_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py index_select_heur_block_n 2 2 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py mm_heur_even_k 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py rand_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py rand_heur_num_warps 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py randn_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py randn_heur_num_warps 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py softmax_heur_tile_k 11 11 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py softmax_heur_tile_n_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py softmax_heur_one_tile_per_cta 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py softmax_heur_num_warps_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py softmax_heur_tile_n_inner 3 3 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py softmax_heur_num_warps_inner 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py softmax_heur_tile_n_bwd_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py softmax_heru_tile_m 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py uniform_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py uniform_heur_num_warps 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py var_mean_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py upsample_nearest2d_NUM_TILE 5 5 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py upsample_nearest2d_TOTAL_TILE 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py upsample_nearest2d_SAME_H 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py upsample_nearest2d_SAME_W 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py upsample_nearest2d_USE_INT32_IDX 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py batch_norm_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py batch_norm_heur_block_n 3 3 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py vdot_heur_block_size 6 6 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py simple_elementwise_blocksize_heur 4 4 0 0%
src/flag_gems/runtime/backend/_enflame/heuristics_config_utils.py (no function) 40 40 0 0%
src/flag_gems/runtime/backend/_enflame/ops/__init__.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_hygon/__init__.py (no function) 4 0 0 100%
src/flag_gems/runtime/backend/_hygon/fused/__init__.py (no function) 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py simple_elementwise_blocksize_heur 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py argmax_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py argmax_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py argmin_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py argmin_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py bmm_heur_divisible_m 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py bmm_heur_divisible_n 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py bmm_heur_divisible_k 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py dropout_heur_block 5 5 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py dropout_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py exponential_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py exponential_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py gather_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py gather_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py index_select_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py index_select_heur_block_n 2 2 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py mm_heur_even_k 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py rand_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py rand_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py randn_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py randn_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py softmax_heur_tile_k 11 11 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py softmax_heur_tile_n_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py softmax_heur_one_tile_per_cta 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py softmax_heur_num_warps_non_inner 6 6 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py softmax_heur_tile_n_inner 3 3 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py softmax_heur_num_warps_inner 6 6 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py softmax_heur_tile_n_bwd_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py softmax_heur_tile_m 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py uniform_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py uniform_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py var_mean_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py upsample_nearest2d_SAME_H 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py upsample_nearest2d_SAME_W 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py batch_norm_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py batch_norm_heur_block_n 3 3 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py vdot_heur_block_size 6 6 0 0%
src/flag_gems/runtime/backend/_hygon/heuristics_config_utils.py (no function) 40 40 0 0%
src/flag_gems/runtime/backend/_hygon/ops/__init__.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_hygon/ops/all.py reduce_all 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/all.py all_kernel_dim 14 14 0 0%
src/flag_gems/runtime/backend/_hygon/ops/all.py all_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_hygon/ops/all.py all_kernel_2 6 6 0 0%
src/flag_gems/runtime/backend/_hygon/ops/all.py all 11 11 0 0%
src/flag_gems/runtime/backend/_hygon/ops/all.py all_dim 19 19 0 0%
src/flag_gems/runtime/backend/_hygon/ops/all.py all_dims 19 19 0 0%
src/flag_gems/runtime/backend/_hygon/ops/all.py (no function) 25 25 0 0%
src/flag_gems/runtime/backend/_hygon/ops/any.py reduce_any 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/any.py any_kernel_dim 14 14 0 0%
src/flag_gems/runtime/backend/_hygon/ops/any.py any_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_hygon/ops/any.py any_kernel_2 6 6 0 0%
src/flag_gems/runtime/backend/_hygon/ops/any.py any 11 11 0 0%
src/flag_gems/runtime/backend/_hygon/ops/any.py any_dim 19 19 0 0%
src/flag_gems/runtime/backend/_hygon/ops/any.py any_dims 19 19 0 0%
src/flag_gems/runtime/backend/_hygon/ops/any.py (no function) 25 25 0 0%
src/flag_gems/runtime/backend/_hygon/ops/attention.py _attn_fwd_inner 51 51 0 0%
src/flag_gems/runtime/backend/_hygon/ops/attention.py _attn_fwd 35 35 0 0%
src/flag_gems/runtime/backend/_hygon/ops/attention.py _attn_bwd_preprocess 8 8 0 0%
src/flag_gems/runtime/backend/_hygon/ops/attention.py _attn_bwd_dkdv 32 32 0 0%
src/flag_gems/runtime/backend/_hygon/ops/attention.py _attn_bwd_dq 26 26 0 0%
src/flag_gems/runtime/backend/_hygon/ops/attention.py _attn_bwd 61 61 0 0%
src/flag_gems/runtime/backend/_hygon/ops/attention.py scaled_dot_product_attention_forward 32 32 0 0%
src/flag_gems/runtime/backend/_hygon/ops/attention.py scaled_dot_product_attention_backward 36 36 0 0%
src/flag_gems/runtime/backend/_hygon/ops/attention.py ScaleDotProductAttention.forward 7 7 0 0%
src/flag_gems/runtime/backend/_hygon/ops/attention.py ScaleDotProductAttention.backward 6 6 0 0%
src/flag_gems/runtime/backend/_hygon/ops/attention.py scaled_dot_product_attention 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/attention.py flash_attention_forward 33 33 0 0%
src/flag_gems/runtime/backend/_hygon/ops/attention.py maybe_contiguous 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/attention.py flash_attn_varlen_func 25 25 0 0%
src/flag_gems/runtime/backend/_hygon/ops/attention.py (no function) 45 45 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py true_div_func 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py true_div_func_tensor_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py true_div_func_scalar_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py true_divide 8 8 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py true_divide_ 4 4 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py trunc_div_func 3 3 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py trunc_div_func_tensor_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py trunc_div_func_scalar_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py trunc_divide 8 8 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py trunc_divide_ 4 4 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py _int_floordiv 4 4 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py _float_floordiv 14 14 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py floor_div_func 7 7 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py floor_div_func_tensor_scalar 7 7 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py floor_div_func_scalar_tensor 7 7 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py floor_divide 8 8 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py floor_divide_ 4 4 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py div_mode 8 8 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py div_mode_ 8 8 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py _remainder 4 4 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py rem_tt 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py rem_ts 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py rem_st 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py remainder 8 8 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py remainder_ 4 4 0 0%
src/flag_gems/runtime/backend/_hygon/ops/div.py (no function) 60 60 0 0%
src/flag_gems/runtime/backend/_hygon/ops/exponential_.py safe_fast_log 10 10 0 0%
src/flag_gems/runtime/backend/_hygon/ops/exponential_.py fused_exponential_kernel 37 37 0 0%
src/flag_gems/runtime/backend/_hygon/ops/exponential_.py paste_u64 3 3 0 0%
src/flag_gems/runtime/backend/_hygon/ops/exponential_.py transform_exponential 4 4 0 0%
src/flag_gems/runtime/backend/_hygon/ops/exponential_.py exponential_ 20 20 0 0%
src/flag_gems/runtime/backend/_hygon/ops/exponential_.py (no function) 19 19 0 0%
src/flag_gems/runtime/backend/_hygon/ops/fill.py fill_scalar_func 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/fill.py fill_tensor_func 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/fill.py fill_scalar 4 4 0 0%
src/flag_gems/runtime/backend/_hygon/ops/fill.py fill_tensor 8 8 0 0%
src/flag_gems/runtime/backend/_hygon/ops/fill.py fill_tensor_ 8 8 0 0%
src/flag_gems/runtime/backend/_hygon/ops/fill.py fill_scalar_ 4 4 0 0%
src/flag_gems/runtime/backend/_hygon/ops/fill.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_api.py CHECK_DEVICE 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_api.py fwd_params.__init__ 57 57 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_api.py fwd_params.args 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_api.py mha_varlan_fwd 154 154 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_api.py mha_fwd 102 102 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_api.py mha_fwd.splits_heuristic 7 7 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_api.py mha_fwd.dispatch 33 33 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_api.py (no function) 18 18 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py u64_to_lohi 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py u64_from_lohi 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py philox_ 21 21 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py apply_dropout_mask 4 4 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py apply_dropout 13 13 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py apply_alibi 7 7 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py apply_mask 11 11 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py softmax_rescale 12 12 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py apply_softcap 3 3 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py block_m_splitkv_heuristic 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py block_n_splitkv_heuristic 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py is_even_mn 5 5 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py block_m_splitkv_heuristic_spec_args 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py block_n_splitkv_heuristic_spec_args 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py is_even_mn_spec_args 5 5 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py keep 4 4 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py prune_fwd_configs 4 4 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py flash_fwd_kernel_heur_block_k 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py flash_fwd_kernel 159 159 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py flash_fwd_bh_parallel_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py flash_fwd_splitkv_kernel_heur_block_k 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py flash_fwd_splitkv_kernel 111 111 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py flash_fwd_splitkv_combine_kernel 23 23 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py virtual_to_cache 6 6 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py load_from_kvcache 9 9 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py flash_varlen_fwd_kernel 92 92 0 0%
src/flag_gems/runtime/backend/_hygon/ops/flash_kernel.py (no function) 53 53 0 0%
src/flag_gems/runtime/backend/_hygon/ops/gelu.py gelu_none 4 4 0 0%
src/flag_gems/runtime/backend/_hygon/ops/gelu.py gelu_tanh 3 3 0 0%
src/flag_gems/runtime/backend/_hygon/ops/gelu.py gelu_backward_none 6 6 0 0%
src/flag_gems/runtime/backend/_hygon/ops/gelu.py gelu_backward_tanh 5 5 0 0%
src/flag_gems/runtime/backend/_hygon/ops/gelu.py Gelu.forward 7 7 0 0%
src/flag_gems/runtime/backend/_hygon/ops/gelu.py Gelu.backward 7 7 0 0%
src/flag_gems/runtime/backend/_hygon/ops/gelu.py gelu 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/gelu.py InplaceGelu.forward 8 8 0 0%
src/flag_gems/runtime/backend/_hygon/ops/gelu.py InplaceGelu.backward 7 7 0 0%
src/flag_gems/runtime/backend/_hygon/ops/gelu.py gelu_ 2 2 0 0%
src/flag_gems/runtime/backend/_hygon/ops/gelu.py (no function) 34 34 0 0%
src/flag_gems/runtime/backend/_hygon/ops/isclose.py isclose_func 13 13 0 0%
src/flag_gems/runtime/backend/_hygon/ops/isclose.py isclose 13 13 0 0%
src/flag_gems/runtime/backend/_hygon/ops/isclose.py allclose 2 2 0 0%
src/flag_gems/runtime/backend/_hygon/ops/isclose.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_hygon/ops/isin.py launch_arg 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/isin.py isin_by_comparation_impl 16 16 0 0%
src/flag_gems/runtime/backend/_hygon/ops/isin.py isin_by_comparation_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_hygon/ops/isin.py isin_by_comparation 20 20 0 0%
src/flag_gems/runtime/backend/_hygon/ops/isin.py isin_by_search_impl 16 16 0 0%
src/flag_gems/runtime/backend/_hygon/ops/isin.py isin_by_search_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_hygon/ops/isin.py isin_by_search 29 29 0 0%
src/flag_gems/runtime/backend/_hygon/ops/isin.py isin 14 14 0 0%
src/flag_gems/runtime/backend/_hygon/ops/isin.py (no function) 26 26 0 0%
src/flag_gems/runtime/backend/_hygon/ops/mm.py prev_multiple_of 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/mm.py mm_kernel 37 37 0 0%
src/flag_gems/runtime/backend/_hygon/ops/mm.py get_higher_dtype 9 9 0 0%
src/flag_gems/runtime/backend/_hygon/ops/mm.py mm 15 15 0 0%
src/flag_gems/runtime/backend/_hygon/ops/mm.py mm_out 13 13 0 0%
src/flag_gems/runtime/backend/_hygon/ops/mm.py (no function) 19 19 0 0%
src/flag_gems/runtime/backend/_hygon/ops/pow.py pow_func 5 5 0 0%
src/flag_gems/runtime/backend/_hygon/ops/pow.py pow_tensor_tensor 2 2 0 0%
src/flag_gems/runtime/backend/_hygon/ops/pow.py pow_tensor_tensor_ 2 2 0 0%
src/flag_gems/runtime/backend/_hygon/ops/pow.py pow_func_tensor_scalar 5 5 0 0%
src/flag_gems/runtime/backend/_hygon/ops/pow.py pow_tensor_scalar 2 2 0 0%
src/flag_gems/runtime/backend/_hygon/ops/pow.py pow_tensor_scalar_ 2 2 0 0%
src/flag_gems/runtime/backend/_hygon/ops/pow.py pow_func_scalar_tensor 5 5 0 0%
src/flag_gems/runtime/backend/_hygon/ops/pow.py pow_scalar 2 2 0 0%
src/flag_gems/runtime/backend/_hygon/ops/pow.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_hygon/ops/randperm.py _get_iinfo_val 21 21 0 0%
src/flag_gems/runtime/backend/_hygon/ops/randperm.py bitonic_sortbykey_kernel 13 13 0 0%
src/flag_gems/runtime/backend/_hygon/ops/randperm.py radix_type_convert 15 15 0 0%
src/flag_gems/runtime/backend/_hygon/ops/randperm.py digit_hist_kernel 19 19 0 0%
src/flag_gems/runtime/backend/_hygon/ops/randperm.py radix_sortbykey_scatter_kernel 45 45 0 0%
src/flag_gems/runtime/backend/_hygon/ops/randperm.py duplicate_keys_shuffle_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_hygon/ops/randperm.py sort_by_key 54 54 0 0%
src/flag_gems/runtime/backend/_hygon/ops/randperm.py randperm 37 37 0 0%
src/flag_gems/runtime/backend/_hygon/ops/randperm.py (no function) 42 42 0 0%
src/flag_gems/runtime/backend/_hygon/ops/silu.py silu_forward 3 3 0 0%
src/flag_gems/runtime/backend/_hygon/ops/silu.py silu_backward_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_hygon/ops/silu.py silu 3 3 0 0%
src/flag_gems/runtime/backend/_hygon/ops/silu.py silu_backward 3 3 0 0%
src/flag_gems/runtime/backend/_hygon/ops/silu.py silu_ 3 3 0 0%
src/flag_gems/runtime/backend/_hygon/ops/silu.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_hygon/ops/sort.py unwrap_if_constexpr 1 1 0 0%
src/flag_gems/runtime/backend/_hygon/ops/sort.py get_int_t 3 3 0 0%
src/flag_gems/runtime/backend/_hygon/ops/sort.py one_zeros 2 2 0 0%
src/flag_gems/runtime/backend/_hygon/ops/sort.py zero_ones 2 2 0 0%
src/flag_gems/runtime/backend/_hygon/ops/sort.py uint_to_uint 2 2 0 0%
src/flag_gems/runtime/backend/_hygon/ops/sort.py int_to_uint 11 11 0 0%
src/flag_gems/runtime/backend/_hygon/ops/sort.py floating_to_uint 14 14 0 0%
src/flag_gems/runtime/backend/_hygon/ops/sort.py convert_to_uint_preverse_order 10 10 0 0%
src/flag_gems/runtime/backend/_hygon/ops/sort.py count_kernel 13 13 0 0%
src/flag_gems/runtime/backend/_hygon/ops/sort.py scatter_kernel 25 25 0 0%
src/flag_gems/runtime/backend/_hygon/ops/sort.py radix_sort 30 30 0 0%
src/flag_gems/runtime/backend/_hygon/ops/sort.py sort_kernel 15 15 0 0%
src/flag_gems/runtime/backend/_hygon/ops/sort.py sort 2 2 0 0%
src/flag_gems/runtime/backend/_hygon/ops/sort.py sort_stable 19 19 0 0%
src/flag_gems/runtime/backend/_hygon/ops/sort.py (no function) 33 33 0 0%
src/flag_gems/runtime/backend/_hygon/ops/unique.py simple_unique_flat_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_hygon/ops/unique.py output_counts_flat_impl 9 9 0 0%
src/flag_gems/runtime/backend/_hygon/ops/unique.py output_counts_flat_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_hygon/ops/unique.py quick_output_flat_impl 11 11 0 0%
src/flag_gems/runtime/backend/_hygon/ops/unique.py quick_output_flat_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_hygon/ops/unique.py local_quick_unique_flat_impl 18 18 0 0%
src/flag_gems/runtime/backend/_hygon/ops/unique.py local_quick_unique_flat_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_hygon/ops/unique.py global_quick_unique_flat_impl 20 20 0 0%
src/flag_gems/runtime/backend/_hygon/ops/unique.py global_quick_unique_flat_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_hygon/ops/unique.py sorted_quick_unique_flat 36 36 0 0%
src/flag_gems/runtime/backend/_hygon/ops/unique.py local_ne_flat_impl 11 11 0 0%
src/flag_gems/runtime/backend/_hygon/ops/unique.py local_ne_flat_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_hygon/ops/unique.py global_cumsum_flat_impl 25 25 0 0%
src/flag_gems/runtime/backend/_hygon/ops/unique.py global_cumsum_flat_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_hygon/ops/unique.py sorted_indices_unique_flat 30 30 0 0%
src/flag_gems/runtime/backend/_hygon/ops/unique.py simple_unique_flat 20 20 0 0%
src/flag_gems/runtime/backend/_hygon/ops/unique.py _unique2 10 10 0 0%
src/flag_gems/runtime/backend/_hygon/ops/unique.py (no function) 45 45 0 0%
src/flag_gems/runtime/backend/_hygon/ops/upsample_nearest2d.py upsample_nearest2d_kernel 27 27 0 0%
src/flag_gems/runtime/backend/_hygon/ops/upsample_nearest2d.py upsample_nearest2d 19 19 0 0%
src/flag_gems/runtime/backend/_hygon/ops/upsample_nearest2d.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_iluvatar/__init__.py (no function) 4 0 0 100%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py simple_elementwise_blocksize_heur 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py argmax_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py argmax_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py argmin_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py argmin_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py dropout_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py dropout_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py exponential_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py exponential_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py gather_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py gather_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py index_select_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py index_select_heur_block_n 2 2 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py mm_heur_even_k 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py rand_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py rand_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py randn_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py randn_heur_num_warps 3 3 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py softmax_heur_tile_k 11 11 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py softmax_heur_tile_n_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py softmax_heur_one_tile_per_cta 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py softmax_heur_num_warps_non_inner 6 6 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py softmax_heur_tile_n_inner 3 3 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py softmax_heur_num_warps_inner 6 6 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py softmax_heur_tile_n_bwd_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py softmax_heur_tile_m 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py uniform_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py uniform_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py var_mean_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py upsample_nearest2d_SAME_H 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py upsample_nearest2d_SAME_W 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py upsample_nearest2d_USE_INT32_IDX 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py batch_norm_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py batch_norm_heur_block_n 3 3 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py vdot_heur_block_size 6 6 0 0%
src/flag_gems/runtime/backend/_iluvatar/heuristics_config_utils.py (no function) 38 38 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/__init__.py (no function) 2 2 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py true_div_func 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py true_div_func_tensor_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py true_div_func_scalar_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py true_divide 8 8 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py true_divide_ 4 4 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py trunc_div_func 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py trunc_div_func_tensor_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py trunc_div_func_scalar_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py trunc_divide 8 8 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py trunc_divide_ 4 4 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py _int_floordiv 4 4 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py _float_floordiv 14 14 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py floor_div_func 3 3 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py floor_div_func_tensor_scalar 3 3 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py floor_div_func_scalar_tensor 3 3 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py floor_divide 8 8 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py floor_divide_ 4 4 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py div_mode 8 8 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py div_mode_ 8 8 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py _remainder 4 4 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py rem_tt 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py rem_ts 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py rem_st 1 1 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py remainder 8 8 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py remainder_ 4 4 0 0%
src/flag_gems/runtime/backend/_iluvatar/ops/div.py (no function) 62 62 0 0%
src/flag_gems/runtime/backend/_kunlunxin/__init__.py (no function) 4 0 0 100%
src/flag_gems/runtime/backend/_kunlunxin/fused/__init__.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/concat_and_cache_mla.py concat_and_cache_mla_kernel 35 35 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/concat_and_cache_mla.py ConcatAndCacheMla.forward 26 26 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/concat_and_cache_mla.py concat_and_cache_mla 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/concat_and_cache_mla.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/cross_entropy_loss.py heur_block_c 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/cross_entropy_loss.py heur_block_d 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/cross_entropy_loss.py celoss_indices_kernel 32 32 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/cross_entropy_loss.py celoss_probability_kernel 35 35 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/cross_entropy_loss.py celoss_indices_smooth_kernel 44 44 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/cross_entropy_loss.py celoss_indices_bwd 35 35 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/cross_entropy_loss.py celoss_probability_bwd 48 48 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/cross_entropy_loss.py celoss_indices_smooth_bwd 48 48 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/cross_entropy_loss.py sum_and_scale 25 25 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/cross_entropy_loss.py CrossEntropyLoss.forward 75 75 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/cross_entropy_loss.py CrossEntropyLoss.backward 41 41 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/cross_entropy_loss.py cross_entropy_loss 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/cross_entropy_loss.py (no function) 44 44 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/flash_mla.py flash_mla_attn_kernel 63 63 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/flash_mla.py flash_mla 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/flash_mla.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/fused_add_rms_norm.py fused_add_rmsnorm_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/fused_add_rms_norm.py fused_add_rmsnorm_kernel_tile 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/fused_add_rms_norm.py fused_add_rms_norm 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/fused_add_rms_norm.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/geglu.py geglu_kernel 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/geglu.py dgeglu_kernel 21 21 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/geglu.py geglu 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/geglu.py dgeglu 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/geglu.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/gelu_and_mul.py gelu_none_and_mul_kernel 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/gelu_and_mul.py gelu_none_and_mul_grad_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/gelu_and_mul.py gelu_tanh_and_mul_kernel 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/gelu_and_mul.py gelu_tanh_and_mul_grad_kernel 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/gelu_and_mul.py GeluAndMul.forward 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/gelu_and_mul.py GeluAndMul.backward 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/gelu_and_mul.py gelu_and_mul 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/gelu_and_mul.py (no function) 28 28 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/instance_norm.py prev_multiple_of 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/instance_norm.py instance_norm_persistent_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/instance_norm.py instance_norm_persistent_kernel_multiline 22 22 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/instance_norm.py instance_norm_loop_kernel_heur_tile_n 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/instance_norm.py instance_norm_loop_kernel 49 49 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/instance_norm.py instancenorm_fwd_kernel_xpu 33 33 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/instance_norm.py instance_norm_use_running_stats_kernel_heur_tile_n 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/instance_norm.py instance_norm_use_running_stats_kernel 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/instance_norm.py update_running_stats_kernel 19 19 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/instance_norm.py instance_norm_backward_kernel_heur_block_row_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/instance_norm.py instance_norm_backward_kernel_heur_block_col_size 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/instance_norm.py instance_norm_backward_kernel 39 39 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/instance_norm.py weight_bias_backward_kernel_heur_block_batch_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/instance_norm.py weight_bias_backward_kernel_heur_block_col_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/instance_norm.py weight_bias_backward_kernel 26 26 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/instance_norm.py InstanceNorm.forward 39 39 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/instance_norm.py InstanceNorm.backward 19 19 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/instance_norm.py instance_norm 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/instance_norm.py (no function) 53 53 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/moe_align_block_size.py ceil_div 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/moe_align_block_size.py round_up 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/moe_align_block_size.py moe_align_block_size_stage1 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/moe_align_block_size.py moe_align_block_size_stage2 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/moe_align_block_size.py moe_align_block_size_stage3 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/moe_align_block_size.py moe_align_block_size_stage4 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/moe_align_block_size.py moe_align_block_size_triton 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/moe_align_block_size.py moe_align_block_size 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/moe_align_block_size.py (no function) 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/outer.py Outer.forward 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/outer.py Outer.backward 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/outer.py outer 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/outer.py (no function) 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/reglu.py heur_tile_m 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/reglu.py heru_tile_n 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/reglu.py dreglu_kernel 19 19 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/reglu.py reglu_kernel 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/reglu.py reglu 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/reglu.py dreglu 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/reglu.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/reshape_and_cache.py reshape_and_cache_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/reshape_and_cache.py reshape_and_cache 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/reshape_and_cache.py (no function) 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/reshape_and_cache_flash.py reshape_and_cache_flash_kernel 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/reshape_and_cache_flash.py reshape_and_cache_flash 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/reshape_and_cache_flash.py (no function) 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/rotary_embedding.py apply_rotary_pos_emb_kernel 42 42 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/rotary_embedding.py apply_rotary_pos_emb_inplace_kernel 38 38 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/rotary_embedding.py apply_rotary_pos_emb 32 32 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/rotary_embedding.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/rwkv_ka_fusion.py rwkv_ka_fusion_kernel 19 19 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/rwkv_ka_fusion.py rwkv_ka_fusion 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/rwkv_ka_fusion.py (no function) 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/rwkv_mm_sparsity.py rwkv_mm_sparsity_kernel 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/rwkv_mm_sparsity.py rwkv_mm_sparsity 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/rwkv_mm_sparsity.py (no function) 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/silu_and_mul.py silu_and_mul_kernel 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/silu_and_mul.py silu_and_mul_grad_kernel 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/silu_and_mul.py SiluAndMul.forward 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/silu_and_mul.py SiluAndMul.backward 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/silu_and_mul.py silu_and_mul 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/silu_and_mul.py silu_and_mul_out 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/silu_and_mul.py (no function) 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/skip_layernorm.py skip_layer_norm_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/skip_layernorm.py skip_layer_norm_kernel_tile 37 37 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/skip_layernorm.py SkipLayerNorm.forward 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/skip_layernorm.py skip_layer_norm 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/skip_layernorm.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/topk_softmax.py topk_gating_softmax_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/topk_softmax.py topk_softmax 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/topk_softmax.py (no function) 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/weight_norm.py heur_row_weight_norm_except_dim_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/weight_norm.py heur_col_weight_norm_except_dim_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/weight_norm.py weight_norm_except_dim_kernel 29 29 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/weight_norm.py weight_norm_except_dim_bwd_kernel 32 32 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/weight_norm.py weight_norm_except_dim 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/weight_norm.py weight_norm_except_dim_backward 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/weight_norm.py WeightNorm.forward 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/weight_norm.py WeightNorm.backward 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/weight_norm.py weight_norm 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/fused/weight_norm.py (no function) 28 28 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py simple_elementwise_blocksize_heur 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py argmax_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py argmax_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py argmin_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py argmin_heur_block_n 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py bmm_heur_divisible_m 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py bmm_heur_divisible_n 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py bmm_heur_divisible_k 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py dropout_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py dropout_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py exponential_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py exponential_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py gather_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py gather_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py index_add_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py index_add_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py index_select_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py index_select_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py mm_heur_even_k 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py rand_heur_block 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py rand_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py randn_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py randn_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py softmax_heur_tile_k 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py softmax_heur_tile_n_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py softmax_heur_one_tile_per_cta 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py softmax_heur_num_warps_non_inner 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py softmax_heur_tile_n_inner 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py softmax_heur_num_warps_inner 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py softmax_heur_tile_n_bwd_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py softmax_heur_tile_m 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py uniform_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py uniform_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py var_mean_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py upsample_nearest2d_SAME_H 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py upsample_nearest2d_SAME_W 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py batch_norm_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py batch_norm_heur_block_n 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py vdot_heur_block_size 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/heuristics_config_utils.py (no function) 42 42 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/__init__.py (no function) 170 170 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/abs.py abs_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/abs.py abs 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/abs.py abs_ 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/abs.py (no function) 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/acos.py acos_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/acos.py acos 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/acos.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/add.py add_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/add.py add_func_tensor_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/add.py add_func_scalar_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/add.py add 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/add.py add_ 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/add.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/addcdiv.py addcdiv_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/addcdiv.py addcdiv 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/addcdiv.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/addcmul.py addcmul_forward 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/addcmul.py addcmul 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/addcmul.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/addmm.py addmm_kernel 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/addmm.py addmm 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/addmm.py addmm_out 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/addmm.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/addmv.py heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/addmv.py heur_block_m 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/addmv.py addmv_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/addmv.py addmv 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/addmv.py addmv_out 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/addmv.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/addr.py addr_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/addr.py addr 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/addr.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/all.py get_block 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/all.py heur_m_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/all.py heur_n_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/all.py reduce_all 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/all.py all_kernel_dim 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/all.py min_kernel_dim 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/all.py all_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/all.py all_kernel_2 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/all.py all 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/all.py all_dim 26 26 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/all.py all_dims 26 26 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/all.py (no function) 36 36 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/amax.py amax_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/amax.py amax_kernel_2 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/amax.py heur_m_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/amax.py heur_n_block_size 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/amax.py amax_kernel 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/amax.py amax 37 37 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/amax.py (no function) 22 22 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/angle.py angle_func 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/angle.py angle_float_and_int 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/angle.py angle 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/angle.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/any.py get_block 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/any.py heur_m_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/any.py heur_n_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/any.py reduce_any 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/any.py any_kernel_dim 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/any.py max_kernel_dim 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/any.py any_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/any.py any_kernel_2 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/any.py any 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/any.py any_dim 26 26 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/any.py any_dims 26 26 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/any.py (no function) 36 36 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/arange.py arange_func 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/arange.py arange_start 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/arange.py arange 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/arange.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/argmax.py argmax_kernel_1 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/argmax.py argmax_kernel_2 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/argmax.py heur_m_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/argmax.py heur_n_block_size 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/argmax.py argmax_kernel 22 22 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/argmax.py argmax_kernel_small_n 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/argmax.py argmax 47 47 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/argmax.py (no function) 29 29 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/argmin.py argmin_kernel_1 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/argmin.py argmin_kernel_2 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/argmin.py heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/argmin.py argmin_kernel 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/argmin.py argmin 38 38 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/argmin.py (no function) 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/atan.py atan_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/atan.py atan 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/atan.py atan_ 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/atan.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/attention.py _attn_fwd_inner 51 51 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/attention.py _attn_fwd 35 35 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/attention.py _attn_bwd_preprocess 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/attention.py _attn_bwd_dkdv 32 32 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/attention.py _attn_bwd_dq 26 26 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/attention.py _attn_bwd 61 61 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/attention.py scaled_dot_product_attention_forward 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/attention.py scaled_dot_product_attention_backward 40 40 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/attention.py ScaleDotProductAttention.forward 38 38 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/attention.py ScaleDotProductAttention.backward 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/attention.py scaled_dot_product_attention 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/attention.py flash_attention_forward 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/attention.py maybe_contiguous 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/attention.py flash_attn_varlen_func 25 25 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/attention.py (no function) 39 39 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/avg_pool2d.py pool2d_output_size 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/avg_pool2d.py avg_pool2d_forward_kernel 33 33 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/avg_pool2d.py avg_pool2d_backward_kernel 44 44 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/avg_pool2d.py _parse_pool_params 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/avg_pool2d.py avg_pool2d 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/avg_pool2d.py avg_pool2d_backward 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/avg_pool2d.py (no function) 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/baddbmm.py baddbmm_kernel 63 63 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/baddbmm.py BaddbmmFunction.forward 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/baddbmm.py BaddbmmFunction.backward 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/baddbmm.py compute_bias_grad 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/baddbmm.py compute_A_grad 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/baddbmm.py compute_B_grad 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/baddbmm.py baddbmm 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/baddbmm.py (no function) 27 27 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/batch_norm.py make_3d_for_bn 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/batch_norm.py batch_norm_forward_kernel 54 54 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/batch_norm.py batch_norm_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/batch_norm.py batch_norm_heur_block_n 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/batch_norm.py batch_norm_backward_kernel 46 46 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/batch_norm.py batch_norm 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/batch_norm.py batch_norm_backward 21 21 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/batch_norm.py (no function) 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_and.py bitwise_and_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_and.py bitwise_and_tensor 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_and.py bitwise_and_tensor_ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_and.py bitwise_and_func_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_and.py bitwise_and_scalar 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_and.py bitwise_and_scalar_ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_and.py bitwise_and_scalar_tensor 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_and.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_left_shift.py bitwise_left_shift_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_left_shift.py bitwise_left_shift 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_left_shift.py (no function) 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_not.py bitwise_not_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_not.py bitwise_not 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_not.py bitwise_not_ 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_not.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_or.py bitwise_or_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_or.py bitwise_or_tensor 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_or.py bitwise_or_tensor_ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_or.py bitwise_or_func_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_or.py bitwise_or_scalar 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_or.py bitwise_or_scalar_ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_or.py bitwise_or_scalar_tensor 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_or.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_right_shift.py bitwise_right_shift_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_right_shift.py bitwise_right_shift 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bitwise_right_shift.py (no function) 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bmm.py heur_group_m 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bmm.py heur_divisible_m 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bmm.py heur_divisible_n 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bmm.py heur_divisible_k 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bmm.py bmm_kernel 58 58 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bmm.py bmm 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bmm.py bmm_out 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/bmm.py (no function) 19 19 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cat.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cat.py cat 38 38 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cat.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/celu.py celu_forward_kernel 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/celu.py celu 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/celu.py celu_ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/celu.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/clamp.py clamp_func_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/clamp.py clamp_func_min_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/clamp.py clamp_func_max_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/clamp.py clamp_tensor 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/clamp.py clamp_tensor_ 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/clamp.py clamp_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/clamp.py clamp_func_min 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/clamp.py clamp_func_max 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/clamp.py clamp_min 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/clamp.py clamp_min_ 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/clamp.py clamp 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/clamp.py clamp_ 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/clamp.py (no function) 29 29 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/contiguous.py contiguous 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/contiguous.py (no function) 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/conv1d.py conv1d 22 22 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/conv1d.py (no function) 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/conv2d.py conv2d_output_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/conv2d.py conv2d_forward_kernel 39 39 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/conv2d.py conv2d_backward_kernel_weight 32 32 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/conv2d.py Conv2d.forward 55 55 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/conv2d.py Conv2d.backward 52 52 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/conv2d.py conv2d 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/conv2d.py (no function) 19 19 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/conv3d.py conv3d_output_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/conv3d.py conv3d_forward_kernel 41 41 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/conv3d.py conv3d 37 37 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/conv3d.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/conv_depthwise2d.py _conv_depthwise2d 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/conv_depthwise2d.py (no function) 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/copy.py copy_slice 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/copy.py _copy_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/copy.py _can_use_triton 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/copy.py _expand_like 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/copy.py copy 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/copy.py copy_ 25 25 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/copy.py (no function) 19 19 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cos.py cos_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cos.py cos 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cos.py cos_ 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cos.py (no function) 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/count_nonzero.py count_nonzero_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/count_nonzero.py count_nonzero_kernel_1_part0_xpu 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/count_nonzero.py count_nonzero_kernel_1_part1_xpu 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/count_nonzero.py heur_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/count_nonzero.py count_nonzero_kernel 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/count_nonzero.py count_nonzero_kernel_xpu 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/count_nonzero.py count_nonzero_combin_kernel_1 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/count_nonzero.py count_nonzero_combin_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/count_nonzero.py count_nonzero 40 40 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/count_nonzero.py (no function) 37 37 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummax.py tl_cummax 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummax.py tl_max_tie_break_right 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummax.py add_base_max_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummax.py scan_part_max_kernel 27 27 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummax.py scan_then_fan_col 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummax.py scan_part_max_abc_kernel 34 34 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummax.py add_base_max_abc_kernel 24 24 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummax.py scan_then_fan 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummax.py scan_part_max_abc_loop_kernel 39 39 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummax.py scan_then_fan_loop 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummax.py cummax 24 24 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummax.py (no function) 35 35 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummin.py tl_cummin 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummin.py tl_min_tie_break_right 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummin.py add_base_min_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummin.py scan_part_min_kernel 27 27 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummin.py scan_then_fan_col 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummin.py scan_part_min_abc_kernel 34 34 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummin.py add_base_min_abc_kernel 24 24 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummin.py scan_then_fan 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummin.py scan_part_min_abc_loop_kernel 39 39 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummin.py scan_then_fan_loop 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummin.py cummin 24 24 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cummin.py (no function) 36 36 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cumsum.py scan_part_sum_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cumsum.py add_base_sum_kernel 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cumsum.py scan_part_sum_abc_kernel 24 24 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cumsum.py add_base_sum_abc_kernel 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cumsum.py scan_then_fan_col 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cumsum.py scan_then_fan 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cumsum.py cumsum_wrapper 22 22 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cumsum.py cumsum 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cumsum.py cumsum_out 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cumsum.py normed_cumsum_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cumsum.py block_cumsum_kernel 35 35 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cumsum.py block_update_kernel 22 22 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cumsum.py normed_cumsum 37 37 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/cumsum.py (no function) 40 40 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/diag.py diag_1d_to_2d_kernel 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/diag.py diag_2d_to_1d_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/diag.py diag_1d_to_2d 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/diag.py diag_2d_to_1d 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/diag.py diag 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/diag.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/diag_embed.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/diag_embed.py diag_embed 19 19 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/diag_embed.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/diagonal.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/diagonal.py diagonal_backward 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/diagonal.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py true_div_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py true_div_func_tensor_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py true_div_func_scalar_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py true_divide 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py true_divide_out 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py true_divide_ 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py trunc_div_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py trunc_div_func_tensor_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py trunc_div_func_scalar_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py trunc_divide 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py trunc_divide_ 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py _int_floordiv 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py _float_floordiv 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py floor_div_func 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py floor_div_func_tensor_scalar 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py floor_div_func_scalar_tensor 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py floor_divide 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py floor_divide_ 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py div_mode 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py div_mode_ 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py _remainder 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py rem_tt 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py rem_ts 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py rem_st 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py remainder 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py remainder_ 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/div.py (no function) 67 67 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/dot.py dot_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/dot.py dot_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/dot.py dot_kernel_2 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/dot.py dot 22 22 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/dot.py (no function) 19 19 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/dropout.py dropout_forward_kernel 38 38 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/dropout.py dropout_backward_kernel 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/dropout.py dropout 21 21 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/dropout.py dropout_backward 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/dropout.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/elu.py elu_forward_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/elu.py elu_backward_kernel 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/elu.py elu 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/elu.py elu_ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/elu.py elu_backward 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/elu.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/embedding.py embedding_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/embedding.py indice_freq_kernel 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/embedding.py embedding_backward_kernel 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/embedding.py embedding_grad_scale_kernel 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/embedding.py embedding 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/embedding.py embedding_backward 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/embedding.py (no function) 22 22 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/eq.py eq_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/eq.py eq 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/eq.py eq_func_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/eq.py eq_scalar 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/eq.py (no function) 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/erf.py erf_func 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/erf.py erf 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/erf.py erf_ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/erf.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/exp.py exp_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/exp.py exp 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/exp.py exp_ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/exp.py exp_out 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/exp.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/exp2.py exp2_func 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/exp2.py exp2 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/exp2.py exp2_ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/exp2.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/exponential_.py heur_block 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/exponential_.py heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/exponential_.py fused_exponential_kernel 37 37 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/exponential_.py paste_u64 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/exponential_.py transform_exponential 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/exponential_.py exponential_ 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/exponential_.py (no function) 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/eye.py eye 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/eye.py (no function) 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/eye_m.py eye_kernel 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/eye_m.py eye_m 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/eye_m.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/fill.py fill_scalar_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/fill.py fill_tensor_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/fill.py fill_scalar 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/fill.py fill_tensor 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/fill.py fill_tensor_ 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/fill.py fill_scalar_ 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/fill.py (no function) 19 19 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_api.py CHECK_DEVICE 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_api.py fwd_params.__init__ 57 57 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_api.py fwd_params.args 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_api.py mha_varlan_fwd 145 145 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_api.py mha_fwd 102 102 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_api.py mha_fwd.splits_heuristic 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_api.py mha_fwd.dispatch 33 33 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_api.py (no function) 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py u64_to_lohi 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py u64_from_lohi 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py philox_ 21 21 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py apply_dropout_mask 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py apply_dropout 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py apply_alibi 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py apply_mask 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py softmax_rescale 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py apply_softcap 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py block_m_splitkv_heuristic 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py block_n_splitkv_heuristic 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py is_even_mn 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py block_m_splitkv_heuristic_spec_args 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py block_n_splitkv_heuristic_spec_args 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py is_even_mn_spec_args 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py keep 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py prune_fwd_configs 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py flash_fwd_kernel 159 159 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py flash_fwd_bh_parallel_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py flash_fwd_splitkv_kernel 111 111 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py flash_fwd_splitkv_combine_kernel 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py virtual_to_cache 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py load_from_kvcache 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py flash_varlen_fwd_kernel 92 92 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flash_kernel.py (no function) 43 43 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flip.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flip.py flip 21 21 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/flip.py (no function) 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/full.py full_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/full.py check_dtype 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/full.py full 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/full.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/full_like.py full_like 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/full_like.py (no function) 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gather.py generate_imports 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gather.py generate_gather_kernel 77 77 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gather.py parameter_for_wrapper 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gather.py generate_gather_wrapper 30 30 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gather.py generate_code 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gather.py GatherFunction.__init__ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gather.py GatherFunction.__call__ 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gather.py GatherFunction.arg_key 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gather.py gather 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gather.py gather_backward 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gather.py (no function) 22 22 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/ge.py ge_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/ge.py ge 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/ge.py ge_func_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/ge.py ge_scalar 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/ge.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gelu.py gelu_none 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gelu.py gelu_tanh 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gelu.py gelu_backward_none 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gelu.py gelu_backward_tanh 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gelu.py gelu 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gelu.py gelu_backward 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gelu.py gelu_ 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gelu.py (no function) 25 25 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/get_scheduler_metadata.py get_dtype_bytes 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/get_scheduler_metadata.py tile_size_fwd_sm8x 50 50 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/get_scheduler_metadata.py get_optimal_block_mn 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/get_scheduler_metadata.py round_up_headdim 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/get_scheduler_metadata.py round_up_headdimv 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/get_scheduler_metadata.py use_one_mma_wg 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/get_scheduler_metadata.py get_num_splits 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/get_scheduler_metadata.py _vllm_num_splits_heuristic 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/get_scheduler_metadata.py _prepare_pass1_kernel 33 33 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/get_scheduler_metadata.py _prepare_pass2_kernel 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/get_scheduler_metadata.py get_pack_gqa 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/get_scheduler_metadata.py get_scheduler_metadata 84 84 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/get_scheduler_metadata.py (no function) 22 22 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/glu.py glu_kernel 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/glu.py glu_backward_kernel 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/glu.py glu 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/glu.py glu_backward 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/glu.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/groupnorm.py group_norm_kernel 29 29 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/groupnorm.py group_norm_backward_kernel 38 38 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/groupnorm.py weight_bias_backward_kernel 21 21 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/groupnorm.py weight_bias_backward_kernel_loop 25 25 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/groupnorm.py group_norm 19 19 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/groupnorm.py group_norm_backward 31 31 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/groupnorm.py (no function) 24 24 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gt.py gt_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gt.py gt 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gt.py gt_func_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gt.py gt_scalar 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/gt.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/hstack.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/hstack.py hstack 30 30 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/hstack.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index.py get_max_rank_shape 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index.py broadcast_indices 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index.py generate_imports 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index.py generate_index_kernel 76 76 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index.py generate_index_wrapper 37 37 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index.py generate_code 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index.py IndexFunction.__init__ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index.py IndexFunction.__call__ 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index.py IndexFunction.arg_key 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index.py index 98 98 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index_add.py index_add_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index_add.py index_add 25 25 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index_add.py index_add_ 28 28 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index_add.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index_put.py get_max_rank_shape 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index_put.py broadcast_indices 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index_put.py generate_imports 22 22 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index_put.py generate_index_put_kernel 70 70 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index_put.py generate_index_put_wrapper 37 37 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index_put.py generate_code 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index_put.py IndexPutFunction.__init__ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index_put.py IndexPutFunction.__call__ 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index_put.py IndexPutFunction.arg_key 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index_put.py index_put 26 26 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index_put.py index_put_ 25 25 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index_put.py (no function) 21 21 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index_select.py index_select_kernel 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index_select.py index_select 22 22 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/index_select.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isclose.py isclose_func 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isclose.py isclose 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isclose.py allclose 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isclose.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isfinite.py isfinite_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isfinite.py isfinite 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isfinite.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isin.py launch_arg 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isin.py isin_by_comparation_impl 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isin.py isin_by_comparation_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isin.py isin_by_comparation 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isin.py isin_by_search_impl 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isin.py isin_by_search_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isin.py isin_by_search 36 36 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isin.py isin 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isin.py (no function) 25 25 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isinf.py isinf_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isinf.py isinf 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isinf.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isnan.py isnan_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isnan.py isnan 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/isnan.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/kron.py prepare_tensor_for_kron 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/kron.py calculate_indices 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/kron.py heur_block_n 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/kron.py heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/kron.py kron_kernel 26 26 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/kron.py kron 38 38 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/kron.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/layernorm.py prev_multiple_of 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/layernorm.py layer_norm_persistent_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/layernorm.py layer_norm_persistent_kernel_multiline 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/layernorm.py layer_norm_loop_kernel 54 54 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/layernorm.py layernorm_fwd_kernel 31 31 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/layernorm.py layer_norm_backward_kernel_heur_block_row_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/layernorm.py layer_norm_backward_kernel_heur_block_col_size 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/layernorm.py layer_norm_backward_kernel 41 41 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/layernorm.py weight_bias_backward_kernel_heur_block_row_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/layernorm.py weight_bias_backward_kernel_heur_block_col_size 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/layernorm.py weight_bias_backward_kernel 24 24 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/layernorm.py layer_norm 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/layernorm.py layer_norm_backward 37 37 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/layernorm.py (no function) 37 37 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/le.py le_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/le.py le 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/le.py le_func_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/le.py le_scalar 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/le.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/lerp.py lerp_tensor_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/lerp.py lerp_scalar_kernel_head 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/lerp.py lerp_scalar_kernel_tail 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/lerp.py lerp_tensor 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/lerp.py lerp_tensor_ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/lerp.py lerp_scalar 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/lerp.py lerp_scalar_ 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/lerp.py (no function) 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/linspace.py linspace_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/linspace.py linspace 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/linspace.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/log.py log_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/log.py log 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/log.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/log_sigmoid.py log_sigmoid_forward 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/log_sigmoid.py log_sigmoid 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/log_sigmoid.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/log_softmax.py heur_block_n 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/log_softmax.py heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/log_softmax.py log_softmax_kernel 26 26 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/log_softmax.py log_softmax_backward_kernel 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/log_softmax.py log_softmax 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/log_softmax.py log_softmax_backward 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/log_softmax.py (no function) 21 21 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/logical_and.py logical_and_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/logical_and.py logical_and 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/logical_and.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/logical_not.py logical_not_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/logical_not.py logical_not 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/logical_not.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/logical_or.py logical_or_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/logical_or.py logical_or 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/logical_or.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/logical_xor.py logical_xor_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/logical_xor.py logical_xor 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/logical_xor.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/logspace.py exp2_tmp 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/logspace.py logspace_kernel 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/logspace.py logspace 19 19 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/logspace.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/lt.py lt_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/lt.py lt 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/lt.py lt_func_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/lt.py lt_scalar 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/lt.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/masked_fill.py masked_fill_kernel_heur_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/masked_fill.py masked_fill_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/masked_fill.py masked_fill_kernel_self_heur_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/masked_fill.py masked_fill_kernel_self 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/masked_fill.py masked_fill 25 25 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/masked_fill.py masked_fill_ 26 26 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/masked_fill.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/masked_scatter.py masked_scatter_single_pass_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/masked_scatter.py mask_part_sum_kernel 24 24 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/masked_scatter.py masked_scatter_kernel 22 22 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/masked_scatter.py masked_scatter_impl 24 24 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/masked_scatter.py masked_scatter 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/masked_scatter.py masked_scatter_ 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/masked_scatter.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/masked_select.py heur_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/masked_select.py masked_select_kernel 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/masked_select.py masked_select 22 22 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/masked_select.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/max.py max_kernel_1 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/max.py max_kernel_2 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/max.py heur_m_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/max.py heur_n_block_size 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/max.py max_kernel 24 24 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/max.py max 26 26 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/max.py max_dim 31 31 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/max.py (no function) 27 27 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/max_pool2d_with_indices.py max_pool2d_output_size 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/max_pool2d_with_indices.py max_pool2d_forward_kernel 34 34 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/max_pool2d_with_indices.py max_pool2d_backward_kernel 31 31 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/max_pool2d_with_indices.py _parse_pool_params 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/max_pool2d_with_indices.py _parse_pool_params._parse_param 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/max_pool2d_with_indices.py max_pool2d_with_indices 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/max_pool2d_with_indices.py max_pool2d_backward 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/max_pool2d_with_indices.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/maximum.py maximum_kernel 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/maximum.py maximum 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/maximum.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mean.py mean_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mean.py mean_kernel_2 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mean.py mean 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mean.py heur_m_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mean.py heur_n_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mean.py mean_dim_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mean.py mean_dim 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mean.py (no function) 24 24 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/min.py min_kernel_1 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/min.py min_kernel_2 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/min.py heur_m_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/min.py heur_n_block_size 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/min.py min_kernel 24 24 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/min.py min 21 21 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/min.py min_dim 24 24 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/min.py (no function) 26 26 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/minimum.py minimum_kernel 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/minimum.py minimum 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/minimum.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mm.py heur_split_k 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mm.py heur_even_k 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mm.py heur_group_m 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mm.py mm_kernel 39 39 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mm.py get_higher_dtype 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mm.py mm 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mm.py mm_out 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mm.py (no function) 25 25 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mse_loss.py kernel_1 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mse_loss.py kernel_2 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mse_loss.py func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mse_loss.py mse_loss 26 26 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mse_loss.py (no function) 25 25 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mul.py mul_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mul.py mul_func_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mul.py mul 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mul.py mul_ 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mul.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/multinomial.py multinomial_with_replacement 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/multinomial.py multinomial 29 29 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/multinomial.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mv.py heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mv.py heur_block_m 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mv.py mv_kernel 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mv.py mv 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mv.py mv_cluster 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/mv.py (no function) 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/nan_to_num.py nan_to_num_func 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/nan_to_num.py nan_to_num 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/nan_to_num.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/ne.py ne_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/ne.py ne 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/ne.py ne_func_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/ne.py ne_scalar 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/ne.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/neg.py neg_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/neg.py neg 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/neg.py neg_ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/neg.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/nllloss.py nll_loss_forward_kernel 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/nllloss.py nll_loss_backward_kernel 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/nllloss.py nll_loss2d_forward_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/nllloss.py nll_loss2d_backward_kernel 21 21 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/nllloss.py nll_loss_forward 27 27 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/nllloss.py nll_loss_backward 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/nllloss.py nll_loss2d_forward 26 26 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/nllloss.py nll_loss2d_backward 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/nllloss.py (no function) 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/nonzero.py nonzero_kernel_heur_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/nonzero.py nonzero_kernel 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/nonzero.py nonzero 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/nonzero.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/normal.py transform_func_tensor_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/normal.py transform_func_tensor_float 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/normal.py transform_func_float_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/normal.py transform_func_float_float 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/normal.py normal_distribution 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/normal.py normal_tensor_tensor 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/normal.py normal_tensor_float 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/normal.py normal_float_tensor 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/normal.py (no function) 26 26 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/ones.py ones_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/ones.py ones 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/ones.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/ones_like.py ones_like 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/ones_like.py (no function) 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pad.py parameter_for_wrapper 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pad.py parameter_for_wrapper_out 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pad.py parameter_ref_for_wrapper 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pad.py output_ref_for_wrapper 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pad.py generate_imports 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pad.py generate_functional_padding_wrapper 29 29 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pad.py generate_destination_passing_padding_wrapper 63 63 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pad.py generate_pad_kernel 85 85 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pad.py generate_code 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pad.py PadFunction.__init__ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pad.py PadFunction.__call__ 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pad.py PadFunction.arg_key 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pad.py pad 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pad.py constant_pad_nd 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pad.py (no function) 24 24 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/per_token_group_quant_fp8.py _per_token_group_quant_fp8 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/per_token_group_quant_fp8.py _per_token_group_quant_fp8_colmajor 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/per_token_group_quant_fp8.py per_token_group_quant_fp8 21 21 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/per_token_group_quant_fp8.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/polar.py polar_kernel 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/polar.py polar 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/polar.py (no function) 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pow.py pow_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pow.py pow_tensor_tensor 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pow.py pow_tensor_tensor_ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pow.py pow_func_tensor_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pow.py pow_tensor_scalar 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pow.py pow_tensor_scalar_ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pow.py pow_func_scalar_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pow.py pow_scalar 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/pow.py (no function) 21 21 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/prod.py reduce_mul 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/prod.py prod_kernel_mid 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/prod.py prod_kernel_result 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/prod.py prod 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/prod.py heur_m_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/prod.py heur_n_block_size 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/prod.py prod_kernel 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/prod.py prod_dim 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/prod.py (no function) 25 25 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/quantile.py heur_block_q 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/quantile.py heur_block_n 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/quantile.py quantile_kernel 28 28 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/quantile.py quantile 34 34 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/quantile.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rand.py rand_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rand.py choose_unroll 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rand.py rand_kernel_1 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rand.py rand_kernel_2 59 59 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rand.py rand 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rand.py (no function) 19 19 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rand_like.py rand_like 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rand_like.py (no function) 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/randn.py randn_kernel 22 22 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/randn.py randn 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/randn.py (no function) 22 22 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/randn_like.py randn_like 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/randn_like.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/randperm.py _get_iinfo_val 21 21 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/randperm.py bitonic_sortbykey_kernel 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/randperm.py radix_type_convert 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/randperm.py digit_hist_kernel 19 19 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/randperm.py radix_sortbykey_scatter_kernel 45 45 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/randperm.py duplicate_keys_shuffle_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/randperm.py sort_by_key 54 54 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/randperm.py randperm 37 37 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/randperm.py (no function) 42 42 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/reciprocal.py reciprocal_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/reciprocal.py reciprocal 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/reciprocal.py reciprocal_ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/reciprocal.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/relu.py relu_forward 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/relu.py relu_backward 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/relu.py relu 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/relu.py relu_ 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/relu.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/repeat.py parameter_for_wrapper 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/repeat.py parameter_for_wrapper_out 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/repeat.py parameter_ref_for_wrapper 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/repeat.py output_ref_for_wrapper 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/repeat.py generate_imports 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/repeat.py generate_functional_repeat_wrapper 38 38 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/repeat.py generate_destination_passing_repeat_wrapper 48 48 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/repeat.py generate_repeat_kernel 89 89 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/repeat.py generate_code 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/repeat.py RepeatFunction.__init__ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/repeat.py RepeatFunction.__call__ 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/repeat.py RepeatFunction.arg_key 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/repeat.py repeat 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/repeat.py (no function) 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/repeat_interleave.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/repeat_interleave.py repeat_interleave_self_int 25 25 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/repeat_interleave.py repeat_interleave_tensor_kernel 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/repeat_interleave.py repeat_interleave_tensor 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/repeat_interleave.py repeat_interleave_self_tensor 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/repeat_interleave.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/resolve_conj.py resolve_conj 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/resolve_conj.py (no function) 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/resolve_neg.py resolve_neg 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/resolve_neg.py (no function) 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rms_norm.py rms_norm_kernel 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rms_norm.py rms_norm_kerne_tile 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rms_norm.py rms_norm_grad_dx_kernel 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rms_norm.py rms_norm_grad_dx_kernel_tile 28 28 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rms_norm.py rms_norm_grad_dw_kernel 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rms_norm.py rms_norm_grad_kernel 19 19 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rms_norm.py rms_norm_forward 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rms_norm.py rms_norm_backward 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rms_norm.py rms_norm_backward_fusion 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rms_norm.py RmsNorm.forward 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rms_norm.py RmsNorm.backward 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rms_norm.py rms_norm 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rms_norm.py (no function) 37 37 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rsqrt.py rsqrt_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rsqrt.py rsqrt 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rsqrt.py rsqrt_ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rsqrt.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rsub.py rsub_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rsub.py rsub_func_tensor_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rsub.py rsub_func_scalar_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rsub.py rsub 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/rsub.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scaled_softmax.py scaled_softmax_forward_kernel 40 40 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scaled_softmax.py scaled_softmax_forward 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scaled_softmax.py scaled_softmax_forward.grid 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scaled_softmax.py scaled_softmax_backward_kernel 34 34 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scaled_softmax.py scaled_softmax_backward 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scaled_softmax.py scaled_softmax_backward.grid 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scaled_softmax.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter.py generate_imports 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter.py generate_scatter_kernel 104 104 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter.py parameter_for_wrapper 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter.py generate_destination_passing_wrapper 39 39 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter.py generate_code 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter.py ScatterFunction.__init__ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter.py ScatterFunction.__call__ 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter.py ScatterFunction.arg_key 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter.py scatter 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter.py scatter_ 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter.py (no function) 21 21 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter_add_.py scatter_add_kernel_1 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter_add_.py generate_imports 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter_add_.py generate_scatter_kernel 76 76 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter_add_.py parameter_for_wrapper 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter_add_.py generate_destination_passing_wrapper 33 33 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter_add_.py generate_code 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter_add_.py ScatterFunction.__init__ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter_add_.py ScatterFunction.__call__ 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter_add_.py ScatterFunction.arg_key 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter_add_.py scatter_add_0 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter_add_.py clip_tensor_to_shape 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter_add_.py scatter_add_1 24 24 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter_add_.py scatter_add_ 19 19 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/scatter_add_.py (no function) 28 28 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/select_scatter.py select_scatter_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/select_scatter.py select_scatter 22 22 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/select_scatter.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sigmoid.py sigmoid_forward 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sigmoid.py sigmoid_backward_kernel 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sigmoid.py sigmoid 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sigmoid.py sigmoid_backward 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sigmoid.py sigmoid_ 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sigmoid.py (no function) 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/silu.py silu_forward 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/silu.py silu_backward_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/silu.py silu 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/silu.py silu_backward 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/silu.py silu_ 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/silu.py (no function) 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sin.py sin_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sin.py sin 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sin.py sin_ 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sin.py (no function) 10 10 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/slice_scatter.py slice_scatter 22 22 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/slice_scatter.py (no function) 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/softmax.py next_multiple_of 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/softmax.py prev_multiple_of 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/softmax.py softmax_kernel_inner 48 48 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/softmax.py softmax_backward_kernel_inner_heur_tile_m 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/softmax.py softmax_backward_kernel_inner_heru_tile_n 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/softmax.py softmax_backward_kernel_inner_heur_one_tile_per_cta 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/softmax.py softmax_backward_kernel_inner 32 32 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/softmax.py softmax 34 34 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/softmax.py softmax_backward 34 34 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/softmax.py (no function) 26 26 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/softplus.py softplus_forward 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/softplus.py softplus 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/softplus.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sort.py unwrap_if_constexpr 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sort.py get_int_t 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sort.py one_zeros 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sort.py zero_ones 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sort.py uint_to_uint 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sort.py int_to_uint 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sort.py floating_to_uint 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sort.py convert_to_uint_preverse_order 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sort.py compute_global_hist_kernel 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sort.py sweep 43 43 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sort.py count_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sort.py scatter_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sort.py radix_sort_low_mem 33 33 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sort.py radix_sort 35 35 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sort.py sort_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sort.py sort 21 21 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sort.py sort_stable 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sort.py (no function) 39 39 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sqrt.py sqrt_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sqrt.py sqrt 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sqrt.py sqrt_ 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sqrt.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/stack.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/stack.py stack 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/stack.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/std.py _std_map_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/std.py _std_reduce_kernel 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/std.py _std_fused_dim_kernel_m 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/std.py _std_fused_dim_kernel_n 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/std.py _std_fused_dim_kernel 30 30 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/std.py std 40 40 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/std.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sub.py sub_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sub.py sub_func_tensor_scalar 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sub.py sub_func_scalar_tensor 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sub.py sub 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sub.py sub_ 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sub.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sum.py sum_kernel_1 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sum.py sum_kernel_2 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sum.py heur_m_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sum.py heur_n_block_size 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sum.py sum_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sum.py sum 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sum.py sum_out 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sum.py sum_dim 25 25 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sum.py sum_dim_out 24 24 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/sum.py (no function) 25 25 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tan.py tan_func 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tan.py tan 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tan.py tan_ 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tan.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tanh.py tanh_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tanh.py tanh_backward_kernel 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tanh.py tanh 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tanh.py tanh_backward 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tanh.py tanh_ 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tanh.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/threshold.py threshold_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/threshold.py threshold_backward_kernel 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/threshold.py threshold 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/threshold.py threshold_backward 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/threshold.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tile.py parameter_for_wrapper 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tile.py parameter_for_wrapper_out 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tile.py parameter_ref_for_wrapper 4 4 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tile.py output_ref_for_wrapper 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tile.py generate_imports 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tile.py generate_functional_tile_wrapper 42 42 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tile.py generate_destination_passing_tile_wrapper 48 48 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tile.py generate_tile_kernel 89 89 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tile.py generate_code 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tile.py TileFunction.__init__ 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tile.py TileFunction.__call__ 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tile.py TileFunction.arg_key 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tile.py tile 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/tile.py (no function) 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/to.py _to_copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/to.py _to_copy_func_close_interleave 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/to.py _resolve_dtype 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/to.py _resolve_device 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/to.py _normalize_memory_format 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/to.py _allocate_preserve_format 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/to.py to_copy 30 30 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/to.py (no function) 21 21 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/topk.py _get_finfo_val 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/topk.py _get_iinfo_val 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/topk.py topk_stage1_kernel 22 22 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/topk.py _compare_and_swap 41 41 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/topk.py _bitonic_merge 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/topk.py argsort 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/topk.py topk_stage2_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/topk.py topk 28 28 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/topk.py (no function) 44 44 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/trace.py trace_kernel 21 21 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/trace.py trace 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/trace.py (no function) 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/triu.py heur_m_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/triu.py heur_n_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/triu.py triu_kernel 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/triu.py heur_batch_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/triu.py heur_mn_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/triu.py triu_batch_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/triu.py triu 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/triu.py (no function) 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/uniform.py uniform_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/uniform.py uniform_ 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/uniform.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py simple_unique_flat_kernel 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py output_counts_flat_impl 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py output_counts_flat_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py quick_output_flat_impl 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py quick_output_flat_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py local_quick_unique_flat_impl 24 24 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py local_quick_unique_flat_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py global_quick_unique_flat_impl 23 23 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py global_quick_unique_flat_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py global_quick_unique_flat_impl_stage_1 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py global_quick_unique_flat_kernel_stage_1 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py global_quick_unique_flat_impl_stage_2 17 17 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py global_quick_unique_flat_kernel_stage_2 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py sorted_quick_unique_flat 73 73 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py local_ne_flat_impl 11 11 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py local_ne_flat_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py global_cumsum_flat_impl 27 27 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py global_cumsum_flat_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py global_cumsum_flat_impl_stage_1 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py global_cumsum_flat_kernel_stage_1 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py global_cumsum_flat_impl_stage_2 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py global_cumsum_flat_kernel_stage_2 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py sorted_indices_unique_flat 86 86 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py simple_unique_flat 38 38 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py _unique2 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/unique.py (no function) 64 64 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/upsample_bicubic2d_aa.py configs 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/upsample_bicubic2d_aa.py heur_m_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/upsample_bicubic2d_aa.py heur_n_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/upsample_bicubic2d_aa.py upsample_bicubic2d_aa_kernel 97 97 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/upsample_bicubic2d_aa.py general_interpolate_bicubic2d_aa_kernel 50 50 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/upsample_bicubic2d_aa.py bicubic_reciprocal_scale 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/upsample_bicubic2d_aa.py _upsample_bicubic2d_aa 21 21 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/upsample_bicubic2d_aa.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/upsample_nearest1d.py upsample_nearest1d_kernel 22 22 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/upsample_nearest1d.py upsample_nearest1d 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/upsample_nearest1d.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/upsample_nearest2d.py heur_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/upsample_nearest2d.py upsample_nearest2d_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/upsample_nearest2d.py upsample_nearest2d 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/upsample_nearest2d.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/var_mean.py heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/var_mean.py heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/var_mean.py welford_func 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/var_mean.py var_mean_welford_kernel 25 25 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/var_mean.py var_mean_kernel_1 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/var_mean.py heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/var_mean.py var_mean_kernel_2 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/var_mean.py var_mean 34 34 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/var_mean.py (no function) 25 25 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vdot.py compute_vdot 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vdot.py vdot_kernel_heur_block_size 3 3 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vdot.py vdot_kernel_complex 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vdot.py dot_kernel_heur_block_size 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vdot.py dot_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vdot.py vdot 33 33 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vdot.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vector_norm.py heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vector_norm.py heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vector_norm.py l2_norm_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vector_norm.py l2_norm_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vector_norm.py l2_norm_kernel_2 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vector_norm.py max_norm_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vector_norm.py max_norm_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vector_norm.py max_norm_kernel_2 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vector_norm.py min_norm_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vector_norm.py min_norm_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vector_norm.py min_norm_kernel_2 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vector_norm.py l0_norm_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vector_norm.py l0_norm_kernel_1 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vector_norm.py l0_norm_kernel_2 6 6 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vector_norm.py v_norm_kernel 15 15 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vector_norm.py l1_norm_kernel_1 9 9 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vector_norm.py l1_norm_kernel_2 7 7 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vector_norm.py vector_norm 54 54 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vector_norm.py (no function) 63 63 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vstack.py heur_block_size 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vstack.py vstack_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vstack.py vstack 42 42 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/vstack.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/weightnorm.py weight_norm_kernel_last_block_row 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/weightnorm.py weight_norm_kernel_last_block_col 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/weightnorm.py weight_norm_kernel_last 21 21 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/weightnorm.py weight_norm_kernel_first_block_row 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/weightnorm.py weight_norm_kernel_first_block_col 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/weightnorm.py weight_norm_kernel_first 21 21 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/weightnorm.py heur_block_m_weight_norm_bwd_kernel_last 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/weightnorm.py heur_block_n_weight_norm_bwd_kernel_last 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/weightnorm.py weight_norm_bwd_kernel_last 24 24 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/weightnorm.py heur_block_m_weight_norm_bwd_kernel_first 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/weightnorm.py heur_block_n_weight_norm_bwd_kernel_first 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/weightnorm.py weight_norm_bwd_kernel_first 24 24 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/weightnorm.py weight_norm_interface 18 18 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/weightnorm.py weight_norm_interface_backward 20 20 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/weightnorm.py (no function) 35 35 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/where.py where_inner 1 1 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/where.py where_self_out 28 28 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/where.py where_self 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/where.py where_scalar_self 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/where.py where_scalar_other 2 2 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/where.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/zeros.py zeros_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/zeros.py zeros 12 12 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/zeros.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/zeros_like.py zeros_like 14 14 0 0%
src/flag_gems/runtime/backend/_kunlunxin/ops/zeros_like.py (no function) 7 7 0 0%
src/flag_gems/runtime/backend/_metax/__init__.py (no function) 4 0 0 100%
src/flag_gems/runtime/backend/_metax/fused/__init__.py (no function) 2 2 0 0%
src/flag_gems/runtime/backend/_metax/fused/flash_mla.py flash_mla_attn_kernel 63 63 0 0%
src/flag_gems/runtime/backend/_metax/fused/flash_mla.py flash_mla 26 26 0 0%
src/flag_gems/runtime/backend/_metax/fused/flash_mla.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py simple_elementwise_blocksize_heur 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py argmax_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py argmax_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py bmm_heur_divisible_m 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py bmm_heur_divisible_n 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py bmm_heur_divisible_k 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py argmin_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py argmin_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py dropout_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py dropout_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py exponential_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py exponential_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py gather_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py gather_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py index_heur_block_0 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py index_heur_block_1 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py index_select_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py index_select_heur_block_n 2 2 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py mm_heur_even_k 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py ones_heur_block_size 5 5 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py ones_heur_num_warps 3 3 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py rand_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py rand_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py randn_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py randn_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py softmax_heur_tile_k 11 11 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py softmax_heur_tile_n_non_inner 2 2 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py softmax_heur_one_tile_per_cta 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py softmax_heur_num_warps_non_inner 10 10 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py softmax_heur_tile_n_inner 3 3 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py softmax_heur_num_warps_inner 6 6 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py softmax_heur_tile_n_bwd_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py softmax_heur_tile_m 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py uniform_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py uniform_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py var_mean_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py upsample_nearest2d_SAME_H 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py upsample_nearest2d_SAME_W 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py upsample_nearest2d_USE_INT32_IDX 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py batch_norm_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py batch_norm_heur_block_n 3 3 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py vdot_heur_block_size 6 6 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py zeros_heur_block_size 5 5 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py zeros_heur_num_warps 3 3 0 0%
src/flag_gems/runtime/backend/_metax/heuristics_config_utils.py (no function) 47 47 0 0%
src/flag_gems/runtime/backend/_metax/ops/__init__.py (no function) 31 31 0 0%
src/flag_gems/runtime/backend/_metax/ops/addmm.py addmm_kernel 26 26 0 0%
src/flag_gems/runtime/backend/_metax/ops/addmm.py addmm 14 14 0 0%
src/flag_gems/runtime/backend/_metax/ops/addmm.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_metax/ops/amax.py amax_kernel_1 9 9 0 0%
src/flag_gems/runtime/backend/_metax/ops/amax.py amax_kernel_2 7 7 0 0%
src/flag_gems/runtime/backend/_metax/ops/amax.py amax_kernel 17 17 0 0%
src/flag_gems/runtime/backend/_metax/ops/amax.py amax 37 37 0 0%
src/flag_gems/runtime/backend/_metax/ops/amax.py (no function) 22 22 0 0%
src/flag_gems/runtime/backend/_metax/ops/arange.py arange_func 7 7 0 0%
src/flag_gems/runtime/backend/_metax/ops/arange.py arange_start 16 16 0 0%
src/flag_gems/runtime/backend/_metax/ops/arange.py arange 1 1 0 0%
src/flag_gems/runtime/backend/_metax/ops/arange.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_metax/ops/bmm.py bmm_kernel 64 64 0 0%
src/flag_gems/runtime/backend/_metax/ops/bmm.py bmm 11 11 0 0%
src/flag_gems/runtime/backend/_metax/ops/bmm.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_metax/ops/exponential_.py heur_block 5 5 0 0%
src/flag_gems/runtime/backend/_metax/ops/exponential_.py heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_metax/ops/exponential_.py fused_exponential_kernel 37 37 0 0%
src/flag_gems/runtime/backend/_metax/ops/exponential_.py fused_exponential_kernel_opt 47 47 0 0%
src/flag_gems/runtime/backend/_metax/ops/exponential_.py paste_u64 3 3 0 0%
src/flag_gems/runtime/backend/_metax/ops/exponential_.py transform_exponential 5 5 0 0%
src/flag_gems/runtime/backend/_metax/ops/exponential_.py transform_exponential_double 5 5 0 0%
src/flag_gems/runtime/backend/_metax/ops/exponential_.py transform_exponential_float 5 5 0 0%
src/flag_gems/runtime/backend/_metax/ops/exponential_.py transform_exponential_float16 5 5 0 0%
src/flag_gems/runtime/backend/_metax/ops/exponential_.py transform_exponential_bfloat16 5 5 0 0%
src/flag_gems/runtime/backend/_metax/ops/exponential_.py exponential_ 22 22 0 0%
src/flag_gems/runtime/backend/_metax/ops/exponential_.py (no function) 32 32 0 0%
src/flag_gems/runtime/backend/_metax/ops/full.py full_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_metax/ops/full.py full_kernel_scale 5 5 0 0%
src/flag_gems/runtime/backend/_metax/ops/full.py check_dtype 8 8 0 0%
src/flag_gems/runtime/backend/_metax/ops/full.py full_ 13 13 0 0%
src/flag_gems/runtime/backend/_metax/ops/full.py full 13 13 0 0%
src/flag_gems/runtime/backend/_metax/ops/full.py (no function) 19 19 0 0%
src/flag_gems/runtime/backend/_metax/ops/full_like.py full_like 9 9 0 0%
src/flag_gems/runtime/backend/_metax/ops/full_like.py (no function) 5 5 0 0%
src/flag_gems/runtime/backend/_metax/ops/groupnorm.py group_norm_kernel 29 29 0 0%
src/flag_gems/runtime/backend/_metax/ops/groupnorm.py group_norm_backward_kernel 30 30 0 0%
src/flag_gems/runtime/backend/_metax/ops/groupnorm.py weight_bias_backward_kernel 23 23 0 0%
src/flag_gems/runtime/backend/_metax/ops/groupnorm.py GroupNorm.forward 21 21 0 0%
src/flag_gems/runtime/backend/_metax/ops/groupnorm.py GroupNorm.backward 19 19 0 0%
src/flag_gems/runtime/backend/_metax/ops/groupnorm.py group_norm 1 1 0 0%
src/flag_gems/runtime/backend/_metax/ops/groupnorm.py (no function) 24 24 0 0%
src/flag_gems/runtime/backend/_metax/ops/index.py get_max_rank_shape 13 13 0 0%
src/flag_gems/runtime/backend/_metax/ops/index.py broadcast_indices 3 3 0 0%
src/flag_gems/runtime/backend/_metax/ops/index.py generate_imports 10 10 0 0%
src/flag_gems/runtime/backend/_metax/ops/index.py generate_index_kernel 65 65 0 0%
src/flag_gems/runtime/backend/_metax/ops/index.py generate_index_wrapper 37 37 0 0%
src/flag_gems/runtime/backend/_metax/ops/index.py generate_code 10 10 0 0%
src/flag_gems/runtime/backend/_metax/ops/index.py IndexFunction.__init__ 2 2 0 0%
src/flag_gems/runtime/backend/_metax/ops/index.py IndexFunction.__call__ 16 16 0 0%
src/flag_gems/runtime/backend/_metax/ops/index.py IndexFunction.arg_key 7 7 0 0%
src/flag_gems/runtime/backend/_metax/ops/index.py index 98 98 0 0%
src/flag_gems/runtime/backend/_metax/ops/index.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_metax/ops/index_put.py get_max_rank_shape 13 13 0 0%
src/flag_gems/runtime/backend/_metax/ops/index_put.py broadcast_indices 3 3 0 0%
src/flag_gems/runtime/backend/_metax/ops/index_put.py generate_imports 10 10 0 0%
src/flag_gems/runtime/backend/_metax/ops/index_put.py generate_index_put_kernel 62 62 0 0%
src/flag_gems/runtime/backend/_metax/ops/index_put.py generate_index_put_wrapper 37 37 0 0%
src/flag_gems/runtime/backend/_metax/ops/index_put.py generate_code 10 10 0 0%
src/flag_gems/runtime/backend/_metax/ops/index_put.py IndexPutFunction.__init__ 2 2 0 0%
src/flag_gems/runtime/backend/_metax/ops/index_put.py IndexPutFunction.__call__ 16 16 0 0%
src/flag_gems/runtime/backend/_metax/ops/index_put.py IndexPutFunction.arg_key 7 7 0 0%
src/flag_gems/runtime/backend/_metax/ops/index_put.py index_put 26 26 0 0%
src/flag_gems/runtime/backend/_metax/ops/index_put.py index_put_ 25 25 0 0%
src/flag_gems/runtime/backend/_metax/ops/index_put.py (no function) 21 21 0 0%
src/flag_gems/runtime/backend/_metax/ops/index_select.py index_select_kernel 11 11 0 0%
src/flag_gems/runtime/backend/_metax/ops/index_select.py index_select_2d_opt_kernel 11 11 0 0%
src/flag_gems/runtime/backend/_metax/ops/index_select.py dim_transpose 1 1 0 0%
src/flag_gems/runtime/backend/_metax/ops/index_select.py index_select 32 32 0 0%
src/flag_gems/runtime/backend/_metax/ops/index_select.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_metax/ops/isin.py launch_arg 1 1 0 0%
src/flag_gems/runtime/backend/_metax/ops/isin.py isin_by_comparation_impl 16 16 0 0%
src/flag_gems/runtime/backend/_metax/ops/isin.py isin_by_comparation_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_metax/ops/isin.py isin_by_comparation 20 20 0 0%
src/flag_gems/runtime/backend/_metax/ops/isin.py isin_by_search_impl 16 16 0 0%
src/flag_gems/runtime/backend/_metax/ops/isin.py isin_by_search_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_metax/ops/isin.py isin_by_search 27 27 0 0%
src/flag_gems/runtime/backend/_metax/ops/isin.py isin 13 13 0 0%
src/flag_gems/runtime/backend/_metax/ops/isin.py (no function) 24 24 0 0%
src/flag_gems/runtime/backend/_metax/ops/log_softmax.py heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_metax/ops/log_softmax.py heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_metax/ops/log_softmax.py log_softmax_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_metax/ops/log_softmax.py log_softmax_backward_kernel 21 21 0 0%
src/flag_gems/runtime/backend/_metax/ops/log_softmax.py log_softmax 18 18 0 0%
src/flag_gems/runtime/backend/_metax/ops/log_softmax.py log_softmax_backward 14 14 0 0%
src/flag_gems/runtime/backend/_metax/ops/log_softmax.py (no function) 23 23 0 0%
src/flag_gems/runtime/backend/_metax/ops/masked_fill.py masked_fill_kernel 7 7 0 0%
src/flag_gems/runtime/backend/_metax/ops/masked_fill.py masked_fill_kernel_self 5 5 0 0%
src/flag_gems/runtime/backend/_metax/ops/masked_fill.py masked_fill 17 17 0 0%
src/flag_gems/runtime/backend/_metax/ops/masked_fill.py masked_fill_ 18 18 0 0%
src/flag_gems/runtime/backend/_metax/ops/masked_fill.py (no function) 18 18 0 0%
src/flag_gems/runtime/backend/_metax/ops/min.py min_kernel_1 9 9 0 0%
src/flag_gems/runtime/backend/_metax/ops/min.py min_kernel_2 7 7 0 0%
src/flag_gems/runtime/backend/_metax/ops/min.py heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_metax/ops/min.py min_kernel 24 24 0 0%
src/flag_gems/runtime/backend/_metax/ops/min.py min 12 12 0 0%
src/flag_gems/runtime/backend/_metax/ops/min.py min_dim 21 21 0 0%
src/flag_gems/runtime/backend/_metax/ops/min.py (no function) 26 26 0 0%
src/flag_gems/runtime/backend/_metax/ops/mm.py mm_kernel 52 52 0 0%
src/flag_gems/runtime/backend/_metax/ops/mm.py get_higher_dtype 9 9 0 0%
src/flag_gems/runtime/backend/_metax/ops/mm.py mm 17 17 0 0%
src/flag_gems/runtime/backend/_metax/ops/mm.py mm_out 15 15 0 0%
src/flag_gems/runtime/backend/_metax/ops/mm.py (no function) 23 23 0 0%
src/flag_gems/runtime/backend/_metax/ops/nonzero.py generate_imports 9 9 0 0%
src/flag_gems/runtime/backend/_metax/ops/nonzero.py generate_nonzero_kernel 33 33 0 0%
src/flag_gems/runtime/backend/_metax/ops/nonzero.py parameter_for_wrapper 8 8 0 0%
src/flag_gems/runtime/backend/_metax/ops/nonzero.py generate_destination_passing_wrapper 15 15 0 0%
src/flag_gems/runtime/backend/_metax/ops/nonzero.py generate_code 6 6 0 0%
src/flag_gems/runtime/backend/_metax/ops/nonzero.py NonzeroFunction.__init__ 2 2 0 0%
src/flag_gems/runtime/backend/_metax/ops/nonzero.py NonzeroFunction.__call__ 14 14 0 0%
src/flag_gems/runtime/backend/_metax/ops/nonzero.py NonzeroFunction.arg_key 1 1 0 0%
src/flag_gems/runtime/backend/_metax/ops/nonzero.py nonzero 19 19 0 0%
src/flag_gems/runtime/backend/_metax/ops/nonzero.py (no function) 19 19 0 0%
src/flag_gems/runtime/backend/_metax/ops/ones.py ones_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_metax/ops/ones.py ones 11 11 0 0%
src/flag_gems/runtime/backend/_metax/ops/ones.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_metax/ops/ones_like.py ones_like 11 11 0 0%
src/flag_gems/runtime/backend/_metax/ops/ones_like.py (no function) 7 7 0 0%
src/flag_gems/runtime/backend/_metax/ops/outer.py mul_outer_kernel 15 15 0 0%
src/flag_gems/runtime/backend/_metax/ops/outer.py mul 12 12 0 0%
src/flag_gems/runtime/backend/_metax/ops/outer.py Outer.forward 9 9 0 0%
src/flag_gems/runtime/backend/_metax/ops/outer.py Outer.backward 6 6 0 0%
src/flag_gems/runtime/backend/_metax/ops/outer.py outer 1 1 0 0%
src/flag_gems/runtime/backend/_metax/ops/outer.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_metax/ops/polar.py polar_kernel_kernel 11 11 0 0%
src/flag_gems/runtime/backend/_metax/ops/polar.py polar 7 7 0 0%
src/flag_gems/runtime/backend/_metax/ops/polar.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_metax/ops/prod.py reduce_mul 1 1 0 0%
src/flag_gems/runtime/backend/_metax/ops/prod.py prod_kernel_mid 8 8 0 0%
src/flag_gems/runtime/backend/_metax/ops/prod.py prod_kernel_result 6 6 0 0%
src/flag_gems/runtime/backend/_metax/ops/prod.py prod 13 13 0 0%
src/flag_gems/runtime/backend/_metax/ops/prod.py heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_metax/ops/prod.py prod_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_metax/ops/prod.py prod_dim 19 19 0 0%
src/flag_gems/runtime/backend/_metax/ops/prod.py (no function) 26 26 0 0%
src/flag_gems/runtime/backend/_metax/ops/repeat_interleave.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_metax/ops/repeat_interleave.py repeat_interleave_self_int 25 25 0 0%
src/flag_gems/runtime/backend/_metax/ops/repeat_interleave.py repeat_interleave_tensor_kernel 11 11 0 0%
src/flag_gems/runtime/backend/_metax/ops/repeat_interleave.py fused_repeat_and_index_select_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_metax/ops/repeat_interleave.py repeat_interleave_tensor 11 11 0 0%
src/flag_gems/runtime/backend/_metax/ops/repeat_interleave.py fused_repeat_and_index_select 13 13 0 0%
src/flag_gems/runtime/backend/_metax/ops/repeat_interleave.py repeat_interleave_self_tensor 20 20 0 0%
src/flag_gems/runtime/backend/_metax/ops/repeat_interleave.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_metax/ops/resolve_conj.py resolve_conj 2 2 0 0%
src/flag_gems/runtime/backend/_metax/ops/resolve_conj.py (no function) 5 5 0 0%
src/flag_gems/runtime/backend/_metax/ops/sigmoid.py sigmoid_forward 2 2 0 0%
src/flag_gems/runtime/backend/_metax/ops/sigmoid.py sigmoid_backward 3 3 0 0%
src/flag_gems/runtime/backend/_metax/ops/sigmoid.py sigmoid_backward_custom_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_metax/ops/sigmoid.py sigmoid_backward_custom 6 6 0 0%
src/flag_gems/runtime/backend/_metax/ops/sigmoid.py Sigmoid.forward 7 7 0 0%
src/flag_gems/runtime/backend/_metax/ops/sigmoid.py Sigmoid.backward 12 12 0 0%
src/flag_gems/runtime/backend/_metax/ops/sigmoid.py sigmoid 1 1 0 0%
src/flag_gems/runtime/backend/_metax/ops/sigmoid.py (no function) 22 22 0 0%
src/flag_gems/runtime/backend/_metax/ops/tanh.py tanh_forward 1 1 0 0%
src/flag_gems/runtime/backend/_metax/ops/tanh.py tanh_backward 1 1 0 0%
src/flag_gems/runtime/backend/_metax/ops/tanh.py tanh_backward_custom_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_metax/ops/tanh.py tanh_backward_custom 6 6 0 0%
src/flag_gems/runtime/backend/_metax/ops/tanh.py Tanh.forward 7 7 0 0%
src/flag_gems/runtime/backend/_metax/ops/tanh.py Tanh.backward 12 12 0 0%
src/flag_gems/runtime/backend/_metax/ops/tanh.py tanh 1 1 0 0%
src/flag_gems/runtime/backend/_metax/ops/tanh.py (no function) 23 23 0 0%
src/flag_gems/runtime/backend/_metax/ops/unique.py simple_unique_flat_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_metax/ops/unique.py output_counts_flat_impl 9 9 0 0%
src/flag_gems/runtime/backend/_metax/ops/unique.py output_counts_flat_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_metax/ops/unique.py quick_output_flat_impl 11 11 0 0%
src/flag_gems/runtime/backend/_metax/ops/unique.py quick_output_flat_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_metax/ops/unique.py local_quick_unique_flat_impl 18 18 0 0%
src/flag_gems/runtime/backend/_metax/ops/unique.py local_quick_unique_flat_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_metax/ops/unique.py global_quick_unique_flat_impl 20 20 0 0%
src/flag_gems/runtime/backend/_metax/ops/unique.py global_quick_unique_flat_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_metax/ops/unique.py sorted_quick_unique_flat 36 36 0 0%
src/flag_gems/runtime/backend/_metax/ops/unique.py local_ne_flat_impl 11 11 0 0%
src/flag_gems/runtime/backend/_metax/ops/unique.py local_ne_flat_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_metax/ops/unique.py global_cumsum_flat_impl 25 25 0 0%
src/flag_gems/runtime/backend/_metax/ops/unique.py global_cumsum_flat_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_metax/ops/unique.py sorted_indices_unique_flat 30 30 0 0%
src/flag_gems/runtime/backend/_metax/ops/unique.py simple_unique_flat 20 20 0 0%
src/flag_gems/runtime/backend/_metax/ops/unique.py _unique2 9 9 0 0%
src/flag_gems/runtime/backend/_metax/ops/unique.py (no function) 43 43 0 0%
src/flag_gems/runtime/backend/_metax/ops/upsample_nearest2d.py upsample_nearest2d_kernel 18 18 0 0%
src/flag_gems/runtime/backend/_metax/ops/upsample_nearest2d.py upsample_nearest2d 18 18 0 0%
src/flag_gems/runtime/backend/_metax/ops/upsample_nearest2d.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_metax/ops/zeros.py zeros_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_metax/ops/zeros.py zeros 11 11 0 0%
src/flag_gems/runtime/backend/_metax/ops/zeros.py (no function) 16 16 0 0%
src/flag_gems/runtime/backend/_metax/ops/zeros_like.py zeros_like 11 11 0 0%
src/flag_gems/runtime/backend/_metax/ops/zeros_like.py (no function) 7 7 0 0%
src/flag_gems/runtime/backend/_mthreads/__init__.py (no function) 4 0 0 100%
src/flag_gems/runtime/backend/_mthreads/fused/__init__.py (no function) 2 2 0 0%
src/flag_gems/runtime/backend/_mthreads/fused/cross_entropy_loss.py celoss_indices_kernel 32 32 0 0%
src/flag_gems/runtime/backend/_mthreads/fused/cross_entropy_loss.py celoss_probability_kernel 35 35 0 0%
src/flag_gems/runtime/backend/_mthreads/fused/cross_entropy_loss.py celoss_indices_smooth_kernel 44 44 0 0%
src/flag_gems/runtime/backend/_mthreads/fused/cross_entropy_loss.py celoss_indices_bwd 36 36 0 0%
src/flag_gems/runtime/backend/_mthreads/fused/cross_entropy_loss.py celoss_probability_bwd 48 48 0 0%
src/flag_gems/runtime/backend/_mthreads/fused/cross_entropy_loss.py celoss_indices_smooth_bwd 48 48 0 0%
src/flag_gems/runtime/backend/_mthreads/fused/cross_entropy_loss.py sum_and_scale 25 25 0 0%
src/flag_gems/runtime/backend/_mthreads/fused/cross_entropy_loss.py CrossEntropyLoss.forward 46 46 0 0%
src/flag_gems/runtime/backend/_mthreads/fused/cross_entropy_loss.py CrossEntropyLoss.backward 18 18 0 0%
src/flag_gems/runtime/backend/_mthreads/fused/cross_entropy_loss.py cross_entropy_loss 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/fused/cross_entropy_loss.py (no function) 43 43 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py simple_elementwise_blocksize_heur 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py argmax_heur_tile_k 18 18 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py argmax_heur_tile_n_non_inner 10 10 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py argmax_heur_one_tile_per_cta 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py argmax_heur_num_warps_non_inner 12 12 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py argmax_heur_tile_n_inner 3 3 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py argmax_heur_num_warps_inner 6 6 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py argmin_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py argmin_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py bmm_heur_divisible_m 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py bmm_heur_divisible_n 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py bmm_heur_divisible_k 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py baddbmm_heur_divisible_m 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py baddbmm_heur_divisible_n 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py baddbmm_heur_divisible_k 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py dropout_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py dropout_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py exponential_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py exponential_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py gather_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py gather_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py index_select_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py index_select_heur_block_n 2 2 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py mm_heur_even_k 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py rand_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py rand_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py randn_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py randn_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py softmax_heur_tile_k 11 11 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py softmax_heur_tile_n_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py softmax_heur_one_tile_per_cta 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py softmax_heur_num_warps_non_inner 6 6 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py softmax_heur_tile_n_inner 3 3 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py softmax_heur_num_warps_inner 6 6 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py softmax_heur_tile_n_bwd_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py softmax_heur_tile_m 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py uniform_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py uniform_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py var_mean_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py upsample_nearest2d_SAME_H 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py upsample_nearest2d_SAME_W 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py upsample_nearest2d_USE_INT32_IDX 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py batch_norm_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py batch_norm_heur_block_n 3 3 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py vdot_heur_block_size 6 6 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py mean_heur_tile_k 17 17 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py mean_heur_tile_n_non_inner 10 10 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py mean_heur_one_tile_per_cta 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/heuristics_config_utils.py (no function) 54 54 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/__init__.py (no function) 38 38 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/addmm.py addmm_kernel 23 23 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/addmm.py addmm_fma 13 13 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/addmm.py addmm_sqmma_kernel 18 18 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/addmm.py get_triton_type 2 2 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/addmm.py addmm_sqmma 26 26 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/addmm.py addmm 17 17 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/addmm.py (no function) 21 21 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/all.py reduce_all 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/all.py all_kernel_dim_strided 17 17 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/all.py _flatten_dim 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/all.py triton_all_dim_strided 15 15 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/all.py all_kernel_dim 14 14 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/all.py all_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/all.py all_kernel_2 6 6 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/all.py all 12 12 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/all.py all_dim 10 10 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/all.py all_dims 19 19 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/all.py (no function) 33 33 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/any.py _flatten_dim 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/any.py _select_reduction_config 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/any.py any_kernel_dim 14 14 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/any.py any_kernel_dim_strided 18 18 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/any.py any_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/any.py any_kernel_2 6 6 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/any.py any 14 14 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/any.py triton_any_dim_strided 17 17 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/any.py any_dim 8 8 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/any.py any_dims 12 12 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/any.py (no function) 28 28 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/arange.py arange_kernel 19 19 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/arange.py _normalize_scalar 3 3 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/arange.py _compute_size 7 7 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/arange.py _use_triton 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/arange.py _launch_triton_kernel 4 4 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/arange.py arange_start 18 18 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/arange.py arange 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/arange.py (no function) 25 25 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/argmin.py _prune_reduction_configs 7 7 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/argmin.py _flatten_dim 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/argmin.py argmin_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/argmin.py argmin_kernel_2 7 7 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/argmin.py argmin_kernel 25 25 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/argmin.py argmin 43 43 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/argmin.py (no function) 26 26 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/batch_norm.py _make_3d_for_bn 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/batch_norm.py _block_size 7 7 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/batch_norm.py _num_warps 7 7 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/batch_norm.py _get_temp_stats 7 7 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/batch_norm.py _bn_forward_stats_stage1 11 11 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/batch_norm.py _bn_reduce_partial_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/batch_norm.py _bn_fused_train_kernel 39 39 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/batch_norm.py _bn_forward_finalize_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/batch_norm.py _bn_forward_apply_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/batch_norm.py _bn_backward_reduce_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/batch_norm.py _bn_backward_reduce_partial_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/batch_norm.py _bn_backward_input_kernel 21 21 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/batch_norm.py _bn_backward_param_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/batch_norm.py _get_launch_config 4 4 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/batch_norm.py batch_norm 44 44 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/batch_norm.py batch_norm_backward 31 31 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/batch_norm.py (no function) 38 38 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/bmm.py bmm_kernel 58 58 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/bmm.py bmm_fma 10 10 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/bmm.py bmm_sqmma_kernel 19 19 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/bmm.py get_triton_type 2 2 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/bmm.py bmm_sqmma 9 9 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/bmm.py bmm 17 17 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/bmm.py (no function) 22 22 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/celu.py celu_kernel_alpha1 11 11 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/celu.py celu_kernel 13 13 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/celu.py _use_triton_kernel 13 13 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/celu.py _launch_celu 10 10 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/celu.py celu 6 6 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/celu.py celu_ 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/celu.py (no function) 24 24 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/conv2d.py conv2d_output_size 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/conv2d.py conv2d_forward_kernel 36 36 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/conv2d.py conv2d_backward_kernel_weight 28 28 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/conv2d.py Conv2d.forward 35 35 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/conv2d.py Conv2d.backward 38 38 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/conv2d.py conv2d 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/conv2d.py (no function) 22 22 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/dropout.py dropout_forward_kernel 38 38 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/dropout.py dropout_backward_kernel 6 6 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/dropout.py dropout 21 21 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/dropout.py dropout_backward 8 8 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/dropout.py (no function) 17 17 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/gather.py _gather_lastdim_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/gather.py _normalize_dim 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/gather.py _use_triton_kernel 15 15 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/gather.py _launch_triton 11 11 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/gather.py gather 7 7 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/gather.py gather_backward 2 2 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/gather.py (no function) 21 21 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/gelu.py gelu_none 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/gelu.py gelu_tanh 2 2 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/gelu.py gelu_backward_none 6 6 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/gelu.py gelu_backward_tanh 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/gelu.py Gelu.forward 7 7 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/gelu.py Gelu.backward 7 7 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/gelu.py gelu 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/gelu.py (no function) 29 29 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/index_put.py get_max_rank_shape 13 13 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/index_put.py broadcast_indices 3 3 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/index_put.py generate_imports 10 10 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/index_put.py generate_index_put_kernel 71 71 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/index_put.py generate_index_put_wrapper 37 37 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/index_put.py generate_code 10 10 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/index_put.py IndexPutFunction.__init__ 2 2 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/index_put.py IndexPutFunction.__call__ 16 16 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/index_put.py IndexPutFunction.arg_key 7 7 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/index_put.py index_put 26 26 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/index_put.py index_put_ 28 28 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/index_put.py (no function) 21 21 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/isin.py launch_arg 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/isin.py isin_by_comparation_impl 16 16 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/isin.py isin_by_comparation_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/isin.py isin_by_comparation 20 20 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/isin.py isin_by_search_impl 16 16 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/isin.py isin_by_search_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/isin.py isin_by_search 27 27 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/isin.py isin 13 13 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/isin.py (no function) 24 24 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/log.py log_kernel 21 21 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/log.py _use_triton_kernel 7 7 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/log.py _launch_log 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/log.py log 6 6 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/log.py (no function) 18 18 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/max.py _prune_reduction_configs 9 9 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/max.py _flatten_dim 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/max.py max_kernel_1 6 6 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/max.py max_kernel_2 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/max.py max_kernel_small 14 14 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/max.py max_kernel 28 28 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/max.py max 19 19 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/max.py max_dim 30 30 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/max.py (no function) 34 34 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/min.py _prune_reduction_configs 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/min.py _flatten_dim 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/min.py min_kernel_1 9 9 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/min.py min_kernel_2 7 7 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/min.py min_kernel 27 27 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/min.py min 15 15 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/min.py min_dim 25 25 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/min.py (no function) 30 30 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/mm.py prev_multiple_of 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/mm.py mm_kernel 38 38 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/mm.py get_higher_dtype 9 9 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/mm.py mm_fma 15 15 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/mm.py mm_out 13 13 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/mm.py mm_sqmma_kernel 24 24 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/mm.py get_triton_type 2 2 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/mm.py mm_sqmma 22 22 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/mm.py mm 18 18 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/mm.py (no function) 26 26 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/ones.py ones_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/ones.py ones 12 12 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/ones.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/ones_like.py ones_like 11 11 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/ones_like.py (no function) 7 7 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/prod.py reduce_mul 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/prod.py _prune_reduction_configs 8 8 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/prod.py _flatten_dim 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/prod.py _reshape_output 6 6 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/prod.py prod_kernel_mid 10 10 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/prod.py prod_kernel_result 8 8 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/prod.py prod_kernel_dim_64 8 8 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/prod.py prod_kernel_dim_contig 10 10 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/prod.py prod_kernel_dim_dense 14 14 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/prod.py prod_kernel_dim 20 20 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/prod.py prod 16 16 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/prod.py prod_dim 49 49 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/prod.py (no function) 33 33 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/rand.py rand_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/rand.py rand 13 13 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/rand.py (no function) 15 15 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/rand_like.py rand_like 13 13 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/rand_like.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/randn.py randn_kernel 22 22 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/randn.py randn 13 13 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/randn.py (no function) 24 24 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/randn_like.py randn_like 13 13 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/randn_like.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/randperm.py _get_iinfo_val 21 21 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/randperm.py bitonic_sortbykey_kernel 13 13 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/randperm.py radix_type_convert 15 15 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/randperm.py digit_hist_kernel 19 19 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/randperm.py radix_sortbykey_scatter_kernel 45 45 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/randperm.py duplicate_keys_shuffle_kernel 20 20 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/randperm.py sort_by_key 54 54 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/randperm.py randperm 37 37 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/randperm.py (no function) 42 42 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/resolve_conj.py resolve_conj_kernel_1d 13 13 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/resolve_conj.py resolve_conj_kernel_2d_strided 15 15 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/resolve_conj.py resolve_conj_kernel_large_2d 16 16 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/resolve_conj.py resolve_conj_triton 39 39 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/resolve_conj.py resolve_conj 6 6 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/resolve_conj.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/sort.py unwrap_if_constexpr 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/sort.py get_int_t 3 3 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/sort.py one_zeros 2 2 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/sort.py zero_ones 2 2 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/sort.py uint_to_uint 2 2 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/sort.py int_to_uint 11 11 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/sort.py floating_to_uint 14 14 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/sort.py convert_to_uint_preverse_order 7 7 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/sort.py compute_global_hist_kernel 23 23 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/sort.py sweep 43 43 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/sort.py radix_sort 35 35 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/sort.py sort_kernel 15 15 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/sort.py sort 2 2 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/sort.py sort_stable 17 17 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/sort.py (no function) 33 33 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/tanh.py tanh_forward 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/tanh.py tanh_backward 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/tanh.py Tanh.forward 7 7 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/tanh.py Tanh.backward 4 4 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/tanh.py tanh 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/tanh.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/unique.py simple_unique_flat_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/unique.py output_counts_flat_impl 9 9 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/unique.py output_counts_flat_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/unique.py quick_output_flat_impl 11 11 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/unique.py quick_output_flat_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/unique.py local_quick_unique_flat_impl 18 18 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/unique.py local_quick_unique_flat_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/unique.py global_quick_unique_flat_impl 20 20 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/unique.py global_quick_unique_flat_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/unique.py sorted_quick_unique_flat 36 36 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/unique.py local_ne_flat_impl 11 11 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/unique.py local_ne_flat_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/unique.py global_cumsum_flat_impl 25 25 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/unique.py global_cumsum_flat_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/unique.py sorted_indices_unique_flat 30 30 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/unique.py simple_unique_flat 20 20 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/unique.py _unique2 9 9 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/unique.py (no function) 43 43 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/utils.py create_tma_device_descriptor 10 10 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/utils.py get_triton_dtype 2 2 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/utils.py should_enable_sqmma 1 1 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/utils.py (no function) 8 8 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/zeros.py zeros_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/zeros.py zeros 11 11 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/zeros.py zero_ 6 6 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/zeros.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/zeros_like.py zeros_like 11 11 0 0%
src/flag_gems/runtime/backend/_mthreads/ops/zeros_like.py (no function) 7 7 0 0%
src/flag_gems/runtime/backend/_nvidia/__init__.py (no function) 5 0 0 100%
src/flag_gems/runtime/backend/_nvidia/ampere/__init__.py (no function) 0 0 0 100%
src/flag_gems/runtime/backend/_nvidia/ampere/ops/__init__.py (no function) 0 0 0 100%
src/flag_gems/runtime/backend/_nvidia/fused/__init__.py (no function) 2 0 0 100%
src/flag_gems/runtime/backend/_nvidia/fused/fused_add_rms_norm.py fused_add_rms_norm_kernel 14 14 0 0%
src/flag_gems/runtime/backend/_nvidia/fused/fused_add_rms_norm.py fused_add_rms_norm 11 11 0 0%
src/flag_gems/runtime/backend/_nvidia/fused/fused_add_rms_norm.py (no function) 12 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py simple_elementwise_blocksize_heur 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py argmax_heur_tile_k 18 1 0 94%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py argmax_heur_tile_n_non_inner 10 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py argmax_heur_one_tile_per_cta 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py argmax_heur_num_warps_non_inner 12 2 0 83%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py argmax_heur_tile_n_inner 3 1 0 67%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py argmax_heur_num_warps_inner 6 3 0 50%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py argmin_heur_block_m 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py argmin_heur_block_n 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py bmm_heur_divisible_m 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py bmm_heur_divisible_n 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py bmm_heur_divisible_k 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py baddbmm_heur_divisible_m 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py baddbmm_heur_divisible_n 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py baddbmm_heur_divisible_k 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py dropout_heur_block 3 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py dropout_heur_num_warps 5 1 0 80%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py exponential_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py exponential_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py gather_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py gather_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py index_select_heur_block_m 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py index_select_heur_block_n 2 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py mm_heur_even_k 1 1 0 0%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py rand_heur_block 3 1 0 67%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py rand_heur_num_warps 5 2 0 60%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py randn_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py randn_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py softmax_heur_tile_k 11 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py softmax_heur_tile_n_non_inner 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py softmax_heur_one_tile_per_cta 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py softmax_heur_num_warps_non_inner 6 1 0 83%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py softmax_heur_tile_n_inner 3 1 0 67%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py softmax_heur_num_warps_inner 6 3 0 50%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py softmax_heur_tile_n_bwd_non_inner 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py softmax_heur_tile_m 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py uniform_heur_block 3 1 0 67%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py uniform_heur_num_warps 5 2 0 60%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py var_mean_heur_block_n 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py upsample_nearest1d_SAME_L 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py upsample_nearest1d_USE_INT32_IDX 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py upsample_nearest2d_SAME_H 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py upsample_nearest2d_SAME_W 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py upsample_nearest2d_USE_INT32_IDX 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py batch_norm_heur_block_m 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py batch_norm_heur_block_n 3 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py vdot_heur_block_size 6 1 0 83%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py mean_heur_tile_k 17 1 0 94%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py mean_heur_tile_n_non_inner 10 1 0 90%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py mean_heur_one_tile_per_cta 1 0 0 100%
src/flag_gems/runtime/backend/_nvidia/heuristics_config_utils.py (no function) 56 0 0 100%
src/flag_gems/runtime/backend/_nvidia/hopper/__init__.py (no function) 0 0 0 100%
src/flag_gems/runtime/backend/_nvidia/hopper/grouped_topk.py topk_with_k2_triton 22 22 0 0%
src/flag_gems/runtime/backend/_nvidia/hopper/grouped_topk.py group_idx_and_topk_triton 72 72 0 0%
src/flag_gems/runtime/backend/_nvidia/hopper/grouped_topk.py grouped_topk 36 36 0 0%
src/flag_gems/runtime/backend/_nvidia/hopper/grouped_topk.py (no function) 9 9 0 0%
src/flag_gems/runtime/backend/_nvidia/hopper/heuristics_config_utils.py (no function) 0 0 0 100%
src/flag_gems/runtime/backend/_nvidia/hopper/ops/__init__.py (no function) 4 4 0 0%
src/flag_gems/runtime/backend/_nvidia/hopper/ops/mm.py is_tma_compatible 1 1 0 0%
src/flag_gems/runtime/backend/_nvidia/hopper/ops/mm.py prev_multiple_of 1 1 0 0%
src/flag_gems/runtime/backend/_nvidia/hopper/ops/mm.py mm_kernel_general 53 53 0 0%
src/flag_gems/runtime/backend/_nvidia/hopper/ops/mm.py matmul_tma_set_block_size_hook 10 10 0 0%
src/flag_gems/runtime/backend/_nvidia/hopper/ops/mm.py matmul_get_configs 1 1 0 0%
src/flag_gems/runtime/backend/_nvidia/hopper/ops/mm.py mm_kernel_general_host_tma 27 27 0 0%
src/flag_gems/runtime/backend/_nvidia/hopper/ops/mm.py get_higher_dtype 10 10 0 0%
src/flag_gems/runtime/backend/_nvidia/hopper/ops/mm.py general_mm 24 24 0 0%
src/flag_gems/runtime/backend/_nvidia/hopper/ops/mm.py gemv_kernel 16 16 0 0%
src/flag_gems/runtime/backend/_nvidia/hopper/ops/mm.py gemv_mm 7 7 0 0%
src/flag_gems/runtime/backend/_nvidia/hopper/ops/mm.py streamk_scenario 2 2 0 0%
src/flag_gems/runtime/backend/_nvidia/hopper/ops/mm.py mm 16 16 0 0%
src/flag_gems/runtime/backend/_nvidia/hopper/ops/mm.py mm_out 13 13 0 0%
src/flag_gems/runtime/backend/_nvidia/hopper/ops/mm.py (no function) 35 35 0 0%
src/flag_gems/runtime/backend/_nvidia/ops/__init__.py (no function) 3 0 0 100%
src/flag_gems/runtime/backend/_nvidia/ops/add.py add_kernel 8 8 0 0%
src/flag_gems/runtime/backend/_nvidia/ops/add.py add 6 6 0 0%
src/flag_gems/runtime/backend/_nvidia/ops/add.py (no function) 6 0 0 100%
src/flag_gems/runtime/backend/_nvidia/ops/gelu.py gelu_none 3 3 0 0%
src/flag_gems/runtime/backend/_nvidia/ops/gelu.py gelu_tanh 2 2 0 0%
src/flag_gems/runtime/backend/_nvidia/ops/gelu.py gelu_backward_none 6 6 0 0%
src/flag_gems/runtime/backend/_nvidia/ops/gelu.py gelu_backward_tanh 5 5 0 0%
src/flag_gems/runtime/backend/_nvidia/ops/gelu.py Gelu.forward 7 7 0 0%
src/flag_gems/runtime/backend/_nvidia/ops/gelu.py Gelu.backward 7 7 0 0%
src/flag_gems/runtime/backend/_nvidia/ops/gelu.py gelu 2 2 0 0%
src/flag_gems/runtime/backend/_nvidia/ops/gelu.py (no function) 28 0 0 100%
src/flag_gems/runtime/backend/_sunrise/__init__.py (no function) 5 4 0 20%
src/flag_gems/runtime/backend/_sunrise/fused/__init__.py (no function) 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py simple_elementwise_blocksize_heur 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py argmax_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py argmax_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py argmin_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py argmin_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py bmm_heur_divisible_m 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py bmm_heur_divisible_n 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py bmm_heur_divisible_k 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py dropout_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py dropout_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py exponential_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py exponential_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py gather_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py gather_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py index_select_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py index_select_heur_block_n 2 2 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py mm_heur_even_k 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py rand_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py rand_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py randn_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py randn_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py softmax_heur_tile_k 11 11 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py softmax_heur_tile_n_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py softmax_heur_one_tile_per_cta 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py softmax_heur_num_warps_non_inner 6 6 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py softmax_heur_tile_n_inner 5 5 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py softmax_heur_num_warps_inner 8 8 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py softmax_heur_tile_n_bwd_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py softmax_heur_tile_m 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py uniform_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py uniform_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py var_mean_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py upsample_nearest2d_SAME_H 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py upsample_nearest2d_SAME_W 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py upsample_nearest2d_USE_INT32_IDX 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py batch_norm_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py batch_norm_heur_block_n 3 3 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py vdot_heur_block_size 6 6 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py sum_heur_num_warps_inner 8 8 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py sum_heur_tile_n_inner 5 5 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py sum_heur_one_tile_per_cta 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py sum_heur_tile_k 11 11 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py sum_heur_tile_n_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_sunrise/heuristics_config_utils.py (no function) 46 46 0 0%
src/flag_gems/runtime/backend/_sunrise/ops/__init__.py (no function) 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/__init__.py TxdaDeviceProperties.__repr__ 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/__init__.py get_device_properties 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/__init__.py get_device_capability 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/__init__.py (no function) 25 20 0 20%
src/flag_gems/runtime/backend/_tsingmicro/fused/__init__.py (no function) 2 2 0 0%
src/flag_gems/runtime/backend/_tsingmicro/fused/cross_entropy_loss.py softmax_forward_kernel 42 42 0 0%
src/flag_gems/runtime/backend/_tsingmicro/fused/cross_entropy_loss.py max_kernel 22 22 0 0%
src/flag_gems/runtime/backend/_tsingmicro/fused/cross_entropy_loss.py softmax_forward_with_max_kernel 24 24 0 0%
src/flag_gems/runtime/backend/_tsingmicro/fused/cross_entropy_loss.py nllloss_without_weight_kernel 17 17 0 0%
src/flag_gems/runtime/backend/_tsingmicro/fused/cross_entropy_loss.py nllloss_with_weight_kernel 21 21 0 0%
src/flag_gems/runtime/backend/_tsingmicro/fused/cross_entropy_loss.py celoss_probability_kernel 35 35 0 0%
src/flag_gems/runtime/backend/_tsingmicro/fused/cross_entropy_loss.py celoss_indices_smooth_kernel 44 44 0 0%
src/flag_gems/runtime/backend/_tsingmicro/fused/cross_entropy_loss.py single_celoss_indice_bwd 7 7 0 0%
src/flag_gems/runtime/backend/_tsingmicro/fused/cross_entropy_loss.py config_prune 7 7 0 0%
src/flag_gems/runtime/backend/_tsingmicro/fused/cross_entropy_loss.py celoss_indice_bwd_with_saved_sum_kernel 41 41 0 0%
src/flag_gems/runtime/backend/_tsingmicro/fused/cross_entropy_loss.py celoss_probability_bwd 48 48 0 0%
src/flag_gems/runtime/backend/_tsingmicro/fused/cross_entropy_loss.py celoss_indices_smooth_bwd 48 48 0 0%
src/flag_gems/runtime/backend/_tsingmicro/fused/cross_entropy_loss.py CrossEntropyLoss.forward 62 62 0 0%
src/flag_gems/runtime/backend/_tsingmicro/fused/cross_entropy_loss.py CrossEntropyLoss.forward.get_result 5 5 0 0%
src/flag_gems/runtime/backend/_tsingmicro/fused/cross_entropy_loss.py CrossEntropyLoss.backward 23 23 0 0%
src/flag_gems/runtime/backend/_tsingmicro/fused/cross_entropy_loss.py cross_entropy_loss 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/fused/cross_entropy_loss.py (no function) 59 59 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py simple_elementwise_blocksize_heur 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py argmax_heur_tile_k 18 18 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py argmax_heur_tile_n_non_inner 10 10 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py argmax_heur_one_tile_per_cta 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py argmax_heur_num_warps_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py argmax_heur_tile_n_inner 3 3 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py argmax_heur_num_warps_inner 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py argmin_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py argmin_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py bmm_heur_divisible_m 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py bmm_heur_divisible_n 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py bmm_heur_divisible_k 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py baddbmm_heur_divisible_m 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py baddbmm_heur_divisible_n 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py baddbmm_heur_divisible_k 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py dropout_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py dropout_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py exponential_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py exponential_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py gather_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py gather_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py index_select_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py index_select_heur_block_n 2 2 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py mm_heur_even_k 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py rand_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py rand_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py randn_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py randn_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py softmax_heur_tile_k 11 11 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py softmax_heur_tile_n_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py softmax_heur_one_tile_per_cta 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py softmax_heur_num_warps_non_inner 6 6 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py softmax_heur_tile_n_inner 3 3 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py softmax_heur_num_warps_inner 6 6 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py softmax_heur_tile_n_bwd_non_inner 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py softmax_heur_tile_m 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py uniform_heur_block 3 3 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py uniform_heur_num_warps 5 5 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py var_mean_heur_block_n 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py upsample_nearest1d_SAME_L 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py upsample_nearest1d_USE_INT32_IDX 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py upsample_nearest2d_SAME_H 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py upsample_nearest2d_SAME_W 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py upsample_nearest2d_USE_INT32_IDX 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py batch_norm_heur_block_m 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py batch_norm_heur_block_n 3 3 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py vdot_heur_block_size 6 6 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py mean_heur_tile_k 13 13 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py mean_heur_tile_n_non_inner 10 10 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py mean_heur_one_tile_per_cta 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/heuristics_config_utils.py (no function) 56 56 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/__init__.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/argmax.py cfggen_reduce_op 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/argmax.py argmax_kernel_once 4 4 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/argmax.py argmax_kernel_1 24 24 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/argmax.py argmax_kernel_2 8 8 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/argmax.py argmax_kernel 22 22 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/argmax.py argmax 47 47 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/argmax.py (no function) 26 26 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/cat.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/cat.py cat 28 28 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/cat.py (no function) 14 14 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/count_nonzero.py count_nonzero_kernel_1 8 8 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/count_nonzero.py count_nonzero_kernel 27 27 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/count_nonzero.py count_nonzero_combin_kernel_1 9 9 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/count_nonzero.py count_nonzero_combin_kernel 9 9 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/count_nonzero.py count_nonzero 36 36 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/count_nonzero.py (no function) 24 24 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/hstack.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/hstack.py hstack 37 37 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/hstack.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/isin.py launch_arg 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/isin.py isin_by_comparation_impl 16 16 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/isin.py isin_by_comparation_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/isin.py isin_by_comparation 20 20 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/isin.py isin_by_search_impl 16 16 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/isin.py isin_by_search_kernel 5 5 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/isin.py isin_by_search 27 27 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/isin.py isin 13 13 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/isin.py (no function) 23 23 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/kron.py prepare_tensor_for_kron 23 23 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/kron.py calculate_indices 13 13 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/kron.py kron_kernel 32 32 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/kron.py kron 39 39 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/kron.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/masked_select.py masked_select_kernel 7 7 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/masked_select.py masked_select 15 15 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/masked_select.py (no function) 13 13 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/mm.py prev_multiple_of 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/mm.py mm_kernel_general 38 38 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/mm.py get_higher_dtype 9 9 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/mm.py general_mm 5 5 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/mm.py mm 12 12 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/mm.py mm_out 9 9 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/mm.py (no function) 20 20 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/rms_norm.py rms_norm_kernel 12 12 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/rms_norm.py rms_norm_kernel_C_split 19 19 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/rms_norm.py rms_norm_grad_dx_kernel 17 17 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/rms_norm.py rms_norm_grad_dx_kernel_C_split 30 30 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/rms_norm.py rms_norm_grad_dw_kernel 18 18 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/rms_norm.py RmsNorm.forward 19 19 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/rms_norm.py RmsNorm.backward 26 26 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/rms_norm.py rms_norm 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/rms_norm.py (no function) 33 33 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/stack.py copy_func 1 1 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/stack.py stack 23 23 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/stack.py (no function) 12 12 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/unique.py get_ne_kernel 12 12 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/unique.py get_unique_out_kernel 18 18 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/unique.py get_output_counts_kernel 12 12 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/unique.py sorted_unique_flat 27 27 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/unique.py _unique2 3 3 0 0%
src/flag_gems/runtime/backend/_tsingmicro/ops/unique.py (no function) 19 19 0 0%
src/flag_gems/runtime/backend/backend_utils.py get_tune_config 19 5 0 74%
src/flag_gems/runtime/backend/backend_utils.py (no function) 11 0 0 100%
src/flag_gems/runtime/backend/device.py DeviceDetector.__new__ 3 0 0 100%
src/flag_gems/runtime/backend/device.py DeviceDetector.__init__ 12 0 0 100%
src/flag_gems/runtime/backend/device.py DeviceDetector.get_vendor 10 2 0 80%
src/flag_gems/runtime/backend/device.py DeviceDetector._get_vendor_from_quick_cmd 12 4 0 67%
src/flag_gems/runtime/backend/device.py DeviceDetector._get_vendor_from_env 2 0 0 100%
src/flag_gems/runtime/backend/device.py DeviceDetector._get_vendor_from_sys 13 1 0 92%
src/flag_gems/runtime/backend/device.py DeviceDetector._get_vendor_from_sys.runcmd 8 0 0 100%
src/flag_gems/runtime/backend/device.py DeviceDetector.get_vendor_name 1 1 0 0%
src/flag_gems/runtime/backend/device.py DeviceDetector._get_vendor_from_lib 1 0 0 100%
src/flag_gems/runtime/backend/device.py (no function) 21 0 0 100%
src/flag_gems/runtime/common.py vendors.get_all_vendors 4 0 0 100%
src/flag_gems/runtime/common.py (no function) 17 0 0 100%
src/flag_gems/runtime/configloader.py ConfigLoader.__new__ 3 0 0 100%
src/flag_gems/runtime/configloader.py ConfigLoader.__init__ 24 5 0 79%
src/flag_gems/runtime/configloader.py ConfigLoader.load_all 2 0 0 100%
src/flag_gems/runtime/configloader.py ConfigLoader.get_vendor_heuristics_config 1 0 0 100%
src/flag_gems/runtime/configloader.py ConfigLoader.get_default_heuristics_config 1 0 0 100%
src/flag_gems/runtime/configloader.py ConfigLoader.get_default_tune_config 1 0 0 100%
src/flag_gems/runtime/configloader.py ConfigLoader.get_vendor_tune_config 1 0 0 100%
src/flag_gems/runtime/configloader.py ConfigLoader.get_heuristics_config 8 5 0 38%
src/flag_gems/runtime/configloader.py ConfigLoader._resolve_iteration_values 5 1 0 80%
src/flag_gems/runtime/configloader.py ConfigLoader._gen_impl 22 0 0 100%
src/flag_gems/runtime/configloader.py ConfigLoader.to_gen_config 14 0 0 100%
src/flag_gems/runtime/configloader.py ConfigLoader.get_tuned_config 22 4 0 82%
src/flag_gems/runtime/configloader.py (no function) 19 0 0 100%
src/flag_gems/runtime/error.py backend_not_support 1 1 0 0%
src/flag_gems/runtime/error.py device_not_found 1 1 0 0%
src/flag_gems/runtime/error.py register_error 1 1 0 0%
src/flag_gems/runtime/error.py customized_op_replace_error 1 1 0 0%
src/flag_gems/runtime/error.py (no function) 4 0 0 100%
src/flag_gems/runtime/register.py Register.__init__ 19 0 0 100%
src/flag_gems/runtime/register.py Register.extract_include_config 23 15 0 35%
src/flag_gems/runtime/register.py Register.config_filter 2 0 0 100%
src/flag_gems/runtime/register.py Register.config_filter.enabled 1 0 0 100%
src/flag_gems/runtime/register.py Register.get_vendor_unused_op 3 1 0 67%
src/flag_gems/runtime/register.py Register.register_impl 6 1 0 83%
src/flag_gems/runtime/register.py Register.for_each 5 2 0 60%
src/flag_gems/runtime/register.py Register.get_all_ops 1 1 0 0%
src/flag_gems/runtime/register.py Register.get_all_keys 1 1 0 0%
src/flag_gems/runtime/register.py Register.get_unused_ops 1 1 0 0%
src/flag_gems/runtime/register.py Register.get_vendor_name 1 1 0 0%
src/flag_gems/runtime/register.py Register.get_current_device 1 1 0 0%
src/flag_gems/runtime/register.py (no function) 15 0 0 100%
src/flag_gems/testing/__init__.py _maybe_move_to_cpu 12 2 0 83%
src/flag_gems/testing/__init__.py assert_close 7 0 0 100%
src/flag_gems/testing/__init__.py assert_equal 1 0 0 100%
src/flag_gems/testing/__init__.py (no function) 9 1 0 89%
src/flag_gems/utils/__init__.py (no function) 6 0 0 100%
src/flag_gems/utils/code_cache.py cache_dir_path 5 1 0 80%
src/flag_gems/utils/code_cache.py cache_dir 3 0 0 100%
src/flag_gems/utils/code_cache.py code_cache_dir 3 0 0 100%
src/flag_gems/utils/code_cache.py config_cache_dir 3 0 0 100%
src/flag_gems/utils/code_cache.py clear_cache 2 2 0 0%
src/flag_gems/utils/code_cache.py (no function) 10 0 0 100%
src/flag_gems/utils/code_utils.py IndentedBuffer.__init__ 2 0 0 100%
src/flag_gems/utils/code_utils.py IndentedBuffer.getvalue 6 0 0 100%
src/flag_gems/utils/code_utils.py IndentedBuffer.clear 1 1 0 0%
src/flag_gems/utils/code_utils.py IndentedBuffer.__bool__ 1 1 0 0%
src/flag_gems/utils/code_utils.py IndentedBuffer.prefix 1 0 0 100%
src/flag_gems/utils/code_utils.py IndentedBuffer.newline 1 0 0 100%
src/flag_gems/utils/code_utils.py IndentedBuffer.writeline 3 0 0 100%
src/flag_gems/utils/code_utils.py IndentedBuffer.tpl 6 6 0 0%
src/flag_gems/utils/code_utils.py IndentedBuffer.writelines 2 0 0 100%
src/flag_gems/utils/code_utils.py IndentedBuffer.writemultiline 1 0 0 100%
src/flag_gems/utils/code_utils.py IndentedBuffer.indent 2 0 0 100%
src/flag_gems/utils/code_utils.py IndentedBuffer.indent.ctx 4 0 0 100%
src/flag_gems/utils/code_utils.py NameSpace.__init__ 4 4 0 0%
src/flag_gems/utils/code_utils.py NameSpace.create_name 20 20 0 0%
src/flag_gems/utils/code_utils.py NameSpace._is_illegal_name 5 5 0 0%
src/flag_gems/utils/code_utils.py write_atomic 7 1 0 86%
src/flag_gems/utils/code_utils.py (no function) 30 0 0 100%
src/flag_gems/utils/codegen_config_utils.py default_heuristics_for_num_warps 5 0 0 100%
src/flag_gems/utils/codegen_config_utils.py metax_heuristics_for_num_warps 5 5 0 0%
src/flag_gems/utils/codegen_config_utils.py hygon_heuristics_for_num_warps 5 5 0 0%
src/flag_gems/utils/codegen_config_utils.py cambricon_heuristics_for_num_warps 1 1 0 0%
src/flag_gems/utils/codegen_config_utils.py tsingmicro_heuristics_for_num_warps 1 1 0 0%
src/flag_gems/utils/codegen_config_utils.py sunrise_heuristics_for_num_warps 7 7 0 0%
src/flag_gems/utils/codegen_config_utils.py enflame_heuristics_for_num_warps 1 1 0 0%
src/flag_gems/utils/codegen_config_utils.py CodeGenConfig.__post_init__ 2 0 0 100%
src/flag_gems/utils/codegen_config_utils.py get_codegen_config 3 1 0 67%
src/flag_gems/utils/codegen_config_utils.py get_heuristics_for_num_warps 3 1 0 67%
src/flag_gems/utils/codegen_config_utils.py (no function) 25 0 0 100%
src/flag_gems/utils/device_info.py get_device_id 5 3 0 40%
src/flag_gems/utils/device_info.py get_device_properties 6 3 0 50%
src/flag_gems/utils/device_info.py get_device_capability 10 5 0 50%
src/flag_gems/utils/device_info.py get_device_info 17 6 0 65%
src/flag_gems/utils/device_info.py get_l2_cache_size 1 1 0 0%
src/flag_gems/utils/device_info.py get_sm_count 1 0 0 100%
src/flag_gems/utils/device_info.py (no function) 19 0 0 100%
src/flag_gems/utils/libentry.py all_kwargs 1 1 0 0%
src/flag_gems/utils/libentry.py Cache.__init__ 3 0 0 100%
src/flag_gems/utils/libentry.py ConfigCache.__init__ 1 0 0 100%
src/flag_gems/utils/libentry.py ConfigCache.__contains__ 1 0 0 100%
src/flag_gems/utils/libentry.py ConfigCache.__getitem__ 4 1 0 75%
src/flag_gems/utils/libentry.py ConfigCache.__setitem__ 1 1 0 0%
src/flag_gems/utils/libentry.py ConfigCache.get 1 0 0 100%
src/flag_gems/utils/libentry.py ConfigCache.set 1 1 0 0%
src/flag_gems/utils/libentry.py BenchmarkCache.__init__ 2 2 0 0%
src/flag_gems/utils/libentry.py BenchmarkCache.__contains__ 1 1 0 0%
src/flag_gems/utils/libentry.py BenchmarkCache.__getitem__ 4 4 0 0%
src/flag_gems/utils/libentry.py BenchmarkCache.__setitem__ 1 1 0 0%
src/flag_gems/utils/libentry.py BenchmarkCache.get 1 1 0 0%
src/flag_gems/utils/libentry.py BenchmarkCache.set 1 1 0 0%
src/flag_gems/utils/libentry.py LibCache.__new__ 3 0 0 100%
src/flag_gems/utils/libentry.py LibCache.__init__ 14 3 0 79%
src/flag_gems/utils/libentry.py LibCache.__getitem__ 1 1 0 0%
src/flag_gems/utils/libentry.py LibCache.__getitem__ 1 1 0 0%
src/flag_gems/utils/libentry.py LibCache.__getitem__ 5 3 0 40%
src/flag_gems/utils/libentry.py LibCache.get_benchmark 5 5 0 0%
src/flag_gems/utils/libentry.py LibCache.get_config 5 0 0 100%
src/flag_gems/utils/libentry.py LibTuner.__init__ 23 8 0 65%
src/flag_gems/utils/libentry.py LibTuner.cache_key 4 0 0 100%
src/flag_gems/utils/libentry.py LibTuner.kernel_hash 1 0 0 100%
src/flag_gems/utils/libentry.py LibTuner.configs_hash 1 0 0 100%
src/flag_gems/utils/libentry.py LibTuner.get_key 5 1 0 80%
src/flag_gems/utils/libentry.py LibTuner.policy 1 1 0 0%
src/flag_gems/utils/libentry.py LibTuner.register 2 0 0 100%
src/flag_gems/utils/libentry.py LibTuner.register.decorator 2 0 0 100%
src/flag_gems/utils/libentry.py LibTuner.get 1 0 0 100%
src/flag_gems/utils/libentry.py LibTuner.get_strategy 1 0 0 100%
src/flag_gems/utils/libentry.py LibTuner.register_policy 3 0 0 100%
src/flag_gems/utils/libentry.py LibTuner.register_policy.decorator 4 0 0 100%
src/flag_gems/utils/libentry.py LibTuner.register_policy.decorator.AnonymousLibTunerImpl.__init__ 1 0 0 100%
src/flag_gems/utils/libentry.py LibTuner.register_policy.decorator.AnonymousLibTunerImpl.policy 1 1 0 0%
src/flag_gems/utils/libentry.py LibTuner.register_strategy 2 0 0 100%
src/flag_gems/utils/libentry.py LibTuner.register_strategy.decorator 2 0 0 100%
src/flag_gems/utils/libentry.py LibTuner.run 36 16 0 56%
src/flag_gems/utils/libentry.py LibTuner.run.bench 5 5 0 0%
src/flag_gems/utils/libentry.py default_strategy 1 0 0 100%
src/flag_gems/utils/libentry.py log2_strategy 1 0 0 100%
src/flag_gems/utils/libentry.py align32_strategy 1 0 0 100%
src/flag_gems/utils/libentry.py default_policy 3 3 0 0%
src/flag_gems/utils/libentry.py libtuner 5 0 0 100%
src/flag_gems/utils/libentry.py libtuner.decorator 1 0 0 100%
src/flag_gems/utils/libentry.py LibEntry.__init__ 11 0 0 100%
src/flag_gems/utils/libentry.py LibEntry.key 5 0 0 100%
src/flag_gems/utils/libentry.py LibEntry.key.spec_arg 3 0 0 100%
src/flag_gems/utils/libentry.py LibEntry.key.dns_arg 9 4 0 56%
src/flag_gems/utils/libentry.py LibEntry.run 88 6 0 93%
src/flag_gems/utils/libentry.py libentry 2 0 0 100%
src/flag_gems/utils/libentry.py libentry.decorator 1 0 0 100%
src/flag_gems/utils/libentry.py (no function) 96 2 0 98%
src/flag_gems/utils/limits.py get_dtype_max 12 12 0 0%
src/flag_gems/utils/limits.py get_dtype_min 11 11 0 0%
src/flag_gems/utils/limits.py (no function) 6 0 0 100%
src/flag_gems/utils/models/__init__.py (no function) 3 0 0 100%
src/flag_gems/utils/models/model.py PersistantModel.__init__ 2 0 0 100%
src/flag_gems/utils/models/model.py PersistantModel.parse_config 1 1 0 0%
src/flag_gems/utils/models/model.py PersistantModel.get_config 1 1 0 0%
src/flag_gems/utils/models/model.py PersistantModel.get_benchmark 1 1 0 0%
src/flag_gems/utils/models/model.py PersistantModel.put_config 1 1 0 0%
src/flag_gems/utils/models/model.py PersistantModel.put_config 1 1 0 0%
src/flag_gems/utils/models/model.py PersistantModel.put_config 1 1 0 0%
src/flag_gems/utils/models/model.py PersistantModel.put_benchmark 1 1 0 0%
src/flag_gems/utils/models/model.py PersistantModel.put_benchmark 1 1 0 0%
src/flag_gems/utils/models/model.py PersistantModel.put_benchmark 1 1 0 0%
src/flag_gems/utils/models/model.py (no function) 26 0 0 100%
src/flag_gems/utils/models/session.py RollbackSession.__init__ 1 0 0 100%
src/flag_gems/utils/models/session.py RollbackSession.commit 4 4 0 0%
src/flag_gems/utils/models/session.py (no function) 7 0 0 100%
src/flag_gems/utils/models/sql.py SQLPersistantModel.__init__ 3 0 0 100%
src/flag_gems/utils/models/sql.py SQLPersistantModel.build_sql_model_by_py 4 4 0 0%
src/flag_gems/utils/models/sql.py SQLPersistantModel.build_sql_model_by_db 4 0 0 100%
src/flag_gems/utils/models/sql.py SQLPersistantModel.get_key_dict 1 0 0 100%
src/flag_gems/utils/models/sql.py SQLPersistantModel.get_config_dict 1 1 0 0%
src/flag_gems/utils/models/sql.py SQLPersistantModel.get_sql_model 16 7 0 56%
src/flag_gems/utils/models/sql.py SQLPersistantModel.get_config 12 2 0 83%
src/flag_gems/utils/models/sql.py SQLPersistantModel.get_benchmark 12 12 0 0%
src/flag_gems/utils/models/sql.py SQLPersistantModel.put_config 9 9 0 0%
src/flag_gems/utils/models/sql.py SQLPersistantModel.put_benchmark 11 11 0 0%
src/flag_gems/utils/models/sql.py (no function) 29 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py _type_name 5 3 0 40%
src/flag_gems/utils/pointwise_dynamic.py _check_typed_list 2 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py _check_sized_list 1 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py _tuple_content 5 1 0 80%
src/flag_gems/utils/pointwise_dynamic.py _cs 1 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py _broadcast_vec 2 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py FunctionSchema.__init__ 41 7 0 83%
src/flag_gems/utils/pointwise_dynamic.py FunctionSchema.canonicalize_promotion_methods 5 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py FunctionSchema.num_inputs 1 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py FunctionSchema.num_outputs 1 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py FunctionSchema.is_tensor 1 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py FunctionSchema.input_type 1 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py FunctionSchema.output_type 1 1 0 0%
src/flag_gems/utils/pointwise_dynamic.py FunctionSchema.num_input_tensors 1 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py FunctionSchema.num_output_tensors 1 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py FunctionSchema.num_non_tensor_args 1 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py FunctionSchema.signature 16 2 0 88%
src/flag_gems/utils/pointwise_dynamic.py FunctionSchema._compute_input_id 10 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py FunctionSchema.input_index 1 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py FunctionSchema.__str__ 1 1 0 0%
src/flag_gems/utils/pointwise_dynamic.py KernelGenerator.__init__ 7 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py KernelGenerator.gen_import_function 4 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py KernelGenerator.gen_decorators 6 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py KernelGenerator.input_name 4 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py KernelGenerator.output_name 1 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py KernelGenerator.gen_signature 40 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py KernelGenerator.gen_signature_1d_tile 33 1 0 97%
src/flag_gems/utils/pointwise_dynamic.py KernelGenerator.gen_num_tiles 4 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py KernelGenerator.gen_body_for_0d 17 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py KernelGenerator.gen_body_one_tile_per_cta_with_bptr 35 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py KernelGenerator.gen_body_gsl_with_bptr 5 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py KernelGenerator.gen_body_one_tile_per_cta_without_bptr 33 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py KernelGenerator.gen_body_gsl_without_bptr 5 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py KernelGenerator.codegen_nd_tile_with_bptr 19 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py KernelGenerator.codegen_nd_tile_without_bptr 19 3 0 84%
src/flag_gems/utils/pointwise_dynamic.py KernelGenerator.codegen_nd_tile 5 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py KernelGenerator.gen_body_one_tile_per_cta_1d_tile 27 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py KernelGenerator.gen_body_gsl_1d_tile 5 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py KernelGenerator.codegen_1d_tile 18 3 0 83%
src/flag_gems/utils/pointwise_dynamic.py WrapperGenerator.__init__ 5 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py WrapperGenerator.input_name 4 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py WrapperGenerator.output_name 1 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py WrapperGenerator.gen_signature 14 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py WrapperGenerator.gen_docstring 3 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py WrapperGenerator.gen_same_shape_check 4 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py WrapperGenerator.gen_task_partition 25 2 0 92%
src/flag_gems/utils/pointwise_dynamic.py WrapperGenerator.gen_task_partition_1d 25 4 0 84%
src/flag_gems/utils/pointwise_dynamic.py WrapperGenerator.gen_kernel_launch 54 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py WrapperGenerator.gen_kernel_launch_1d 34 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py WrapperGenerator.gen_return 2 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py WrapperGenerator.codegen_nd_tile 9 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py WrapperGenerator.codegen_1d_tile 9 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py ModuleGenerator.__init__ 3 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py ModuleGenerator.generate_imports 18 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py ModuleGenerator.codegen 7 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py PointwiseDynamicFunction.__init__ 7 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py PointwiseDynamicFunction.__call__ 4 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py PointwiseDynamicFunction.use_fast_path 1 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py PointwiseDynamicFunction.prepare_args 52 4 0 92%
src/flag_gems/utils/pointwise_dynamic.py PointwiseDynamicFunction._unwrap 4 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py PointwiseDynamicFunction.instantiate 20 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py pointwise_dynamic 4 1 0 75%
src/flag_gems/utils/pointwise_dynamic.py pointwise_dynamic.decorator 4 0 0 100%
src/flag_gems/utils/pointwise_dynamic.py (no function) 90 0 0 100%
src/flag_gems/utils/random_utils.py philox_backend_seed_offset 12 1 0 92%
src/flag_gems/utils/random_utils.py set_philox_state 8 0 0 100%
src/flag_gems/utils/random_utils.py per_thread_offset 4 4 0 0%
src/flag_gems/utils/random_utils.py uniform 13 13 0 0%
src/flag_gems/utils/random_utils.py (no function) 23 11 0 52%
src/flag_gems/utils/shape_utils.py bracket_next_power_of_2 1 0 0 100%
src/flag_gems/utils/shape_utils.py broadcast 21 1 0 95%
src/flag_gems/utils/shape_utils.py broadcastable 14 3 0 79%
src/flag_gems/utils/shape_utils.py broadcastable_to 14 3 0 79%
src/flag_gems/utils/shape_utils.py broadcast_shapes 6 1 0 83%
src/flag_gems/utils/shape_utils.py broadcasted_stride 8 0 0 100%
src/flag_gems/utils/shape_utils.py volume 1 0 0 100%
src/flag_gems/utils/shape_utils.py is_valid_perm 6 6 0 0%
src/flag_gems/utils/shape_utils.py unravel_index 8 8 0 0%
src/flag_gems/utils/shape_utils.py c_contiguous_stride 6 0 0 100%
src/flag_gems/utils/shape_utils.py f_contiguous_stride 6 0 0 100%
src/flag_gems/utils/shape_utils.py ordered_stride 6 0 0 100%
src/flag_gems/utils/shape_utils.py stride_order 1 0 0 100%
src/flag_gems/utils/shape_utils.py all_the_same_shape 4 0 0 100%
src/flag_gems/utils/shape_utils.py all_the_same_stride 4 0 0 100%
src/flag_gems/utils/shape_utils.py all_c_contiguous 3 0 0 100%
src/flag_gems/utils/shape_utils.py heuristics_for_tile_size 8 0 0 100%
src/flag_gems/utils/shape_utils.py heuristics_for_num_warps 1 0 0 100%
src/flag_gems/utils/shape_utils.py dim_compress 8 0 0 100%
src/flag_gems/utils/shape_utils.py size_in_bytes 1 1 0 0%
src/flag_gems/utils/shape_utils.py can_use_int32_index 9 9 0 0%
src/flag_gems/utils/shape_utils.py has_internal_overlapping 8 0 0 100%
src/flag_gems/utils/shape_utils.py restride_dim 3 0 0 100%
src/flag_gems/utils/shape_utils.py cfggen 4 0 0 100%
src/flag_gems/utils/shape_utils.py add_on_kernel 12 12 0 0%
src/flag_gems/utils/shape_utils.py check_tensor_attributes 7 2 0 71%
src/flag_gems/utils/shape_utils.py offset_calculator 15 15 0 0%
src/flag_gems/utils/shape_utils.py offsetCalculator 12 12 0 0%
src/flag_gems/utils/shape_utils.py (no function) 48 0 0 100%
src/flag_gems/utils/tensor_wrapper.py TypedPtr.__init__ 2 0 0 100%
src/flag_gems/utils/tensor_wrapper.py TypedPtr.data_ptr 1 0 0 100%
src/flag_gems/utils/tensor_wrapper.py TypedPtr.untyped_storage 1 1 0 0%
src/flag_gems/utils/tensor_wrapper.py TypedPtr.from_tensor 1 0 0 100%
src/flag_gems/utils/tensor_wrapper.py TypedPtr.reinterpret_tensor 1 0 0 100%
src/flag_gems/utils/tensor_wrapper.py StridedBuffer.__init__ 17 5 0 71%
src/flag_gems/utils/tensor_wrapper.py StridedBuffer.stride 1 0 0 100%
src/flag_gems/utils/tensor_wrapper.py StridedBuffer.size 1 0 0 100%
src/flag_gems/utils/tensor_wrapper.py StridedBuffer.element_size 1 1 0 0%
src/flag_gems/utils/tensor_wrapper.py StridedBuffer.numel 1 0 0 100%
src/flag_gems/utils/tensor_wrapper.py StridedBuffer.dim 1 1 0 0%
src/flag_gems/utils/tensor_wrapper.py StridedBuffer.unwrap 1 0 0 100%
src/flag_gems/utils/tensor_wrapper.py StridedBuffer.data_ptr 1 0 0 100%
src/flag_gems/utils/tensor_wrapper.py StridedBuffer.untyped_storage 1 1 0 0%
src/flag_gems/utils/tensor_wrapper.py StridedBuffer.clone 1 1 0 0%
src/flag_gems/utils/tensor_wrapper.py StridedBuffer.copy_ 10 10 0 0%
src/flag_gems/utils/tensor_wrapper.py (no function) 23 0 0 100%
src/flag_gems/utils/triton_driver_helper.py (no function) 6 3 0 50%
src/flag_gems/utils/triton_lang_extension.py program_id 1 1 0 0%
src/flag_gems/utils/triton_lang_extension.py num_programs 1 1 0 0%
src/flag_gems/utils/triton_lang_extension.py promote_to_tensor 1 1 0 0%
src/flag_gems/utils/triton_lang_extension.py is_floating 1 1 0 0%
src/flag_gems/utils/triton_lang_extension.py minimum_with_index_tie_break_right 9 9 0 0%
src/flag_gems/utils/triton_lang_extension.py maximum_with_index_tie_break_right 9 9 0 0%
src/flag_gems/utils/triton_lang_extension.py div_rn 2 2 0 0%
src/flag_gems/utils/triton_lang_extension.py div_rz 2 2 0 0%
src/flag_gems/utils/triton_lang_extension.py fmod 2 2 0 0%
src/flag_gems/utils/triton_lang_extension.py trunc 1 1 0 0%
src/flag_gems/utils/triton_lang_extension.py (no function) 27 0 0 100%
src/flag_gems/utils/triton_lang_helper.py use_backend 2 0 0 100%
src/flag_gems/utils/triton_lang_helper.py use_backend.decorator 7 3 0 57%
src/flag_gems/utils/triton_lang_helper.py use_tl_extra 1 0 0 100%
src/flag_gems/utils/triton_lang_helper.py (no function) 16 6 0 62%
src/flag_gems/utils/type_utils.py type_promotion 2 0 0 100%
src/flag_gems/utils/type_utils.py get_accumulator_dtype 1 0 0 100%
src/flag_gems/utils/type_utils.py (no function) 5 0 0 100%
Total   83586 70927 2 15%

No items found using the specified filter.