vllm0.20.2-kunlunxin-xre5.37.1

Prerequisites link

• Architecture: x86_64
• Chip models: Kunlunxin P800
• Host driver: 5.37.1
• Container toolkit (optional) ⓘ: xpu_container >= 1.0.13

Image contents link

Built on link

Python link

3.10

Application package link

vllm==0.20.2+flagos

vllm-plugin-fl==0.2.2

Environment link

• VLLM_FL_PLATFORM=kunlunxin
• VLLM_FL_PREFER=flagos
• USE_FLAGGEMS=1
• VLLM_FL_FLAGOS_WHITELIST=silu_and_mul,rms_norm,rotary_embedding

Launch link

Published: harbor.baai.ac.cn/flagos-app/vllm0.20.2-kunlunxin-xre5.37.1:2.2.0-0.2.2

The image name is long — assign it to a variable first:

  IMG=harbor.baai.ac.cn/flagos-app/vllm0.20.2-kunlunxin-xre5.37.1:2.2.0-0.2.2
  

The two approaches below are alternatives — pick the one that matches how your host runs containers:

With the container toolkit link

Start an interactive shell:

  docker run --rm -it \
  --runtime xpu \
  -e CXPU_VISIBLE_DEVICES=0 \
  $IMG bash
  

Start the app with its default settings:

  docker run --rm -it \
  --runtime xpu \
  -e CXPU_VISIBLE_DEVICES=0 \
  $IMG
  

Pass arguments to the launcher:

  docker run --rm -it \
  --runtime xpu \
  -e CXPU_VISIBLE_DEVICES=0 \
  $IMG vllm-serve --model <path> --port 9000
  

Without a toolkit — plain docker / podman link

Start an interactive shell:

  docker run --rm -it \
  --device /dev/xpu0 \
  --device /dev/xpuctrl \
  $IMG bash
  

Start the app with its default settings:

  docker run --rm -it \
  --device /dev/xpu0 \
  --device /dev/xpuctrl \
  $IMG
  

Pass arguments to the launcher:

  docker run --rm -it \
  --device /dev/xpu0 \
  --device /dev/xpuctrl \
  $IMG vllm-serve --model <path> --port 9000