Prerequisites

  • Architecture: x86_64
  • Chip models: Generic GPU
  • Host driver: 610.43.02
  • Container toolkit (optional) : nvidia-container-toolkit

Image contents

Built on

harbor.baai.ac.cn/flagos-runtime/flagos-runtime-nvidia-cuda13.3:2.2.0 open_in_new

Python

3.12

Application package

vllm==0.24.0+flagos

vllm-plugin-fl==0.3.0

Environment

  • VLLM_USE_FLASHINFER_SAMPLER=0

Launch

Published: harbor.baai.ac.cn/flagos-app/vllm0.24.0-generic-13.3:2.2.0-0.3.0

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

  IMG=harbor.baai.ac.cn/flagos-app/vllm0.24.0-generic-13.3:2.2.0-0.3.0

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

With the container toolkit

Start an interactive shell:

  docker run --rm -it \
  --gpus all \
  $IMG bash

Start the app with its default settings:

  docker run --rm -it \
  --gpus all \
  $IMG

Pass arguments to the launcher:

  docker run --rm -it \
  --gpus all \
  $IMG vllm-serve --model <path> --port 9000

Without a toolkit — plain docker / podman

Start an interactive shell:

  docker run --rm -it \
  --device /dev/nvidia0 \
  --device /dev/nvidiactl \
  --device /dev/nvidia-uvm \
  -v /usr/bin/nvidia-smi:/usr/bin/nvidia-smi:ro \
  -v /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.1:/usr/lib/x86_64-linux-gnu/libnvidia-ml.so.1:ro \
  -v /usr/lib/x86_64-linux-gnu/libcuda.so.1:/usr/lib/x86_64-linux-gnu/libcuda.so.1:ro \
  $IMG bash

Start the app with its default settings:

  docker run --rm -it \
  --device /dev/nvidia0 \
  --device /dev/nvidiactl \
  --device /dev/nvidia-uvm \
  -v /usr/bin/nvidia-smi:/usr/bin/nvidia-smi:ro \
  -v /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.1:/usr/lib/x86_64-linux-gnu/libnvidia-ml.so.1:ro \
  -v /usr/lib/x86_64-linux-gnu/libcuda.so.1:/usr/lib/x86_64-linux-gnu/libcuda.so.1:ro \
  $IMG

Pass arguments to the launcher:

  docker run --rm -it \
  --device /dev/nvidia0 \
  --device /dev/nvidiactl \
  --device /dev/nvidia-uvm \
  -v /usr/bin/nvidia-smi:/usr/bin/nvidia-smi:ro \
  -v /usr/lib/x86_64-linux-gnu/libnvidia-ml.so.1:/usr/lib/x86_64-linux-gnu/libnvidia-ml.so.1:ro \
  -v /usr/lib/x86_64-linux-gnu/libcuda.so.1:/usr/lib/x86_64-linux-gnu/libcuda.so.1:ro \
  $IMG vllm-serve --model <path> --port 9000
Edit this page

Last updated 28 Sep 2026, 22:18 +0800. history