vllm0.20.2-sunrise-tangrt1.2.0

Prerequisites link

• Architecture: x86_64
• Chip models: Sunrise SR-SUN-S2-X1
• Host driver: 0.24.0

Image contents link

Built on link

Python link

3.10

Application package link

vllm==0.20.2+flagos

vllm-plugin-fl==0.2.2

Launch link

Published: harbor.baai.ac.cn/flagos-app/vllm0.20.2-sunrise-tangrt1.2.0:2.2.0-0.2.2

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

  IMG=harbor.baai.ac.cn/flagos-app/vllm0.20.2-sunrise-tangrt1.2.0:2.2.0-0.2.2
  

Without a toolkit — plain docker / podman link

Start an interactive shell:

  docker run --rm -it \
  --privileged \
  -v /dev:/dev \
  -e TANG_VISIBLE_DEVICES=all \
  $IMG bash
  

Start the app with its default settings:

  docker run --rm -it \
  --privileged \
  -v /dev:/dev \
  -e TANG_VISIBLE_DEVICES=all \
  $IMG
  

Pass arguments to the launcher:

  docker run --rm -it \
  --privileged \
  -v /dev:/dev \
  -e TANG_VISIBLE_DEVICES=all \
  $IMG vllm-serve --model <path> --port 9000