LM/SGLang: Difference between revisions

From Fundamental Ramen
< LM
Jump to navigation Jump to search
Line 122: Line 122:
= TODO =
= TODO =


{{ref web
<references/>
  |url=https://hub.docker.com/r/lmsysorg/sglang/tags?name=xpu
  |title=Official SGLang docker image
  |site=hub.docker.com
}}
 
{{ref web
  |url=https://hub.docker.com/r/intel/sglang-dev
  |title=Intel patched SGLang docker image
  |site=hub.docker.com
}}
 
{{ref web
  |url=https://docs.sglang.io/docs/hardware-platforms/xpu#xpu
  |title=Hardware Platforms XPU
  |site=docs.sglang.io
}}
 
{{ref web
  |url=https://docs.sglang.io/docs/advanced_features/server_arguments#server-arguments
  |title=SGLang server arguments
  |site=docs.sglang.io
}}

Revision as of 01:30, 11 November 2026

Engine works fine, but most models cannot loaded in xpu mode.

Rebuild docker image from source

cd sglang
git pull
cd docker
docker build -t sglang-xpu:latest -f xpu.Dockerfile .

Run

docker run \
    -it \
    --privileged \
    --ipc=host \
    --network=host \
    --user root \
    --group-add $(getent group video | cut -d: -f3) \
    --device /dev/dri \
    -v /dev/dri/by-path:/dev/dri/by-path \
    -v /dev/shm:/dev/shm \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    -p 30000:30000 \
    -e "HF_TOKEN=$HF_TOKEN" \
    sglang-xpu:latest /bin/bash

[1] [2] [3] [4]

Structure

TODO