LM/SGLang: Difference between revisions

From Fundamental Ramen
< LM
Jump to navigation Jump to search
Line 23: Line 23:
     -v ~/.cache/huggingface:/root/.cache/huggingface \
     -v ~/.cache/huggingface:/root/.cache/huggingface \
     -p 30000:30000 \
     -p 30000:30000 \
     -e "HF_TOKEN=$HFTOKEN" \
     -e "HF_TOKEN=$HF_TOKEN" \
     sglang-xpu:latest /bin/bash
     sglang-xpu:latest /bin/bash
</syntaxhighlight>
</syntaxhighlight>

Revision as of 06:55, 17 September 2026

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

Structure

TODO