diff --git a/README.md b/README.md index 224e0a47d..a3e7beee6 100644 --- a/README.md +++ b/README.md @@ -286,6 +286,17 @@ Launch [Qwen2-7B-Instruct](https://www.modelscope.cn/models/qwen/qwen2-7b-instru ``` SGLANG_USE_MODELSCOPE=true python -m sglang.launch_server --model-path qwen/Qwen2-7B-Instruct --port 30000 ``` + +Or start it by docker. +```bash +docker run --gpus all \ + -p 30000:30000 \ + -v ~/.cache/modelscope:/root/.cache/modelscope \ + --env "SGLANG_USE_MODELSCOPE=true" \ + --ipc=host \ + lmsysorg/sglang:latest \ + python3 -m sglang.launch_server --model-path Qwen/Qwen2.5-7B-Instruct --host 0.0.0.0 --port 30000 +``` diff --git a/docker/compose.yaml b/docker/compose.yaml index f2da3a416..148014622 100644 --- a/docker/compose.yaml +++ b/docker/compose.yaml @@ -4,6 +4,8 @@ services: container_name: sglang volumes: - ${HOME}/.cache/huggingface:/root/.cache/huggingface + # If you use modelscope, you need mount this directory + # - ${HOME}/.cache/modelscope:/root/.cache/modelscope restart: always network_mode: host # Or you can only publish port 30000 @@ -11,6 +13,8 @@ services: # - 30000:30000 environment: HF_TOKEN: + # if you use modelscope to download model, you need set this environment + # - SGLANG_USE_MODELSCOPE: true entrypoint: python3 -m sglang.launch_server command: --model-path meta-llama/Meta-Llama-3.1-8B-Instruct diff --git a/python/pyproject.toml b/python/pyproject.toml index 9700d824c..69bfb7ca4 100644 --- a/python/pyproject.toml +++ b/python/pyproject.toml @@ -23,7 +23,7 @@ dependencies = [ srt = ["aiohttp", "decord", "fastapi", "hf_transfer", "huggingface_hub", "interegular", "packaging", "pillow", "psutil", "pydantic", "python-multipart", "torch", "torchao", "uvicorn", "uvloop", "zmq", - "vllm==0.5.5", "outlines>=0.0.44"] + "vllm==0.5.5", "outlines>=0.0.44", "modelscope"] openai = ["openai>=1.0", "tiktoken"] anthropic = ["anthropic>=0.20.0"] litellm = ["litellm>=1.0.0"]