diff --git a/docker/Dockerfile.xpu b/docker/Dockerfile.xpu new file mode 100644 index 000000000..f75bd568b --- /dev/null +++ b/docker/Dockerfile.xpu @@ -0,0 +1,139 @@ +# Argument to configure vllm base image if pre-built +ARG VLLM_BASE=vllm-base + +FROM intel/deep-learning-essentials:2025.3.2-0-devel-ubuntu24.04 AS vllm-base + +WORKDIR /workspace/ + +ARG PYTHON_VERSION=3.12 +ARG PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/xpu" + +RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | tee /usr/share/keyrings/oneapi-archive-keyring.gpg > /dev/null && \ + echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main" | tee /etc/apt/sources.list.d/oneAPI.list && \ + add-apt-repository -y ppa:kobuk-team/intel-graphics + +RUN apt clean && apt-get update -y && \ + apt-get install -y --no-install-recommends --fix-missing \ + curl \ + ffmpeg \ + git \ + libsndfile1 \ + libsm6 \ + libxext6 \ + libgl1 \ + lsb-release \ + libaio-dev \ + numactl \ + wget \ + vim \ + python3.12 \ + python3.12-dev \ + python3-pip + +RUN apt update && apt upgrade -y && \ + apt install -y libze1 libze-dev libze-intel-gpu1 intel-opencl-icd libze-intel-gpu-raytracing intel-ocloc && \ + apt install -y intel-oneapi-compiler-dpcpp-cpp-2025.3 + +ENV PATH="/root/.local/bin:$PATH" +ENV VIRTUAL_ENV="/opt/venv" +ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python +RUN curl -LsSf https://astral.sh/uv/install.sh | sh +RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV} +ENV PATH="$VIRTUAL_ENV/bin:$PATH" + +# This oneccl contains the BMG support which is not the case for default version of oneapi 2025.2. +ARG ONECCL_INSTALLER="intel-oneccl-2021.15.7.8_offline.sh" +RUN wget "https://github.com/uxlfoundation/oneCCL/releases/download/2021.15.7/${ONECCL_INSTALLER}" && \ + bash "${ONECCL_INSTALLER}" -a --silent --eula accept && \ + rm "${ONECCL_INSTALLER}" && \ + echo "source /opt/intel/oneapi/setvars.sh --force" >> /root/.bashrc && \ + echo "source /opt/intel/oneapi/ccl/2021.15/env/vars.sh --force" >> /root/.bashrc +RUN rm -f /opt/intel/oneapi/ccl/latest && \ + ln -s /opt/intel/oneapi/ccl/2021.15 /opt/intel/oneapi/ccl/latest + +SHELL ["bash", "-c"] +CMD ["bash", "-c", "source /root/.bashrc && exec bash"] + +WORKDIR /workspace/ +ENV UV_HTTP_TIMEOUT=500 + +# Configure package index for XPU +ENV PIP_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL} +ENV UV_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL} +ENV UV_INDEX_STRATEGY="unsafe-best-match" +ENV UV_LINK_MODE="copy" + +ARG VLLM_VERSION=v0.16.0 +RUN git clone -b ${VLLM_VERSION} https://github.com/vllm-project/vllm +WORKDIR /workspace/vllm + +RUN --mount=type=cache,target=/root/.cache/uv \ + uv pip install --upgrade pip && \ + uv pip install -r requirements/xpu.txt + + # used for suffix method speculative decoding + # build deps for proto + nanobind-based extensions to set up the build environment +RUN --mount=type=cache,target=/root/.cache/uv \ + uv pip install grpcio-tools protobuf nanobind + # arctic-inference is built from source which needs torch-xpu properly installed first +RUN --mount=type=cache,target=/root/.cache/uv \ + source /opt/intel/oneapi/setvars.sh --force && \ + source /opt/intel/oneapi/ccl/2021.15/env/vars.sh --force && \ + export CMAKE_PREFIX_PATH="$(python -c 'import site; print(site.getsitepackages()[0])'):${CMAKE_PREFIX_PATH}" && \ + uv pip install --no-build-isolation arctic-inference==0.1.1 + +ENV LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/lib/" + +ENV VLLM_TARGET_DEVICE=xpu +ENV VLLM_WORKER_MULTIPROC_METHOD=spawn + +RUN --mount=type=cache,target=/root/.cache/uv \ + uv pip install --no-build-isolation . + +CMD ["/bin/bash"] + +FROM vllm-base AS vllm-openai + +# install additional dependencies for openai api server +RUN --mount=type=cache,target=/root/.cache/uv \ + uv pip install accelerate hf_transfer pytest pytest_asyncio lm_eval[api] modelscope + +# install development dependencies (for testing) +RUN uv pip install -e tests/vllm_test_utils + +# install nixl from source code +ENV NIXL_VERSION=0.7.0 +RUN python /workspace/vllm/tools/install_nixl_from_source_ubuntu.py + +# ensure vllm is properly installed +RUN python -c "import vllm, inspect; print(vllm.__file__)" +RUN uv pip show vllm + +CMD ["/bin/bash"] + +ENTRYPOINT [] + +FROM ${VLLM_BASE} AS vllm-omni + +WORKDIR /workspace/vllm-omni +COPY . . + +ENV VLLM_OMNI_TARGET_DEVICE=xpu +RUN uv pip install --no-cache-dir ".[dev]" --no-build-isolation + +# FIX triton +RUN --mount=type=cache,target=/root/.cache/uv \ + uv pip uninstall triton triton-xpu && \ + uv pip install triton-xpu==3.6.0 + +# remove torch bundled oneccl to avoid conflicts +RUN --mount=type=cache,target=/root/.cache/uv \ + uv pip uninstall oneccl oneccl-devel + +FROM vllm-omni AS vllm-omni-openai + +RUN ln -sf /usr/bin/python3 /usr/bin/python + +ENV VLLM_WORKER_MULTIPROC_METHOD=spawn + +ENTRYPOINT ["vllm", "serve", "--omni"] diff --git a/docs/getting_started/installation/README.md b/docs/getting_started/installation/README.md index 20a737dca..353fbe1c0 100644 --- a/docs/getting_started/installation/README.md +++ b/docs/getting_started/installation/README.md @@ -5,4 +5,5 @@ vLLM-Omni supports the following hardware platforms: - [GPU](gpu.md) - [NVIDIA CUDA](gpu.md) - [AMD ROCm](gpu.md) + - [Intel XPU](gpu.md) - [NPU](npu.md) diff --git a/docs/getting_started/installation/gpu.md b/docs/getting_started/installation/gpu.md index 141256dbc..963e38de4 100644 --- a/docs/getting_started/installation/gpu.md +++ b/docs/getting_started/installation/gpu.md @@ -18,6 +18,10 @@ vLLM-Omni is a Python library that supports the following GPU variants. The libr --8<-- "docs/getting_started/installation/gpu/rocm.inc.md:requirements" +=== "Intel XPU" + + --8<-- "docs/getting_started/installation/gpu/xpu.inc.md:requirements" + ## Set up using Python ### Create a new Python environment @@ -32,11 +36,14 @@ Note: Pre-built wheels are currently only available for vLLM-Omni 0.11.0rc1, 0.1 --8<-- "docs/getting_started/installation/gpu/cuda.inc.md:pre-built-wheels" - === "AMD ROCm" --8<-- "docs/getting_started/installation/gpu/rocm.inc.md:pre-built-wheels" +=== "Intel XPU" + + --8<-- "docs/getting_started/installation/gpu/xpu.inc.md:pre-built-wheels" + [](){ #build-from-source } ### Build wheel from source @@ -49,6 +56,10 @@ Note: Pre-built wheels are currently only available for vLLM-Omni 0.11.0rc1, 0.1 --8<-- "docs/getting_started/installation/gpu/rocm.inc.md:build-wheel-from-source" +=== "Intel XPU" + + --8<-- "docs/getting_started/installation/gpu/xpu.inc.md:build-wheel-from-source" + ## Set up using Docker ### Pre-built images @@ -61,8 +72,16 @@ Note: Pre-built wheels are currently only available for vLLM-Omni 0.11.0rc1, 0.1 --8<-- "docs/getting_started/installation/gpu/rocm.inc.md:pre-built-images" +=== "Intel XPU" + + --8<-- "docs/getting_started/installation/gpu/xpu.inc.md:pre-built-images" + ### Build your own docker image === "AMD ROCm" --8<-- "docs/getting_started/installation/gpu/rocm.inc.md:build-docker" + +=== "Intel XPU" + + --8<-- "docs/getting_started/installation/gpu/xpu.inc.md:build-docker" diff --git a/docs/getting_started/installation/gpu/xpu.inc.md b/docs/getting_started/installation/gpu/xpu.inc.md new file mode 100644 index 000000000..8822e3a7c --- /dev/null +++ b/docs/getting_started/installation/gpu/xpu.inc.md @@ -0,0 +1,48 @@ +# --8<-- [start:requirements] + +- GPU: Validated on Intel® Arc™ B-Series. + +# --8<-- [end:requirements] +# --8<-- [start:set-up-using-python] + +vLLM-Omni currently recommends using the Docker image setup steps below. + +# --8<-- [start:pre-built-wheels] + +# --8<-- [end:pre-built-wheels] + +# --8<-- [start:build-wheel-from-source] + +# --8<-- [end:build-wheel-from-source] + +# --8<-- [start:build-docker] + +#### Build docker image + +```bash +DOCKER_BUILDKIT=1 docker build -f docker/Dockerfile.xpu -t vllm-omni-xpu --shm-size=4g . +``` + +#### Launch the docker image + +##### Launch with OpenAI API Server + +``` +docker run -it -d --shm-size 10g \ + --name {container_name} \ + --net=host \ + --ipc=host \ + --privileged \ + -v /dev/dri/by-path:/dev/dri/by-path \ + --device /dev/dri:/dev/dri \ + -v ~/.cache/huggingface:/root/.cache/huggingface \ + --env "HF_TOKEN=$HF_TOKEN" \ + vllm-omni-xpu \ + --model Qwen/Qwen2.5-Omni-3B --port 8091 +``` + +# --8<-- [end:build-docker] + +# --8<-- [start:pre-built-images] + +# --8<-- [end:pre-built-images]