vllm/docker/Dockerfile.cpu

# This vLLM Dockerfile is used to build images that can run vLLM on both x86_64 and arm64 CPU platforms.
#
# Supported platforms:
#   - linux/amd64 (x86_64)
#   - linux/arm64 (aarch64)
#
# Use the `--platform` option with `docker buildx build` to specify the target architecture, e.g.:
#   docker buildx build --platform=linux/arm64 -f docker/Dockerfile.cpu .
#
# Build targets:
#   vllm-openai (default): used for serving deployment
#   vllm-test: used for CI tests
#   vllm-dev: used for development
#
# Build arguments:
#   PYTHON_VERSION=3.13|3.12 (default)|3.11|3.10
#   VLLM_CPU_DISABLE_AVX512=false (default)|true
#   VLLM_CPU_AVX512BF16=false (default)|true
#   VLLM_CPU_AVX512VNNI=false (default)|true
#

######################### COMMON BASE IMAGE #########################
FROM ubuntu:22.04 AS base-common

WORKDIR /workspace/

ARG PYTHON_VERSION=3.12
ARG PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu"

# Install minimal dependencies and uv
RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
    --mount=type=cache,target=/var/lib/apt,sharing=locked \
    apt-get update -y \
    && apt-get install -y --no-install-recommends ccache git curl wget ca-certificates \
        gcc-12 g++-12 libtcmalloc-minimal4 libnuma-dev ffmpeg libsm6 libxext6 libgl1 jq lsof \
    && update-alternatives --install /usr/bin/gcc gcc /usr/bin/gcc-12 10 --slave /usr/bin/g++ g++ /usr/bin/g++-12 \
    && curl -LsSf https://astral.sh/uv/install.sh | sh

ENV CCACHE_DIR=/root/.cache/ccache
ENV CMAKE_CXX_COMPILER_LAUNCHER=ccache

ENV PATH="/root/.local/bin:$PATH"
ENV VIRTUAL_ENV="/opt/venv"
ENV UV_PYTHON_INSTALL_DIR=/opt/uv/python
RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
ENV PATH="$VIRTUAL_ENV/bin:$PATH"

ENV UV_HTTP_TIMEOUT=500

# Install Python dependencies
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"
RUN --mount=type=cache,target=/root/.cache/uv \
    --mount=type=bind,src=requirements/common.txt,target=requirements/common.txt \
    --mount=type=bind,src=requirements/cpu.txt,target=requirements/cpu.txt \
    uv pip install --upgrade pip && \
    uv pip install -r requirements/cpu.txt

ARG TARGETARCH
ENV TARGETARCH=${TARGETARCH}

######################### x86_64 BASE IMAGE #########################
FROM base-common AS base-amd64

ENV LD_PRELOAD="/usr/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4:/opt/venv/lib/libiomp5.so"

######################### arm64 BASE IMAGE #########################
FROM base-common AS base-arm64

ENV LD_PRELOAD="/usr/lib/aarch64-linux-gnu/libtcmalloc_minimal.so.4"

######################### BASE IMAGE #########################
FROM base-${TARGETARCH} AS base

RUN echo 'ulimit -c 0' >> ~/.bashrc

######################### BUILD IMAGE #########################
FROM base AS vllm-build

ARG GIT_REPO_CHECK=0
# Support for building with non-AVX512 vLLM: docker build --build-arg VLLM_CPU_DISABLE_AVX512="true" ...
ARG VLLM_CPU_DISABLE_AVX512=0
ENV VLLM_CPU_DISABLE_AVX512=${VLLM_CPU_DISABLE_AVX512}
# Support for building with AVX512BF16 ISA: docker build --build-arg VLLM_CPU_AVX512BF16="true" ...
ARG VLLM_CPU_AVX512BF16=0
ENV VLLM_CPU_AVX512BF16=${VLLM_CPU_AVX512BF16}
# Support for building with AVX512VNNI ISA: docker build --build-arg VLLM_CPU_AVX512VNNI="true" ...
ARG VLLM_CPU_AVX512VNNI=0
ENV VLLM_CPU_AVX512VNNI=${VLLM_CPU_AVX512VNNI}

WORKDIR /workspace/vllm

RUN --mount=type=cache,target=/root/.cache/uv \
    --mount=type=bind,src=requirements/cpu-build.txt,target=requirements/build.txt \
    uv pip install -r requirements/build.txt

COPY . .
RUN --mount=type=bind,source=.git,target=.git \
    if [ "$GIT_REPO_CHECK" != 0 ]; then bash tools/check_repo.sh ; fi

RUN --mount=type=cache,target=/root/.cache/uv \
    --mount=type=cache,target=/root/.cache/ccache \
    --mount=type=cache,target=/workspace/vllm/.deps,sharing=locked \
    --mount=type=bind,source=.git,target=.git \
    VLLM_TARGET_DEVICE=cpu python3 setup.py bdist_wheel

#################### WHEEL BUILD IMAGE ####################
FROM base AS build
ARG TARGETPLATFORM

ARG PIP_INDEX_URL UV_INDEX_URL
ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL

# install build dependencies
COPY requirements/build.txt requirements/build.txt

# This timeout (in seconds) is necessary when installing some dependencies via uv since it's likely to time out
# Reference: https://github.com/astral-sh/uv/pull/1694
ENV UV_HTTP_TIMEOUT=500
ENV UV_INDEX_STRATEGY="unsafe-best-match"
# Use copy mode to avoid hardlink failures with Docker cache mounts
ENV UV_LINK_MODE=copy

RUN --mount=type=cache,target=/root/.cache/uv \
    uv pip install --python /opt/venv/bin/python3 -r requirements/build.txt

COPY . .
ARG GIT_REPO_CHECK=0
RUN --mount=type=bind,source=.git,target=.git \
    if [ "$GIT_REPO_CHECK" != "0" ]; then bash tools/check_repo.sh ; fi

# max jobs used by Ninja to build extensions
ARG max_jobs=2
ENV MAX_JOBS=${max_jobs}

ARG USE_SCCACHE
ARG SCCACHE_DOWNLOAD_URL=https://github.com/mozilla/sccache/releases/download/v0.8.1/sccache-v0.8.1-x86_64-unknown-linux-musl.tar.gz
ARG SCCACHE_ENDPOINT
ARG SCCACHE_BUCKET_NAME=vllm-build-sccache
ARG SCCACHE_REGION_NAME=us-west-2
ARG SCCACHE_S3_NO_CREDENTIALS=0

# Flag to control whether to use pre-built vLLM wheels
ARG VLLM_USE_PRECOMPILED=""

# if USE_SCCACHE is set, use sccache to speed up compilation
RUN --mount=type=cache,target=/root/.cache/uv \
    --mount=type=bind,source=.git,target=.git \
    if [ "$USE_SCCACHE" = "1" ]; then \
        echo "Installing sccache..." \
        && curl -L -o sccache.tar.gz ${SCCACHE_DOWNLOAD_URL} \
        && tar -xzf sccache.tar.gz \
        && sudo mv sccache-v0.8.1-x86_64-unknown-linux-musl/sccache /usr/bin/sccache \
        && rm -rf sccache.tar.gz sccache-v0.8.1-x86_64-unknown-linux-musl \
        && if [ ! -z ${SCCACHE_ENDPOINT} ] ; then export SCCACHE_ENDPOINT=${SCCACHE_ENDPOINT} ; fi \
        && export SCCACHE_BUCKET=${SCCACHE_BUCKET_NAME} \
        && export SCCACHE_REGION=${SCCACHE_REGION_NAME} \
        && export SCCACHE_S3_NO_CREDENTIALS=${SCCACHE_S3_NO_CREDENTIALS} \
        && export SCCACHE_IDLE_TIMEOUT=0 \
        && export CMAKE_BUILD_TYPE=Release \
        && export VLLM_USE_PRECOMPILED="${VLLM_USE_PRECOMPILED}" \
        && export VLLM_DOCKER_BUILD_CONTEXT=1 \
        && sccache --show-stats \
        && python3 setup.py bdist_wheel --dist-dir=dist --py-limited-api=cp38 \
        && sccache --show-stats; \
    fi

ARG vllm_target_device="cpu"
ENV VLLM_TARGET_DEVICE=${vllm_target_device}
ENV CCACHE_DIR=/root/.cache/ccache
RUN --mount=type=cache,target=/root/.cache/ccache \
    --mount=type=cache,target=/root/.cache/uv \
    --mount=type=bind,source=.git,target=.git  \
    if [ "$USE_SCCACHE" != "1" ]; then \
        # Clean any existing CMake artifacts
        rm -rf .deps && \
        mkdir -p .deps && \
        export VLLM_USE_PRECOMPILED="${VLLM_USE_PRECOMPILED}" && \
        export VLLM_DOCKER_BUILD_CONTEXT=1 && \
        python3 setup.py bdist_wheel --dist-dir=dist --py-limited-api=cp38; \
    fi

# Check the size of the wheel if RUN_WHEEL_CHECK is true
COPY .buildkite/check-wheel-size.py check-wheel-size.py
# sync the default value with .buildkite/check-wheel-size.py
ARG VLLM_MAX_SIZE_MB=450
ENV VLLM_MAX_SIZE_MB=$VLLM_MAX_SIZE_MB
ARG RUN_WHEEL_CHECK=true
RUN if [ "$RUN_WHEEL_CHECK" = "true" ]; then \
        python3 check-wheel-size.py dist; \
    else \
        echo "Skipping wheel size check."; \
    fi

######################### TEST DEPS #########################
FROM base AS vllm-test-deps

WORKDIR /workspace/vllm

RUN --mount=type=bind,src=requirements/test.in,target=requirements/test.in \
    cp requirements/test.in requirements/cpu-test.in && \
    sed -i '/mamba_ssm/d' requirements/cpu-test.in && \
    uv pip compile requirements/cpu-test.in -o requirements/cpu-test.txt --index-strategy unsafe-best-match --torch-backend cpu

RUN --mount=type=cache,target=/root/.cache/uv \
    uv pip install -r requirements/cpu-test.txt

######################### DEV IMAGE #########################
FROM vllm-build AS vllm-dev

WORKDIR /workspace/vllm

RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
    --mount=type=cache,target=/var/lib/apt,sharing=locked \
    apt-get install -y --no-install-recommends vim numactl xz-utils

# install development dependencies (for testing)
RUN --mount=type=cache,target=/root/.cache/uv \
    uv pip install -e tests/vllm_test_utils

RUN --mount=type=cache,target=/root/.cache/uv \
    --mount=type=cache,target=/root/.cache/ccache \
    --mount=type=bind,source=.git,target=.git \
    VLLM_TARGET_DEVICE=cpu python3 setup.py develop

COPY --from=vllm-test-deps /workspace/vllm/requirements/cpu-test.txt requirements/test.txt

RUN --mount=type=cache,target=/root/.cache/uv \
    uv pip install -r requirements/dev.txt && \
    pre-commit install --hook-type pre-commit --hook-type commit-msg

ENTRYPOINT ["bash"]

######################### TEST IMAGE #########################
FROM vllm-test-deps AS vllm-test

WORKDIR /workspace/

RUN --mount=type=cache,target=/root/.cache/uv \
    --mount=type=bind,from=vllm-build,src=/workspace/vllm/dist,target=dist \
    uv pip install dist/*.whl

ADD ./tests/ ./tests/
ADD ./examples/ ./examples/
ADD ./benchmarks/ ./benchmarks/
ADD ./vllm/collect_env.py .
ADD ./.buildkite/ ./.buildkite/

# Create symlink for vllm-workspace to maintain CI compatibility
RUN ln -sf /workspace /vllm-workspace

# install development dependencies (for testing)
RUN --mount=type=cache,target=/root/.cache/uv \
    uv pip install -e tests/vllm_test_utils

######################### RELEASE IMAGE #########################
FROM base AS vllm-openai

WORKDIR /workspace/

RUN --mount=type=cache,target=/root/.cache/uv \
    --mount=type=cache,target=/root/.cache/ccache \
    --mount=type=bind,from=vllm-build,src=/workspace/vllm/dist,target=dist \
    uv pip install dist/*.whl

ENTRYPOINT ["vllm", "serve"]