biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CPU] Improve CPU Docker build (#30953)

Browse Source 
Signed-off-by: Maryam Tahhan <mtahhan@redhat.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
This commit is contained in:
Maryam Tahhan
2026-01-24 17:08:24 +00:00
committed by GitHub
parent 17ab54de81
commit 203d0bc0c2
3 changed files with 123 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

61
docker/Dockerfile.cpu
View File

@@ -15,9 +15,11 @@
# 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
# VLLM_CPU_AMXBF16=false |true (default)
# VLLM_CPU_AVX2=false (default)|true (for cross-compilation)
# VLLM_CPU_AVX512=false (default)|true (for cross-compilation)
# VLLM_CPU_AVX512BF16=false (default)|true (for cross-compilation)
# VLLM_CPU_AVX512VNNI=false (default)|true (for cross-compilation)
# VLLM_CPU_AMXBF16=false (default)|true (for cross-compilation)
#
######################### COMMON BASE IMAGE #########################
@@ -54,9 +56,12 @@ 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"
# Copy requirements files for installation
COPY requirements/common.txt requirements/common.txt
COPY requirements/cpu.txt requirements/cpu.txt
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
@@ -88,6 +93,12 @@ 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=${VLLM_CPU_DISABLE_AVX512}
# Support for cross-compilation with AVX2 ISA: docker build --build-arg VLLM_CPU_AVX2="1" ...
ARG VLLM_CPU_AVX2=0
ENV VLLM_CPU_AVX2=${VLLM_CPU_AVX2}
# Support for cross-compilation with AVX512 ISA: docker build --build-arg VLLM_CPU_AVX512="1" ...
ARG VLLM_CPU_AVX512=0
ENV VLLM_CPU_AVX512=${VLLM_CPU_AVX512}
# Support for building with AVX512BF16 ISA: docker build --build-arg VLLM_CPU_AVX512BF16="true" ...
ARG VLLM_CPU_AVX512BF16=0
ENV VLLM_CPU_AVX512BF16=${VLLM_CPU_AVX512BF16}
@@ -100,18 +111,19 @@ ENV VLLM_CPU_AMXBF16=${VLLM_CPU_AMXBF16}
WORKDIR /workspace/vllm
# Copy build requirements
COPY requirements/cpu-build.txt requirements/build.txt
RUN --mount=type=cache,target=/root/.cache/uv \
--mount=type=bind,src=requirements/cpu-build.txt,target=requirements/build.txt \
uv pip install -r requirements/build.txt
COPY . .
RUN --mount=type=bind,source=.git,target=.git \
if [ "$GIT_REPO_CHECK" != 0 ]; then bash tools/check_repo.sh ; fi
RUN if [ "$GIT_REPO_CHECK" != 0 ]; then bash tools/check_repo.sh ; fi
RUN --mount=type=cache,target=/root/.cache/uv \
--mount=type=cache,target=/root/.cache/ccache \
--mount=type=cache,target=/workspace/vllm/.deps,sharing=locked \
--mount=type=bind,source=.git,target=.git \
VLLM_TARGET_DEVICE=cpu python3 setup.py bdist_wheel --dist-dir=dist --py-limited-api=cp38
######################### TEST DEPS #########################
@@ -119,9 +131,11 @@ FROM base AS vllm-test-deps
WORKDIR /workspace/vllm
# Copy test requirements
COPY requirements/test.in requirements/cpu-test.in
# TODO: Update to 2.9.0 when there is a new build for intel_extension_for_pytorch for that version
RUN --mount=type=bind,src=requirements/test.in,target=requirements/test.in \
cp requirements/test.in requirements/cpu-test.in && \
RUN \
sed -i '/mamba_ssm/d' requirements/cpu-test.in && \
remove_packages_not_supported_on_aarch64() { \
case "$(uname -m)" in \
@@ -200,4 +214,29 @@ 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 labels to document build configuration
LABEL org.opencontainers.image.title="vLLM CPU"
LABEL org.opencontainers.image.description="vLLM inference engine for CPU platforms"
LABEL org.opencontainers.image.vendor="vLLM Project"
LABEL org.opencontainers.image.source="https://github.com/vllm-project/vllm"
# Build configuration labels
ARG TARGETARCH
ARG VLLM_CPU_DISABLE_AVX512
ARG VLLM_CPU_AVX2
ARG VLLM_CPU_AVX512
ARG VLLM_CPU_AVX512BF16
ARG VLLM_CPU_AVX512VNNI
ARG VLLM_CPU_AMXBF16
ARG PYTHON_VERSION
LABEL ai.vllm.build.target-arch="${TARGETARCH}"
LABEL ai.vllm.build.cpu-disable-avx512="${VLLM_CPU_DISABLE_AVX512:-false}"
LABEL ai.vllm.build.cpu-avx2="${VLLM_CPU_AVX2:-false}"
LABEL ai.vllm.build.cpu-avx512="${VLLM_CPU_AVX512:-false}"
LABEL ai.vllm.build.cpu-avx512bf16="${VLLM_CPU_AVX512BF16:-false}"
LABEL ai.vllm.build.cpu-avx512vnni="${VLLM_CPU_AVX512VNNI:-false}"
LABEL ai.vllm.build.cpu-amxbf16="${VLLM_CPU_AMXBF16:-false}"
LABEL ai.vllm.build.python-version="${PYTHON_VERSION:-3.12}"
ENTRYPOINT ["vllm", "serve"]