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

docker: docker-aware precompiled wheel support (#21127)

Browse Source 
Signed-off-by: dougbtv <dosmith@redhat.com>
This commit is contained in:
Doug Smith
2025-07-29 17:45:19 -04:00
committed by GitHub
parent a33ea28b1b
commit a1873db23d
3 changed files with 68 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
docker/Dockerfile
View File

@@ -209,16 +209,7 @@ 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
# TODO: in setup.py VLLM_USE_PRECOMPILED is sensitive to truthiness, it will take =0 as "true", this should be fixed
ENV VLLM_USE_PRECOMPILED=""
RUN if [ "${VLLM_USE_PRECOMPILED}" = "1" ]; then \
export VLLM_USE_PRECOMPILED=1 && \
echo "Using precompiled wheels"; \
else \
unset VLLM_USE_PRECOMPILED && \
echo "Leaving VLLM_USE_PRECOMPILED unset to build wheels from source"; \
fi
ARG VLLM_USE_PRECOMPILED=""
# if USE_SCCACHE is set, use sccache to speed up compilation
RUN --mount=type=cache,target=/root/.cache/uv \
@@ -235,6 +226,8 @@ RUN --mount=type=cache,target=/root/.cache/uv \
&& export SCCACHE_S3_NO_CREDENTIALS=${SCCACHE_S3_NO_CREDENTIALS} \
&& export SCCACHE_IDLE_TIMEOUT=0 \
&& export CMAKE_BUILD_TYPE=Release \
&& export VLLM_USE_PRECOMPILED="${VLLM_USE_PRECOMPILED}" \
&& export VLLM_DOCKER_BUILD_CONTEXT=1 \
&& sccache --show-stats \
&& python3 setup.py bdist_wheel --dist-dir=dist --py-limited-api=cp38 \
&& sccache --show-stats; \
@@ -248,9 +241,22 @@ RUN --mount=type=cache,target=/root/.cache/ccache \
# Clean any existing CMake artifacts
rm -rf .deps && \
mkdir -p .deps && \
export VLLM_USE_PRECOMPILED="${VLLM_USE_PRECOMPILED}" && \
export VLLM_DOCKER_BUILD_CONTEXT=1 && \
python3 setup.py bdist_wheel --dist-dir=dist --py-limited-api=cp38; \
fi
# When using precompiled wheels, keep only the newest manylinux1 wheel and delete others
RUN if [ "$VLLM_USE_PRECOMPILED" = "1" ]; then \
echo "Cleaning up extra wheels in dist/..." && \
# Identify the most recent manylinux1_x86_64 wheel
KEEP_WHEEL=$(ls -t dist/*manylinux1_x86_64.whl 2>/dev/null | head -n1) && \
if [ -n "$KEEP_WHEEL" ]; then \
echo "Keeping wheel: $KEEP_WHEEL"; \
find dist/ -type f -name "*.whl" ! -path "${KEEP_WHEEL}" -delete; \
fi; \
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