[CI/Build][CPU] Fix flaky rust downloads, broken prune flag, and triton-cpu cache coupling (#56247)

Signed-off-by: jiang1.li <jiang1.li@intel.com>
This commit is contained in:
Li, Jiang
2026-09-10 22:27:26 +08:00
committed by GitHub
parent 2e0ee66cab
commit 46bae7e98c
3 changed files with 111 additions and 68 deletions
+60 -49
View File
@@ -105,6 +105,60 @@ ENV UV_HTTP_TIMEOUT=500
ENV UV_INDEX_STRATEGY="unsafe-best-match"
ENV UV_LINK_MODE="copy"
ENV TARGETARCH=${TARGETARCH}
######################### TRITON-CPU BUILD IMAGE #########################
# Branches off base-common directly (before requirements/cpu.txt is installed
# below) so a torch/etc. version bump doesn't invalidate this stage's cache --
# it builds triton-cpu in an isolated `uv build` environment and never touches
# these packages.
FROM base-common AS vllm-triton-cpu-build
# Support for cross-compilation with x86 ISA including AVX2 and AVX512: docker build --build-arg VLLM_CPU_X86="true" ...
# Re-declared here because this stage is `FROM base-common` (not `vllm-build`),
# so it does not inherit the ARG/ENV defined there. Without it, the guard
# below would see an empty value and build triton-cpu on non-x86 targets
# (e.g. arm64).
ARG VLLM_CPU_X86=0
ARG USE_SCCACHE
ARG SCCACHE_ENDPOINT
ARG SCCACHE_LOCAL_ONLY=0
WORKDIR /vllm-workspace
RUN mkdir dist
RUN --mount=type=cache,target=/root/.cache/uv \
--mount=type=cache,target=/root/.cache/ccache \
--mount=type=cache,target=/root/.cache/sccache-local,sharing=locked \
--mount=type=cache,target=/vllm-workspace/.deps,sharing=locked \
--mount=type=cache,target=/root/.triton \
--mount=type=secret,id=aws-credentials,target=/root/.aws/credentials,required=false \
set -ex; \
if [ "$TARGETARCH" = "amd64" ] || [ "$VLLM_CPU_X86" != "0" ]; then \
git clone --recurse-submodules --shallow-submodules --filter=blob:none "https://github.com/triton-lang/triton-cpu.git"; \
cd triton-cpu; \
git checkout "270e696d"; \
if [ "$USE_SCCACHE" = "1" ]; then \
if [ "$SCCACHE_LOCAL_ONLY" = "1" ]; then \
unset SCCACHE_BUCKET SCCACHE_REGION; \
export SCCACHE_DIR=/root/.cache/sccache-local SCCACHE_CACHE_SIZE=20G; \
elif [ -n "${SCCACHE_ENDPOINT}" ]; then \
export SCCACHE_ENDPOINT="${SCCACHE_ENDPOINT}"; \
fi; \
export TRITON_APPEND_CMAKE_ARGS="-DCMAKE_C_COMPILER_LAUNCHER=sccache -DCMAKE_CXX_COMPILER_LAUNCHER=sccache"; \
sccache --show-stats; \
fi; \
uv build --wheel --out-dir=../dist; \
if [ "$USE_SCCACHE" = "1" ]; then sccache --show-stats; fi; \
cd ..; \
rm -rf triton-cpu; \
fi
######################### COMMON BASE IMAGE + PYTHON DEPS #########################
FROM base-common AS base-common-pydeps
# PyTorch provides its own indexes for standard and nightly builds.
# PYTORCH_NIGHTLY=1 builds the CPU image against torch nightly (parity with the
# GPU torch-nightly lane); default 0 keeps the pinned release CPU build.
@@ -133,15 +187,13 @@ RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install -r requirements/cpu.txt --torch-backend cpu; \
fi
ENV TARGETARCH=${TARGETARCH}
######################### x86_64 BASE IMAGE #########################
FROM base-common AS base-amd64
FROM base-common-pydeps AS base-amd64
ENV LD_PRELOAD="/usr/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4:/opt/venv/lib/libiomp5.so"
######################### arm64 BASE IMAGE #########################
FROM base-common AS base-arm64
FROM base-common-pydeps AS base-arm64
ENV LD_PRELOAD="/usr/lib/aarch64-linux-gnu/libtcmalloc_minimal.so.4"
@@ -210,6 +262,10 @@ RUN --mount=type=cache,target=/root/.cargo/registry,sharing=locked \
SETUPTOOLS_SCM_PRETEND_VERSION="0.0.0+docker.cache" bash build_rust.sh && \
if [ "$USE_SCCACHE" = "1" ]; then sccache --show-stats; fi
# build_rust.sh installed rustup here via rustup.rs; put it on PATH so the
# child stage below finds it on disk instead of re-downloading it.
ENV PATH="/root/.cargo/bin:${PATH}"
# Relink with the exact Git-derived package version.
FROM rust-build-cache AS rust-build
@@ -308,51 +364,6 @@ RUN --mount=type=cache,target=/root/.cache/uv \
VLLM_TARGET_DEVICE=cpu python3 setup.py bdist_wheel --dist-dir=dist --py-limited-api=cp38 && \
if [ "$USE_SCCACHE" = "1" ]; then sccache --show-stats; fi
######################### TRITON-CPU BUILD IMAGE #########################
FROM base-arch AS vllm-triton-cpu-build
# Support for cross-compilation with x86 ISA including AVX2 and AVX512: docker build --build-arg VLLM_CPU_X86="true" ...
# Re-declared here because this stage is `FROM base-arch` (not `vllm-build`),
# so it does not inherit the ARG/ENV defined there. Without it, the guard
# below would see an empty value and build triton-cpu on non-x86 targets
# (e.g. arm64).
ARG VLLM_CPU_X86=0
ARG USE_SCCACHE
ARG SCCACHE_ENDPOINT
ARG SCCACHE_LOCAL_ONLY=0
WORKDIR /vllm-workspace
RUN mkdir dist
RUN --mount=type=cache,target=/root/.cache/uv \
--mount=type=cache,target=/root/.cache/ccache \
--mount=type=cache,target=/root/.cache/sccache-local,sharing=locked \
--mount=type=cache,target=/vllm-workspace/.deps,sharing=locked \
--mount=type=cache,target=/root/.triton \
--mount=type=secret,id=aws-credentials,target=/root/.aws/credentials,required=false \
set -ex; \
if [ "$TARGETARCH" = "amd64" ] || [ "$VLLM_CPU_X86" != "0" ]; then \
git clone --recurse-submodules --shallow-submodules --filter=blob:none "https://github.com/triton-lang/triton-cpu.git"; \
cd triton-cpu; \
git checkout "270e696d"; \
if [ "$USE_SCCACHE" = "1" ]; then \
if [ "$SCCACHE_LOCAL_ONLY" = "1" ]; then \
unset SCCACHE_BUCKET SCCACHE_REGION; \
export SCCACHE_DIR=/root/.cache/sccache-local SCCACHE_CACHE_SIZE=20G; \
elif [ -n "${SCCACHE_ENDPOINT}" ]; then \
export SCCACHE_ENDPOINT="${SCCACHE_ENDPOINT}"; \
fi; \
export TRITON_APPEND_CMAKE_ARGS="-DCMAKE_C_COMPILER_LAUNCHER=sccache -DCMAKE_CXX_COMPILER_LAUNCHER=sccache"; \
sccache --show-stats; \
fi; \
uv build --wheel --out-dir=../dist; \
if [ "$USE_SCCACHE" = "1" ]; then sccache --show-stats; fi; \
cd ..; \
rm -rf triton-cpu; \
fi
######################### TEST DEPS #########################
FROM base-arch AS vllm-test-deps