[Refactor] Move auxiliary files out of the repository root (#58572)

Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Misha Goin
2026-09-24 12:38:56 -07:00
committed by GitHub
parent cd06e81c41
commit 58aa2f1ef1
35 changed files with 134 additions and 130 deletions
+19 -19
View File
@@ -207,7 +207,7 @@ ARG PYTORCH_NIGHTLY
# Check whether to install torch nightly instead of release for this build
COPY requirements/common.txt requirements/common.txt
COPY requirements/cuda.txt requirements/cuda.txt
COPY use_existing_torch.py use_existing_torch.py
COPY tools/use_existing_torch.py tools/use_existing_torch.py
COPY pyproject.toml pyproject.toml
RUN --mount=type=cache,target=/opt/uv/cache \
--mount=type=bind,source=requirements,target=/tmp/vllm-requirements,ro \
@@ -229,7 +229,7 @@ RUN --mount=type=cache,target=/opt/uv/cache \
fi \
&& if [ "${INSTALL_RUBIN_PRERELEASE}" = "true" ]; then \
echo "Installing Rubin prerelease requirements..." \
&& /opt/venv/bin/python3 use_existing_torch.py --prefix \
&& /opt/venv/bin/python3 tools/use_existing_torch.py --prefix \
&& uv pip install --python /opt/venv/bin/python3 \
--prerelease=allow --index-strategy unsafe-first-match \
-r /tmp/vllm-requirements/rubin-prerelease.txt \
@@ -243,7 +243,7 @@ RUN --mount=type=cache,target=/opt/uv/cache \
&& uv pip install --python /opt/venv/bin/python3 torch torchaudio torchvision --pre \
--index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') \
&& echo "Installing other requirements..." \
&& /opt/venv/bin/python3 use_existing_torch.py --prefix \
&& /opt/venv/bin/python3 tools/use_existing_torch.py --prefix \
&& uv pip install --python /opt/venv/bin/python3 -r requirements/cuda.txt \
--extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.'); \
else \
@@ -316,12 +316,12 @@ COPY requirements/build/rust.txt requirements/build/rust.txt
RUN --mount=type=cache,target=/opt/uv/cache \
uv pip install --python /opt/venv/bin/python3 -r requirements/build/rust.txt
# Copy only the Rust build inputs; build_rust.sh publishes artifacts needed
# Copy only the Rust build inputs; tools/build_rust.sh publishes artifacts needed
# by the wheel build stage.
COPY rust rust
COPY rust-toolchain.toml rust-toolchain.toml
COPY tools/build_rust.py tools/build_rust.py
COPY build_rust.sh build_rust.sh
COPY tools/build_rust.sh tools/build_rust.sh
# Cap cargo parallelism to avoid exhausting the CI host's open-file limit
# (rustc spawns enough concurrent processes to hit RLIMIT_NOFILE otherwise).
@@ -341,7 +341,7 @@ RUN --mount=type=cache,target=/root/.cargo/registry,sharing=locked \
export RUSTC_WRAPPER=sccache; \
sccache --show-stats; \
fi \
&& SETUPTOOLS_SCM_PRETEND_VERSION="0.0.0+docker.cache" bash build_rust.sh \
&& SETUPTOOLS_SCM_PRETEND_VERSION="0.0.0+docker.cache" bash tools/build_rust.sh \
&& if [ "$USE_SCCACHE" = "1" ]; then \
sccache --show-stats; \
fi
@@ -352,7 +352,7 @@ FROM rust-build-cache AS rust-build
RUN --mount=type=cache,target=/root/.cargo/registry,sharing=locked \
--mount=type=cache,target=/root/.cargo/git,sharing=locked \
--mount=type=bind,source=.git,target=.git \
SETUPTOOLS_SCM_PRETEND_METADATA="{dirty=false}" bash build_rust.sh
SETUPTOOLS_SCM_PRETEND_METADATA="{dirty=false}" bash tools/build_rust.sh
#################### RUST BUILD IMAGE ####################
#################### CSRC BUILD IMAGE ####################
@@ -368,7 +368,7 @@ ARG PYTORCH_NIGHTLY
# Install build dependencies
COPY requirements/build/cuda.txt requirements/build/cuda.txt
COPY use_existing_torch.py use_existing_torch.py
COPY tools/use_existing_torch.py tools/use_existing_torch.py
COPY --from=base /workspace/torch_lib_versions.txt torch_lib_versions.txt
# This timeout (in seconds) is necessary when installing some dependencies via uv since it's likely to time out
@@ -381,11 +381,11 @@ ENV UV_LINK_MODE=copy
RUN --mount=type=cache,target=/opt/uv/cache \
if [ "${INSTALL_RUBIN_PRERELEASE}" = "true" ]; then \
echo "Installing build requirements with Rubin prerelease PyTorch..." \
&& python3 use_existing_torch.py --prefix \
&& python3 tools/use_existing_torch.py --prefix \
&& uv pip install --python /opt/venv/bin/python3 -r requirements/build/cuda.txt; \
elif [ "${PYTORCH_NIGHTLY}" = "1" ]; then \
echo "Installing build requirements without torch..." \
&& python3 use_existing_torch.py --prefix \
&& python3 tools/use_existing_torch.py --prefix \
&& uv pip install --python /opt/venv/bin/python3 -r requirements/build/cuda.txt \
&& echo "Installing torch nightly..." \
&& uv pip install --python /opt/venv/bin/python3 $(cat torch_lib_versions.txt | grep -i "^torch=" | xargs) --pre \
@@ -427,7 +427,7 @@ ENV SETUPTOOLS_SCM_PRETEND_VERSION="0.0.0+csrc.build"
RUN --mount=type=cache,target=/opt/uv/cache \
if [ "${PYTORCH_NIGHTLY}" = "1" ] || \
[ "${INSTALL_RUBIN_PRERELEASE}" = "true" ]; then \
python3 use_existing_torch.py --prefix; \
python3 tools/use_existing_torch.py --prefix; \
fi
# Provision one bare Python per `requires-python` entry; cmake reads
@@ -605,7 +605,7 @@ ARG PYTORCH_NIGHTLY
# Install build dependencies
COPY requirements/build/cuda.txt requirements/build/cuda.txt
COPY use_existing_torch.py use_existing_torch.py
COPY tools/use_existing_torch.py tools/use_existing_torch.py
COPY --from=base /workspace/torch_lib_versions.txt torch_lib_versions.txt
# This timeout (in seconds) is necessary when installing some dependencies via uv since it's likely to time out
@@ -618,11 +618,11 @@ ENV UV_LINK_MODE=copy
RUN --mount=type=cache,target=/opt/uv/cache \
if [ "${INSTALL_RUBIN_PRERELEASE}" = "true" ]; then \
echo "Installing build requirements with Rubin prerelease PyTorch..." \
&& python3 use_existing_torch.py --prefix \
&& python3 tools/use_existing_torch.py --prefix \
&& uv pip install --python /opt/venv/bin/python3 -r requirements/build/cuda.txt; \
elif [ "${PYTORCH_NIGHTLY}" = "1" ]; then \
echo "Installing build requirements without torch..." \
&& python3 use_existing_torch.py --prefix \
&& python3 tools/use_existing_torch.py --prefix \
&& uv pip install --python /opt/venv/bin/python3 -r requirements/build/cuda.txt \
&& echo "Installing torch nightly..." \
&& uv pip install --python /opt/venv/bin/python3 $(cat torch_lib_versions.txt | grep -i "^torch=" | xargs) --pre \
@@ -658,7 +658,7 @@ ENV VLLM_SKIP_PRECOMPILED_VERSION_SUFFIX=1
RUN --mount=type=cache,target=/opt/uv/cache \
if [ "${PYTORCH_NIGHTLY}" = "1" ] || \
[ "${INSTALL_RUBIN_PRERELEASE}" = "true" ]; then \
python3 use_existing_torch.py --prefix; \
python3 tools/use_existing_torch.py --prefix; \
fi \
&& if [ "${INSTALL_RUBIN_PRERELEASE}" = "true" ]; then \
sed -Ei '/^[[:space:]]*(flashinfer-python|nvidia-cutlass-dsl\[cu13\]|quack-kernels)[[:space:]]*==/Id' \
@@ -729,12 +729,12 @@ COPY requirements/lint.txt requirements/lint.txt
COPY requirements/test/cuda.in requirements/test/cuda.in
COPY requirements/test/cuda.txt requirements/test/cuda.txt
COPY requirements/dev.txt requirements/dev.txt
COPY use_existing_torch.py use_existing_torch.py
COPY tools/use_existing_torch.py tools/use_existing_torch.py
COPY --from=base /workspace/torch_lib_versions.txt torch_lib_versions.txt
RUN --mount=type=cache,target=/opt/uv/cache \
if [ "${PYTORCH_NIGHTLY}" = "1" ]; then \
echo "Installing dev requirements plus torch nightly..." \
&& python3 use_existing_torch.py --prefix \
&& python3 tools/use_existing_torch.py --prefix \
&& cat torch_lib_versions.txt >> requirements/test/cuda.in \
&& uv pip compile requirements/test/cuda.in -o requirements/test/cuda.txt --index-strategy unsafe-best-match \
--extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') \
@@ -1143,14 +1143,14 @@ COPY requirements/lint.txt requirements/lint.txt
COPY requirements/test/cuda.in requirements/test/cuda.in
COPY requirements/test/cuda.txt requirements/test/cuda.txt
COPY requirements/dev.txt requirements/dev.txt
COPY use_existing_torch.py use_existing_torch.py
COPY tools/use_existing_torch.py tools/use_existing_torch.py
COPY --from=base /workspace/torch_lib_versions.txt torch_lib_versions.txt
RUN --mount=type=cache,target=/opt/uv/cache \
CUDA_MAJOR="${CUDA_VERSION%%.*}"; \
if [ "$CUDA_MAJOR" -ge 12 ]; then \
if [ "${PYTORCH_NIGHTLY}" = "1" ]; then \
echo "Installing dev requirements plus torch nightly..." \
&& python3 use_existing_torch.py --prefix \
&& python3 tools/use_existing_torch.py --prefix \
&& cat torch_lib_versions.txt >> requirements/test/cuda.in \
&& uv pip compile requirements/test/cuda.in -o requirements/test/cuda.txt --index-strategy unsafe-best-match \
--extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/nightly/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') \
+11 -11
View File
@@ -119,10 +119,10 @@ ARG PYTORCH_CPU_INDEX_BASE_URL=https://download.pytorch.org/whl
# Copy requirements files for installation
COPY requirements/common.txt requirements/common.txt
COPY requirements/cpu.txt requirements/cpu.txt
COPY use_existing_torch.py use_existing_torch.py
COPY tools/use_existing_torch.py tools/use_existing_torch.py
# For nightly: install torch nightly (CPU) first, strip torch pins from the
# requirements via use_existing_torch.py so they can't pull it back to a release
# requirements via tools/use_existing_torch.py so they can't pull it back to a release
# build, then install the rest from the nightly CPU index (no --torch-backend,
# which would force the stable channel). Release path is unchanged.
RUN --mount=type=cache,target=/root/.cache/uv \
@@ -131,7 +131,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
echo "Installing torch nightly (CPU)..." \
&& uv pip install torch torchaudio torchvision torchcodec --pre \
--index-url ${PYTORCH_CPU_INDEX_BASE_URL}/nightly/cpu \
&& python3 use_existing_torch.py --prefix \
&& python3 tools/use_existing_torch.py --prefix \
&& uv pip install -r requirements/cpu.txt \
--extra-index-url ${PYTORCH_CPU_INDEX_BASE_URL}/nightly/cpu; \
else \
@@ -183,12 +183,12 @@ ENV SCCACHE_REGION=${USE_SCCACHE:+${SCCACHE_REGION_NAME}}
# Avoid port collision with vllm-build's own sccache daemon.
ENV SCCACHE_SERVER_PORT=4227
# Copy only the Rust build inputs; build_rust.sh publishes artifacts needed
# Copy only the Rust build inputs; tools/build_rust.sh publishes artifacts needed
# by the wheel build stage.
COPY rust rust
COPY rust-toolchain.toml rust-toolchain.toml
COPY tools/build_rust.py tools/build_rust.py
COPY build_rust.sh build_rust.sh
COPY tools/build_rust.sh tools/build_rust.sh
# Cap cargo parallelism to avoid exhausting the CI host's open-file limit
# (rustc spawns enough concurrent processes to hit RLIMIT_NOFILE otherwise).
@@ -210,10 +210,10 @@ RUN --mount=type=cache,target=/root/.cargo/registry,sharing=locked \
fi; \
sccache --show-stats; \
fi && \
SETUPTOOLS_SCM_PRETEND_VERSION="0.0.0+docker.cache" bash build_rust.sh && \
SETUPTOOLS_SCM_PRETEND_VERSION="0.0.0+docker.cache" bash tools/build_rust.sh && \
if [ "$USE_SCCACHE" = "1" ]; then sccache --show-stats; fi
# build_rust.sh installed rustup here via rustup.rs; put it on PATH so the
# tools/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:${PATH}"
@@ -223,7 +223,7 @@ FROM rust-build-cache AS rust-build
RUN --mount=type=cache,target=/root/.cargo/registry,sharing=locked \
--mount=type=cache,target=/root/.cargo/git,sharing=locked \
--mount=type=bind,source=.git,target=.git \
SETUPTOOLS_SCM_PRETEND_METADATA="{dirty=false}" bash build_rust.sh
SETUPTOOLS_SCM_PRETEND_METADATA="{dirty=false}" bash tools/build_rust.sh
######################### SOURCE PREP IMAGE #########################
# Shared prep (source, rust artifacts, build deps) for both vllm-build and
@@ -262,7 +262,7 @@ COPY requirements/build/cpu.txt requirements/build/cpu.txt
RUN --mount=type=cache,target=/root/.cache/uv \
if [ "${PYTORCH_NIGHTLY}" = "1" ]; then \
python3 /workspace/use_existing_torch.py --prefix \
python3 /workspace/tools/use_existing_torch.py --prefix \
&& uv pip install -r requirements/build/cpu.txt \
--extra-index-url ${PYTORCH_CPU_INDEX_BASE_URL}/nightly/cpu; \
else \
@@ -287,7 +287,7 @@ RUN if [ "$GIT_REPO_CHECK" != 0 ]; then bash tools/check_repo.sh ; fi
# now-unpinned dependency. Done at the end of vllm-src so vllm-build and
# vllm-dev, which both derive from it, inherit the unpinned tree.
RUN if [ "${PYTORCH_NIGHTLY}" = "1" ]; then \
python3 /workspace/use_existing_torch.py --prefix; \
python3 /workspace/tools/use_existing_torch.py --prefix; \
fi
######################### BUILD IMAGE #########################
@@ -343,7 +343,7 @@ RUN case "$(uname -m)" in \
RUN --mount=type=cache,target=/root/.cache/uv \
export CFLAGS="${CFLAGS:+${CFLAGS} }-std=gnu17" && \
if [ "${PYTORCH_NIGHTLY}" = "1" ]; then \
python3 /workspace/use_existing_torch.py --prefix \
python3 /workspace/tools/use_existing_torch.py --prefix \
&& uv pip install -r requirements/test/cpu.txt \
--extra-index-url ${PYTORCH_CPU_INDEX_BASE_URL}/nightly/cpu; \
else \
+2 -2
View File
@@ -36,10 +36,10 @@ COPY pyproject.toml ./
# The script is expected to install whatever python dependencies are missing
# as well as whatever system libraries need to be installed from source
COPY build_vllm_*.sh ./
COPY docker/build_vllm_*.sh docker/
RUN --mount=type=cache,target=/root/.cache/uv \
sh ./build_vllm_$(uname -m).sh
sh ./docker/build_vllm_$(uname -m).sh
# copy vllm source code to build cache
COPY . .
+6 -6
View File
@@ -171,7 +171,7 @@ COPY rust/proto /rust-input/vllm/rust/proto
COPY rust/src /rust-input/vllm/rust/src
COPY rust-toolchain.toml /rust-input/vllm/rust-toolchain.toml
COPY tools/build_rust.py /rust-input/vllm/tools/build_rust.py
COPY build_rust.sh /rust-input/vllm/build_rust.sh
COPY tools/build_rust.sh /rust-input/vllm/tools/build_rust.sh
FROM base AS rust_input_1
ARG VLLM_REPO
@@ -188,7 +188,7 @@ RUN git clone --no-checkout --filter=blob:none ${VLLM_REPO} /rust-input/vllm \
rust/src/** \
rust-toolchain.toml \
tools/build_rust.py \
build_rust.sh \
tools/build_rust.sh \
&& git checkout FETCH_HEAD
FROM rust_input_${REMOTE_VLLM} AS rust-input
@@ -244,7 +244,7 @@ RUN --mount=type=cache,id=vllm-rocm-uv,target=/root/.cache/uv \
COPY --from=rust-input /rust-input/vllm/rust rust
COPY --from=rust-input /rust-input/vllm/rust-toolchain.toml rust-toolchain.toml
COPY --from=rust-input /rust-input/vllm/tools/build_rust.py tools/build_rust.py
COPY --from=rust-input /rust-input/vllm/build_rust.sh build_rust.sh
COPY --from=rust-input /rust-input/vllm/tools/build_rust.sh tools/build_rust.sh
COPY --from=vllm-version /vllm-version.txt /tmp/vllm-version.txt
# Build the release binary. Cargo's registry/git caches can be written by
@@ -258,7 +258,7 @@ RUN --mount=type=cache,id=vllm-rocm-cargo-registry,target=/root/.cargo/registry,
&& sccache --show-stats; \
fi \
&& export SETUPTOOLS_SCM_PRETEND_VERSION="$(cat /tmp/vllm-version.txt)" \
&& bash build_rust.sh \
&& bash tools/build_rust.sh \
&& test -x vllm/vllm-rs \
&& if [ "$USE_SCCACHE" = "1" ]; then \
sccache --show-stats; \
@@ -368,7 +368,7 @@ COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/requirements /requirements
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/benchmarks /benchmarks
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/tests /tests
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/examples /examples
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/scripts/benchmark_helion_kernels.py /scripts/benchmark_helion_kernels.py
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/tools/benchmark_helion_kernels.py /tools/benchmark_helion_kernels.py
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/tools/install_torchcodec_rocm.sh /tools/install_torchcodec_rocm.sh
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/docker/Dockerfile /docker/Dockerfile
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/docker/Dockerfile.cpu /docker/Dockerfile.cpu
@@ -729,7 +729,7 @@ COPY --from=build_vllm_wheel_release ${COMMON_WORKDIR}/vllm/requirements /requir
COPY --from=build_vllm_wheel_release ${COMMON_WORKDIR}/vllm/benchmarks /benchmarks
COPY --from=build_vllm_wheel_release ${COMMON_WORKDIR}/vllm/tests /tests
COPY --from=build_vllm_wheel_release ${COMMON_WORKDIR}/vllm/examples /examples
COPY --from=build_vllm_wheel_release ${COMMON_WORKDIR}/vllm/scripts/benchmark_helion_kernels.py /scripts/benchmark_helion_kernels.py
COPY --from=build_vllm_wheel_release ${COMMON_WORKDIR}/vllm/tools/benchmark_helion_kernels.py /tools/benchmark_helion_kernels.py
COPY --from=build_vllm_wheel_release ${COMMON_WORKDIR}/vllm/tools/install_torchcodec_rocm.sh /tools/install_torchcodec_rocm.sh
COPY --from=build_vllm_wheel_release ${COMMON_WORKDIR}/vllm/docker/Dockerfile /docker/Dockerfile
COPY --from=build_vllm_wheel_release ${COMMON_WORKDIR}/vllm/docker/Dockerfile.cpu /docker/Dockerfile.cpu
+4 -6
View File
@@ -171,7 +171,7 @@ COPY rust/proto /rust-input/vllm/rust/proto
COPY rust/src /rust-input/vllm/rust/src
COPY rust-toolchain.toml /rust-input/vllm/rust-toolchain.toml
COPY tools/build_rust.py /rust-input/vllm/tools/build_rust.py
COPY build_rust.sh /rust-input/vllm/build_rust.sh
COPY tools/build_rust.sh /rust-input/vllm/tools/build_rust.sh
FROM base AS rust_input_1
ARG VLLM_REPO
@@ -188,7 +188,7 @@ RUN git clone --no-checkout --filter=blob:none ${VLLM_REPO} /rust-input/vllm \
rust/src/** \
rust-toolchain.toml \
tools/build_rust.py \
build_rust.sh \
tools/build_rust.sh \
&& git checkout FETCH_HEAD
FROM rust_input_${REMOTE_VLLM} AS rust-input
@@ -244,7 +244,7 @@ RUN --mount=type=cache,id=vllm-rocm-uv,target=/root/.cache/uv \
COPY --from=rust-input /rust-input/vllm/rust rust
COPY --from=rust-input /rust-input/vllm/rust-toolchain.toml rust-toolchain.toml
COPY --from=rust-input /rust-input/vllm/tools/build_rust.py tools/build_rust.py
COPY --from=rust-input /rust-input/vllm/build_rust.sh build_rust.sh
COPY --from=rust-input /rust-input/vllm/tools/build_rust.sh tools/build_rust.sh
COPY --from=vllm-version /vllm-version.txt /tmp/vllm-version.txt
# Build the release binary. Cargo's registry/git caches can be written by
@@ -258,7 +258,7 @@ RUN --mount=type=cache,id=vllm-rocm-cargo-registry,target=/root/.cargo/registry,
&& sccache --show-stats; \
fi \
&& export SETUPTOOLS_SCM_PRETEND_VERSION="$(cat /tmp/vllm-version.txt)" \
&& bash build_rust.sh \
&& bash tools/build_rust.sh \
&& test -x vllm/vllm-rs \
&& if [ "$USE_SCCACHE" = "1" ]; then \
sccache --show-stats; \
@@ -366,7 +366,6 @@ COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/requirements /requirements
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/benchmarks /benchmarks
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/tests /tests
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/examples /examples
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/scripts/benchmark_helion_kernels.py /scripts/benchmark_helion_kernels.py
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/tools /tools
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/docker/Dockerfile /docker/Dockerfile
COPY --from=build_vllm ${COMMON_WORKDIR}/vllm/docker/Dockerfile.cpu /docker/Dockerfile.cpu
@@ -749,7 +748,6 @@ COPY --from=build_vllm_wheel_release ${COMMON_WORKDIR}/vllm/requirements /requir
COPY --from=build_vllm_wheel_release ${COMMON_WORKDIR}/vllm/benchmarks /benchmarks
COPY --from=build_vllm_wheel_release ${COMMON_WORKDIR}/vllm/tests /tests
COPY --from=build_vllm_wheel_release ${COMMON_WORKDIR}/vllm/examples /examples
COPY --from=build_vllm_wheel_release ${COMMON_WORKDIR}/vllm/scripts/benchmark_helion_kernels.py /scripts/benchmark_helion_kernels.py
COPY --from=build_vllm_wheel_release ${COMMON_WORKDIR}/vllm/tools /tools
COPY --from=build_vllm_wheel_release ${COMMON_WORKDIR}/vllm/docker/Dockerfile /docker/Dockerfile
COPY --from=build_vllm_wheel_release ${COMMON_WORKDIR}/vllm/docker/Dockerfile.cpu /docker/Dockerfile.cpu
+1 -1
View File
@@ -166,7 +166,7 @@ RUN --mount=type=cache,id=vllm-rocm-cargo-registry,target=/root/.cargo/registry,
--mount=type=cache,id=vllm-rocm-cargo-git,target=/root/.cargo/git,sharing=locked \
cd ${COMMON_WORKDIR}/vllm \
&& export SETUPTOOLS_SCM_PRETEND_VERSION="$(cat /tmp/vllm-version.txt)" \
&& bash build_rust.sh \
&& bash tools/build_rust.sh \
&& test -x vllm/vllm-rs
# -----------------------
+4 -4
View File
@@ -14,12 +14,12 @@ WORKDIR /workspace
COPY requirements/build/rust.txt requirements/build/rust.txt
RUN python3 -m pip install --no-cache-dir -r requirements/build/rust.txt
# Copy only the Rust build inputs; build_rust.sh publishes artifacts needed
# Copy only the Rust build inputs; tools/build_rust.sh publishes artifacts needed
# by the wheel build stage.
COPY rust rust
COPY rust-toolchain.toml rust-toolchain.toml
COPY tools/build_rust.py tools/build_rust.py
COPY build_rust.sh build_rust.sh
COPY tools/build_rust.sh tools/build_rust.sh
# Cap cargo parallelism to avoid exhausting the CI host's open-file limit
# (rustc spawns enough concurrent processes to hit RLIMIT_NOFILE otherwise).
@@ -29,7 +29,7 @@ ENV CARGO_BUILD_JOBS=4
# inputs. The child stage below relinks the crates that embed the exact version.
RUN --mount=type=cache,target=/root/.cargo/registry,sharing=locked \
--mount=type=cache,target=/root/.cargo/git,sharing=locked \
SETUPTOOLS_SCM_PRETEND_VERSION="0.0.0+docker.cache" bash build_rust.sh
SETUPTOOLS_SCM_PRETEND_VERSION="0.0.0+docker.cache" bash tools/build_rust.sh
# Relink with the exact Git-derived package version.
FROM rust-build-cache AS rust-build
@@ -37,7 +37,7 @@ FROM rust-build-cache AS rust-build
RUN --mount=type=cache,target=/root/.cargo/registry,sharing=locked \
--mount=type=cache,target=/root/.cargo/git,sharing=locked \
--mount=type=bind,source=.git,target=.git \
SETUPTOOLS_SCM_PRETEND_METADATA="{dirty=false}" bash build_rust.sh
SETUPTOOLS_SCM_PRETEND_METADATA="{dirty=false}" bash tools/build_rust.sh
FROM ubuntu:24.04 AS vllm-base
+241
View File
@@ -0,0 +1,241 @@
#!/bin/bash
set -eoux pipefail
########################################
# Resolve repo root (IMPORTANT)
########################################
REPO_ROOT="$(pwd)"
cd "$REPO_ROOT"
########################################
# DevPI configuration
########################################
IBM_DEVPI_URL=${IBM_DEVPI_URL:-"https://wheels.developerfirst.ibm.com/ppc64le/linux/+simple/"}
RHOAI_INDEX_URL=${RHOAI_INDEX_URL:-"https://console.redhat.com/api/pypi/public-rhai/rhoai/3.4/cpu-ubi9/simple/"}
########################################
# wheel dir
########################################
WHEEL_DIR=${WHEEL_DIR:-"/tmp/wheels"}
mkdir -p "$WHEEL_DIR"
########################################
# Helpers
########################################
try_install_from_devpi() {
local pkg=$1
uv pip install \
--extra-index-url "${IBM_DEVPI_URL}" \
--index-strategy unsafe-best-match \
--no-build-isolation \
"${pkg}"
}
########################################
# Package Versions
########################################
cd "$REPO_ROOT"
TORCH_VERSION=${TORCH_VERSION:-$(grep -E '^torch==.+==\s*"ppc64le"' requirements/cpu.txt | grep -Eo '\b[0-9\.]+\b' || true)}
TORCH_VERSION=${TORCH_VERSION:-2.11.0}
TORCHVISION_VERSION=${TORCHVISION_VERSION:-0.26.0}
TORCHAUDIO_VERSION=${TORCHAUDIO_VERSION:-${TORCH_VERSION}}
export TORCH_VERSION
export TORCHVISION_VERSION
export TORCHAUDIO_VERSION
export OPENCV_VERSION=${OPENCV_VERSION:-4.13.0.92}
export XGRAMMAR_VERSION=${XGRAMMAR_VERSION:-0.2.1}
########################################
# install system dependencies
########################################
rpm -ivh https://dl.fedoraproject.org/pub/epel/epel-release-latest-9.noarch.rpm || true
microdnf install -y \
python3.12 python3.12-devel python3.12-pip gcc \
git jq gcc-toolset-14 gcc-toolset-14-libatomic-devel \
automake libtool clang-devel openssl-devel \
harfbuzz-devel kmod lcms2-devel libimagequant-devel libjpeg-turbo-devel \
llvm15-devel libraqm-devel libtiff-devel libwebp-devel libxcb-devel \
ninja-build openjpeg2-devel pkgconfig \
tcl-devel tk-devel xsimd-devel zeromq-devel zlib-devel patchelf file openblas openblas-devel protobuf numactl numactl-devel openmpi openmpi-devel
rpm -ivh --nodeps \
https://mirror.stream.centos.org/9-stream/CRB/ppc64le/os/Packages/protobuf-lite-devel-3.14.0-17.el9.ppc64le.rpm
rpm -ivh --nodeps \
https://mirror.stream.centos.org/9-stream/CRB/ppc64le/os/Packages/protobuf-devel-3.14.0-17.el9.ppc64le.rpm
rpm -ivh --nodeps \
https://mirror.stream.centos.org/9-stream/CRB/ppc64le/os/Packages/protobuf-compiler-3.14.0-17.el9.ppc64le.rpm
########################################
# Python 3.12 virtual environment
########################################
python3.12 -m venv /opt/vllm
source /opt/vllm/bin/activate
export PATH=/opt/vllm/bin:$PATH
python --version
########################################
# install build tools (stable uv)
########################################
pip install -U pip setuptools-rust
pip install uv
pip install "setuptools<70" build wheel cmake auditwheel
uv pip install "setuptools<70" cython meson-python pybind11 "sympy>=1.13.3" --no-build-isolation
########################################
# Rust
########################################
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
source /root/.cargo/env
########################################
# Compiler env
########################################
source /opt/rh/gcc-toolset-14/enable
export PATH=/usr/lib64/llvm15/bin:$PATH
export LLVM_CONFIG=/usr/lib64/llvm15/bin/llvm-config
export CMAKE_ARGS="-DPython3_EXECUTABLE=python"
export MAX_JOBS=${MAX_JOBS:-$(nproc)}
export GRPC_PYTHON_BUILD_SYSTEM_OPENSSL=1
########################################
# Install Packages From Devpi
########################################
uv pip install numpy==2.3.5 pillow==12.2.0 --extra-index-url "$IBM_DEVPI_URL"
try_install_from_devpi "opencv-python-headless==${OPENCV_VERSION}"
try_install_from_devpi "torch==${TORCH_VERSION}"
try_install_from_devpi "torchvision==${TORCHVISION_VERSION}"
########################################
# torch audio
########################################
TEMP_BUILD_DIR=$(mktemp -d)
cd "${TEMP_BUILD_DIR}"
export BUILD_SOX=1 BUILD_KALDI=1 BUILD_RNNT=1 USE_FFMPEG=0 USE_ROCM=0 USE_CUDA=0
export TORCHAUDIO_TEST_ALLOW_SKIP_IF_NO_FFMPEG=1
git clone --recursive https://github.com/pytorch/audio.git -b "v${TORCHAUDIO_VERSION}"
cd audio
#patching
sed -i '
s|_CSRC_DIR / "_torchaudio.cpp"|str(_CSRC_DIR / "_torchaudio.cpp")|;
s|_CSRC_DIR / "utils.cpp"|str(_CSRC_DIR / "utils.cpp")|;
s|sources=\[_CSRC_DIR / s for s in sources\]|sources=[str(_CSRC_DIR / s) for s in sources]|;
' tools/setup_helpers/extension.py
MAX_JOBS=${MAX_JOBS:-$(nproc)} \
BUILD_VERSION=${TORCHAUDIO_VERSION} \
uv build --wheel --out-dir "${WHEEL_DIR}" --no-build-isolation
uv pip install "${WHEEL_DIR}"/torchaudio*.whl
cd "${REPO_ROOT}"
rm -rf "${TEMP_BUILD_DIR}"
########################################
# Xgrammar
########################################
uv pip install \
"scikit-build-core==0.11.6" \
"pyproject-metadata<0.8" \
pathspec \
packaging \
distro \
"setuptools<70" \
setuptools_scm \
cmake \
ninja \
pybind11 \
nanobind
uv pip install apache-tvm-ffi==0.1.12 \
--no-build-isolation \
--no-cache
TEMP_BUILD_DIR=$(mktemp -d)
pushd "${TEMP_BUILD_DIR}"
export CFLAGS="-fno-lto -mcpu=power9"
export CXXFLAGS="-fno-lto -mcpu=power9"
export LDFLAGS="-fno-lto"
export PATH=/opt/vllm/bin:$PATH
export Python_EXECUTABLE=/opt/vllm/bin/python3
export Python3_EXECUTABLE=/opt/vllm/bin/python3
export PYTHON_EXECUTABLE=/opt/vllm/bin/python3
export Python_ROOT_DIR=/opt/vllm
export Python3_ROOT_DIR=/opt/vllm
git clone \
--recursive \
https://github.com/mlc-ai/xgrammar \
-b "v${XGRAMMAR_VERSION}"
cd xgrammar
cp cmake/config.cmake .
export PYTHONPATH=/opt/vllm/lib64/python3.12/site-packages:/opt/vllm/lib/python3.12/site-packages:${PYTHONPATH:-}
uv build \
--wheel \
--out-dir "${WHEEL_DIR}" \
--no-build-isolation
uv pip install "${WHEEL_DIR}"/xgrammar*.whl -v
popd
rm -rf "${TEMP_BUILD_DIR}"
cd "${REPO_ROOT}"
########################################
# RHOAI Binary Downloads
########################################
pip download \
--index-url "${RHOAI_INDEX_URL}" \
--only-binary=:all: \
--no-deps \
llvmlite==0.47.0 \
-d "${WHEEL_DIR}"
pip download \
--index-url "${RHOAI_INDEX_URL}" \
--only-binary=:all: \
--no-deps \
Numba==0.65.0 \
-d "${WHEEL_DIR}"
########################################
# install built wheels
########################################
uv pip install setuptools_scm maturin setuptools-rust ninja scikit-build-core pybind11 nanobind \
--no-build-isolation
uv pip install "${WHEEL_DIR}"/*.whl
########################################
# install remaining deps
########################################
sed -i.bak -e 's/.*torch.*//g' pyproject.toml requirements/*.txt
uv pip install "setuptools>=78.1.1" --no-build-isolation
export PKG_CONFIG_PATH=/usr/local/lib/pkgconfig:/usr/local/lib64/pkgconfig:/usr/lib64/pkgconfig
uv pip install -r requirements/common.txt \
-r requirements/cpu.txt \
-r requirements/build/cpu.txt --index-strategy unsafe-best-match