Skip to content

[CI/Build] Use uv python for docker rather than ppa:deadsnakes/ppa #13569

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Mar 6, 2025
Merged

[CI/Build] Use uv python for docker rather than ppa:deadsnakes/ppa #13569

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
73102bb
[CI/Build] Use uv in the Dockerfile
mgoin Feb 19, 2025
cf28e17
Updates
mgoin Feb 19, 2025
3b00185
Use uv python for Docker
mgoin Feb 19, 2025
c926def
Merge branch 'main' into use-uv-python-for-docker
mgoin Feb 20, 2025
1fe1e31
Merge branch 'main' into use-uv-python-for-docker
mgoin Mar 5, 2025
8a13dec
Fix flashinfer install
mgoin Mar 5, 2025
11802b5
Prunes and fixes
mgoin Mar 6, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
82 changes: 38 additions & 44 deletions Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,22 +14,19 @@ ARG PYTHON_VERSION=3.12
ARG TARGETPLATFORM
ENV DEBIAN_FRONTEND=noninteractive

# Install Python and other dependencies
# Install minimal dependencies and uv
RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
&& echo 'tzdata tzdata/Zones/America select Los_Angeles' | debconf-set-selections \
&& apt-get update -y \
&& apt-get install -y ccache software-properties-common git curl sudo \
&& add-apt-repository ppa:deadsnakes/ppa \
&& apt-get update -y \
&& apt-get install -y python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python${PYTHON_VERSION}-venv \
&& update-alternatives --install /usr/bin/python3 python3 /usr/bin/python${PYTHON_VERSION} 1 \
&& update-alternatives --set python3 /usr/bin/python${PYTHON_VERSION} \
&& ln -sf /usr/bin/python${PYTHON_VERSION}-config /usr/bin/python3-config \
&& curl -sS https://bootstrap.pypa.io/get-pip.py | python${PYTHON_VERSION} \
&& python3 --version && python3 -m pip --version
# Install uv for faster pip installs
RUN --mount=type=cache,target=/root/.cache/uv \
python3 -m pip install uv
&& apt-get install -y ccache git curl wget sudo \
&& curl -LsSf https://astral.sh/uv/install.sh | sh

# Add uv to PATH
ENV PATH="/root/.local/bin:$PATH"
# Create venv with specified Python and activate by placing at the front of path
ENV VIRTUAL_ENV="/opt/venv"
RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
ENV PATH="$VIRTUAL_ENV/bin:$PATH"

# Upgrade to GCC 10 to avoid https://gcc.gnu.org/bugzilla/show_bug.cgi?id=92519
# as it was causing spam when compiling the CUTLASS kernels
Expand All @@ -47,21 +44,19 @@ RUN ldconfig /usr/local/cuda-$(echo $CUDA_VERSION | cut -d. -f1,2)/compat/

WORKDIR /workspace

# install build and runtime dependencies

# arm64 (GH200) build follows the practice of "use existing pytorch" build,
# we need to install torch and torchvision from the nightly builds first,
# pytorch will not appear as a vLLM dependency in all of the following steps
# after this step
RUN --mount=type=cache,target=/root/.cache/uv \
if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
uv pip install --system --index-url https://download.pytorch.org/whl/nightly/cu126 "torch==2.7.0.dev20250121+cu126" "torchvision==0.22.0.dev20250121"; \
uv pip install --index-url https://download.pytorch.org/whl/nightly/cu126 "torch==2.7.0.dev20250121+cu126" "torchvision==0.22.0.dev20250121"; \
fi

COPY requirements-common.txt requirements-common.txt
COPY requirements-cuda.txt requirements-cuda.txt
RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install --system -r requirements-cuda.txt
uv pip install -r requirements-cuda.txt

# cuda arch list used by torch
# can be useful for both `dev` and `test`
Expand All @@ -82,12 +77,12 @@ ARG TARGETPLATFORM
COPY requirements-build.txt requirements-build.txt

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

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

# max jobs used by Ninja to build extensions
ARG max_jobs=2
Expand Down Expand Up @@ -124,6 +119,9 @@ 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 && \
python3 setup.py bdist_wheel --dist-dir=dist --py-limited-api=cp38; \
fi

Expand All @@ -147,7 +145,7 @@ COPY requirements-lint.txt requirements-lint.txt
COPY requirements-test.txt requirements-test.txt
COPY requirements-dev.txt requirements-dev.txt
RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install --system -r requirements-dev.txt
uv pip install -r requirements-dev.txt
#################### DEV IMAGE ####################

#################### vLLM installation IMAGE ####################
Expand All @@ -163,23 +161,20 @@ ARG TARGETPLATFORM
RUN PYTHON_VERSION_STR=$(echo ${PYTHON_VERSION} | sed 's/\.//g') && \
echo "export PYTHON_VERSION_STR=${PYTHON_VERSION_STR}" >> /etc/environment

# Install Python and other dependencies
# Install minimal dependencies and uv
RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
&& echo 'tzdata tzdata/Zones/America select Los_Angeles' | debconf-set-selections \
&& apt-get update -y \
&& apt-get install -y ccache software-properties-common git curl wget sudo vim python3-pip \
&& apt-get install -y ffmpeg libsm6 libxext6 libgl1 \
&& add-apt-repository ppa:deadsnakes/ppa \
&& apt-get update -y \
&& apt-get install -y python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python${PYTHON_VERSION}-venv libibverbs-dev \
&& update-alternatives --install /usr/bin/python3 python3 /usr/bin/python${PYTHON_VERSION} 1 \
&& update-alternatives --set python3 /usr/bin/python${PYTHON_VERSION} \
&& ln -sf /usr/bin/python${PYTHON_VERSION}-config /usr/bin/python3-config \
&& curl -sS https://bootstrap.pypa.io/get-pip.py | python${PYTHON_VERSION} \
&& python3 --version && python3 -m pip --version
# Install uv for faster pip installs
RUN --mount=type=cache,target=/root/.cache/uv \
python3 -m pip install uv
&& apt-get install -y ccache git curl wget sudo vim \
&& apt-get install -y ffmpeg libsm6 libxext6 libgl1 libibverbs-dev \
&& curl -LsSf https://astral.sh/uv/install.sh | sh

# Add uv to PATH
ENV PATH="/root/.local/bin:$PATH"
# Create venv with specified Python and activate by placing at the front of path
ENV VIRTUAL_ENV="/opt/venv"
RUN uv venv --python ${PYTHON_VERSION} --seed ${VIRTUAL_ENV}
ENV PATH="$VIRTUAL_ENV/bin:$PATH"

# Workaround for https://github.com/openai/triton/issues/2507 and
# https://github.com/pytorch/pytorch/issues/107960 -- hopefully
Expand All @@ -193,13 +188,13 @@ RUN ldconfig /usr/local/cuda-$(echo $CUDA_VERSION | cut -d. -f1,2)/compat/
# after this step
RUN --mount=type=cache,target=/root/.cache/uv \
if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
uv pip install --system --index-url https://download.pytorch.org/whl/nightly/cu124 "torch==2.6.0.dev20241210+cu124" "torchvision==0.22.0.dev20241215"; \
uv pip install --index-url https://download.pytorch.org/whl/nightly/cu124 "torch==2.6.0.dev20241210+cu124" "torchvision==0.22.0.dev20241215"; \
fi

# Install vllm wheel first, so that torch etc will be installed.
RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist \
--mount=type=cache,target=/root/.cache/uv \
uv pip install --system dist/*.whl --verbose
uv pip install dist/*.whl --verbose

# If we need to build FlashInfer wheel before its release:
# $ export FLASHINFER_ENABLE_AOT=1
Expand All @@ -214,9 +209,8 @@ RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist
# $ # upload the wheel to a public location, e.g. https://wheels.vllm.ai/flashinfer/524304395bd1d8cd7d07db083859523fcaa246a4/flashinfer_python-0.2.1.post1+cu124torch2.5-cp38-abi3-linux_x86_64.whl

RUN --mount=type=cache,target=/root/.cache/uv \
. /etc/environment && \
if [ "$TARGETPLATFORM" != "linux/arm64" ]; then \
uv pip install --system https://github.com/flashinfer-ai/flashinfer/releases/download/v0.2.1.post1/flashinfer_python-0.2.1.post1+cu124torch2.5-cp38-abi3-linux_x86_64.whl ; \
uv pip install https://github.com/flashinfer-ai/flashinfer/releases/download/v0.2.1.post1/flashinfer_python-0.2.1.post1+cu124torch2.5-cp38-abi3-linux_x86_64.whl ; \
fi
COPY examples examples

Expand All @@ -226,7 +220,7 @@ COPY examples examples
# TODO: Remove this once FlashInfer AOT wheel is fixed
COPY requirements-build.txt requirements-build.txt
RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install --system -r requirements-build.txt
uv pip install -r requirements-build.txt

#################### vLLM installation IMAGE ####################

Expand All @@ -239,15 +233,15 @@ ADD . /vllm-workspace/

# install development dependencies (for testing)
RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install --system -r requirements-dev.txt
uv pip install -r requirements-dev.txt

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

# enable fast downloads from hf (for testing)
RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install --system hf_transfer
uv pip install hf_transfer
ENV HF_HUB_ENABLE_HF_TRANSFER 1

# Copy in the v1 package for testing (it isn't distributed yet)
Expand All @@ -268,9 +262,9 @@ FROM vllm-base AS vllm-openai-base
# install additional dependencies for openai api server
RUN --mount=type=cache,target=/root/.cache/uv \
if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
uv pip install --system accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.42.0' 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3]; \
uv pip install accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.42.0' 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3]; \
else \
uv pip install --system accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.45.0' 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3]; \
uv pip install accelerate hf_transfer 'modelscope!=1.15.0' 'bitsandbytes>=0.45.0' 'timm==0.9.10' boto3 runai-model-streamer runai-model-streamer[s3]; \
fi

ENV VLLM_USAGE_SOURCE production-docker-image
Expand Down