Skip to content

GitLab

Unverified Commit 3c545c0c authored by Fabien Dupont's avatar Fabien Dupont Committed by GitHub
Browse files

[CI/Build] Allow hermetic builds (#18064) 


Signed-off-by: default avatarFabien Dupont <fdupont@redhat.com>
Signed-off-by: default avatarTyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: default avatarFabien Dupont <fabiendupont@pm.me>
Signed-off-by: default avatarHarry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: default avatarTyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: default avatarElias Levy <eliaslevy@google.com>
Co-authored-by: default avatarHarry Mellor <19981378+hmellor@users.noreply.github.com>
parent e8c3bd2c
Show whitespace changes
Inline Side-by-side
Showing with 158 additions and 30 deletions
docker/Dockerfile
View file @ 3c545c0c
...@@ -6,30 +6,106 @@ ...@@ -6,30 +6,106 @@
# docs/assets/contributing/dockerfile-stages-dependency.png # docs/assets/contributing/dockerfile-stages-dependency.png
ARG CUDA_VERSION=12.8.1 ARG CUDA_VERSION=12.8.1
ARG PYTHON_VERSION=3.12
# By parameterizing the base images, we allow third-party to use their own
# base images. One use case is hermetic builds with base images stored in
# private registries that use a different repository naming conventions.
#
# Example:
# docker build --build-arg BUILD_BASE_IMAGE=registry.acme.org/mirror/nvidia/cuda:${CUDA_VERSION}-devel-ubuntu20.04
ARG BUILD_BASE_IMAGE=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu20.04
ARG FINAL_BASE_IMAGE=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu22.04
# By parameterizing the Deadsnakes repository URL, we allow third-party to use
# their own mirror. When doing so, we don't benefit from the transparent
# installation of the GPG key of the PPA, as done by add-apt-repository, so we
# also need a URL for the GPG key.
ARG DEADSNAKES_MIRROR_URL
ARG DEADSNAKES_GPGKEY_URL
# The PyPA get-pip.py script is a self contained script+zip file, that provides
# both the installer script and the pip base85-encoded zip archive. This allows
# bootstrapping pip in environment where a dsitribution package does not exist.
#
# By parameterizing the URL for get-pip.py installation script, we allow
# third-party to use their own copy of the script stored in a private mirror.
# We set the default value to the PyPA owned get-pip.py script.
#
# Reference: https://pip.pypa.io/en/stable/installation/#get-pip-py
ARG GET_PIP_URL="https://bootstrap.pypa.io/get-pip.py"
# PIP supports fetching the packages from custom indexes, allowing third-party
# to host the packages in private mirrors. The PIP_INDEX_URL and
# PIP_EXTRA_INDEX_URL are standard PIP environment variables to override the
# default indexes. By letting them empty by default, PIP will use its default
# indexes if the build process doesn't override the indexes.
#
# Uv uses different variables. We set them by default to the same values as
# PIP, but they can be overridden.
ARG PIP_INDEX_URL
ARG PIP_EXTRA_INDEX_URL
ARG UV_INDEX_URL=${PIP_INDEX_URL}
ARG UV_EXTRA_INDEX_URL=${PIP_EXTRA_INDEX_URL}
# PyTorch provides its own indexes for standard and nightly builds
ARG PYTORCH_CUDA_INDEX_BASE_URL=https://download.pytorch.org/whl
ARG PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL=https://download.pytorch.org/whl/nightly
# PIP supports multiple authentication schemes, including keyring
# By parameterizing the PIP_KEYRING_PROVIDER variable and setting it to
# disabled by default, we allow third-party to use keyring authentication for
# their private Python indexes, while not changing the default behavior which
# is no authentication.
#
# Reference: https://pip.pypa.io/en/stable/topics/authentication/#keyring-support
ARG PIP_KEYRING_PROVIDER=disabled
ARG UV_KEYRING_PROVIDER=${PIP_KEYRING_PROVIDER}
#################### BASE BUILD IMAGE #################### #################### BASE BUILD IMAGE ####################
# prepare basic build environment # prepare basic build environment
FROM nvidia/cuda:${CUDA_VERSION}-devel-ubuntu20.04 AS base FROM ${BUILD_BASE_IMAGE} AS base
ARG CUDA_VERSION=12.8.1 ARG CUDA_VERSION
ARG PYTHON_VERSION=3.12 ARG PYTHON_VERSION
ARG TARGETPLATFORM ARG TARGETPLATFORM
ENV DEBIAN_FRONTEND=noninteractive ENV DEBIAN_FRONTEND=noninteractive
ARG DEADSNAKES_MIRROR_URL
ARG DEADSNAKES_GPGKEY_URL
ARG GET_PIP_URL
# Install Python and other dependencies # Install Python and other dependencies
RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \ RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
&& echo 'tzdata tzdata/Zones/America select Los_Angeles' | debconf-set-selections \ && echo 'tzdata tzdata/Zones/America select Los_Angeles' | debconf-set-selections \
&& apt-get update -y \ && apt-get update -y \
&& apt-get install -y ccache software-properties-common git curl sudo \ && apt-get install -y ccache software-properties-common git curl sudo \
&& for i in 1 2 3; do \ && if [ ! -z ${DEADSNAKES_MIRROR_URL} ] ; then \
if [ ! -z "${DEADSNAKES_GPGKEY_URL}" ] ; then \
mkdir -p -m 0755 /etc/apt/keyrings ; \
curl -L ${DEADSNAKES_GPGKEY_URL} | gpg --dearmor > /etc/apt/keyrings/deadsnakes.gpg ; \
sudo chmod 644 /etc/apt/keyrings/deadsnakes.gpg ; \
echo "deb [signed-by=/etc/apt/keyrings/deadsnakes.gpg] ${DEADSNAKES_MIRROR_URL} $(lsb_release -cs) main" > /etc/apt/sources.list.d/deadsnakes.list ; \
fi ; \
else \
for i in 1 2 3; do \
add-apt-repository -y ppa:deadsnakes/ppa && break || \ add-apt-repository -y ppa:deadsnakes/ppa && break || \
{ echo "Attempt $i failed, retrying in 5s..."; sleep 5; }; \ { echo "Attempt $i failed, retrying in 5s..."; sleep 5; }; \
done \ done ; \
fi \
&& apt-get update -y \ && apt-get update -y \
&& apt-get install -y python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python${PYTHON_VERSION}-venv \ && 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 --install /usr/bin/python3 python3 /usr/bin/python${PYTHON_VERSION} 1 \
&& update-alternatives --set python3 /usr/bin/python${PYTHON_VERSION} \ && update-alternatives --set python3 /usr/bin/python${PYTHON_VERSION} \
&& ln -sf /usr/bin/python${PYTHON_VERSION}-config /usr/bin/python3-config \ && ln -sf /usr/bin/python${PYTHON_VERSION}-config /usr/bin/python3-config \
&& curl -sS https://bootstrap.pypa.io/get-pip.py | python${PYTHON_VERSION} \ && curl -sS ${GET_PIP_URL} | python${PYTHON_VERSION} \
&& python3 --version && python3 -m pip --version && python3 --version && python3 -m pip --version
ARG PIP_INDEX_URL UV_INDEX_URL
ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
ARG PYTORCH_CUDA_INDEX_BASE_URL
ARG PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL
ARG PIP_KEYRING_PROVIDER UV_KEYRING_PROVIDER
# Install uv for faster pip installs # Install uv for faster pip installs
RUN --mount=type=cache,target=/root/.cache/uv \ RUN --mount=type=cache,target=/root/.cache/uv \
python3 -m pip install uv python3 -m pip install uv
...@@ -63,15 +139,19 @@ WORKDIR /workspace ...@@ -63,15 +139,19 @@ WORKDIR /workspace
# after this step # after this step
RUN --mount=type=cache,target=/root/.cache/uv \ RUN --mount=type=cache,target=/root/.cache/uv \
if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \ if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
uv pip install --system --index-url https://download.pytorch.org/whl/nightly/cu128 "torch==2.8.0.dev20250318+cu128" "torchvision==0.22.0.dev20250319"; \ uv pip install --system \
uv pip install --system --index-url https://download.pytorch.org/whl/nightly/cu128 --pre pytorch_triton==3.3.0+gitab727c40; \ --index-url ${PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') \
"torch==2.8.0.dev20250318+cu128" "torchvision==0.22.0.dev20250319"; \
uv pip install --system \
--index-url ${PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') \
--pre pytorch_triton==3.3.0+gitab727c40; \
fi fi
COPY requirements/common.txt requirements/common.txt COPY requirements/common.txt requirements/common.txt
COPY requirements/cuda.txt requirements/cuda.txt COPY requirements/cuda.txt requirements/cuda.txt
RUN --mount=type=cache,target=/root/.cache/uv \ RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install --system -r requirements/cuda.txt \ uv pip install --system -r requirements/cuda.txt \
--extra-index-url https://download.pytorch.org/whl/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')
# cuda arch list used by torch # cuda arch list used by torch
# can be useful for both `dev` and `test` # can be useful for both `dev` and `test`
...@@ -88,6 +168,10 @@ ENV VLLM_FA_CMAKE_GPU_ARCHES=${vllm_fa_cmake_gpu_arches} ...@@ -88,6 +168,10 @@ ENV VLLM_FA_CMAKE_GPU_ARCHES=${vllm_fa_cmake_gpu_arches}
FROM base AS build FROM base AS build
ARG TARGETPLATFORM ARG TARGETPLATFORM
ARG PIP_INDEX_URL UV_INDEX_URL
ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
ARG PYTORCH_CUDA_INDEX_BASE_URL
# install build dependencies # install build dependencies
COPY requirements/build.txt requirements/build.txt COPY requirements/build.txt requirements/build.txt
...@@ -98,7 +182,7 @@ ENV UV_INDEX_STRATEGY="unsafe-best-match" ...@@ -98,7 +182,7 @@ ENV UV_INDEX_STRATEGY="unsafe-best-match"
RUN --mount=type=cache,target=/root/.cache/uv \ RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install --system -r requirements/build.txt \ uv pip install --system -r requirements/build.txt \
--extra-index-url https://download.pytorch.org/whl/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')
COPY . . COPY . .
ARG GIT_REPO_CHECK=0 ARG GIT_REPO_CHECK=0
...@@ -113,6 +197,8 @@ ARG nvcc_threads=8 ...@@ -113,6 +197,8 @@ ARG nvcc_threads=8
ENV NVCC_THREADS=$nvcc_threads ENV NVCC_THREADS=$nvcc_threads
ARG USE_SCCACHE ARG USE_SCCACHE
ARG SCCACHE_DOWNLOAD_URL=https://github.com/mozilla/sccache/releases/download/v0.8.1/sccache-v0.8.1-x86_64-unknown-linux-musl.tar.gz
ARG SCCACHE_ENDPOINT
ARG SCCACHE_BUCKET_NAME=vllm-build-sccache ARG SCCACHE_BUCKET_NAME=vllm-build-sccache
ARG SCCACHE_REGION_NAME=us-west-2 ARG SCCACHE_REGION_NAME=us-west-2
ARG SCCACHE_S3_NO_CREDENTIALS=0 ARG SCCACHE_S3_NO_CREDENTIALS=0
...@@ -121,10 +207,11 @@ RUN --mount=type=cache,target=/root/.cache/uv \ ...@@ -121,10 +207,11 @@ RUN --mount=type=cache,target=/root/.cache/uv \
--mount=type=bind,source=.git,target=.git \ --mount=type=bind,source=.git,target=.git \
if [ "$USE_SCCACHE" = "1" ]; then \ if [ "$USE_SCCACHE" = "1" ]; then \
echo "Installing sccache..." \ echo "Installing sccache..." \
&& curl -L -o sccache.tar.gz https://github.com/mozilla/sccache/releases/download/v0.8.1/sccache-v0.8.1-x86_64-unknown-linux-musl.tar.gz \ && curl -L -o sccache.tar.gz ${SCCACHE_DOWNLOAD_URL} \
&& tar -xzf sccache.tar.gz \ && tar -xzf sccache.tar.gz \
&& sudo mv sccache-v0.8.1-x86_64-unknown-linux-musl/sccache /usr/bin/sccache \ && sudo mv sccache-v0.8.1-x86_64-unknown-linux-musl/sccache /usr/bin/sccache \
&& rm -rf sccache.tar.gz sccache-v0.8.1-x86_64-unknown-linux-musl \ && rm -rf sccache.tar.gz sccache-v0.8.1-x86_64-unknown-linux-musl \
&& if [ ! -z ${SCCACHE_ENDPOINT} ] ; then export SCCACHE_ENDPOINT=${SCCACHE_ENDPOINT} ; fi \
&& export SCCACHE_BUCKET=${SCCACHE_BUCKET_NAME} \ && export SCCACHE_BUCKET=${SCCACHE_BUCKET_NAME} \
&& export SCCACHE_REGION=${SCCACHE_REGION_NAME} \ && export SCCACHE_REGION=${SCCACHE_REGION_NAME} \
&& export SCCACHE_S3_NO_CREDENTIALS=${SCCACHE_S3_NO_CREDENTIALS} \ && export SCCACHE_S3_NO_CREDENTIALS=${SCCACHE_S3_NO_CREDENTIALS} \
...@@ -162,6 +249,10 @@ RUN if [ "$RUN_WHEEL_CHECK" = "true" ]; then \ ...@@ -162,6 +249,10 @@ RUN if [ "$RUN_WHEEL_CHECK" = "true" ]; then \
#################### DEV IMAGE #################### #################### DEV IMAGE ####################
FROM base as dev FROM base as dev
ARG PIP_INDEX_URL UV_INDEX_URL
ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
ARG PYTORCH_CUDA_INDEX_BASE_URL
# This timeout (in seconds) is necessary when installing some dependencies via uv since it's likely to time out # This timeout (in seconds) is necessary when installing some dependencies via uv since it's likely to time out
# Reference: https://github.com/astral-sh/uv/pull/1694 # Reference: https://github.com/astral-sh/uv/pull/1694
ENV UV_HTTP_TIMEOUT=500 ENV UV_HTTP_TIMEOUT=500
...@@ -176,21 +267,25 @@ COPY requirements/test.txt requirements/test.txt ...@@ -176,21 +267,25 @@ COPY requirements/test.txt requirements/test.txt
COPY requirements/dev.txt requirements/dev.txt COPY requirements/dev.txt requirements/dev.txt
RUN --mount=type=cache,target=/root/.cache/uv \ RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install --system -r requirements/dev.txt \ uv pip install --system -r requirements/dev.txt \
--extra-index-url https://download.pytorch.org/whl/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')
#################### DEV IMAGE #################### #################### DEV IMAGE ####################
#################### vLLM installation IMAGE #################### #################### vLLM installation IMAGE ####################
# image with vLLM installed # image with vLLM installed
# TODO: Restore to base image after FlashInfer AOT wheel fixed # TODO: Restore to base image after FlashInfer AOT wheel fixed
FROM nvidia/cuda:${CUDA_VERSION}-devel-ubuntu22.04 AS vllm-base FROM ${FINAL_BASE_IMAGE} AS vllm-base
ARG CUDA_VERSION=12.8.1 ARG CUDA_VERSION
ARG PYTHON_VERSION=3.12 ARG PYTHON_VERSION
WORKDIR /vllm-workspace WORKDIR /vllm-workspace
ENV DEBIAN_FRONTEND=noninteractive ENV DEBIAN_FRONTEND=noninteractive
ARG TARGETPLATFORM ARG TARGETPLATFORM
SHELL ["/bin/bash", "-c"] SHELL ["/bin/bash", "-c"]
ARG DEADSNAKES_MIRROR_URL
ARG DEADSNAKES_GPGKEY_URL
ARG GET_PIP_URL
RUN PYTHON_VERSION_STR=$(echo ${PYTHON_VERSION} | sed 's/\.//g') && \ RUN PYTHON_VERSION_STR=$(echo ${PYTHON_VERSION} | sed 's/\.//g') && \
echo "export PYTHON_VERSION_STR=${PYTHON_VERSION_STR}" >> /etc/environment echo "export PYTHON_VERSION_STR=${PYTHON_VERSION_STR}" >> /etc/environment
...@@ -200,17 +295,33 @@ RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \ ...@@ -200,17 +295,33 @@ RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
&& apt-get update -y \ && apt-get update -y \
&& apt-get install -y ccache software-properties-common git curl wget sudo vim python3-pip \ && apt-get install -y ccache software-properties-common git curl wget sudo vim python3-pip \
&& apt-get install -y ffmpeg libsm6 libxext6 libgl1 \ && apt-get install -y ffmpeg libsm6 libxext6 libgl1 \
&& for i in 1 2 3; do \ && if [ ! -z ${DEADSNAKES_MIRROR_URL} ] ; then \
if [ ! -z "${DEADSNAKES_GPGKEY_URL}" ] ; then \
mkdir -p -m 0755 /etc/apt/keyrings ; \
curl -L ${DEADSNAKES_GPGKEY_URL} | gpg --dearmor > /etc/apt/keyrings/deadsnakes.gpg ; \
sudo chmod 644 /etc/apt/keyrings/deadsnakes.gpg ; \
echo "deb [signed-by=/etc/apt/keyrings/deadsnakes.gpg] ${DEADSNAKES_MIRROR_URL} $(lsb_release -cs) main" > /etc/apt/sources.list.d/deadsnakes.list ; \
fi ; \
else \
for i in 1 2 3; do \
add-apt-repository -y ppa:deadsnakes/ppa && break || \ add-apt-repository -y ppa:deadsnakes/ppa && break || \
{ echo "Attempt $i failed, retrying in 5s..."; sleep 5; }; \ { echo "Attempt $i failed, retrying in 5s..."; sleep 5; }; \
done \ done ; \
fi \
&& apt-get update -y \ && apt-get update -y \
&& apt-get install -y python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python${PYTHON_VERSION}-venv libibverbs-dev \ && 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 --install /usr/bin/python3 python3 /usr/bin/python${PYTHON_VERSION} 1 \
&& update-alternatives --set python3 /usr/bin/python${PYTHON_VERSION} \ && update-alternatives --set python3 /usr/bin/python${PYTHON_VERSION} \
&& ln -sf /usr/bin/python${PYTHON_VERSION}-config /usr/bin/python3-config \ && ln -sf /usr/bin/python${PYTHON_VERSION}-config /usr/bin/python3-config \
&& curl -sS https://bootstrap.pypa.io/get-pip.py | python${PYTHON_VERSION} \ && curl -sS ${GET_PIP_URL} | python${PYTHON_VERSION} \
&& python3 --version && python3 -m pip --version && python3 --version && python3 -m pip --version
ARG PIP_INDEX_URL UV_INDEX_URL
ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
ARG PYTORCH_CUDA_INDEX_BASE_URL
ARG PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL
ARG PIP_KEYRING_PROVIDER UV_KEYRING_PROVIDER
# Install uv for faster pip installs # Install uv for faster pip installs
RUN --mount=type=cache,target=/root/.cache/uv \ RUN --mount=type=cache,target=/root/.cache/uv \
python3 -m pip install uv python3 -m pip install uv
...@@ -232,15 +343,19 @@ RUN ldconfig /usr/local/cuda-$(echo $CUDA_VERSION | cut -d. -f1,2)/compat/ ...@@ -232,15 +343,19 @@ RUN ldconfig /usr/local/cuda-$(echo $CUDA_VERSION | cut -d. -f1,2)/compat/
# after this step # after this step
RUN --mount=type=cache,target=/root/.cache/uv \ RUN --mount=type=cache,target=/root/.cache/uv \
if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \ if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
uv pip install --system --index-url https://download.pytorch.org/whl/nightly/cu128 "torch==2.8.0.dev20250318+cu128" "torchvision==0.22.0.dev20250319"; \ uv pip install --system \
uv pip install --system --index-url https://download.pytorch.org/whl/nightly/cu128 --pre pytorch_triton==3.3.0+gitab727c40; \ --index-url ${PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') \
"torch==2.8.0.dev20250318+cu128" "torchvision==0.22.0.dev20250319" ; \
uv pip install --system \
--index-url ${PYTORCH_CUDA_NIGHTLY_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') \
--pre pytorch_triton==3.3.0+gitab727c40 ; \
fi fi
# Install vllm wheel first, so that torch etc will be installed. # Install vllm wheel first, so that torch etc will be installed.
RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist \ RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist \
--mount=type=cache,target=/root/.cache/uv \ --mount=type=cache,target=/root/.cache/uv \
uv pip install --system dist/*.whl --verbose \ uv pip install --system dist/*.whl --verbose \
--extra-index-url https://download.pytorch.org/whl/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')
# If we need to build FlashInfer wheel before its release: # If we need to build FlashInfer wheel before its release:
# $ # Note we remove 7.0 from the arch list compared to the list below, since FlashInfer only supports sm75+ # $ # Note we remove 7.0 from the arch list compared to the list below, since FlashInfer only supports sm75+
...@@ -254,15 +369,20 @@ RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist ...@@ -254,15 +369,20 @@ RUN --mount=type=bind,from=build,src=/workspace/dist,target=/vllm-workspace/dist
# -rw-rw-r-- 1 mgoin mgoin 205M Jun 9 18:03 flashinfer_python-0.2.6.post1-cp39-abi3-linux_x86_64.whl # -rw-rw-r-- 1 mgoin mgoin 205M Jun 9 18:03 flashinfer_python-0.2.6.post1-cp39-abi3-linux_x86_64.whl
# $ # upload the wheel to a public location, e.g. https://wheels.vllm.ai/flashinfer/v0.2.6.post1/flashinfer_python-0.2.6.post1-cp39-abi3-linux_x86_64.whl # $ # upload the wheel to a public location, e.g. https://wheels.vllm.ai/flashinfer/v0.2.6.post1/flashinfer_python-0.2.6.post1-cp39-abi3-linux_x86_64.whl
# Allow specifying a version, Git revision or local .whl file
ARG FLASHINFER_CUDA128_INDEX_URL="https://download.pytorch.org/whl/cu128/flashinfer"
ARG FLASHINFER_CUDA128_WHEEL="flashinfer_python-0.2.6.post1%2Bcu128torch2.7-cp39-abi3-linux_x86_64.whl"
ARG FLASHINFER_GIT_REPO="https://github.com/flashinfer-ai/flashinfer.git"
ARG FLASHINFER_GIT_REF="v0.2.6.post1"
RUN --mount=type=cache,target=/root/.cache/uv \ RUN --mount=type=cache,target=/root/.cache/uv \
. /etc/environment && \ . /etc/environment && \
if [ "$TARGETPLATFORM" != "linux/arm64" ]; then \ if [ "$TARGETPLATFORM" != "linux/arm64" ]; then \
# FlashInfer already has a wheel for PyTorch 2.7.0 and CUDA 12.8. This is enough for CI use # FlashInfer already has a wheel for PyTorch 2.7.0 and CUDA 12.8. This is enough for CI use
if [[ "$CUDA_VERSION" == 12.8* ]]; then \ if [[ "$CUDA_VERSION" == 12.8* ]]; then \
uv pip install --system https://download.pytorch.org/whl/cu128/flashinfer/flashinfer_python-0.2.6.post1%2Bcu128torch2.7-cp39-abi3-linux_x86_64.whl; \ uv pip install --system ${FLASHINFER_CUDA128_INDEX_URL}/${FLASHINFER_CUDA128_WHEEL} ; \
else \ else \
export TORCH_CUDA_ARCH_LIST='7.5 8.0 8.9 9.0a 10.0a 12.0' && \ export TORCH_CUDA_ARCH_LIST='7.5 8.0 8.9 9.0a 10.0a 12.0' && \
git clone https://github.com/flashinfer-ai/flashinfer.git --single-branch --branch v0.2.6.post1 --recursive && \ git clone ${FLASHINFER_GIT_REPO} --single-branch --branch ${FLASHINFER_GIT_REF} --recursive && \
# Needed to build AOT kernels # Needed to build AOT kernels
(cd flashinfer && \ (cd flashinfer && \
python3 -m flashinfer.aot && \ python3 -m flashinfer.aot && \
...@@ -286,7 +406,7 @@ uv pip list ...@@ -286,7 +406,7 @@ uv pip list
COPY requirements/build.txt requirements/build.txt COPY requirements/build.txt requirements/build.txt
RUN --mount=type=cache,target=/root/.cache/uv \ RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install --system -r requirements/build.txt \ uv pip install --system -r requirements/build.txt \
--extra-index-url https://download.pytorch.org/whl/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.') --extra-index-url ${PYTORCH_CUDA_INDEX_BASE_URL}/cu$(echo $CUDA_VERSION | cut -d. -f1,2 | tr -d '.')
#################### vLLM installation IMAGE #################### #################### vLLM installation IMAGE ####################
...@@ -297,6 +417,11 @@ FROM vllm-base AS test ...@@ -297,6 +417,11 @@ FROM vllm-base AS test
ADD . /vllm-workspace/ ADD . /vllm-workspace/
ARG PYTHON_VERSION
ARG PIP_INDEX_URL UV_INDEX_URL
ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
# This timeout (in seconds) is necessary when installing some dependencies via uv since it's likely to time out # This timeout (in seconds) is necessary when installing some dependencies via uv since it's likely to time out
# Reference: https://github.com/astral-sh/uv/pull/1694 # Reference: https://github.com/astral-sh/uv/pull/1694
ENV UV_HTTP_TIMEOUT=500 ENV UV_HTTP_TIMEOUT=500
...@@ -323,7 +448,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \ ...@@ -323,7 +448,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
ENV HF_HUB_ENABLE_HF_TRANSFER 1 ENV HF_HUB_ENABLE_HF_TRANSFER 1
# Copy in the v1 package for testing (it isn't distributed yet) # Copy in the v1 package for testing (it isn't distributed yet)
COPY vllm/v1 /usr/local/lib/python3.12/dist-packages/vllm/v1 COPY vllm/v1 /usr/local/lib/python${PYTHON_VERSION}/dist-packages/vllm/v1
# doc requires source code # doc requires source code
# we hide them inside `test_docs/` , so that this source code # we hide them inside `test_docs/` , so that this source code
...@@ -340,6 +465,9 @@ RUN mv mkdocs.yaml test_docs/ ...@@ -340,6 +465,9 @@ RUN mv mkdocs.yaml test_docs/
FROM vllm-base AS vllm-openai-base FROM vllm-base AS vllm-openai-base
ARG TARGETPLATFORM ARG TARGETPLATFORM
ARG PIP_INDEX_URL UV_INDEX_URL
ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL
# This timeout (in seconds) is necessary when installing some dependencies via uv since it's likely to time out # This timeout (in seconds) is necessary when installing some dependencies via uv since it's likely to time out
# Reference: https://github.com/astral-sh/uv/pull/1694 # Reference: https://github.com/astral-sh/uv/pull/1694
ENV UV_HTTP_TIMEOUT=500 ENV UV_HTTP_TIMEOUT=500
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment