mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-14 20:48:00 +00:00
5c3c7643db
### Description <!-- Describe your changes. --> * Remove deprecated gpu arch to control nuget/python package size (latest TRT supports sm75 Turing and newer arch) * Add 90 to support blackwell series in next release (86;89 not considered as adding them will rapidly increase package size) | arch_range | Python-cuda12 | Nuget-cuda12 | | -------------- | ------------------------------------------------------------ | ---------------------------------- | | 60;61;70;75;80 | Linux: 279MB Win: 267MB | Linux: 247MB Win: 235MB | | 75;80 | Linux: 174MB Win: 162MB | Linux: 168MB Win: 156MB | | **75;80;90** | **Linux: 299MB Win: 277MB** | **Linux: 294MB Win: 271MB** | | 75;80;86;89 | [Linux: MB Win: 390MB](https://aiinfra.visualstudio.com/Lotus/_build/results?buildId=647457&view=results) | Linux: 416MB Win: 383MB | | 75;80;86;89;90 | [Linux: MB Win: 505MB](https://aiinfra.visualstudio.com/Lotus/_build/results?buildId=646536&view=results) | Linux: 541MB Win: 498MB | ### Motivation and Context <!-- - Why is this change required? What problem does it solve? - If it fixes an open issue, please link to the issue here. --> Callout: While adding sm90 support, the build of cuda11.8+cudnn8 will be dropped in the coming ORT release, as the build has issue with blackwell (mentioned in comments) and demand on cuda 11 is minor, according to internal ort-cuda11 repo.
112 lines
4.1 KiB
Text
112 lines
4.1 KiB
Text
# --------------------------------------------------------------
|
|
# Copyright (c) Microsoft Corporation. All rights reserved.
|
|
# Licensed under the MIT License.
|
|
# --------------------------------------------------------------
|
|
# Build onnxruntime-gpu python package with CUDA 12.x & CUDNN 9.x for python 3.12 in Ubuntu 24.04.
|
|
# If memory is less than 64GB, you may change "--parallel" to "--parallel 4" to avoid out-of-memory error.
|
|
|
|
ARG CUDA_VERSION=12.6.1
|
|
ARG CUDNN_VERSION=9.5.0.50
|
|
ARG OS=ubuntu24.04
|
|
|
|
FROM nvcr.io/nvidia/cuda:${CUDA_VERSION}-devel-${OS}
|
|
ARG CUDA_VERSION
|
|
ARG CUDNN_VERSION
|
|
# Adjust as needed
|
|
# Check your CUDA arch: https://developer.nvidia.com/cuda-gpus
|
|
ARG CMAKE_CUDA_ARCHITECTURES="75;80;90"
|
|
|
|
ENV DEBIAN_FRONTEND=noninteractive
|
|
|
|
# Add source code to /code
|
|
ADD . /code
|
|
|
|
ENV PATH=/usr/local/cuda/bin:${PATH}
|
|
|
|
# Install required packages
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
ca-certificates \
|
|
g++ \
|
|
gcc \
|
|
make \
|
|
git \
|
|
cmake \
|
|
wget \
|
|
ninja-build \
|
|
python3-pip \
|
|
python3.12-dev \
|
|
python3.12-venv \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# Install CUDNN 9.4.0.58 for building ONNX Runtime with CUDA.
|
|
RUN cudnn_tar="cudnn-linux-x86_64-${CUDNN_VERSION}_cuda${CUDA_VERSION%%.*}-archive.tar.xz" \
|
|
&& wget "https://developer.download.nvidia.com/compute/cudnn/redist/cudnn/linux-x86_64/${cudnn_tar}" \
|
|
&& mkdir -p /code/build/cudnn \
|
|
&& tar -Jxvf ${cudnn_tar} -C /code/build/cudnn --strip=1 \
|
|
&& rm -f ${cudnn_tar}
|
|
|
|
# Create a virtual environment and install dependencies, then build ONNX Runtime with CUDA support.
|
|
RUN cd /code \
|
|
&& python3 -m venv /code/env \
|
|
&& . /code/env/bin/activate \
|
|
&& pip install --upgrade psutil setuptools wheel packaging \
|
|
&& pip install -r /code/tools/ci_build/github/linux/python/requirements.txt \
|
|
&& python /code/tools/ci_build/build.py --build_dir /code/build/Linux \
|
|
--allow_running_as_root --skip_submodule_sync \
|
|
--use_cuda --cuda_home /usr/local/cuda \
|
|
--cudnn_home /code/build/cudnn \
|
|
--build_shared_lib --skip_tests \
|
|
--config Release --build_wheel --update --build --parallel \
|
|
--cmake_generator Ninja \
|
|
--cmake_extra_defines ONNXRUNTIME_VERSION=$(cat ./VERSION_NUMBER) "CMAKE_CUDA_ARCHITECTURES=${CMAKE_CUDA_ARCHITECTURES}" onnxruntime_BUILD_UNIT_TESTS=OFF
|
|
|
|
# Start second stage to copy the build artifacts
|
|
FROM nvcr.io/nvidia/cuda:${CUDA_VERSION}-runtime-${OS}
|
|
ARG CUDA_VERSION
|
|
ARG CUDNN_VERSION
|
|
ARG GIT_COMMIT
|
|
ARG GIT_BRANCH
|
|
ARG ONNXRUNTIME_VERSION
|
|
|
|
# Make sure the required build arguments are set. See README.md for more information.
|
|
RUN test -n ${GIT_COMMIT:?}
|
|
RUN test -n ${GIT_BRANCH:?}
|
|
RUN test -n ${ONNXRUNTIME_VERSION:?}
|
|
|
|
LABEL CUDA_VERSION="${CUDA_VERSION}"
|
|
LABEL CUDNN_VERSION="${CUDNN_VERSION}"
|
|
LABEL maintainer="Changming Sun <chasun@microsoft.com>"
|
|
LABEL onnxruntime_version="${ONNXRUNTIME_VERSION}"
|
|
LABEL onnxruntime_git_branch="${GIT_BRANCH}"
|
|
LABEL onnxruntime_git_commit="${GIT_COMMIT}"
|
|
|
|
# Copy built wheel and license
|
|
COPY --from=0 /code/build/Linux/Release/dist /ort
|
|
COPY --from=0 /code/dockerfiles/LICENSE-IMAGE.txt /code/LICENSE-IMAGE.txt
|
|
|
|
# Set environment variables
|
|
ENV DEBIAN_FRONTEND=noninteractive
|
|
ENV CUDNN_VERSION=$CUDNN_VERSION
|
|
ENV ONNXRUNTIME_VERSION=$ONNXRUNTIME_VERSION
|
|
# CUDNN from nvidia-cudnn-cu12 python package is located in the site-packages directory of python virtual environment.
|
|
ENV LD_LIBRARY_PATH="/ort/env/lib/python3.12/site-packages/nvidia/cudnn/lib:/usr/local/cuda/lib64"
|
|
|
|
# Install runtime dependencies
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
libstdc++6 \
|
|
ca-certificates \
|
|
python3-pip \
|
|
python3.12-venv \
|
|
&& python3 -m venv /ort/env \
|
|
&& . /ort/env/bin/activate \
|
|
&& pip install /ort/*.whl \
|
|
&& pip install nvidia-cudnn-cu${CUDA_VERSION%%.*}==${CUDNN_VERSION} \
|
|
&& python -c 'import onnxruntime; print(onnxruntime.get_available_providers())' \
|
|
&& rm -rf /ort/*.whl \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# Ensure the virtual environment is always activated when running commands in the container.
|
|
RUN echo ". /ort/env/bin/activate" >> ~/.bashrc
|
|
|
|
# Set the default command to start an interactive bash shell
|
|
CMD [ "/bin/bash" ]
|