mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-07-29 20:14:01 +00:00
57dfd15d7b
### Description
1. Remove 'dnf update' from docker build scripts, because it upgrades TRT
packages from CUDA 11.x to CUDA 12.x.
To reproduce it, you can run the following commands in a CentOS CUDA
11.x docker image such as nvidia/cuda:11.8.0-cudnn8-devel-ubi8.
```
export v=8.6.1.6-1.cuda11.8
dnf install -y libnvinfer8-${v} libnvparsers8-${v} libnvonnxparsers8-${v} libnvinfer-plugin8-${v} libnvinfer-vc-plugin8-${v} libnvinfer-devel-${v} libnvparsers-devel-${v} libnvonnxparsers-devel-${v} libnvinfer-plugin-devel-${v} libnvinfer-vc-plugin-devel-${v} libnvinfer-headers-devel-${v} libnvinfer-headers-plugin-devel-${v}
dnf update -y
```
The last command will generate the following outputs:
```
========================================================================================================================
Package Architecture Version Repository Size
========================================================================================================================
Upgrading:
libnvinfer-devel x86_64 8.6.1.6-1.cuda12.0 cuda 542 M
libnvinfer-headers-devel x86_64 8.6.1.6-1.cuda12.0 cuda 118 k
libnvinfer-headers-plugin-devel x86_64 8.6.1.6-1.cuda12.0 cuda 14 k
libnvinfer-plugin-devel x86_64 8.6.1.6-1.cuda12.0 cuda 13 M
libnvinfer-plugin8 x86_64 8.6.1.6-1.cuda12.0 cuda 13 M
libnvinfer-vc-plugin-devel x86_64 8.6.1.6-1.cuda12.0 cuda 107 k
libnvinfer-vc-plugin8 x86_64 8.6.1.6-1.cuda12.0 cuda 251 k
libnvinfer8 x86_64 8.6.1.6-1.cuda12.0 cuda 543 M
libnvonnxparsers-devel x86_64 8.6.1.6-1.cuda12.0 cuda 467 k
libnvonnxparsers8 x86_64 8.6.1.6-1.cuda12.0 cuda 757 k
libnvparsers-devel x86_64 8.6.1.6-1.cuda12.0 cuda 2.0 M
libnvparsers8 x86_64 8.6.1.6-1.cuda12.0 cuda 854 k
Installing dependencies:
cuda-toolkit-12-0-config-common noarch 12.0.146-1 cuda 7.7 k
cuda-toolkit-12-config-common noarch 12.2.140-1 cuda 7.9 k
libcublas-12-0 x86_64 12.0.2.224-1 cuda 361 M
libcublas-devel-12-0 x86_64 12.0.2.224-1 cuda 397 M
Transaction Summary
========================================================================================================================
```
As you can see from the output, they are CUDA 12 packages.
The problem can also be solved by lock the packages' versions by using
"dnf versionlock" command right after installing the CUDA/TRT packages.
However, going forward, to get the better reproducibility, I suggest
manually fix dnf package versions in the installation scripts like we do
for TRT now.
```bash
v="8.6.1.6-1.cuda11.8" &&\
yum-config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/rhel8/x86_64/cuda-rhel8.repo &&\
yum -y install libnvinfer8-${v} libnvparsers8-${v} libnvonnxparsers8-${v} libnvinfer-plugin8-${v} libnvinfer-vc-plugin8-${v}\
libnvinfer-devel-${v} libnvparsers-devel-${v} libnvonnxparsers-devel-${v} libnvinfer-plugin-devel-${v} libnvinfer-vc-plugin-devel-${v} libnvinfer-headers-devel-${v} libnvinfer-headers-plugin-devel-${v}
```
When we have a need to upgrade a package due to security alert or some
other reasons, we manually change the version string instead of relying
on "dnf update". Though this approach increases efforts, it can make our
pipeines more stable.
2. Move python test to docker
### Motivation and Context
Right now the nightly gpu package mixes using CUDA 11.x and CUDA 12.x
and the result package is totally not usable(crashes every time)
210 lines
7.7 KiB
YAML
210 lines
7.7 KiB
YAML
##### start trigger Don't edit it manually, Please do edit set-trigger-rules.py ####
|
|
trigger:
|
|
branches:
|
|
include:
|
|
- main
|
|
- rel-*
|
|
paths:
|
|
exclude:
|
|
- docs/**
|
|
- README.md
|
|
- CONTRIBUTING.md
|
|
- BUILD.md
|
|
- 'js/web'
|
|
- 'onnxruntime/core/providers/js'
|
|
pr:
|
|
branches:
|
|
include:
|
|
- main
|
|
- rel-*
|
|
paths:
|
|
exclude:
|
|
- docs/**
|
|
- README.md
|
|
- CONTRIBUTING.md
|
|
- BUILD.md
|
|
- 'js/web'
|
|
- 'onnxruntime/core/providers/js'
|
|
#### end trigger ####
|
|
|
|
resources:
|
|
repositories:
|
|
- repository: manylinux # The name used to reference this repository in the checkout step
|
|
type: Github
|
|
endpoint: Microsoft
|
|
name: pypa/manylinux
|
|
ref: 5eda9aded5462201e6310105728d33016e637ea7
|
|
stages:
|
|
- stage: x64
|
|
dependsOn: []
|
|
jobs:
|
|
- job: Linux_Build
|
|
timeoutInMinutes: 180
|
|
workspace:
|
|
clean: all
|
|
variables:
|
|
skipComponentGovernanceDetection: true
|
|
ORT_CACHE_DIR: $(Agent.TempDirectory)/ort_ccache
|
|
TODAY: $[format('{0:dd}{0:MM}{0:yyyy}', pipeline.startTime)]
|
|
pool: onnxruntime-Ubuntu2004-AMD-CPU
|
|
steps:
|
|
- task: mspremier.PostBuildCleanup.PostBuildCleanup-task.PostBuildCleanup@3
|
|
displayName: 'Clean Agent Directories'
|
|
condition: always()
|
|
|
|
- checkout: self
|
|
clean: true
|
|
submodules: none
|
|
|
|
- task: NodeTool@0
|
|
inputs:
|
|
versionSpec: '16.x'
|
|
|
|
- task: UsePythonVersion@0
|
|
inputs:
|
|
versionSpec: '3.8'
|
|
addToPath: true
|
|
|
|
- template: templates/get-docker-image-steps.yml
|
|
parameters:
|
|
Dockerfile: tools/ci_build/github/linux/docker/Dockerfile.manylinux2_28_cpu
|
|
Context: tools/ci_build/github/linux/docker/
|
|
DockerBuildArgs: "--build-arg BUILD_UID=$( id -u ) --build-arg BASEIMAGE=registry.access.redhat.com/ubi8/ubi"
|
|
Repository: onnxruntimecpubuild
|
|
|
|
- template: templates/linux-build-step-with-cache.yml
|
|
parameters:
|
|
WithCache: true
|
|
Today: $(TODAY)
|
|
AdditionalKey: onnxruntime
|
|
CacheDir: $(ORT_CACHE_DIR)
|
|
ChangeEveryCommit: true
|
|
BuildStep:
|
|
- task: CmdLine@2
|
|
displayName: 'build'
|
|
inputs:
|
|
script: |
|
|
mkdir -p $HOME/.onnx
|
|
docker run --rm \
|
|
--volume /data/onnx:/data/onnx:ro \
|
|
--volume $(Build.SourcesDirectory):/onnxruntime_src \
|
|
--volume $(Build.BinariesDirectory):/build \
|
|
--volume $HOME/.onnx:/home/onnxruntimedev/.onnx \
|
|
--volume $(ORT_CACHE_DIR):/cache \
|
|
-e ALLOW_RELEASED_ONNX_OPSET_ONLY=0 \
|
|
-e NIGHTLY_BUILD \
|
|
-e BUILD_BUILDNUMBER \
|
|
-e CCACHE_DIR=/cache \
|
|
onnxruntimecpubuild \
|
|
/bin/bash -c "
|
|
set -ex; \
|
|
ccache -s; \
|
|
/opt/python/cp38-cp38/bin/python3 /onnxruntime_src/tools/ci_build/build.py \
|
|
--build_dir /build --cmake_generator 'Ninja' \
|
|
--config Debug Release \
|
|
--skip_submodule_sync \
|
|
--build_shared_lib \
|
|
--parallel \
|
|
--build_wheel \
|
|
--build_csharp \
|
|
--enable_onnx_tests \
|
|
--enable_transformers_tool_test \
|
|
--use_cache \
|
|
--update --build --cmake_extra_defines onnxruntime_BUILD_BENCHMARKS=ON; \
|
|
ccache -sv; \
|
|
ccache -z"
|
|
workingDirectory: $(Build.SourcesDirectory)
|
|
|
|
- script: |
|
|
ln -s /data/models $(Build.BinariesDirectory)/models
|
|
displayName: link model dir
|
|
|
|
- bash: |
|
|
mkdir -p $HOME/.onnx
|
|
docker run --rm \
|
|
--volume /data/onnx:/data/onnx:ro \
|
|
--volume $(Build.SourcesDirectory):/onnxruntime_src \
|
|
--volume $(Build.BinariesDirectory):/build \
|
|
--volume /data/models:/build/models:ro \
|
|
--volume $HOME/.onnx:/home/onnxruntimedev/.onnx \
|
|
-e ALLOW_RELEASED_ONNX_OPSET_ONLY=0 \
|
|
-e NIGHTLY_BUILD \
|
|
-e BUILD_BUILDNUMBER \
|
|
onnxruntimecpubuild \
|
|
/bin/bash -c "
|
|
set -ex; \
|
|
pushd /onnxruntime_src/csharp; \
|
|
dotnet restore /onnxruntime_src/csharp/OnnxRuntime.DesktopOnly.CSharp.sln; \
|
|
dotnet build /onnxruntime_src/csharp/OnnxRuntime.DesktopOnly.CSharp.sln; \
|
|
dotnet test /onnxruntime_src/csharp/OnnxRuntime.DesktopOnly.CSharp.sln -f net6.0 --no-build -l \"console;verbosity=normal\"; \
|
|
popd
|
|
"
|
|
displayName: 'Dotnet build C# sln and Test'
|
|
|
|
- bash: |
|
|
mkdir -p $HOME/.onnx
|
|
docker run --rm \
|
|
--volume /data/onnx:/data/onnx:ro \
|
|
--volume $(Build.SourcesDirectory):/onnxruntime_src \
|
|
--volume $(Build.BinariesDirectory):/build \
|
|
--volume /data/models:/build/models:ro \
|
|
--volume $HOME/.onnx:/home/onnxruntimedev/.onnx \
|
|
-e ALLOW_RELEASED_ONNX_OPSET_ONLY=0 \
|
|
-e NIGHTLY_BUILD \
|
|
-e BUILD_BUILDNUMBER \
|
|
onnxruntimecpubuild \
|
|
/bin/bash -c "
|
|
set -ex; \
|
|
/bin/bash /onnxruntime_src/tools/scripts/python_test.sh /onnxruntime_src /build Release && \
|
|
/bin/bash /onnxruntime_src/tools/scripts/symbolic_shape_infer_test.sh /build
|
|
"
|
|
displayName: 'Run Release tests and symbolic shape infer test'
|
|
|
|
- bash: |
|
|
mkdir -p $HOME/.onnx
|
|
docker run --rm \
|
|
--volume /data/onnx:/data/onnx:ro \
|
|
--volume $(Build.SourcesDirectory):/onnxruntime_src \
|
|
--volume $(Build.BinariesDirectory):/build \
|
|
--volume /data/models:/build/models:ro \
|
|
--volume $HOME/.onnx:/home/onnxruntimedev/.onnx \
|
|
-e ALLOW_RELEASED_ONNX_OPSET_ONLY=0 \
|
|
-e NIGHTLY_BUILD \
|
|
-e BUILD_BUILDNUMBER \
|
|
onnxruntimecpubuild \
|
|
/bin/bash /onnxruntime_src/tools/scripts/python_test.sh /onnxruntime_src /build Debug
|
|
displayName: 'Run Debug tests'
|
|
|
|
- task: PublishTestResults@2
|
|
displayName: 'Publish unit test results'
|
|
inputs:
|
|
testResultsFiles: '**/*.results.xml'
|
|
searchFolder: '$(Build.BinariesDirectory)'
|
|
testRunTitle: 'Unit Test Run'
|
|
condition: succeededOrFailed()
|
|
|
|
- stage: arm64_build
|
|
dependsOn: []
|
|
jobs:
|
|
- template: templates/py-linux.yml
|
|
parameters:
|
|
arch: 'aarch64'
|
|
machine_pool: 'onnxruntime-linux-ARM64-CPU-2019'
|
|
base_image: 'arm64v8/almalinux:8'
|
|
devtoolset_rootpath: /opt/rh/gcc-toolset-12/root
|
|
ld_library_path_arg: /opt/rh/gcc-toolset-12/root/usr/lib64:/opt/rh/gcc-toolset-12/root/usr/lib:/opt/rh/gcc-toolset-12/root/usr/lib64/dyninst:/opt/rh/gcc-toolset-12/root/usr/lib/dyninst:/usr/local/lib64
|
|
prepend_path: '/opt/rh/gcc-toolset-12/root/usr/bin:'
|
|
with_cache: true
|
|
cmake_build_type: Release
|
|
|
|
- stage: arm64_test
|
|
dependsOn: ['arm64_build']
|
|
jobs:
|
|
- template: templates/py-packaging-linux-test-cpu.yml
|
|
parameters:
|
|
arch: 'aarch64'
|
|
machine_pool: 'onnxruntime-linux-ARM64-CPU-2019'
|
|
base_image: 'arm64v8/almalinux:8'
|
|
devtoolset_rootpath: /opt/rh/gcc-toolset-12/root
|
|
ld_library_path_arg: /opt/rh/gcc-toolset-12/root/usr/lib64:/opt/rh/gcc-toolset-12/root/usr/lib:/opt/rh/gcc-toolset-12/root/usr/lib64/dyninst:/opt/rh/gcc-toolset-12/root/usr/lib/dyninst:/usr/local/lib64
|
|
prepend_path: '/opt/rh/gcc-toolset-12/root/usr/bin:'
|