onnxruntime/tools/ci_build/github/azure-pipelines/templates/py-win-gpu.yml
Yi Zhang cd6d3aea45
Refactor Python CUDA packaging pipeline to fix random hangs in building (#19989)
### Description
1. Move building on CPU machine.
2. Optimize the pipeline
3. Since there isn't official ONNX package for python 12, the python 12
test stage uses the packages built with ONNX source in build stage.


### Motivation and Context
1. Resolve the random hang in compilation
4. Save a lot of GPU resources.

---------
2024-03-22 09:16:00 +08:00

279 lines
11 KiB
YAML

parameters:
- name: EP_NAME
type: string
- name: PYTHON_VERSION
type: string
- name: EP_BUILD_FLAGS
type: string
- name: ENV_SETUP_SCRIPT
type: string
default: ''
- name: BUILD_PY_PARAMETERS
displayName: >
Extra parameters to pass to build.py. Don't put newlines in here.
type: string
default: ''
- name: CudaVersion
type: string
default: '11.8'
values:
- 11.8
- 12.2
- name: SpecificArtifact
displayName: Use Specific Artifact
type: boolean
default: false
- name: BuildId
displayName: Specific Artifact's BuildId
type: string
default: '0'
stages:
- stage: Win_py_${{ parameters.EP_NAME }}_Wheels_${{ replace(parameters.PYTHON_VERSION,'.','_') }}_Build
dependsOn: []
jobs:
- job: Win_py_${{ parameters.EP_NAME }}_Wheels_${{ replace(parameters.PYTHON_VERSION,'.','_') }}_Build
timeoutInMinutes: 120
workspace:
clean: all
pool:
name: onnxruntime-Win-CPU-2022
# demands:
# - ImageVersionOverride -equals 1.0.367516
variables:
GRADLE_OPTS: '-Dorg.gradle.daemon=false'
VSGenerator: 'Visual Studio 17 2022'
CUDA_MODULE_LOADING: 'LAZY'
steps:
- task: mspremier.PostBuildCleanup.PostBuildCleanup-task.PostBuildCleanup@3
displayName: 'Clean Agent Directories'
condition: always()
- checkout: self
clean: true
submodules: recursive
- template: telemetry-steps.yml
- task: UsePythonVersion@0
inputs:
versionSpec: ${{ parameters.PYTHON_VERSION }}
addToPath: true
architecture: 'x64'
- task: onebranch.pipeline.tsaoptions@1
displayName: 'OneBranch TSAOptions'
inputs:
tsaConfigFilePath: '$(Build.SourcesDirectory)\.config\tsaoptions.json'
appendSourceBranchName: false
- task: PythonScript@0
inputs:
scriptSource: inline
script: |
import sys
np_version = 'numpy==1.21.6' if sys.version_info < (3, 11) else 'numpy==1.26'
import subprocess
try:
subprocess.check_call(['pip', 'install', '-q', 'setuptools', 'wheel', np_version])
except subprocess.CalledProcessError:
sys.exit(1)
workingDirectory: '$(Build.BinariesDirectory)'
displayName: 'Install python modules'
- template: download-deps.yml
- ${{ if ne(parameters.ENV_SETUP_SCRIPT, '') }}:
- template: jobs/set-winenv.yml
parameters:
EnvSetupScript: ${{ parameters.ENV_SETUP_SCRIPT }}
${{ if or(contains(parameters.EP_BUILD_FLAGS, 'use_cuda'), contains(parameters.EP_BUILD_FLAGS, 'use_tensorrt')) }}:
DownloadCUDA: true
- ${{ if eq(parameters.ENV_SETUP_SCRIPT, '') }}:
- template: jobs/download_win_gpu_library.yml
parameters:
CudaVersion: ${{ parameters.CudaVersion }}
${{ if or(contains(parameters.EP_BUILD_FLAGS, 'use_cuda'), contains(parameters.EP_BUILD_FLAGS, 'use_tensorrt')) }}:
DownloadCUDA: true
${{ if contains(parameters.EP_BUILD_FLAGS, 'use_tensorrt') }}:
DownloadTRT: true
- task: PythonScript@0
displayName: 'Update deps.txt'
inputs:
scriptPath: $(Build.SourcesDirectory)/tools/ci_build/replace_urls_in_deps.py
arguments: --new_dir $(Build.BinariesDirectory)/deps
workingDirectory: $(Build.BinariesDirectory)
- task: PowerShell@2
displayName: 'Install ONNX'
inputs:
filePath: '$(Build.SourcesDirectory)/tools/ci_build/github/windows/install_third_party_deps.ps1'
workingDirectory: '$(Build.BinariesDirectory)'
arguments: -cpu_arch x64 -install_prefix $(Build.BinariesDirectory)\RelWithDebInfo\installed -build_config RelWithDebInfo
# it could be removed once there's onnx wheel for python 3.12
- ${{ if eq(parameters.PYTHON_VERSION, '3.12') }}:
- task: PublishPipelineArtifact@1
displayName: 'Publish Artifact: ONNX python 12 wheel'
inputs:
targetPath: '$(Agent.TempDirectory)\onnx\onnx-1.15.0\dist\'
publishLocation: 'pipeline'
artifactName: onnx_py12_wheel
- template: set-nightly-build-option-variable-step.yml
- task: PythonScript@0
displayName: 'Generate cmake config'
inputs:
scriptPath: '$(Build.SourcesDirectory)\tools\ci_build\build.py'
arguments: >
--config RelWithDebInfo
--build_dir $(Build.BinariesDirectory)
--skip_submodule_sync
--cmake_generator "$(VSGenerator)"
--enable_pybind
--enable_onnx_tests
--parallel --use_binskim_compliant_compile_flags --update
$(TelemetryOption) ${{ parameters.BUILD_PY_PARAMETERS }} ${{ parameters.EP_BUILD_FLAGS }}
workingDirectory: '$(Build.BinariesDirectory)'
# building with build.py so the parallelization parameters are added to the msbuild command
- task: PythonScript@0
displayName: 'Build'
inputs:
scriptPath: '$(Build.SourcesDirectory)\tools\ci_build\build.py'
arguments: >
--config RelWithDebInfo
--build_dir $(Build.BinariesDirectory)
--parallel --build
$(TelemetryOption) ${{ parameters.BUILD_PY_PARAMETERS }} ${{ parameters.EP_BUILD_FLAGS }}
workingDirectory: '$(Build.BinariesDirectory)'
# Esrp signing
- template: win-esrp-dll.yml
parameters:
FolderPath: '$(Build.BinariesDirectory)\RelWithDebInfo\RelWithDebInfo\onnxruntime\capi'
DisplayName: 'ESRP - Sign Native dlls'
DoEsrp: true
Pattern: '*.pyd,*.dll'
- task: PythonScript@0
displayName: 'Build wheel'
inputs:
scriptPath: '$(Build.SourcesDirectory)\setup.py'
arguments: 'bdist_wheel ${{ parameters.BUILD_PY_PARAMETERS }} $(NightlyBuildOption) --wheel_name_suffix=${{ parameters.EP_NAME }}'
workingDirectory: '$(Build.BinariesDirectory)\RelWithDebInfo\RelWithDebInfo'
- task: CopyFiles@2
displayName: 'Copy Python Wheel to: $(Build.ArtifactStagingDirectory)'
inputs:
SourceFolder: '$(Build.BinariesDirectory)\RelWithDebInfo\RelWithDebInfo\dist'
Contents: '*.whl'
TargetFolder: '$(Build.ArtifactStagingDirectory)'
- task: PublishBuildArtifacts@1
displayName: 'Publish Artifact: ONNXRuntime python wheel'
inputs:
ArtifactName: onnxruntime_${{ parameters.EP_NAME }}
- script: |
7z x *.whl
workingDirectory: '$(Build.ArtifactStagingDirectory)'
displayName: 'unzip the package'
- task: CredScan@3
displayName: 'Run CredScan'
inputs:
debugMode: false
continueOnError: true
- task: BinSkim@4
displayName: 'Run BinSkim'
inputs:
AnalyzeTargetGlob: '+:file|$(Build.ArtifactStagingDirectory)\**\*.dll;-:file|$(Build.ArtifactStagingDirectory)\**\DirectML.dll'
- stage: Win_py_${{ parameters.EP_NAME }}_Wheels_${{ replace(parameters.PYTHON_VERSION,'.','_') }}_Tests
dependsOn: Win_py_${{ parameters.EP_NAME }}_Wheels_${{ replace(parameters.PYTHON_VERSION,'.','_') }}_Build
jobs:
- job: Win_py_${{ parameters.EP_NAME }}_Wheels_${{ replace(parameters.PYTHON_VERSION,'.','_') }}_Tests
workspace:
clean: all
pool:
name: onnxruntime-Win2022-GPU-T4
steps:
- task: mspremier.PostBuildCleanup.PostBuildCleanup-task.PostBuildCleanup@3
displayName: 'Clean Agent Directories'
condition: always()
- checkout: self
clean: true
submodules: none
- task: UsePythonVersion@0
inputs:
versionSpec: ${{ parameters.PYTHON_VERSION }}
addToPath: true
architecture: 'x64'
- template: flex-downloadPipelineArtifact.yml
parameters:
ArtifactName: "onnxruntime_${{ parameters.EP_NAME }}"
StepName: 'Download Pipeline Artifact - Windows GPU Build'
TargetPath: '$(Build.ArtifactStagingDirectory)'
SpecificArtifact: ${{ parameters.SpecificArtifact }}
BuildId: ${{ parameters.BuildId }}
# It could be remove once there's onnx wheel for python 3.12
- ${{ if eq(parameters.PYTHON_VERSION, '3.12') }}:
- template: flex-downloadPipelineArtifact.yml
parameters:
ArtifactName: "onnx_py12_wheel"
StepName: 'Download Pipeline Artifact - Onnx Python12 wheel'
TargetPath: '$(Agent.TempDirectory)\onnx\'
SpecificArtifact: ${{ parameters.SpecificArtifact }}
BuildId: ${{ parameters.BuildId }}
- powershell: |
python -m pip install upgrade pip
Get-ChildItem -Path $(Agent.TempDirectory)\onnx\*.whl | foreach {pip --disable-pip-version-check install --upgrade $_.fullname tabulate}
python -m pip install pytest
workingDirectory: '$(Build.SourcesDirectory)'
displayName: 'Install ONNX and pytest'
- ${{ else }}:
- powershell: |
pushd onnxruntime/test/python
python -m pip install --upgrade pip
python -m pip install -r requirements.txt
popd
workingDirectory: '$(Build.SourcesDirectory)'
displayName: 'Install ONNX'
- powershell: |
python -m pip uninstall -y ort-nightly-gpu ort-nightly onnxruntime onnxruntime-gpu -qq
Get-ChildItem -Path $(Build.ArtifactStagingDirectory)/*cp${{ replace(parameters.PYTHON_VERSION,'.','') }}*.whl | foreach {pip --disable-pip-version-check install --upgrade $_.fullname tabulate}
mkdir -p $(Agent.TempDirectory)\ort_test_data
Copy-Item -Path $(Build.sourcesDirectory)/onnxruntime/test/python/onnx_backend_test_series.py -Destination $(Agent.TempDirectory)\ort_test_data
Copy-Item -Recurse -Path $(Build.sourcesDirectory)/onnxruntime/test/testdata -Destination $(Agent.TempDirectory)\ort_test_data
cd $(Agent.TempDirectory)\ort_test_data
python onnx_backend_test_series.py
workingDirectory: '$(Build.sourcesDirectory)'
displayName: 'Run Python Tests'
- task: TSAUpload@2
displayName: 'TSA upload'
condition: and (succeeded(), eq(variables['Build.SourceBranch'], 'refs/heads/main'))
inputs:
GdnPublishTsaOnboard: false
GdnPublishTsaConfigFile: '$(Build.sourcesDirectory)\.gdn\.gdntsa'
- template: component-governance-component-detection-steps.yml
parameters:
condition: 'succeeded'