[CPU] MoE Kernel #6208
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Windows GPU TensorRT CI Pipeline | |
| on: | |
| push: | |
| branches: | |
| - main | |
| - rel-* | |
| pull_request: | |
| branches: | |
| - main | |
| - rel-* | |
| workflow_dispatch: | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.event_name == 'pull_request' && github.ref || github.sha }} | |
| cancel-in-progress: true | |
| #TODO: enable --build_nodejs | |
| jobs: | |
| build: | |
| name: Windows GPU TensorRT CI Pipeline | |
| runs-on: ["self-hosted", "1ES.Pool=onnxruntime-github-vs2022-mms"] | |
| steps: | |
| - uses: actions/checkout@v5 | |
| with: | |
| fetch-depth: 0 | |
| submodules: 'none' | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: '3.12' | |
| architecture: x64 | |
| - name: Locate vcvarsall and Setup Env | |
| uses: ./.github/actions/locate-vcvarsall-and-setup-env | |
| with: | |
| architecture: x64 | |
| - name: Install python modules | |
| run: python -m pip install -r .\tools\ci_build\github\windows\python\requirements.txt | |
| working-directory: ${{ github.workspace }} | |
| shell: cmd | |
| - name: Download CUDA SDK v12.2 | |
| working-directory: ${{ runner.temp }} | |
| run: | | |
| azcopy.exe cp --recursive "https://lotusscus.blob.core.windows.net/models/cuda_sdk/v12.2" . | |
| dir | |
| shell: pwsh | |
| - name: Download TensorRT-10.9.0.34.Windows10.x86_64.cuda-12.8 | |
| run: 'azcopy.exe cp --recursive "https://lotusscus.blob.core.windows.net/models/local/TensorRT-10.9.0.34.Windows10.x86_64.cuda-12.8" ${{ runner.temp }}' | |
| shell: pwsh | |
| - name: Add CUDA to PATH | |
| shell: powershell | |
| run: | | |
| Write-Host "Adding CUDA to PATH" | |
| Write-Host "CUDA Path: $env:RUNNER_TEMP\v12.2\bin" | |
| Add-Content -Path $env:GITHUB_PATH -Value "$env:RUNNER_TEMP\v12.2\bin" | |
| Add-Content -Path $env:GITHUB_PATH -Value "$env:RUNNER_TEMP\v12.2\extras\CUPTI\lib64" | |
| Add-Content -Path $env:GITHUB_PATH -Value "$env:RUNNER_TEMP\TensorRT-10.9.0.34.Windows10.x86_64.cuda-12.8\lib" | |
| - uses: actions/setup-node@v4 | |
| with: | |
| node-version: '20.x' | |
| - uses: actions/setup-java@v5 | |
| with: | |
| distribution: 'temurin' | |
| java-version: '17' | |
| architecture: x64 | |
| - uses: actions/cache@v4 | |
| id: onnx-node-tests-cache | |
| with: | |
| path: ${{ github.workspace }}/js/test/ | |
| key: onnxnodetests-${{ hashFiles('js/scripts/prepare-onnx-node-tests.ts') }} | |
| - name: API Documentation Check and generate | |
| run: | | |
| set ORT_DOXY_SRC=${{ github.workspace }} | |
| set ORT_DOXY_OUT=${{ runner.temp }}\build\RelWithDebInfo\RelWithDebInfo | |
| mkdir %ORT_DOXY_SRC% | |
| mkdir %ORT_DOXY_OUT% | |
| "C:\Program Files\doxygen\bin\doxygen.exe" ${{ github.workspace }}\tools\ci_build\github\Doxyfile_csharp.cfg | |
| working-directory: ${{ github.workspace }} | |
| shell: cmd | |
| - uses: actions/setup-dotnet@v4 | |
| env: | |
| PROCESSOR_ARCHITECTURE: x64 | |
| with: | |
| dotnet-version: '8.x' | |
| - name: Use Nuget 6.x | |
| uses: nuget/setup-nuget@v2 | |
| with: | |
| nuget-version: '6.x' | |
| - name: NuGet restore | |
| run: nuget restore ${{ github.workspace }}\packages.config -ConfigFile ${{ github.workspace }}\NuGet.config -PackagesDirectory ${{ runner.temp }}\build\RelWithDebInfo | |
| shell: cmd | |
| - name: Set OnnxRuntimeBuildDirectory | |
| shell: pwsh | |
| run: | | |
| $buildDir = Join-Path ${{ runner.temp }} "build" | |
| echo "OnnxRuntimeBuildDirectory=$buildDir" >> $env:GITHUB_ENV | |
| - name: Build and Clean Binaries | |
| working-directory: ${{ runner.temp }} | |
| run: | | |
| npm install -g typescript | |
| if ($lastExitCode -ne 0) { | |
| exit $lastExitCode | |
| } | |
| # Execute the build process | |
| python ${{ github.workspace }}\tools\ci_build\build.py --config RelWithDebInfo --parallel --use_binskim_compliant_compile_flags --build_dir build --skip_submodule_sync --build_shared_lib --build --update --cmake_generator "Visual Studio 17 2022" --build_wheel --enable_onnx_tests --use_tensorrt --tensorrt_home="${{ runner.temp }}\TensorRT-10.9.0.34.Windows10.x86_64.cuda-12.8" --cuda_home="${{ runner.temp }}\v12.2" --use_vcpkg --use_vcpkg_ms_internal_asset_cache --cmake_extra_defines CMAKE_CUDA_ARCHITECTURES=86 | |
| if ($lastExitCode -ne 0) { | |
| exit $lastExitCode | |
| } | |
| # Clean up the output directory before uploading artifacts | |
| $outputDir = "${{ runner.temp }}\build\RelWithDebInfo" | |
| Write-Host "Cleaning up files from $outputDir..." | |
| Remove-Item -Path "$outputDir\onnxruntime" -Recurse -Force -ErrorAction SilentlyContinue | |
| Remove-Item -Path "$outputDir\pybind11" -Recurse -Force -ErrorAction SilentlyContinue | |
| Remove-Item -Path "$outputDir\models" -Recurse -Force -ErrorAction SilentlyContinue | |
| Remove-Item -Path "$outputDir\vcpkg_installed" -Recurse -Force -ErrorAction SilentlyContinue | |
| Remove-Item -Path "$outputDir\_deps" -Recurse -Force -ErrorAction SilentlyContinue | |
| Remove-Item -Path "$outputDir\CMakeCache.txt" -Force -ErrorAction SilentlyContinue | |
| Remove-Item -Path "$outputDir\CMakeFiles" -Recurse -Force -ErrorAction SilentlyContinue | |
| # Remove intermediate object files as in the original script | |
| Remove-Item -Path $outputDir -Include "*.obj" -Recurse | |
| shell: pwsh | |
| - name: Upload build artifacts | |
| uses: actions/upload-artifact@v4 | |
| with: | |
| name: build-artifacts | |
| path: ${{ runner.temp }}\build | |
| env: | |
| OrtPackageId: Microsoft.ML.OnnxRuntime.Gpu | |
| DOTNET_SKIP_FIRST_TIME_EXPERIENCE: true | |
| setVcvars: true | |
| ALLOW_RELEASED_ONNX_OPSET_ONLY: '0' | |
| DocUpdateNeeded: false | |
| ONNXRUNTIME_TEST_GPU_DEVICE_ID: '0' | |
| AZCOPY_AUTO_LOGIN_TYPE: MSI | |
| AZCOPY_MSI_CLIENT_ID: 63b63039-6328-442f-954b-5a64d124e5b4 | |
| test: | |
| name: Windows GPU TensorRT CI Pipeline Test Job | |
| needs: build | |
| timeout-minutes: 300 | |
| runs-on: ["self-hosted", "1ES.Pool=onnxruntime-github-Win2022-GPU-A10"] | |
| steps: | |
| - uses: actions/checkout@v5 | |
| with: | |
| fetch-depth: 0 | |
| submodules: 'none' | |
| - name: Download build artifacts | |
| uses: actions/download-artifact@v5 | |
| with: | |
| name: build-artifacts | |
| path: ${{ runner.temp }}\build | |
| - uses: actions/setup-python@v5 | |
| with: | |
| python-version: '3.12' | |
| architecture: x64 | |
| - uses: actions/setup-node@v4 | |
| with: | |
| node-version: '20.x' | |
| - uses: actions/setup-java@v5 | |
| with: | |
| distribution: 'temurin' | |
| java-version: '17' | |
| architecture: x64 | |
| - name: Locate vcvarsall and Setup Env | |
| uses: ./.github/actions/locate-vcvarsall-and-setup-env | |
| with: | |
| architecture: x64 | |
| - name: Install python modules | |
| run: python -m pip install -r .\tools\ci_build\github\windows\python\requirements.txt | |
| working-directory: ${{ github.workspace }} | |
| shell: cmd | |
| - name: Download CUDA SDK v12.2 | |
| working-directory: ${{ runner.temp }} | |
| run: | | |
| azcopy.exe cp --recursive "https://lotusscus.blob.core.windows.net/models/cuda_sdk/v12.2" . | |
| dir | |
| shell: pwsh | |
| - name: Download TensorRT-10.9.0.34.Windows10.x86_64.cuda-12.8 | |
| run: 'azcopy.exe cp --recursive "https://lotusscus.blob.core.windows.net/models/local/TensorRT-10.9.0.34.Windows10.x86_64.cuda-12.8" ${{ runner.temp }}' | |
| shell: pwsh | |
| - name: Add CUDA to PATH | |
| shell: powershell | |
| run: | | |
| Write-Host "Adding CUDA to PATH" | |
| Write-Host "CUDA Path: $env:RUNNER_TEMP\v12.2\bin" | |
| Add-Content -Path $env:GITHUB_PATH -Value "$env:RUNNER_TEMP\v12.2\bin" | |
| Add-Content -Path $env:GITHUB_PATH -Value "$env:RUNNER_TEMP\v12.2\extras\CUPTI\lib64" | |
| Add-Content -Path $env:GITHUB_PATH -Value "$env:RUNNER_TEMP\TensorRT-10.9.0.34.Windows10.x86_64.cuda-12.8\lib" | |
| - name: Set OnnxRuntimeBuildDirectory | |
| shell: pwsh | |
| run: | | |
| $buildDir = Join-Path ${{ runner.temp }} "build" | |
| echo "OnnxRuntimeBuildDirectory=$buildDir" >> $env:GITHUB_ENV | |
| - name: Install ONNX Runtime Wheel | |
| uses: ./.github/actions/install-onnxruntime-wheel | |
| with: | |
| whl-directory: ${{ runner.temp }}\build\RelWithDebInfo\RelWithDebInfo\dist | |
| - name: Run Tests | |
| working-directory: ${{ runner.temp }} | |
| run: | | |
| npm install -g typescript | |
| if ($lastExitCode -ne 0) { | |
| exit $lastExitCode | |
| } | |
| python.exe ${{ github.workspace }}\tools\python\update_ctest_path.py "${{ runner.temp }}\build\RelWithDebInfo\CTestTestfile.cmake" "${{ runner.temp }}\build\RelWithDebInfo" | |
| if ($lastExitCode -ne 0) { | |
| exit $lastExitCode | |
| } | |
| python ${{ github.workspace }}\tools\ci_build\build.py --config RelWithDebInfo --parallel --use_binskim_compliant_compile_flags --build_dir build --skip_submodule_sync --build_shared_lib --test --cmake_generator "Visual Studio 17 2022" --build_wheel --enable_onnx_tests --use_tensorrt --tensorrt_home="${{ runner.temp }}\TensorRT-10.9.0.34.Windows10.x86_64.cuda-12.8" --cuda_home="${{ runner.temp }}\v12.2" --use_vcpkg --use_vcpkg_ms_internal_asset_cache --cmake_extra_defines CMAKE_CUDA_ARCHITECTURES=86 | |
| if ($lastExitCode -ne 0) { | |
| exit $lastExitCode | |
| } | |
| shell: pwsh | |
| - name: Validate C# native delegates | |
| run: python tools\ValidateNativeDelegateAttributes.py | |
| working-directory: ${{ github.workspace }}\csharp | |
| shell: cmd | |
| env: | |
| OrtPackageId: Microsoft.ML.OnnxRuntime.Gpu | |
| DOTNET_SKIP_FIRST_TIME_EXPERIENCE: true | |
| setVcvars: true | |
| ALLOW_RELEASED_ONNX_OPSET_ONLY: '0' | |
| DocUpdateNeeded: false | |
| ONNXRUNTIME_TEST_GPU_DEVICE_ID: '0' | |
| AZCOPY_AUTO_LOGIN_TYPE: MSI | |
| AZCOPY_MSI_CLIENT_ID: 63b63039-6328-442f-954b-5a64d124e5b4 |