resources: pipelines: - pipeline: build source: 'Python-CUDA-Packaging-Pipeline' trigger: true branch: main # branch to pick the artifact, Used only for manual triggered pipeline runs for testing the pipeline itself stages: # ****The following Stage depend on all previous tags. *** # GPU resources are very limited, # To utilize gpu resource more efficiently, run GPU job only after all cpus jobs succeed - stage: Linux_Test_CUDA_x86_64_stage dependsOn: jobs: - template: templates/py-packaging-linux-test-cuda.yml parameters: arch: 'x86_64' machine_pool: 'Onnxruntime-Linux-GPU' python_wheel_suffix: '_gpu' timeout: 480 docker_base_image: onnxruntimebuildcache.azurecr.io/internal/azureml/onnxruntime/build/cuda12_x64_ubi8_gcc12:20250124.1 cuda_version: '12.2' - stage: Republish_Wheels dependsOn: jobs: - job: Python_Publishing_GPU pool: 'onnxruntime-Ubuntu2204-AMD-CPU' steps: - checkout: none - download: build displayName: 'Download Pipeline Artifact - onnxruntime_gpu' artifact: 'onnxruntime_gpu' patterns: '*.whl' - download: build displayName: 'Download Pipeline Artifact - Win GPU 3.10' artifact: 'win_gpu_wheel_3.10' patterns: '*.whl' - download: build displayName: 'Download Pipeline Artifact - Win GPU 3.11' artifact: 'win_gpu_wheel_3.11' patterns: '*.whl' - download: build displayName: 'Download Pipeline Artifact - Win GPU 3.12' artifact: 'win_gpu_wheel_3.12' patterns: '*.whl' - download: build displayName: 'Download Pipeline Artifact - Win GPU 3.13' artifact: 'win_gpu_wheel_3.13' patterns: '*.whl' - script: find $(Pipeline.Workspace) -name \*win_amd64.whl -exec mv {} $(Pipeline.Workspace)/build/onnxruntime_gpu \; displayName: 'Merge files together' - publish: $(Pipeline.Workspace)/build/onnxruntime_gpu artifact: whl displayName: Republish artifacts