[benchmarks] Fix verifier error handling and OOM. #9592
This file contains 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: Build and test | |
| on: | |
| pull_request: | |
| branches: | |
| - master | |
| - r[0-9]+.[0-9]+ | |
| paths-ignore: | |
| - 'experimental/torch_xla2/**' | |
| push: | |
| branches: | |
| - master | |
| - r[0-9]+.[0-9]+ | |
| paths-ignore: | |
| - 'experimental/torch_xla2/**' | |
| workflow_dispatch: | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}-${{ github.event_name == 'workflow_dispatch' }}-${{ github.event_name == 'schedule' }} | |
| cancel-in-progress: true | |
| jobs: | |
| get-torch-commit: | |
| runs-on: ubuntu-latest | |
| outputs: | |
| torch_commit: ${{ steps.commit.outputs.torch_commit }} | |
| steps: | |
| - id: commit | |
| name: Get latest torch commit | |
| run: | | |
| echo "torch_commit=$(git ls-remote https://github.com/pytorch/pytorch.git HEAD | awk '{print $1}')" >> "$GITHUB_OUTPUT" | |
| build-torch-xla: | |
| name: "Build PyTorch/XLA" | |
| uses: ./.github/workflows/_build_torch_xla.yml | |
| needs: get-torch-commit | |
| with: | |
| dev-image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/development:3.10_tpuvm | |
| torch-commit: ${{needs.get-torch-commit.outputs.torch_commit}} | |
| secrets: | |
| gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }} | |
| build-torch-with-cuda: | |
| name: "Build PyTorch with CUDA" | |
| uses: ./.github/workflows/_build_torch_with_cuda.yml | |
| needs: get-torch-commit | |
| with: | |
| # note that to build a torch wheel with CUDA enabled, we do not need a GPU runner. | |
| dev-image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/development:3.10_cuda_12.1 | |
| torch-commit: ${{needs.get-torch-commit.outputs.torch_commit}} | |
| runner: linux.24xlarge | |
| build-cuda-plugin: | |
| name: "Build XLA CUDA plugin" | |
| uses: ./.github/workflows/_build_plugin.yml | |
| with: | |
| dev-image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/development:3.10_cuda_12.1 | |
| secrets: | |
| gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }} | |
| test-python-cpu: | |
| name: "CPU tests" | |
| uses: ./.github/workflows/_test.yml | |
| needs: [build-torch-xla, get-torch-commit] | |
| with: | |
| dev-image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/development:3.10_tpuvm | |
| timeout-minutes: 120 | |
| collect-coverage: false | |
| torch-commit: ${{needs.get-torch-commit.outputs.torch_commit}} | |
| secrets: | |
| gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }} | |
| test-cuda: | |
| name: "GPU tests" | |
| uses: ./.github/workflows/_test.yml | |
| needs: [build-torch-xla, build-cuda-plugin, get-torch-commit] | |
| with: | |
| dev-image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/development:3.10_cuda_12.1 | |
| runner: linux.8xlarge.nvidia.gpu | |
| timeout-minutes: 300 | |
| collect-coverage: false | |
| install-cuda-plugin: true | |
| torch-commit: ${{needs.get-torch-commit.outputs.torch_commit}} | |
| secrets: | |
| gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }} | |
| test-cuda-with-pytorch-cuda-enabled: | |
| name: "GPU tests requiring torch CUDA" | |
| uses: ./.github/workflows/_test_requiring_torch_cuda.yml | |
| needs: [build-torch-with-cuda, build-torch-xla, build-cuda-plugin, get-torch-commit] | |
| with: | |
| dev-image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/development:3.10_cuda_12.1 | |
| runner: linux.8xlarge.nvidia.gpu | |
| timeout-minutes: 300 | |
| collect-coverage: false | |
| torch-commit: ${{needs.get-torch-commit.outputs.torch_commit}} | |
| test-tpu: | |
| name: "TPU tests" | |
| uses: ./.github/workflows/_tpu_ci.yml | |
| needs: build-torch-xla | |
| # Only run this for HEAD and releases | |
| if: github.event_name == 'push' || contains(github.event.pull_request.labels.*.name, 'tpuci') | |
| push-docs: | |
| name: "Build docs" | |
| uses: ./.github/workflows/_docs.yml | |
| needs: build-torch-xla | |
| with: | |
| dev-image: us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/development:3.10_tpuvm | |
| secrets: | |
| torchxla-bot-token: ${{ secrets.TORCH_XLA_BOT_TOKEN }} |