[SPMD] Add debug of SPMD for single/multi host #3321
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
| on: | |
| pull_request: | |
| branches: | |
| - master | |
| - r[0-9]+.[0-9]+ | |
| push: | |
| branches: | |
| - master | |
| - r[0-9]+.[0-9]+ | |
| 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: | |
| build: | |
| name: "Build XLA" | |
| uses: ./.github/workflows/_build.yml | |
| with: | |
| ecr-docker-image-base: 308535385114.dkr.ecr.us-east-1.amazonaws.com/pytorch/xla_base | |
| gcr-docker-image: gcr.io/tpu-pytorch/xla_base:dev-3.8_cuda_12.1 | |
| cuda: 1 | |
| secrets: | |
| gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }} | |
| test-cpu: | |
| name: "CPU tests" | |
| uses: ./.github/workflows/_test.yml | |
| needs: build | |
| with: | |
| docker-image: ${{ needs.build.outputs.docker-image }} | |
| timeout-minutes: 90 | |
| disable-xrt: 1 | |
| secrets: | |
| gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }} | |
| test-cuda: | |
| name: "GPU tests" | |
| uses: ./.github/workflows/_test.yml | |
| needs: build | |
| with: | |
| docker-image: ${{ needs.build.outputs.docker-image }} | |
| runner: linux.8xlarge.nvidia.gpu | |
| timeout-minutes: 180 | |
| disable-xrt: 1 | |
| secrets: | |
| gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }} | |
| test-cpu-coverage: | |
| name: "Collect CPU test coverage" | |
| if: github.event_name == 'push' && github.event.ref == 'refs/heads/master' | |
| uses: ./.github/workflows/_coverage.yml | |
| needs: build | |
| with: | |
| docker-image: ${{ needs.build.outputs.docker-image }} | |
| collect-coverage: true | |
| timeout-minutes: 120 | |
| disable-xrt: 1 | |
| secrets: | |
| gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }} | |
| test-gpu-coverage: | |
| name: "Collect GPU test coverage" | |
| if: github.event_name == 'push' && github.event.ref == 'refs/heads/master' | |
| uses: ./.github/workflows/_coverage.yml | |
| needs: build | |
| with: | |
| docker-image: ${{ needs.build.outputs.docker-image }} | |
| runner: linux.8xlarge.nvidia.gpu | |
| timeout-minutes: 300 | |
| collect-coverage: true | |
| disable-xrt: 1 | |
| secrets: | |
| gcloud-service-key: ${{ secrets.GCLOUD_SERVICE_KEY }} | |
| push-docs: | |
| name: "Build & publish docs" | |
| if: github.event_name == 'push' && (github.event.ref == 'refs/heads/master' || startsWith(github.event.ref, 'refs/tags/r')) | |
| uses: ./.github/workflows/_docs.yml | |
| needs: build | |
| with: | |
| docker-image: ${{ needs.build.outputs.docker-image }} | |
| secrets: | |
| torchxla-bot-token: ${{ secrets.TORCH_XLA_BOT_TOKEN }} |