Limited CI on H100 #791
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
| # Owner(s): ["module: cuda"] | |
| name: Limited CI on H100 | |
| on: | |
| pull_request: | |
| paths: | |
| - .github/workflows/test-h100.yml | |
| - test/inductor/test_max_autotune.py | |
| - torch/_inductor/kernel/mm.py | |
| - torch/_inductor/kernel/mm_grouped.py | |
| workflow_dispatch: | |
| schedule: | |
| - cron: 0 4,10,16,22 * * * # every 6 hours | |
| push: | |
| tags: | |
| - ciflow/h100/* | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}-${{ github.event_name == 'workflow_dispatch' }}-${{ github.event_name == 'schedule' }} | |
| cancel-in-progress: true | |
| permissions: | |
| id-token: write | |
| contents: read | |
| actions: read | |
| jobs: | |
| get-label-type: | |
| if: github.repository_owner == 'pytorch' | |
| name: get-label-type | |
| uses: pytorch/pytorch/.github/workflows/_runner-determinator.yml@main | |
| with: | |
| triggering_actor: ${{ github.triggering_actor }} | |
| issue_owner: ${{ github.event.pull_request.user.login || github.event.issue.user.login }} | |
| curr_branch: ${{ github.head_ref || github.ref_name }} | |
| curr_ref_type: ${{ github.ref_type }} | |
| check_experiments: arc,lf | |
| linux-jammy-cuda13_0-py3_10-gcc11-sm90-build: | |
| name: linux-jammy-cuda13.0-py3.10-gcc11-sm90 | |
| uses: ./.github/workflows/_linux-build.yml | |
| needs: get-label-type | |
| with: | |
| runner_prefix: "${{ needs.get-label-type.outputs.label-type }}" | |
| build-environment: linux-jammy-cuda13.0-py3.10-gcc11-sm90 | |
| docker-image-name: ci-image:pytorch-linux-jammy-cuda13.0-cudnn9-py3-gcc11 | |
| ci-docker-hash: ${{ needs.get-label-type.outputs.ci-docker-hash }} | |
| cuda-arch-list: '9.0' | |
| test-matrix: | | |
| { include: [ | |
| { config: "smoke", shard: 1, num_shards: 1, runner: "linux.aws.h100" }, | |
| ]} | |
| use-arc: ${{ needs.get-label-type.outputs.use-arc == 'true' }} | |
| python-version: "3.10" | |
| compiler: gcc11 | |
| cuda-version: "13.0" | |
| secrets: inherit | |
| linux-jammy-cuda13_0-py3_10-gcc11-sm90-test: | |
| name: linux-jammy-cuda13.0-py3.10-gcc11-sm90 | |
| uses: ./.github/workflows/_linux-test.yml | |
| needs: | |
| - linux-jammy-cuda13_0-py3_10-gcc11-sm90-build | |
| - get-label-type | |
| with: | |
| build-environment: ${{ needs.linux-jammy-cuda13_0-py3_10-gcc11-sm90-build.outputs.build-environment }} | |
| docker-image: ${{ needs.linux-jammy-cuda13_0-py3_10-gcc11-sm90-build.outputs.docker-image }} | |
| test-matrix: ${{ needs.linux-jammy-cuda13_0-py3_10-gcc11-sm90-build.outputs.test-matrix }} | |
| use-arc: ${{ needs.get-label-type.outputs.use-arc == 'true' }} | |
| python-version: "3.10" | |
| compiler: gcc11 | |
| cuda-version: "13.0" | |
| secrets: inherit | |
| linux-jammy-cuda13_0-py3_10-gcc11-sm90-FA3-ABI-stable-test: | |
| name: linux-jammy-cuda13_0-py3_10-gcc11-sm90-FA3-ABI-stable-test | |
| uses: ./.github/workflows/_linux-test-stable-fa3.yml | |
| needs: | |
| - linux-jammy-cuda13_0-py3_10-gcc11-sm90-build | |
| - get-label-type | |
| with: | |
| build-environment: linux-jammy-cuda13.0-py3.10-gcc11-sm90 | |
| docker-image: ${{ needs.linux-jammy-cuda13_0-py3_10-gcc11-sm90-build.outputs.docker-image }} | |
| timeout-minutes: 30 | |
| s3-bucket: gha-artifacts | |
| use-arc: ${{ needs.get-label-type.outputs.use-arc == 'true' }} | |
| python-version: "3.10" | |
| compiler: gcc11 | |
| cuda-version: "13.0" | |
| secrets: inherit |