Generate GPU L2 size inputs in flash_attention Triton Bench #2580
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: TritonBench PR Test | |
| on: | |
| pull_request: | |
| paths: | |
| - .github/workflows/pr.yml | |
| - .github/workflows/_linux-test-*.yml | |
| - tritonbench/** | |
| push: | |
| branches: | |
| - main | |
| jobs: | |
| h100-pytorch-test: | |
| uses: ./.github/workflows/_linux-test-h100.yml | |
| with: | |
| conda_env: "pytorch" | |
| h100-triton-main-test: | |
| uses: ./.github/workflows/_linux-test-h100.yml | |
| with: | |
| conda_env: "triton-main" | |
| mi350-triton-main-test: | |
| uses: ./.github/workflows/_linux-test-mi350.yml | |
| with: | |
| conda_env: "triton-main" | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}-${{ github.event_name == 'workflow_dispatch' }} | |
| cancel-in-progress: true |