diff --git a/.claude/skills/ci-workflow-guide/SKILL.md b/.claude/skills/ci-workflow-guide/SKILL.md index 430f5a306..8877ba300 100644 --- a/.claude/skills/ci-workflow-guide/SKILL.md +++ b/.claude/skills/ci-workflow-guide/SKILL.md @@ -270,7 +270,7 @@ Large suites are split across matrix jobs using the **LPT (Longest Processing Ti | Suite | Partitions | Runner | max_parallel | |-------|-----------|--------|-------------| | `stage-a-test-1-gpu-small` | 1 (no matrix) | `1-gpu-5090` | — | -| `stage-a-test-cpu` | 1 (no matrix) | `ubuntu-latest` | — | +| `stage-a-test-cpu` | 4 | `ubuntu-latest` | — | | `stage-b-test-1-gpu-small` | 8 | `1-gpu-5090` | 8 | | `stage-b-test-1-gpu-large` | 14 | `1-gpu-h100` | dynamic (3 or 14) | | `stage-b-test-2-gpu-large` | 4 | `2-gpu-h100` | — | diff --git a/.github/workflows/pr-test.yml b/.github/workflows/pr-test.yml index dcef4f7e5..fdb549f6f 100644 --- a/.github/workflows/pr-test.yml +++ b/.github/workflows/pr-test.yml @@ -361,7 +361,7 @@ jobs: id: wait with: stage-name: stage-a - jobs: '["stage-a-test-1-gpu-small", "stage-a-test-cpu"]' + jobs: '["stage-a-test-1-gpu-small", {"prefix": "stage-a-test-cpu", "expected_count": 4}]' max-wait-minutes: '240' wait-for-stage-b: @@ -616,6 +616,10 @@ jobs: ) runs-on: ubuntu-latest timeout-minutes: 240 + strategy: + fail-fast: false + matrix: + partition: [0, 1, 2, 3] steps: - name: Free disk space run: | @@ -661,7 +665,7 @@ jobs: CONTINUE_ON_ERROR_FLAG: ${{ needs.check-changes.outputs.continue_on_error == 'true' && '--continue-on-error' || '' }} run: | cd test/ - python3 run_suite.py --hw cpu --suite stage-a-test-cpu $CONTINUE_ON_ERROR_FLAG + python3 run_suite.py --hw cpu --suite stage-a-test-cpu --auto-partition-id ${{ matrix.partition }} --auto-partition-size 4 $CONTINUE_ON_ERROR_FLAG # Runs on 5090 (32GB, SM120) stage-b-test-1-gpu-small: