Add archive pipeline: SakanaAI-format T4 dataset generator (45 problems, Jaxpr IR, LLM variants) #11
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: CPU Correctness (interpret=True) | |
| on: | |
| push: | |
| branches: [main, master] | |
| pull_request: | |
| branches: [main, master] | |
| jobs: | |
| correctness: | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| os: [ubuntu-latest, macos-latest] | |
| python-version: ["3.11", "3.12"] | |
| runs-on: ${{ matrix.os }} | |
| name: correctness (${{ matrix.os }}, py${{ matrix.python-version }}) | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: Set up Python | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: ${{ matrix.python-version }} | |
| - name: Install dependencies | |
| run: | | |
| pip install -e ".[dev]" | |
| - name: Run correctness tests (interpret=True, SMALL size) | |
| run: | | |
| python scripts/run_benchmark.py \ | |
| --levels 1 2 3 \ | |
| --size SMALL \ | |
| --interpret \ | |
| --correctness-only \ | |
| --output-dir results/ | |
| env: | |
| JAX_PLATFORMS: cpu | |
| - name: Upload results | |
| uses: actions/upload-artifact@v4 | |
| if: always() | |
| with: | |
| name: correctness-${{ matrix.os }}-py${{ matrix.python-version }} | |
| path: results/*.json |