Test Example on Schedule #52
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
| name: Test Example on Schedule | |
| on: | |
| # run at 00:00 of every Sunday(singapore time) so here is UTC time Saturday 16:00 | |
| schedule: | |
| - cron: '0 16 * * 6' | |
| workflow_dispatch: | |
| jobs: | |
| # This is for all files' weekly check. Specifically, this job is to find all the directories. | |
| matrix_preparation: | |
| if: github.repository == 'hpcaitech/ColossalAI' | |
| name: Prepare matrix for weekly check | |
| runs-on: ubuntu-latest | |
| outputs: | |
| matrix: ${{ steps.setup-matrix.outputs.matrix }} | |
| steps: | |
| - name: 📚 Checkout | |
| uses: actions/checkout@v3 | |
| - name: setup matrix | |
| id: setup-matrix | |
| run: | | |
| res=`python .github/workflows/scripts/example_checks/check_example_weekly.py` | |
| all_loc=$( IFS=',' ; echo "${res[*]}" ) | |
| echo "Found the examples: $all_loc" | |
| echo "matrix={\"directory\":$(echo "$all_loc")}" >> $GITHUB_OUTPUT | |
| weekly_check: | |
| if: github.repository == 'hpcaitech/ColossalAI' | |
| name: Weekly check all examples | |
| needs: matrix_preparation | |
| runs-on: [self-hosted, gpu] | |
| strategy: | |
| fail-fast: false | |
| matrix: ${{fromJson(needs.matrix_preparation.outputs.matrix)}} | |
| container: | |
| image: hpcaitech/pytorch-cuda:2.1.0-12.1.0 | |
| timeout-minutes: 10 | |
| steps: | |
| - name: 📚 Checkout | |
| uses: actions/checkout@v3 | |
| - name: Install Colossal-AI | |
| run: | | |
| CUDA_EXT=1 pip install -v . | |
| - name: Traverse all files | |
| run: | | |
| example_dir=${{ matrix.directory }} | |
| echo "Testing ${example_dir} now" | |
| cd "${PWD}/examples/${example_dir}" | |
| bash test_ci.sh | |
| env: | |
| NCCL_SHM_DISABLE: 1 | |
| - name: Notify Lark | |
| id: message-preparation | |
| if: ${{ failure() }} | |
| run: | | |
| url=$SERVER_URL/$REPO/actions/runs/$RUN_ID | |
| msg="Example tests failed for $EXAMPLE_DIR, please visit $url for details" | |
| echo $msg | |
| python .github/workflows/scripts/send_message_to_lark.py -m "$msg" -u $WEBHOOK_URL | |
| env: | |
| SERVER_URL: ${{github.server_url }} | |
| REPO: ${{ github.repository }} | |
| RUN_ID: ${{ github.run_id }} | |
| WEBHOOK_URL: ${{ secrets.LARK_NOTIFICATION_WEBHOOK_URL }} | |
| EXAMPLE_DIR: ${{ matrix.directory }} |