Refactor CI and e2e tests #259
Workflow file for this run
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
| ################################################################################ | |
| # This file is auto-generated from the .j2 file via generate_github_workflows.py. Do not edit manually. | |
| ################################################################################ | |
| name: PR Test | |
| on: | |
| # Do not run CI on push to reduce CI time | |
| # push: | |
| # branches: [main] | |
| pull_request: | |
| branches: [main] | |
| types: [synchronize, labeled] | |
| workflow_dispatch: | |
| inputs: | |
| infinite_run: | |
| description: 'Run training infinitely' | |
| required: false | |
| type: boolean | |
| default: false | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }} | |
| cancel-in-progress: true | |
| jobs: | |
| e2e-test-short: | |
| if: (github.event_name == 'workflow_dispatch') || (github.event.pull_request && contains(github.event.pull_request.labels.*.name, 'run-ci-short')) | |
| runs-on: self-hosted | |
| container: | |
| image: slimerl/slime:latest | |
| options: > | |
| --gpus all | |
| --ipc=host | |
| --shm-size=16g | |
| --ulimit memlock=-1 | |
| --ulimit stack=67108864 | |
| --memory=0 | |
| --memory-swap=0 | |
| -v /data/slime_ci:/data/slime_ci | |
| -v /data/slime_ci/models:/root/models | |
| -v /data/slime_ci/datasets:/root/datasets | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| info: [{"num_gpus": 8, "test_file": "test_quick_start_glm4_9B.py"}, {"num_gpus": 8, "test_file": "test_qwen3_30B_A3B.py"}] | |
| defaults: | |
| run: | |
| working-directory: ${{ github.workspace }} | |
| env: | |
| GITHUB_COMMIT_NAME: ${{ github.sha }}_${{ github.event.pull_request.number || 'non-pr' }} | |
| WANDB_API_KEY: ${{ secrets.WANDB_API_KEY }} | |
| SLIME_TEST_ENABLE_INFINITE_RUN: ${{ (github.event_name == 'workflow_dispatch' && github.event.inputs.infinite_run) || 'false' }} | |
| steps: | |
| - name: Checkout repository | |
| uses: actions/checkout@v4 | |
| - name: Install | |
| shell: bash | |
| run: cd $GITHUB_WORKSPACE && pip install -e . | |
| - name: Execute | |
| shell: bash | |
| run: python tests/ci/gpu_lock_exec.py --count ${{ matrix.info.num_gpus }} -- python tests/${{ matrix.info.test_file }} | |
| e2e-test-long: | |
| if: (github.event_name == 'workflow_dispatch') || (github.event.pull_request && contains(github.event.pull_request.labels.*.name, 'run-ci-long')) | |
| runs-on: self-hosted | |
| container: | |
| image: slimerl/slime:latest | |
| options: > | |
| --gpus all | |
| --ipc=host | |
| --shm-size=16g | |
| --ulimit memlock=-1 | |
| --ulimit stack=67108864 | |
| --memory=0 | |
| --memory-swap=0 | |
| -v /data/slime_ci:/data/slime_ci | |
| -v /data/slime_ci/models:/root/models | |
| -v /data/slime_ci/datasets:/root/datasets | |
| strategy: | |
| fail-fast: false | |
| matrix: | |
| info: [{"num_gpus": 2, "test_file": "test_qwen2.5_0.5B_gsm8k.py"}, {"num_gpus": 2, "test_file": "test_qwen2.5_0.5B_gsm8k_async.py"}, {"num_gpus": 2, "test_file": "test_qwen3_0.6B_fsdp_colocated_2xGPU.py"}, {"num_gpus": 2, "test_file": "test_qwen3_0.6B_fsdp_distributed.py"}] | |
| defaults: | |
| run: | |
| working-directory: ${{ github.workspace }} | |
| env: | |
| GITHUB_COMMIT_NAME: ${{ github.sha }}_${{ github.event.pull_request.number || 'non-pr' }} | |
| WANDB_API_KEY: ${{ secrets.WANDB_API_KEY }} | |
| SLIME_TEST_ENABLE_INFINITE_RUN: ${{ (github.event_name == 'workflow_dispatch' && github.event.inputs.infinite_run) || 'false' }} | |
| steps: | |
| - name: Checkout repository | |
| uses: actions/checkout@v4 | |
| - name: Install | |
| shell: bash | |
| run: cd $GITHUB_WORKSPACE && pip install -e . | |
| - name: Execute | |
| shell: bash | |
| run: python tests/ci/gpu_lock_exec.py --count ${{ matrix.info.num_gpus }} -- python tests/${{ matrix.info.test_file }} |