[DO NOT MERGE] Log test results to file #11915
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: nv-torch-latest-v100 | |
| on: | |
| workflow_dispatch: | |
| pull_request: | |
| paths-ignore: | |
| - 'docs/**' | |
| - 'blogs/**' | |
| - 'deepspeed/inference/v2/**' | |
| - 'tests/unit/inference/v2/**' | |
| merge_group: | |
| branches: [ master ] | |
| schedule: | |
| - cron: "0 0 * * *" | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.ref }} | |
| cancel-in-progress: true | |
| jobs: | |
| unit-tests: | |
| runs-on: [self-hosted, nvidia, cu121, v100] | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - id: setup-venv | |
| uses: ./.github/workflows/setup-venv | |
| - name: Install pytorch | |
| run: | | |
| pip install -U --cache-dir $TORCH_CACHE torch torchvision --index-url https://download.pytorch.org/whl/cu121 | |
| python -c "import torch; print('torch:', torch.__version__, torch)" | |
| python -c "import torch; print('CUDA available:', torch.cuda.is_available())" | |
| - name: Install transformers | |
| run: | | |
| git clone https://github.com/huggingface/transformers | |
| cd transformers | |
| # if needed switch to the last known good SHA until transformers@master is fixed | |
| # git checkout 1cc453d33 | |
| git rev-parse --short HEAD | |
| pip install . | |
| - name: Install deepspeed | |
| run: | | |
| pip install .[dev,1bit,autotuning] | |
| ds_report | |
| - name: Python environment | |
| run: | | |
| pip list | |
| - name: Unit tests | |
| run: | | |
| unset TORCH_CUDA_ARCH_LIST # only jit compile for current arch | |
| cd tests | |
| TEST_LOG_FILE="/tmp/test_log_${GITHUB_RUN_ID}.log" | |
| echo "Running tests and logging to ${TEST_LOG_FILE}" | |
| # Let this line return true so that we can grep for "Failed" in the log file | |
| set +e | |
| DS_UNITTEST_FILE_STORE_DIR=/dev/shm RUNNING_TEST_LOG_FILE=${TEST_LOG_FILE} pytest $PYTEST_OPTS --forked -n 4 unit/ --torch_ver="2.5" --cuda_ver="12.1" | |
| PYTEST_EXIT_CODE=$? | |
| if [ $PYTEST_EXIT_CODE -ne 0 ]; then | |
| # We don't clean the file here for debugging | |
| echo "pytest failed with exit code $PYTEST_EXIT_CODE" | |
| exit $PYTEST_EXIT_CODE | |
| fi | |
| grep "Failed" ${TEST_LOG_FILE} | |
| rm -f ${TEST_LOG_FILE} | |
| # Do the same as above | |
| DS_UNITTEST_FILE_STORE_DIR=/dev/shm RUNNING_TEST_LOG_FILE=${TEST_LOG_FILE} pytest $PYTEST_OPTS --forked -m 'sequential' unit/ --torch_ver="2.5" --cuda_ver="12.1" | |
| PYTEST_EXIT_CODE=$? | |
| grep "Failed" ${TEST_LOG_FILE} | |
| if [ $PYTEST_EXIT_CODE -ne 0 ]; then | |
| echo "pytest failed with exit code $PYTEST_EXIT_CODE" | |
| exit $PYTEST_EXIT_CODE | |
| fi | |
| rm -f ${TEST_LOG_FILE} |