Fixed few of attention test failure #1260
Workflow file for this run
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: Build and test | |
| on: | |
| workflow_dispatch: | |
| pull_request: | |
| branches: | |
| - llvm-target | |
| push: | |
| branches: | |
| - llvm-target | |
| permissions: read-all | |
| env: | |
| BASE: /home/runner | |
| LLVM_SYSPATH: /home/runner/packages/llvm | |
| BACKEND: XPU | |
| TRITON_DISABLE_LINE_INFO: 1 | |
| jobs: | |
| pre-commit: | |
| name: Pre-commit checks | |
| runs-on: | |
| - glados | |
| - spr | |
| - cpu | |
| steps: | |
| - name: Checkout repository | |
| uses: actions/checkout@v4 | |
| - name: Load pip cache | |
| id: pip-cache | |
| uses: ./.github/actions/load | |
| env: | |
| # Increase this value to reset cache | |
| CACHE_NUMBER: 1 | |
| with: | |
| path: $HOME/.cache/pip | |
| key: pip-3.9-${{ hashFiles('.pre-commit-config.yaml') }}-${{ env.CACHE_NUMBER }} | |
| - name: Install Python 3.9 | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: '3.9' | |
| - name: Run pre-commit checks | |
| run: | | |
| pip install --upgrade pre-commit | |
| # TODO: ignore the first yapf failure until https://github.com/google/yapf/issues/1164 is fixed | |
| python3 -m pre_commit run --all-files --verbose yapf &> /dev/null || true | |
| # If first run of yapf worked and made changes reset the tree to the original state | |
| git reset --hard | |
| python3 -m pre_commit run --show-diff-on-failure --color=always --all-files --verbose | |
| - name: Save pip cache | |
| if: ${{ steps.pip-cache.outputs.status == 'miss' }} | |
| uses: ./.github/actions/save | |
| with: | |
| path: ${{ steps.pip-cache.outputs.path }} | |
| dest: ${{ steps.pip-cache.outputs.dest }} | |
| integration-tests: | |
| name: Integration tests | |
| runs-on: | |
| - glados | |
| - spr | |
| - runner-0.0.6 | |
| strategy: | |
| matrix: | |
| python: | |
| - "3.9" | |
| - "3.10" | |
| defaults: | |
| run: | |
| shell: bash -noprofile --norc -eo pipefail -c "source /home/runner/intel/oneapi/setvars.sh > /dev/null; source {0}" | |
| steps: | |
| - name: Checkout repository | |
| uses: actions/checkout@v4 | |
| - name: Load pip cache | |
| id: pip-cache | |
| uses: ./.github/actions/load | |
| env: | |
| # Increase this value to reset cache | |
| CACHE_NUMBER: 1 | |
| with: | |
| path: $HOME/.cache/pip | |
| key: pip-${{ matrix.python }}-${{ hashFiles('python/pyproject.toml', 'python/setup.py') }}-${{ env.CACHE_NUMBER }} | |
| - name: Install Python ${{ matrix.python }} | |
| uses: actions/setup-python@v5 | |
| with: | |
| python-version: ${{ matrix.python }} | |
| - name: Get LLVM commit id | |
| uses: ./.github/actions/get-commit-id | |
| with: | |
| repository: intel/llvm.git | |
| branch: genx | |
| variable: LLVM_COMMIT_ID | |
| - name: Calculate packages cache key | |
| run: | | |
| PACKAGES_CACHE_KEY=$(echo $LLVM_COMMIT_ID ${{ hashFiles('scripts/compile-triton.sh') }} | sha256sum - | cut -d\ -f1) | |
| echo "PACKAGES_CACHE_KEY=$PACKAGES_CACHE_KEY" >> "${GITHUB_ENV}" | |
| - name: Load packages cache | |
| id: packages-cache | |
| uses: ./.github/actions/load | |
| env: | |
| # Increase this value to reset cache | |
| CACHE_NUMBER: 1 | |
| with: | |
| path: $HOME/packages | |
| key: packages-${{ env.PACKAGES_CACHE_KEY }}-${{ env.CACHE_NUMBER }} | |
| - name: Build packages | |
| if: ${{ steps.packages-cache.outputs.status == 'miss' }} | |
| run: | | |
| ./scripts/compile-triton.sh --llvm | |
| - name: Save packages cache | |
| if: ${{ steps.packages-cache.outputs.status == 'miss' }} | |
| uses: ./.github/actions/save | |
| with: | |
| path: ${{ steps.packages-cache.outputs.path }} | |
| dest: ${{ steps.packages-cache.outputs.dest }} | |
| - name: Setup PyTorch | |
| uses: ./.github/actions/setup-pytorch | |
| - name: Setup IPEX | |
| uses: ./.github/actions/setup-ipex | |
| - name: Build Triton | |
| run: | | |
| cd python | |
| pip install wheel pytest pytest-xdist pytest-rerunfailures | |
| pip install --no-build-isolation '.[build,tests,tutorials]' | |
| - name: Run lit tests | |
| run: | | |
| cd python | |
| lit -v build/*/test | |
| - name: Create directory for tests reports | |
| run: | | |
| mkdir ~/reports | |
| - name: Run core tests | |
| run: | | |
| cd python/test/unit | |
| python3 -m pytest --junitxml=~/reports/language.xml -n 8 --verbose --device xpu language/ --ignore=language/test_line_info.py | |
| # run runtime tests serially to avoid race condition with cache handling. | |
| python3 -m pytest --junitxml=~/reports/runtime.xml --device xpu runtime/ | |
| # run test_line_info.py separately with TRITON_DISABLE_LINE_INFO=0 | |
| TRITON_DISABLE_LINE_INFO=0 python3 -m pytest --junitxml=~/reports/line_info.xml --verbose --device xpu language/test_line_info.py | |
| - name: Clear cache | |
| run: | | |
| rm -rf ~/.triton | |
| - name: Run interpreter tests | |
| env: | |
| TRITON_INTERPRET: "1" | |
| run: | | |
| cd python/test/unit | |
| python3 -m pytest --junitxml=~/reports/interpreter_core.xml -vvv -n 4 -m interpreter language/test_core.py --device cpu | |
| python3 -m pytest --junitxml=~/reports/interpreter_flash_attention.xml -n 8 -m interpreter -vvv -s operators/test_flash_attention.py::test_op --device cpu | |
| - name: Run partial operators tests | |
| run: | | |
| cd python/test/unit | |
| python3 -m pytest --junitxml=~/reports/operators.xml -n 8 --verbose --device xpu operators | |
| - name: Regression tests | |
| run: | | |
| cd python/test/regression | |
| python3 -m pytest --junitxml=~/reports/regression.xml -vvv -s --device xpu . --reruns 10 --ignore=test_performance.py | |
| - name: Run XPU python tests | |
| run: | | |
| cd python/test/backend/third_party_backends | |
| python3 -m pytest -n auto --verbose test_xpu_backend.py | |
| - name: Run Tutorials | |
| run: | | |
| cd python/tutorials | |
| python3 01-vector-add.py | |
| python3 02-fused-softmax.py | |
| python3 03-matrix-multiplication.py | |
| python3 04-low-memory-dropout.py | |
| python3 05-layer-norm.py | |
| python3 06-fused-attention.py | |
| python3 07-extern-functions.py | |
| python3 08-experimental-block-pointer.py | |
| python3 09-experimental-tma-matrix-multiplication.py | |
| python3 10-experimental-tma-store-matrix-multiplication.py | |
| python3 11-grouped-gemm.py | |
| - name: Run CXX unittests | |
| run: | | |
| cd python/build/*cmake* | |
| ctest | |
| - name: Run E2E test | |
| run: | | |
| # Set WORKSPACE for inductor_xpu_test.sh to make sure it creates "inductor_log" outside of pytorch cloned directory | |
| export WORKSPACE=$GITHUB_WORKSPACE | |
| cd pytorch | |
| TRANSFORMERS_VERSION="$(<.ci/docker/ci_commit_pins/huggingface.txt)" | |
| pip install pyyaml pandas scipy numpy psutil pyre_extensions torchrec transformers==$TRANSFORMERS_VERSION | |
| # TODO: Find the fastest Hugging Face model | |
| $GITHUB_WORKSPACE/scripts/inductor_xpu_test.sh huggingface float32 inference accuracy xpu 0 static 1 0 AlbertForMaskedLM | |
| # The script above always returns 0, so we need an additional check to see if the accuracy test passed | |
| cat $WORKSPACE/inductor_log/*/*/*.csv | |
| grep AlbertForMaskedLM $WORKSPACE/inductor_log/*/*/*.csv | grep -q ,pass, | |
| - name: Save pip cache | |
| if: ${{ steps.pip-cache.outputs.status == 'miss' }} | |
| uses: ./.github/actions/save | |
| with: | |
| path: ${{ steps.pip-cache.outputs.path }} | |
| dest: ${{ steps.pip-cache.outputs.dest }} | |
| - name: Pass rate | |
| run: | | |
| python3 scripts/pass_rate.py --reports ~/reports | |
| mkdir -p /cache/reports/pass-rate | |
| TMPFILE=$(mktemp -p /cache/reports/pass-rate XXXXXXXXXX) | |
| python3 scripts/pass_rate.py --reports ~/reports --json > $TMPFILE | |
| mv $TMPFILE $TMPFILE.json |