flash_attention_v2_backward #78443
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 CI | |
| on: | |
| pull_request: | |
| types: [opened, review_requested, ready_for_review, synchronize, unlocked] | |
| merge_group: | |
| types: [checks_requested] | |
| concurrency: | |
| group: build-and-test-${{ github.ref }} | |
| cancel-in-progress: true | |
| env: | |
| OSS_ACCESS_KEY_ID: ${{ secrets.OSS_ACCESS_KEY_ID }} | |
| OSS_ACCESS_KEY_SECRET: ${{ secrets.OSS_ACCESS_KEY_SECRET }} | |
| ONEFLOW_TIMEOUT_SECONDS: 90 | |
| ONEFLOW_THRAED_LOCAL_CACHED_SIZE: 16384 | |
| FLOW_VISION_SRC: flow_vision | |
| FLOW_VISION_COMMIT: ca8ebc663b58667cf8cd1b6ef0c861522780b7bb | |
| LIBAI_SRC: libai | |
| LIBAI_COMMIT: 94eb85ff0131e8dfce953a3a916de7a4f897c647 | |
| ONEFLOW_FACE_SRC: oneflow_face | |
| ONEFLOW_FACE_COMMIT: 110a97e8d5737a1f1856281a7df556a5ac8f06de | |
| ONEFLOW_IREE_SRC: oneflow_iree | |
| ONEFLOW_IREE_COMMIT: 42fd479de7047e6af1d42c6e62b9b056e0a762aa | |
| ONE_FX_SRC: one-fx | |
| ONE_FX_COMMIT: da4051c7f1ace7a20b3f54395b580cd102fc99da | |
| TEST_WITH_TORCH_IMG_TAG: registry.cn-beijing.aliyuncs.com/oneflow/test-with-pytorch-1.10.0-cuda11.3-cudnn8-runtime:25817b5c0e1dd79bef8fdd43d729b98af381e7d5 | |
| MLIR_DOCKER_ARGS: "-e ONEFLOW_MLIR_ENABLE_ROUND_TRIP=1 -e ONEFLOW_MLIR_PREFER_NHWC=0 -e ONEFLOW_MLIR_ENABLE_INFERENCE_OPTIMIZATION=1" | |
| SSH_TANK_HOST: 192.168.1.40 | |
| SSH_TANK_PATH: /data/tank | |
| jobs: | |
| source_info: | |
| name: Collect information about PR and source | |
| runs-on: ubuntu-20.04 | |
| if: github.event.pull_request.draft == false && github.base_ref == 'master' | |
| steps: | |
| - name: Check out OneFlow | |
| uses: actions/checkout@v2 | |
| with: | |
| ref: ${{ github.event.pull_request.head.sha }} | |
| repository: ${{github.event.pull_request.head.repo.full_name}} | |
| fetch-depth: 0 | |
| - name: Python diff | |
| id: py-diff | |
| run: | | |
| ONEFLOW_TEST_FILES="$(git diff --diff-filter=d --name-only ${{ github.event.pull_request.base.sha }} -- python/oneflow/test/**/test_*.py | { grep -v expensive || true; })" | |
| ONEFLOW_TEST_FILES=$(echo "${ONEFLOW_TEST_FILES}" | xargs) | |
| if [ -z "$ONEFLOW_TEST_FILES" ]; then | |
| echo "no changed python tests" | |
| echo "has_changed_python_tests=false" >> $GITHUB_OUTPUT | |
| else | |
| echo "changed python tests: ${ONEFLOW_TEST_FILES}" | |
| echo "has_changed_python_tests=true" >> $GITHUB_OUTPUT | |
| fi | |
| echo "changed_python_tests=${ONEFLOW_TEST_FILES}" >> $GITHUB_OUTPUT | |
| outputs: | |
| changed_python_tests: ${{ steps.py-diff.outputs.changed_python_tests }} | |
| has_changed_python_tests: ${{ steps.py-diff.outputs.has_changed_python_tests }} | |
| mirror_third_party: | |
| name: Mirror third party dependencies | |
| runs-on: ubuntu-20.04 | |
| if: github.event.pull_request.draft == false && github.base_ref == 'master' | |
| steps: | |
| - uses: actions/checkout@v2 | |
| - name: Mirror dependencies to aliyun | |
| if: github.event.pull_request.head.repo.full_name == github.repository | |
| run: | | |
| set -x | |
| if [ -z "$OSS_ACCESS_KEY_ID" ] | |
| then | |
| exit 0 | |
| fi | |
| python3 -m pip install -U pip setuptools wheel | |
| python3 -m pip install 'cryptography<2.2' oss2 | |
| python3 tools/package_mirror.py -i $PWD | |
| check_license_and_format: | |
| name: License and format | |
| runs-on: ubuntu-20.04 | |
| if: github.event.pull_request.draft == false | |
| steps: | |
| - uses: actions/checkout@v2 | |
| with: | |
| repository: ${{github.event.pull_request.head.repo.full_name}} | |
| ref: ${{ github.head_ref }} | |
| - name: Check license | |
| id: license_check | |
| run: | | |
| python3 ci/check/run_license_format.py -i oneflow -c | |
| python3 ci/check/run_license_format.py -i python -c | |
| - name: Add license | |
| id: license_fmt | |
| if: ${{ failure() }} | |
| run: | | |
| python3 ci/check/run_license_format.py -i oneflow --fix | |
| python3 ci/check/run_license_format.py -i python --fix | |
| - name: Check C++/CUDA format | |
| id: cpp_check | |
| run: | | |
| python3 ci/check/run_clang_format.py --clang_format_binary clang-format --source_dir oneflow | |
| - name: Run C++/CUDA format | |
| id: cpp_fmt | |
| if: ${{ failure() }} | |
| run: | | |
| python3 ci/check/run_clang_format.py --clang_format_binary clang-format --source_dir oneflow --fix | |
| - name: Check Python format | |
| id: py_check | |
| run: | | |
| python3 -m pip install black==19.10b0 click==8.0.0 | |
| python3 ci/check/run_py_format.py --source_dir $PWD | |
| - name: Run Python Format | |
| id: py_fmt | |
| if: ${{ failure() }} | |
| run: | | |
| python3 ci/check/run_py_format.py --source_dir $PWD --fix | |
| - name: Check CMake format | |
| id: cmake_check | |
| run: | | |
| python3 -m pip install cmakelang | |
| python3 ci/check/run_cmake_format.py --source_dir $PWD | |
| - name: Run CMake Format | |
| id: cmake_fmt | |
| if: ${{ failure() }} | |
| run: | | |
| python3 -m pip install cmakelang | |
| python3 ci/check/run_cmake_format.py --source_dir $PWD --fix | |
| - name: Git push | |
| id: git_push | |
| if: ${{ failure() }} | |
| run: | | |
| git diff -p > license_and_format.patch | |
| cat license_and_format.patch | |
| git config --global user.email "ci-bot@oneflow.org" | |
| git config --global user.name "oneflow-ci-bot" | |
| git add -u | |
| git commit -m "auto format by CI" | |
| git push | |
| - name: Upload patch | |
| if: ${{ failure() && steps.git_push.outcome == 'failure' }} | |
| uses: actions/upload-artifact@v2 | |
| with: | |
| name: license_and_format-${{ github.sha }}.patch | |
| path: license_and_format.patch | |
| - name: Add comment | |
| if: ${{ failure() }} | |
| uses: actions/github-script@v4 | |
| with: | |
| script: | | |
| github.issues.createComment({ | |
| issue_number: context.issue.number, | |
| owner: context.repo.owner, | |
| repo: context.repo.repo, | |
| body: 'Code got formatted by CI. Please request CI again if you still want to have this PR merged. If the PR is from a forked repo, please download the patch files from the GitHub Actions web page and apply them locally.' | |
| }) | |
| - name: Please request CI again | |
| if: ${{ failure() }} | |
| run: | | |
| exit 1 | |
| - name: Check source code (prevent creating files at wrong places) | |
| run: | | |
| python3 tools/check_src.py | |
| find-build-cache: | |
| name: "Find build cache" | |
| if: github.event.pull_request.draft == false && github.base_ref == 'master' | |
| runs-on: ubuntu-latest | |
| env: | |
| ONEFLOW_SRC: . | |
| outputs: | |
| matrix: ${{ steps.find-cache.outputs.matrix }} | |
| steps: | |
| - name: Checkout Oneflow-Inc/oneflow | |
| uses: actions/checkout@v2 | |
| with: | |
| ref: ${{ github.event.pull_request.head.sha }} | |
| repository: ${{github.event.pull_request.head.repo.full_name}} | |
| - uses: Oneflow-Inc/get-oneflow/cache-complete/matrix/build@whl-skip-nccl | |
| name: find cache | |
| id: find-cache | |
| timeout-minutes: 5 | |
| with: | |
| delete-cache: ${{ contains(github.event.pull_request.labels.*.name, 'need-clean-ccache') }} | |
| runner-labels: | | |
| self-hosted | |
| linux | |
| builder | |
| oneflow-src: ${{ env.ONEFLOW_SRC }} | |
| entries: | | |
| cu116 | |
| cpu | |
| cpu-asan-ubsan | |
| cpu-tsan | |
| llvm15 | |
| build-oneflow: | |
| name: "Build OneFlow" | |
| if: github.event.pull_request.draft == false && github.base_ref == 'master' | |
| runs-on: ${{ matrix.runs-on }} | |
| needs: [find-build-cache] | |
| timeout-minutes: 80 | |
| strategy: | |
| fail-fast: true | |
| max-parallel: 5 | |
| matrix: ${{ fromJson(needs.find-build-cache.outputs.matrix) }} | |
| env: | |
| ONEFLOW_SRC: . | |
| MANYLINUX_CACHE_DIR: ~/manylinux-cache-dir/${{ matrix.entry }} | |
| WHEELHOUSE_DIR: manylinux-wheelhouse | |
| steps: | |
| - name: Set proxy | |
| if: ${{ contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| echo "https_proxy=${{ secrets.ONEFLOW_CI_HTTP_PROXY }}" >> $GITHUB_ENV | |
| - name: Fix permissions | |
| if: ${{ contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| set -x | |
| docker run --rm -v $PWD:$PWD -w $PWD busybox rm -rf * | |
| - name: Checkout Oneflow-Inc/oneflow | |
| uses: actions/checkout@v2 | |
| with: | |
| ref: ${{ github.event.pull_request.head.sha }} | |
| repository: ${{github.event.pull_request.head.repo.full_name}} | |
| - uses: Oneflow-Inc/get-oneflow/cache-complete@whl-skip-nccl | |
| name: Save cache if successful | |
| id: save-cache | |
| timeout-minutes: 5 | |
| with: | |
| oneflow-src: ${{ env.ONEFLOW_SRC }} | |
| entry: ${{ matrix.entry }} | |
| digest-type: build | |
| mark-as-completed: ${{ contains(matrix.runs-on, 'self-hosted') && github.event.pull_request.head.repo.full_name == github.repository }} | |
| - name: Check digest cache result. If this step failed, usually it is caused by new commits pushed when this CI run is running. | |
| if: ${{ fromJSON(steps.save-cache.outputs.cache-hit) != matrix.cache-hit }} | |
| run: | | |
| echo "::error file=test.yml,line=204,col=10::steps.save-cache.outputs.cache-hit != matrix.cache-hit" | |
| exit 1 | |
| - uses: Oneflow-Inc/get-oneflow@whl-skip-nccl | |
| name: Build manylinux ${{ matrix.entry }} | |
| id: build-cpu | |
| if: ${{ matrix.entry =='cpu' && !matrix.cache-hit }} | |
| with: | |
| cmake-init-cache: ${{ env.ONEFLOW_SRC }}/cmake/caches/ci/cpu.cmake | |
| build-script: ${{ env.ONEFLOW_SRC }}/ci/manylinux/build.sh | |
| run-lit: true | |
| oneflow-src: ${{ env.ONEFLOW_SRC }} | |
| oneflow-build-env: manylinux | |
| wheelhouse-dir: ${{ env.WHEELHOUSE_DIR }} | |
| clear-wheelhouse-dir: true | |
| self-hosted: ${{ contains(matrix.runs-on, 'self-hosted') }} | |
| cuda-version: none | |
| manylinux-cache-dir: ${{ env.MANYLINUX_CACHE_DIR }} | |
| docker-run-use-system-http-proxy: false | |
| docker-run-use-lld: true | |
| retry-failed-build: true | |
| clean-ccache: ${{ contains(github.event.pull_request.labels.*.name, 'need-clean-ccache') }} | |
| python-versions: | | |
| 3.7 | |
| 3.8 | |
| - uses: Oneflow-Inc/get-oneflow@whl-skip-nccl | |
| name: Build manylinux ${{ matrix.entry }} | |
| id: build-cpu-sanitizers | |
| if: ${{ (matrix.entry == 'cpu-asan-ubsan' || matrix.entry == 'cpu-tsan') && !matrix.cache-hit && false }} | |
| with: | |
| cmake-init-cache: ${{ env.ONEFLOW_SRC }}/cmake/caches/ci/${{ matrix.entry }}.cmake | |
| build-script: ${{ env.ONEFLOW_SRC }}/ci/manylinux/build.sh | |
| run-lit: false | |
| oneflow-src: ${{ env.ONEFLOW_SRC }} | |
| oneflow-build-env: manylinux | |
| wheelhouse-dir: ${{ env.WHEELHOUSE_DIR }} | |
| clear-wheelhouse-dir: true | |
| self-hosted: ${{ contains(matrix.runs-on, 'self-hosted') }} | |
| cuda-version: none | |
| manylinux-cache-dir: ${{ env.MANYLINUX_CACHE_DIR }} | |
| docker-run-use-system-http-proxy: false | |
| docker-run-use-lld: true | |
| retry-failed-build: true | |
| clean-ccache: ${{ contains(github.event.pull_request.labels.*.name, 'need-clean-ccache') }} | |
| python-versions: | | |
| 3.8 | |
| - uses: Oneflow-Inc/get-oneflow@whl-skip-nccl | |
| name: Build manylinux ${{ matrix.entry }} | |
| id: build-cuda | |
| if: ${{ matrix.entry =='cu116' && !matrix.cache-hit }} | |
| with: | |
| cmake-init-cache: ${{ env.ONEFLOW_SRC }}/cmake/caches/ci/cuda.cmake | |
| build-script: ${{ env.ONEFLOW_SRC }}/ci/manylinux/build-gcc9.sh | |
| oneflow-src: ${{ env.ONEFLOW_SRC }} | |
| oneflow-build-env: manylinux | |
| wheelhouse-dir: ${{ env.WHEELHOUSE_DIR }} | |
| clear-wheelhouse-dir: true | |
| self-hosted: ${{ contains(matrix.runs-on, 'self-hosted') }} | |
| cuda-version: "11.6" | |
| manylinux-cache-dir: ${{ env.MANYLINUX_CACHE_DIR }} | |
| docker-run-use-system-http-proxy: false | |
| docker-run-use-lld: false | |
| retry-failed-build: true | |
| clean-ccache: ${{ contains(github.event.pull_request.labels.*.name, 'need-clean-ccache') }} | |
| python-versions: | | |
| 3.7 | |
| - uses: Oneflow-Inc/get-oneflow@whl-skip-nccl | |
| name: Build ${{ matrix.entry }} | |
| if: ${{ matrix.entry == 'llvm15' && !matrix.cache-hit }} | |
| with: | |
| cmake-init-cache: ${{ env.ONEFLOW_SRC }}/cmake/caches/ci/llvm/cuda-75-clang.cmake | |
| build-script: ${{ env.ONEFLOW_SRC }}/ci/clang/build-llvm.sh | |
| oneflow-src: ${{ env.ONEFLOW_SRC }} | |
| oneflow-build-env: llvm | |
| wheelhouse-dir: ${{ env.WHEELHOUSE_DIR }} | |
| clear-wheelhouse-dir: true | |
| self-hosted: true | |
| cuda-version: ${{ env.CUDA_VERSION }} | |
| manylinux-cache-dir: ${{ env.MANYLINUX_CACHE_DIR }} | |
| docker-run-use-system-http-proxy: false | |
| docker-run-use-lld: false | |
| retry-failed-build: true | |
| clean-ccache: ${{ contains(github.event.pull_request.labels.*.name, 'need-clean-ccache') }} | |
| wheel-audit: false | |
| python-versions: | | |
| 3.8 | |
| - name: Remove automerge | |
| if: ${{ failure() && contains(matrix.runs-on, 'self-hosted') && cancelled() == false && contains(github.event.pull_request.labels.*.name, 'automerge') }} | |
| uses: actions/github-script@v4 | |
| with: | |
| script: | | |
| github.issues.removeLabel({ | |
| issue_number: context.issue.number, | |
| owner: context.repo.owner, | |
| repo: context.repo.repo, | |
| name: 'automerge' | |
| }) | |
| github.issues.createComment({ | |
| issue_number: context.issue.number, | |
| owner: context.repo.owner, | |
| repo: context.repo.repo, | |
| body: 'CI failed when running job: Build ${{ matrix.entry }}. PR label automerge has been removed' | |
| }) | |
| - name: Upload packed liboneflow | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.entry != 'llvm15' && matrix.entry != 'cpu-asan-ubsan' && matrix.entry != 'cpu-tsan' }} | |
| uses: Oneflow-Inc/get-oneflow/digest/upload@whl-skip-nccl | |
| timeout-minutes: 10 | |
| with: | |
| digest: ${{ steps.save-cache.outputs.build-digest }} | |
| entry: ${{ matrix.entry }} | |
| ssh-tank-host: ${{ env.SSH_TANK_HOST }} | |
| ssh-tank-path: ${{ env.SSH_TANK_PATH }} | |
| src-dir: ${{ env.MANYLINUX_CACHE_DIR }}/build/cpack | |
| dst-dir: cpack | |
| - name: Upload whl | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.entry != 'llvm15' && matrix.entry != 'cpu-asan-ubsan' && matrix.entry != 'cpu-tsan' }} | |
| uses: Oneflow-Inc/get-oneflow/digest/upload@whl-skip-nccl | |
| timeout-minutes: 10 | |
| with: | |
| digest: ${{ steps.save-cache.outputs.build-digest }} | |
| entry: ${{ matrix.entry }} | |
| ssh-tank-host: ${{ env.SSH_TANK_HOST }} | |
| ssh-tank-path: ${{ env.SSH_TANK_PATH }} | |
| src-dir: ${{ env.WHEELHOUSE_DIR }} | |
| dst-dir: whl | |
| find-test-cache-distributed: | |
| name: "Find test cache (distributed)" | |
| if: github.event.pull_request.draft == false && github.base_ref == 'master' && contains(github.event.pull_request.labels.*.name, 'need-test-distributed') | |
| runs-on: ubuntu-latest | |
| needs: [build-oneflow] | |
| env: | |
| ONEFLOW_SRC: . | |
| outputs: | |
| matrix: ${{ steps.find-cache.outputs.matrix }} | |
| steps: | |
| - name: Checkout Oneflow-Inc/oneflow | |
| uses: actions/checkout@v2 | |
| with: | |
| ref: ${{ github.event.pull_request.head.sha }} | |
| repository: ${{github.event.pull_request.head.repo.full_name}} | |
| - uses: Oneflow-Inc/get-oneflow/cache-complete/matrix/test@whl-skip-nccl | |
| name: find cache | |
| id: find-cache | |
| timeout-minutes: 5 | |
| with: | |
| runner-labels: | | |
| self-hosted | |
| linux | |
| oneflow-src: ${{ env.ONEFLOW_SRC }} | |
| include-distributed: true | |
| world-size: 2 | |
| devices: | | |
| cuda | |
| tests: | | |
| module | |
| find-test-cache: | |
| name: "Find test cache" | |
| if: github.event.pull_request.draft == false && github.base_ref == 'master' | |
| runs-on: ubuntu-latest | |
| needs: [build-oneflow] | |
| env: | |
| ONEFLOW_SRC: . | |
| outputs: | |
| matrix: ${{ steps.find-cache.outputs.matrix }} | |
| steps: | |
| - name: Checkout Oneflow-Inc/oneflow | |
| uses: actions/checkout@v2 | |
| with: | |
| ref: ${{ github.event.pull_request.head.sha }} | |
| repository: ${{github.event.pull_request.head.repo.full_name}} | |
| - uses: Oneflow-Inc/get-oneflow/cache-complete/matrix/test@whl-skip-nccl | |
| name: find cache | |
| id: find-cache | |
| timeout-minutes: 5 | |
| with: | |
| runner-labels: | | |
| self-hosted | |
| linux | |
| oneflow-src: ${{ env.ONEFLOW_SRC }} | |
| devices: | | |
| cuda | |
| cpu | |
| tests: | | |
| module | |
| misc | |
| speed-test | |
| test-distributed: | |
| name: Distributed test suite | |
| needs: [find-test-cache-distributed, test] | |
| runs-on: ${{ matrix.runs-on }} | |
| timeout-minutes: 120 | |
| if: github.event.pull_request.draft == false && github.base_ref == 'master' && contains(github.event.pull_request.labels.*.name, 'need-test-distributed') | |
| concurrency: | |
| group: distributed-test-${{ matrix.entry }}-rank-${{ matrix.rank }} | |
| cancel-in-progress: false | |
| strategy: | |
| fail-fast: true | |
| max-parallel: 2 | |
| matrix: ${{ fromJson(needs.find-test-cache-distributed.outputs.matrix) }} | |
| env: | |
| ONEFLOW_SRC: . | |
| TEST_CONTAINER_NAME: "ci-test-distributed" | |
| steps: | |
| - name: Fix permissions | |
| if: ${{ contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| set -x | |
| docker run --rm -v $PWD:$PWD -w $PWD busybox rm -rf * | |
| docker run --rm -v $PWD:$PWD -w $PWD busybox rm -rf .pytest_cache | |
| - name: Checkout Oneflow-Inc/oneflow | |
| uses: actions/checkout@v2 | |
| with: | |
| ref: ${{ github.event.pull_request.head.sha }} | |
| repository: ${{github.event.pull_request.head.repo.full_name}} | |
| - name: Checkout Oneflow-Inc/vision | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| uses: actions/checkout@v2 | |
| with: | |
| repository: Oneflow-Inc/vision | |
| # please use a commit here | |
| ref: ${{ env.FLOW_VISION_COMMIT}} | |
| path: ${{ env.FLOW_VISION_SRC}} | |
| - name: Checkout Oneflow-Inc/one-fx | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| uses: actions/checkout@v2 | |
| with: | |
| repository: Oneflow-Inc/one-fx | |
| # please use a commit here | |
| ref: ${{ env.ONE_FX_COMMIT}} | |
| path: ${{ env.ONE_FX_SRC}} | |
| - name: Checkout Oneflow-Inc/libai | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| uses: actions/checkout@v2 | |
| with: | |
| repository: Oneflow-Inc/libai | |
| # please use a commit here | |
| ref: ${{ env.LIBAI_COMMIT}} | |
| path: ${{ env.LIBAI_SRC}} | |
| - name: Checkout Oneflow-Inc/oneflow_iree | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| uses: actions/checkout@v2 | |
| with: | |
| repository: Oneflow-Inc/oneflow_iree | |
| # please use a commit here | |
| ref: ${{ env.ONEFLOW_IREE_COMMIT}} | |
| path: ${{ env.ONEFLOW_IREE_SRC}} | |
| - name: Remove container | |
| timeout-minutes: 45 | |
| if: ${{ contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| docker rm -f ${{ env.TEST_CONTAINER_NAME }} || true | |
| - uses: Oneflow-Inc/get-oneflow/cache-complete@whl-skip-nccl | |
| name: Save cache if successful | |
| id: save-cache | |
| timeout-minutes: 5 | |
| with: | |
| oneflow-src: ${{ env.ONEFLOW_SRC }} | |
| entry: ${{ matrix.entry }} | |
| digest-type: ${{ matrix.digest-type }} | |
| mark-as-completed: ${{ contains(matrix.runs-on, 'self-hosted') && github.event.pull_request.head.repo.full_name == github.repository }} | |
| - name: Check digest cache result. If this step failed, usually it is caused by new commits pushed when this CI run is running. | |
| if: ${{ fromJSON(steps.save-cache.outputs.cache-hit) != matrix.cache-hit }} | |
| run: | | |
| echo "::error file=test.yml,line=204,col=10::steps.save-cache.outputs.cache-hit != matrix.cache-hit" | |
| exit 1 | |
| - name: Download wheel and packed liboneflow | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| uses: Oneflow-Inc/get-oneflow/digest/download@whl-skip-nccl | |
| id: download-digest | |
| timeout-minutes: 10 | |
| with: | |
| digest: ${{ steps.save-cache.outputs.build-digest }} | |
| entry: ${{ matrix.compute-platform }} | |
| ssh-tank-host: ${{ env.SSH_TANK_HOST }} | |
| ssh-tank-path: ${{ env.SSH_TANK_PATH }} | |
| - name: Get primary node | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| uses: Oneflow-Inc/get-oneflow/master-address@whl-skip-nccl | |
| id: get-primary-node | |
| with: | |
| rank: ${{ matrix.rank }} | |
| - name: Set environment variables | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| set -x | |
| extra_docker_args="" | |
| if [ "${{ matrix.device }}" == "cpu" ]; then | |
| extra_docker_args+=" --env ONEFLOW_TEST_CPU_ONLY=1" | |
| extra_docker_args+=" --env CUDA_VISIBLE_DEVICES=-1" | |
| fi | |
| echo "EXTRA_DOCKER_ARGS=${extra_docker_args}" >> $GITHUB_ENV | |
| echo "ONEFLOW_TEST_CACHE_DIR=$HOME/ci-cache/test_cache" >> $GITHUB_ENV | |
| echo "ONEFLOW_TEST_DATASET_DIR=$HOME/dataset" >> $GITHUB_ENV | |
| echo "ONEFLOW_WHEEL_PATH=${{ steps.download-digest.outputs.entry-dir }}/whl" >> $GITHUB_ENV | |
| echo "ONEFLOW_CPACK_PATH=${{ steps.download-digest.outputs.entry-dir }}/cpack" >> $GITHUB_ENV | |
| - name: Set environment variables (distributed) | |
| if: ${{ fromJson(matrix.is-distributed) }} | |
| run: | | |
| set -x | |
| EXTRA_DOCKER_ARGS+=" --network host " | |
| echo "EXTRA_DOCKER_ARGS=${EXTRA_DOCKER_ARGS}" >> $GITHUB_ENV | |
| - name: Enable ONEFLOW_TEST_VERBOSE | |
| if: ${{ contains(github.event.pull_request.labels.*.name, 'need-test-verbose') }} | |
| run: | | |
| EXTRA_DOCKER_ARGS+=" --env ONEFLOW_TEST_VERBOSE=1" | |
| echo "EXTRA_DOCKER_ARGS=${EXTRA_DOCKER_ARGS}" >> $GITHUB_ENV | |
| - name: Start container | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| working-directory: ${{ env.ONEFLOW_SRC }} | |
| run: | | |
| docker run --gpus=all -d --rm --privileged --shm-size=8g \ | |
| --pids-limit 2000 \ | |
| --cap-add=SYS_PTRACE --security-opt seccomp=unconfined \ | |
| -v ${ONEFLOW_TEST_DATASET_DIR}:${ONEFLOW_TEST_DATASET_DIR}:ro \ | |
| -v ${ONEFLOW_WHEEL_PATH}:${ONEFLOW_WHEEL_PATH}:ro \ | |
| -v $HOME/test-container-cache/dot-local:/root/.local \ | |
| -v $HOME/test-container-cache/dot-cache:/root/.cache \ | |
| -e NODE_RANK=${{ matrix.rank }} \ | |
| -e _MASTER_ADDR=${{ steps.get-primary-node.outputs.master-address }} \ | |
| -e ONEFLOW_WHEEL_PATH=${ONEFLOW_WHEEL_PATH} \ | |
| -e ONEFLOW_CI=1 \ | |
| -v $PWD:$PWD \ | |
| -w $PWD \ | |
| -v ${ONEFLOW_TEST_CACHE_DIR}:${ONEFLOW_TEST_CACHE_DIR} \ | |
| -e ONEFLOW_TEST_CACHE_DIR=${ONEFLOW_TEST_CACHE_DIR} \ | |
| -e ONEFLOW_TEST_DATASET_DIR=${ONEFLOW_TEST_DATASET_DIR} \ | |
| -e ONEFLOW_TIMEOUT_SECONDS=${{ env.ONEFLOW_TIMEOUT_SECONDS }} \ | |
| -e ONEFLOW_THRAED_LOCAL_CACHED_SIZE=${{ env.ONEFLOW_THRAED_LOCAL_CACHED_SIZE }} \ | |
| ${{ env.MLIR_DOCKER_ARGS }} \ | |
| --name ${TEST_CONTAINER_NAME} \ | |
| ${{ env.EXTRA_DOCKER_ARGS }} \ | |
| ${{ env.TEST_WITH_TORCH_IMG_TAG }} \ | |
| sleep 5400 | |
| - name: Test container | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| docker exec ${{ env.TEST_CONTAINER_NAME }} ls | |
| docker exec ${{ env.TEST_CONTAINER_NAME }} python3 -m pip list | |
| - name: Install OneFlow | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| ls ${ONEFLOW_WHEEL_PATH} | |
| docker exec ${TEST_CONTAINER_NAME} python3 -m pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple | |
| docker exec ${TEST_CONTAINER_NAME} python3 -m pip install --find-links=${ONEFLOW_WHEEL_PATH} oneflow | |
| - name: Install downstream libs | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| docker exec ${TEST_CONTAINER_NAME} python3 -m pip install -e ${{ env.FLOW_VISION_SRC}} | |
| docker exec ${TEST_CONTAINER_NAME} python3 -m pip install pybind11 --user | |
| docker exec ${TEST_CONTAINER_NAME} python3 -m pip install tensorboardX==2.6 --user | |
| docker exec ${TEST_CONTAINER_NAME} python3 -m pip install -e ${{ env.LIBAI_SRC}} | |
| docker exec ${TEST_CONTAINER_NAME} python3 -m pip install -e ${{ env.ONEFLOW_IREE_SRC}} | |
| docker exec ${TEST_CONTAINER_NAME} python3 -m pip install -e ${{ env.ONE_FX_SRC}} | |
| - name: Module API test (distributed) | |
| timeout-minutes: 90 | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'module' && matrix.device == 'cuda' && fromJson(matrix.is-distributed) }} | |
| continue-on-error: false | |
| run: | | |
| docker exec -e ONEFLOW_TEST_DIR=$PWD/python/oneflow/test/modules ${{ env.TEST_CONTAINER_NAME }} bash ci/test/2node_op_test_multi_client.sh | |
| - name: Module API test (distributed, without IB) | |
| timeout-minutes: 60 | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'module' && matrix.device == 'cuda' && fromJson(matrix.is-distributed) && contains(github.event.pull_request.labels.*.name, 'need-distributed-without-ib')}} | |
| continue-on-error: false | |
| run: | | |
| docker exec -e ONEFLOW_TEST_DIR=$PWD/python/oneflow/test/modules \ | |
| -e ONEFLOW_LIBIBVERBS_PATH=invalid_lib \ | |
| -e ONEFLOW_CI_DEVICE_NUMS="4" \ | |
| ${{ env.TEST_CONTAINER_NAME }} bash ci/test/2node_op_test_multi_client.sh | |
| - name: Print stacks in all core files | |
| timeout-minutes: 45 | |
| if: ${{ failure() && contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| docker exec ${{ env.TEST_CONTAINER_NAME }} bash ci/test/print_stack_in_all_dirs.sh || true | |
| - name: Remove automerge | |
| if: ${{ failure() && contains(matrix.runs-on, 'self-hosted') && cancelled() == false && contains(github.event.pull_request.labels.*.name, 'automerge') }} | |
| uses: actions/github-script@v4 | |
| with: | |
| script: | | |
| github.issues.removeLabel({ | |
| issue_number: context.issue.number, | |
| owner: context.repo.owner, | |
| repo: context.repo.repo, | |
| name: 'automerge' | |
| }) | |
| github.issues.createComment({ | |
| issue_number: context.issue.number, | |
| owner: context.repo.owner, | |
| repo: context.repo.repo, | |
| body: 'CI failed when running job: ${{ matrix.entry }}. PR label automerge has been removed' | |
| }) | |
| - name: Remove container | |
| timeout-minutes: 45 | |
| if: ${{ always() && contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| docker rm -f ${{ env.TEST_CONTAINER_NAME }} || true | |
| docker run --rm -v $PWD:$PWD -w $PWD busybox rm -rf * | |
| test: | |
| name: Test suite | |
| needs: [find-test-cache, source_info] | |
| timeout-minutes: 120 | |
| runs-on: ${{ matrix.runs-on }} | |
| if: github.event.pull_request.draft == false && github.base_ref == 'master' | |
| strategy: | |
| fail-fast: ${{ !contains(github.event.pull_request.labels.*.name, 'need-all-tests-even-fail') }} | |
| max-parallel: 10 | |
| matrix: ${{ fromJson(needs.find-test-cache.outputs.matrix) }} | |
| env: | |
| ONEFLOW_SRC: . | |
| TEST_CONTAINER_NAME: "pr-${{ github.event.pull_request.number }}-run-id-${{ github.run_id }}-${{ matrix.entry }}-test" | |
| TEST_MANYLINUX_CONTAINER_NAME: "pr-${{ github.event.pull_request.number }}-run-id-${{ github.run_id }}-${{ matrix.entry }}-test-manylinux" | |
| TEST_WITH_TF_IMG_TAG: registry.cn-beijing.aliyuncs.com/oneflow/test-with-tf-2.3.0:2f831e9354298a11447578e869d983959feb046f | |
| TEST_MANYLINUX_IMG_TAG: registry.cn-beijing.aliyuncs.com/oneflow/manylinux2014_x86_64_cuda11.6:328e477069c80035adb3cd4db9632997e6284edd | |
| METRICS_DIR: metrics | |
| steps: | |
| - name: Set proxy | |
| if: ${{ contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| echo "https_proxy=${{ secrets.ONEFLOW_CI_HTTP_PROXY }}" >> $GITHUB_ENV | |
| - name: Fix permissions | |
| if: ${{ contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| set -x | |
| docker run --rm -v $PWD:$PWD -w $PWD busybox rm -rf * | |
| docker run --rm -v $PWD:$PWD -w $PWD busybox rm -rf .pytest_cache | |
| - name: Checkout Oneflow-Inc/oneflow | |
| uses: actions/checkout@v2 | |
| with: | |
| ref: ${{ github.event.pull_request.head.sha }} | |
| repository: ${{github.event.pull_request.head.repo.full_name}} | |
| - name: Checkout Oneflow-Inc/vision | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| uses: actions/checkout@v2 | |
| with: | |
| repository: Oneflow-Inc/vision | |
| # please use a commit here | |
| ref: ${{ env.FLOW_VISION_COMMIT}} | |
| path: ${{ env.FLOW_VISION_SRC}} | |
| - name: Checkout Oneflow-Inc/libai | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| uses: actions/checkout@v2 | |
| with: | |
| repository: Oneflow-Inc/libai | |
| # please use a commit here | |
| ref: ${{ env.LIBAI_COMMIT}} | |
| path: ${{ env.LIBAI_SRC}} | |
| - name: Checkout Oneflow-Inc/oneflow_face | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| uses: actions/checkout@v2 | |
| with: | |
| repository: Oneflow-Inc/oneflow_face | |
| # please use a commit here | |
| ref: ${{ env.ONEFLOW_FACE_COMMIT}} | |
| path: ${{ env.ONEFLOW_FACE_SRC}} | |
| - name: Checkout Oneflow-Inc/oneflow_iree | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| uses: actions/checkout@v2 | |
| with: | |
| repository: Oneflow-Inc/oneflow_iree | |
| # please use a commit here | |
| ref: ${{ env.ONEFLOW_IREE_COMMIT}} | |
| path: ${{ env.ONEFLOW_IREE_SRC}} | |
| - name: Checkout Oneflow-Inc/one-fx | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| uses: actions/checkout@v2 | |
| with: | |
| repository: Oneflow-Inc/one-fx | |
| # please use a commit here | |
| ref: ${{ env.ONE_FX_COMMIT}} | |
| path: ${{ env.ONE_FX_SRC}} | |
| - name: Remove container | |
| timeout-minutes: 45 | |
| if: ${{ contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| docker rm -f ${{ env.TEST_CONTAINER_NAME }} || true | |
| - name: Remove manylinux container | |
| timeout-minutes: 45 | |
| if: ${{ contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| docker rm -f ${{ env.TEST_MANYLINUX_CONTAINER_NAME }} || true | |
| - uses: Oneflow-Inc/get-oneflow/cache-complete@whl-skip-nccl | |
| name: Save cache if successful | |
| id: save-cache | |
| timeout-minutes: 5 | |
| with: | |
| oneflow-src: ${{ env.ONEFLOW_SRC }} | |
| entry: ${{ matrix.entry }} | |
| digest-type: ${{ matrix.digest-type }} | |
| mark-as-completed: ${{ contains(matrix.runs-on, 'self-hosted') && github.event.pull_request.head.repo.full_name == github.repository }} | |
| - name: Check digest cache result. If this step failed, usually it is caused by new commits pushed when this CI run is running. | |
| if: ${{ fromJSON(steps.save-cache.outputs.cache-hit) != matrix.cache-hit }} | |
| run: | | |
| echo "::error file=test.yml,line=204,col=10::steps.save-cache.outputs.cache-hit != matrix.cache-hit" | |
| exit 1 | |
| - name: Download wheel and packed liboneflow | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| uses: Oneflow-Inc/get-oneflow/digest/download@whl-skip-nccl | |
| id: download-digest | |
| timeout-minutes: 10 | |
| with: | |
| digest: ${{ steps.save-cache.outputs.build-digest }} | |
| entry: ${{ matrix.compute-platform }} | |
| ssh-tank-host: ${{ env.SSH_TANK_HOST }} | |
| ssh-tank-path: ${{ env.SSH_TANK_PATH }} | |
| - name: Download ASAN and UBSAN wheel and packed liboneflow | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') && matrix.device == 'cpu' && false }} | |
| uses: Oneflow-Inc/get-oneflow/digest/download@whl-skip-nccl | |
| id: asan-ubsan-download-digest | |
| timeout-minutes: 10 | |
| with: | |
| digest: ${{ steps.save-cache.outputs.build-digest }} | |
| entry: cpu-asan-ubsan | |
| ssh-tank-host: ${{ env.SSH_TANK_HOST }} | |
| ssh-tank-path: ${{ env.SSH_TANK_PATH }} | |
| - name: Download TSAN wheel and packed liboneflow | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') && matrix.device == 'cpu' && false }} | |
| uses: Oneflow-Inc/get-oneflow/digest/download@whl-skip-nccl | |
| id: tsan-download-digest | |
| timeout-minutes: 10 | |
| with: | |
| digest: ${{ steps.save-cache.outputs.build-digest }} | |
| entry: cpu-tsan | |
| ssh-tank-host: ${{ env.SSH_TANK_HOST }} | |
| ssh-tank-path: ${{ env.SSH_TANK_PATH }} | |
| - name: Enable TF container | |
| if: ${{ fromJSON(matrix.is-single-client) }} | |
| run: | | |
| echo "TEST_IMG_TAG=${TEST_WITH_TF_IMG_TAG}" >> $GITHUB_ENV | |
| - name: Enable Pytorch container | |
| if: ${{ !fromJSON(matrix.is-single-client) }} | |
| run: | | |
| echo "TEST_IMG_TAG=${TEST_WITH_TORCH_IMG_TAG}" >> $GITHUB_ENV | |
| - name: Set environment variables | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| set -x | |
| extra_docker_args="" | |
| if [ "${{ matrix.device }}" == "cpu" ]; then | |
| extra_docker_args+=" --env ONEFLOW_TEST_CPU_ONLY=1" | |
| extra_docker_args+=" --env CUDA_VISIBLE_DEVICES=-1" | |
| fi | |
| echo "EXTRA_DOCKER_ARGS=${extra_docker_args}" >> $GITHUB_ENV | |
| echo "ONEFLOW_TEST_CACHE_DIR=$HOME/ci-cache/test_cache" >> $GITHUB_ENV | |
| echo "ONEFLOW_TEST_DATASET_DIR=$HOME/dataset" >> $GITHUB_ENV | |
| echo "ONEFLOW_WHEEL_PATH=${{ steps.download-digest.outputs.entry-dir }}/whl" >> $GITHUB_ENV | |
| echo "ONEFLOW_CPACK_PATH=${{ steps.download-digest.outputs.entry-dir }}/cpack" >> $GITHUB_ENV | |
| echo "DOCS_PATH=docs/${{ github.repository }}/pr/${{ github.event.pull_request.number }}" >> $GITHUB_ENV | |
| - name: Set environment variables (experimental flags) | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') && fromJson(matrix.is-experimental) }} | |
| run: | | |
| EXTRA_DOCKER_ARGS+=" --env ONEFLOW_KERNEL_ENABLE_CUDA_GRAPH=1" | |
| EXTRA_DOCKER_ARGS+=" --env ONEFLOW_THREAD_ENABLE_LOCAL_MESSAGE_QUEUE=1" | |
| EXTRA_DOCKER_ARGS+=" --env ONEFLOW_KERNEL_DISABLE_BLOB_ACCESS_CHECKER=1" | |
| echo "EXTRA_DOCKER_ARGS=${EXTRA_DOCKER_ARGS}" >> $GITHUB_ENV | |
| - name: Set Thread Limit (CPU) | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.device == 'cpu' }} | |
| run: | | |
| echo "THREAD_LIMIT=25000" >> $GITHUB_ENV | |
| - name: Set Thread Limit (CUDA) | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.device == 'cuda' }} | |
| run: | | |
| echo "THREAD_LIMIT=20000" >> $GITHUB_ENV | |
| - name: Enable ONEFLOW_TEST_VERBOSE | |
| if: ${{ contains(github.event.pull_request.labels.*.name, 'need-test-verbose') }} | |
| run: | | |
| EXTRA_DOCKER_ARGS+=" --env ONEFLOW_TEST_VERBOSE=1" | |
| echo "EXTRA_DOCKER_ARGS=${EXTRA_DOCKER_ARGS}" >> $GITHUB_ENV | |
| - name: Pull image | |
| continue-on-error: true | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| docker pull ${{ env.TEST_IMG_TAG }} | |
| - name: Unzip packed liboneflow | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') && !fromJson(matrix.is-xla) }} | |
| run: | | |
| unzip ${{ env.ONEFLOW_CPACK_PATH }}/liboneflow-ci-linux.zip | |
| - name: Unzip packed sanitized liboneflow | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') && !fromJson(matrix.is-xla) && matrix.device == 'cpu' && false }} | |
| run: | | |
| unzip ${{ steps.asan-ubsan-download-digest.outputs.entry-dir }}/cpack/liboneflow-ci-linux.zip -d asan-ubsan | |
| unzip ${{ steps.tsan-download-digest.outputs.entry-dir }}/cpack/liboneflow-ci-linux.zip -d tsan | |
| - name: Start container | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| working-directory: ${{ env.ONEFLOW_SRC }} | |
| run: | | |
| docker run --gpus=all -d --rm --privileged --shm-size=8g \ | |
| --pids-limit ${{ env.THREAD_LIMIT }} \ | |
| --cap-add=SYS_PTRACE --security-opt seccomp=unconfined \ | |
| -v ${ONEFLOW_TEST_DATASET_DIR}:${ONEFLOW_TEST_DATASET_DIR}:ro \ | |
| -v ${ONEFLOW_WHEEL_PATH}:${ONEFLOW_WHEEL_PATH}:ro \ | |
| -v $HOME/test-container-cache/dot-local:/root/.local \ | |
| -v $HOME/test-container-cache/dot-cache:/root/.cache \ | |
| -e ONEFLOW_WHEEL_PATH=${ONEFLOW_WHEEL_PATH} \ | |
| -e ONEFLOW_CI=1 \ | |
| -e NVIDIA_TF32_OVERRIDE=0 \ | |
| -e NCCL_P2P_DISABLE=1 \ | |
| -v $PWD:$PWD \ | |
| -w $PWD \ | |
| -v ${ONEFLOW_TEST_CACHE_DIR}:${ONEFLOW_TEST_CACHE_DIR} \ | |
| -e ONEFLOW_TEST_CACHE_DIR=${ONEFLOW_TEST_CACHE_DIR} \ | |
| -e ONEFLOW_TEST_DATASET_DIR=${ONEFLOW_TEST_DATASET_DIR} \ | |
| -e ONEFLOW_TIMEOUT_SECONDS=${{ env.ONEFLOW_TIMEOUT_SECONDS }} \ | |
| -e ONEFLOW_THRAED_LOCAL_CACHED_SIZE=${{ env.ONEFLOW_THRAED_LOCAL_CACHED_SIZE }} \ | |
| ${{ env.MLIR_DOCKER_ARGS }} \ | |
| --name ${TEST_CONTAINER_NAME} \ | |
| ${{ env.EXTRA_DOCKER_ARGS }} \ | |
| ${{ env.TEST_IMG_TAG }} \ | |
| sleep 7200 | |
| - name: Start manylinux container | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| working-directory: ${{ env.ONEFLOW_SRC }} | |
| # For unknown reason we need to disable the requirement from nvidia docker | |
| # by -e NVIDIA_DISABLE_REQUIRE=true | |
| run: | | |
| docker run --gpus=all -d --rm --privileged --shm-size=8g \ | |
| --pids-limit ${{ env.THREAD_LIMIT }} \ | |
| --cap-add=SYS_PTRACE --security-opt seccomp=unconfined \ | |
| -v ${ONEFLOW_TEST_DATASET_DIR}:${ONEFLOW_TEST_DATASET_DIR}:ro \ | |
| -v ${ONEFLOW_WHEEL_PATH}:${ONEFLOW_WHEEL_PATH}:ro \ | |
| -v $HOME/test-container-cache/dot-local:/root/.local \ | |
| -v $HOME/test-container-cache/dot-cache:/root/.cache \ | |
| -e NVIDIA_DISABLE_REQUIRE=true \ | |
| -e ONEFLOW_WHEEL_PATH=${ONEFLOW_WHEEL_PATH} \ | |
| -e ONEFLOW_CI=1 \ | |
| -v $PWD:$PWD \ | |
| -w $PWD \ | |
| -v ${ONEFLOW_TEST_CACHE_DIR}:${ONEFLOW_TEST_CACHE_DIR} \ | |
| -e ONEFLOW_TEST_CACHE_DIR=${ONEFLOW_TEST_CACHE_DIR} \ | |
| -e ONEFLOW_TEST_DATASET_DIR=${ONEFLOW_TEST_DATASET_DIR} \ | |
| -e ONEFLOW_TIMEOUT_SECONDS=${{ env.ONEFLOW_TIMEOUT_SECONDS }} \ | |
| -e ONEFLOW_THRAED_LOCAL_CACHED_SIZE=${{ env.ONEFLOW_THRAED_LOCAL_CACHED_SIZE }} \ | |
| ${{ env.MLIR_DOCKER_ARGS }} \ | |
| --name ${TEST_MANYLINUX_CONTAINER_NAME} \ | |
| ${{ env.EXTRA_DOCKER_ARGS }} \ | |
| ${{ env.TEST_MANYLINUX_IMG_TAG }} \ | |
| sleep 7200 | |
| - name: Exe test | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'misc' }} | |
| timeout-minutes: 20 | |
| run: | | |
| docker exec ${{ env.TEST_MANYLINUX_CONTAINER_NAME }} ./liboneflow-ci-linux/bin/oneflow_testexe | |
| - name: Exe test (C++ API) | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'misc' }} | |
| timeout-minutes: 20 | |
| run: | | |
| docker exec -e ONEFLOW_SERVING_DEBUG=1 ${{ env.TEST_MANYLINUX_CONTAINER_NAME }} ./liboneflow-ci-linux/bin/oneflow_cpp_api_testexe --gtest_filter=-Api.embedding* | |
| - name: Exe test (C++ API with sanitizers) | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'misc' && matrix.device == 'cpu' && false }} | |
| timeout-minutes: 10 | |
| run: | | |
| docker exec -e UBSAN_OPTIONS=suppressions=.ubsan-suppressions -e ASAN_OPTIONS=strict_string_checks=1:detect_stack_use_after_return=1 -e LSAN_OPTIONS=suppressions=.lsan-suppressions ${{ env.TEST_MANYLINUX_CONTAINER_NAME }} ./asan-ubsan/liboneflow-ci-linux/bin/oneflow_cpp_api_testexe --gtest_filter=Api.graph_\* | |
| # Run 5 times to avoid false positive because of occasional lack of stack info | |
| docker exec -e TSAN_OPTIONS="history_size=7 suppressions=.tsan-suppressions" ${{ env.TEST_MANYLINUX_CONTAINER_NAME }} bash -c "./tsan/liboneflow-ci-linux/bin/oneflow_cpp_api_testexe || ./tsan/liboneflow-ci-linux/bin/oneflow_cpp_api_testexe || ./tsan/liboneflow-ci-linux/bin/oneflow_cpp_api_testexe || ./tsan/liboneflow-ci-linux/bin/oneflow_cpp_api_testexe || ./tsan/liboneflow-ci-linux/bin/oneflow_cpp_api_testexe" | |
| - name: Test container | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| docker exec ${{ env.TEST_CONTAINER_NAME }} ls | |
| docker exec ${{ env.TEST_CONTAINER_NAME }} python3 -m pip list | |
| - name: Install OneFlow | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| ls ${ONEFLOW_WHEEL_PATH} | |
| docker exec ${TEST_CONTAINER_NAME} python3 -m pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple | |
| docker exec ${TEST_CONTAINER_NAME} python3 -m pip install --find-links=${ONEFLOW_WHEEL_PATH} oneflow | |
| - name: Install downstream libs | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| docker exec ${TEST_CONTAINER_NAME} python3 -m pip install -e ${{ env.FLOW_VISION_SRC}} | |
| docker exec ${TEST_CONTAINER_NAME} python3 -m pip install pybind11 --user | |
| docker exec ${TEST_CONTAINER_NAME} python3 -m pip install tensorboardX==2.6 --user | |
| docker exec ${TEST_CONTAINER_NAME} python3 -m pip install -e ${{ env.LIBAI_SRC}} | |
| docker exec ${TEST_CONTAINER_NAME} python3 -m pip install -e ${{ env.ONEFLOW_FACE_SRC}} | |
| docker exec ${TEST_CONTAINER_NAME} python3 -m pip install -e ${{ env.ONEFLOW_IREE_SRC}} | |
| docker exec ${TEST_CONTAINER_NAME} python3 -m pip install -e ${{ env.ONE_FX_SRC}} | |
| - name: Run OneFlow doctor | |
| if: ${{ !fromJson(matrix.cache-hit) && contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| docker exec ${{ env.TEST_CONTAINER_NAME }} python3 -m oneflow --doctor | |
| - name: Build documentation | |
| timeout-minutes: 10 | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'misc' && matrix.device == 'cpu' }} | |
| run: | | |
| docker exec ${{ env.TEST_CONTAINER_NAME }} bash ci/test/build_docs.sh | |
| - name: Upload documentation | |
| id: upload-docs | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'misc' && matrix.device == 'cpu' && github.repository == 'Oneflow-Inc/oneflow' }} | |
| continue-on-error: true | |
| uses: ./.github/actions/upload_oss | |
| with: | |
| src_path: build-docs/build/html | |
| oss_dst_path: oss://oneflow-staging/${{ env.DOCS_PATH }} | |
| oss_access_key_id: ${{ secrets.OSS_ACCESS_KEY_ID }} | |
| oss_access_key_secret: ${{ secrets.OSS_ACCESS_KEY_SECRET }} | |
| - name: Post docs url | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'misc' && matrix.device == 'cpu' && github.repository == 'Oneflow-Inc/oneflow' && steps.upload-docs.outcome == 'success' }} | |
| continue-on-error: true | |
| uses: actions/github-script@v4 | |
| with: | |
| script: | | |
| github.issues.createComment({ | |
| issue_number: context.issue.number, | |
| owner: context.repo.owner, | |
| repo: context.repo.repo, | |
| body: "View latest API docs preview at: https://oneflow-staging.oss-cn-beijing.aliyuncs.com/${{ env.DOCS_PATH }}/" | |
| }) | |
| - name: Doctest | |
| timeout-minutes: 45 | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'misc' && matrix.device == 'cuda' }} | |
| run: | | |
| docker exec ${{ env.TEST_CONTAINER_NAME }} bash ci/test/doctest.sh | |
| - name: Checkout Oneflow-Inc/models | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'speed-test' && matrix.device == 'cuda' }} | |
| uses: actions/checkout@v2 | |
| with: | |
| repository: Oneflow-Inc/models | |
| ref: d6b2b8260e87541726ed87361171438d258e6a4d | |
| path: oneflow-models | |
| - name: ResNet50 Graph DDP test | |
| id: models-resnet50 | |
| timeout-minutes: 20 | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'speed-test' && matrix.device == 'cuda' }} | |
| run: | | |
| docker exec -e NCCL_DEBUG=INFO -e ONEFLOW_MODELS_DIR=$PWD/oneflow-models ${{ env.TEST_CONTAINER_NAME }} bash ci/test/test_resnet50_graph_ddp.sh | |
| - name: Speed test | |
| id: speed | |
| timeout-minutes: 20 | |
| continue-on-error: ${{ !contains(github.event.pull_request.labels.*.name, 'need-pass-speed-test') }} | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'speed-test' && matrix.device == 'cuda' }} | |
| run: | | |
| docker exec -e ONEFLOW_MODELS_DIR=$PWD/oneflow-models ${{ env.TEST_CONTAINER_NAME }} bash ci/test/test_speed_multi_client.sh | |
| - name: Save speed stats | |
| if: ${{ always() && !fromJson(matrix.cache-hit) && matrix.test-type == 'speed-test' && matrix.device == 'cuda' }} | |
| run: | | |
| mkdir -p ${{ env.METRICS_DIR }} | |
| echo "${{ steps.speed.outputs.stats }}" >> ${{ env.METRICS_DIR }}/speed_stats.txt | |
| - name: Upload speed stats | |
| if: ${{ always() && !fromJson(matrix.cache-hit) && matrix.test-type == 'speed-test' && matrix.device == 'cuda' }} | |
| # must succeed if it is a branch of Oneflow-Inc/oneflow | |
| continue-on-error: ${{ !(github.repository == 'Oneflow-Inc/oneflow') }} | |
| uses: ./.github/actions/upload_oss | |
| with: | |
| src_path: ${{ env.METRICS_DIR }} | |
| oss_dst_path: oss://oneflow-log/${{ github.repository }}/metrics/pr/${{ github.event.pull_request.number }}/${{ github.event.pull_request.head.sha }}/${{github.run_id}} | |
| oss_access_key_id: ${{ secrets.OSS_ACCESS_KEY_ID }} | |
| oss_access_key_secret: ${{ secrets.OSS_ACCESS_KEY_SECRET }} | |
| - name: Post speed stats | |
| if: ${{ always() && !fromJson(matrix.cache-hit) && matrix.test-type == 'speed-test' && matrix.device == 'cuda' }} | |
| continue-on-error: true | |
| uses: actions/github-script@v4 | |
| with: | |
| script: | | |
| github.issues.createComment({ | |
| issue_number: context.issue.number, | |
| owner: context.repo.owner, | |
| repo: context.repo.repo, | |
| body: "<details>\n <summary>Speed stats:</summary>\n\n ``` \n${{ steps.speed.outputs.stats }}\n ``` \n\n</details>".replace(/\\n/g, '\n') | |
| }) | |
| - name: Run tests in changed files compared to default branch 100 times | |
| timeout-minutes: 60 | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'module' && !fromJson(matrix.is-distributed) && steps.py-diff.outputs.has_changed_python_tests }} | |
| run: | | |
| docker exec -e ONEFLOW_TEST_DIR=diff \ | |
| -e ONEFLOW_TEST_FILES="${{needs.source_info.outputs.changed_python_tests}}" \ | |
| ${{ env.TEST_CONTAINER_NAME }} bash ci/test/generic_test_multi_client.sh | |
| - name: Expensive tests (models, cases require exclusive access to GPU) | |
| timeout-minutes: 45 | |
| if: ${{ !fromJson(matrix.cache-hit) && (matrix.test-type == 'speed-test' || (matrix.test-type == 'misc' && matrix.device == 'cuda')) && !fromJson(matrix.is-distributed) }} | |
| run: | | |
| docker exec \ | |
| -e ONEFLOW_TEST_TENSOR_SIZE_LIMIT_MB=1024 \ | |
| -e ONEFLOW_TEST_DIR=$PWD/python/oneflow/test/expensive \ | |
| ${{ env.TEST_CONTAINER_NAME }} bash ci/test/expensive_generic_test_multi_client.sh | |
| - name: Module API test | |
| timeout-minutes: 60 | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'module' && !fromJson(matrix.is-distributed) }} | |
| run: | | |
| docker exec -e ONEFLOW_TEST_DIR=$PWD/python/oneflow/test/modules ${{ env.TEST_CONTAINER_NAME }} bash ci/test/generic_test_multi_client.sh | |
| - name: Graph API test | |
| timeout-minutes: 45 | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'misc' }} | |
| run: | | |
| docker exec -e ONEFLOW_TEST_DIR=$PWD/python/oneflow/test/graph ${{ env.TEST_CONTAINER_NAME }} bash ci/test/generic_test_multi_client.sh | |
| docker exec ${{ env.TEST_CONTAINER_NAME }} python3 -m oneflow.distributed.launch --nproc_per_node 8 $PWD/python/oneflow/test/graph/test_neq_device_process_num.py | |
| - name: libai test | |
| timeout-minutes: 45 | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'misc' && matrix.device == 'cuda' }} | |
| run: | | |
| docker exec -e ONEFLOW_TEST_DEVICE_NUM=4 -w $PWD/${{ env.LIBAI_SRC }} ${{ env.TEST_CONTAINER_NAME }} python3 -m oneflow.distributed.launch --nproc_per_node 4 -m unittest -f tests/models/test_bert.py | |
| docker exec -e ONEFLOW_TEST_DEVICE_NUM=4 -w $PWD/${{ env.LIBAI_SRC }} ${{ env.TEST_CONTAINER_NAME }} python3 -m oneflow.distributed.launch --nproc_per_node 4 -m unittest -f tests/models/test_gpt.py | |
| docker exec -e ONEFLOW_TEST_DEVICE_NUM=4 -w $PWD/${{ env.LIBAI_SRC }} ${{ env.TEST_CONTAINER_NAME }} python3 -m oneflow.distributed.launch --nproc_per_node 4 -m unittest -f tests/models/test_t5.py | |
| docker exec -e ONEFLOW_TEST_DEVICE_NUM=4 -w $PWD/${{ env.LIBAI_SRC }} ${{ env.TEST_CONTAINER_NAME }} python3 -m oneflow.distributed.launch --nproc_per_node 4 -m unittest -f tests/models/test_vit.py | |
| - name: oneflow_face test | |
| timeout-minutes: 30 | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'misc' && matrix.device == 'cuda' }} | |
| run: | | |
| docker exec -e ONEFLOW_TEST_DEVICE_NUM=4 -w $PWD/${{ env.ONEFLOW_FACE_SRC }} ${{ env.TEST_CONTAINER_NAME }} python3 -m oneflow.distributed.launch --nproc_per_node 4 -m pytest tests/train/test_train.py | |
| - name: oneflow_iree test | |
| timeout-minutes: 45 | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'misc' && false }} | |
| run: | | |
| docker exec -w $PWD/${{ env.ONEFLOW_IREE_SRC }} ${{ env.TEST_CONTAINER_NAME }} python3 -m pytest examples | |
| - name: IR tests | |
| timeout-minutes: 45 | |
| if: ${{ !fromJson(matrix.cache-hit) && (matrix.test-type == 'misc' && matrix.device == 'cuda') && !fromJson(matrix.is-distributed) }} | |
| run: | | |
| docker exec \ | |
| -e ONEFLOW_TEST_TENSOR_SIZE_LIMIT_MB=1024 \ | |
| ${{ env.TEST_CONTAINER_NAME }} bash ci/test/ir_tests.sh | |
| - name: Exception API test | |
| timeout-minutes: 45 | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'misc' && false }} | |
| run: docker exec ${{ env.TEST_CONTAINER_NAME }} bash ci/test/multi_client_exception_test.sh | |
| - name: Misc test | |
| timeout-minutes: 45 | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'misc' }} | |
| run: | | |
| docker exec -e ONEFLOW_TEST_DIR=$PWD/python/oneflow/test/misc ${{ env.TEST_CONTAINER_NAME }} bash ci/test/generic_test_multi_client.sh | |
| - name: Dataloader API test | |
| timeout-minutes: 45 | |
| # TODO(luyang): dataset check fails | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'misc' && false}} | |
| run: | | |
| docker exec -e ONEFLOW_TEST_DIR=$PWD/python/oneflow/test/dataloader ${{ env.TEST_CONTAINER_NAME }} bash ci/test/generic_test_multi_client.sh | |
| - name: Tensor API test | |
| timeout-minutes: 45 | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'misc' }} | |
| run: | | |
| docker exec -e ONEFLOW_TEST_DIR=$PWD/python/oneflow/test/tensor ${{ env.TEST_CONTAINER_NAME }} bash ci/test/generic_test_multi_client.sh | |
| - name: Test mocking torch by script | |
| timeout-minutes: 45 | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'module' }} | |
| run: | | |
| docker exec ${{ env.TEST_CONTAINER_NAME }} bash -x ci/test/test_mock_script.sh | |
| - name: Test mocking torch by function | |
| timeout-minutes: 45 | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'module' }} | |
| run: | | |
| docker exec ${{ env.TEST_CONTAINER_NAME }} bash -x ci/test/test_mock_function.sh | |
| - name: Benchmark Test | |
| timeout-minutes: 100 | |
| if: ${{ !fromJson(matrix.cache-hit) && matrix.test-type == 'benchmark' && matrix.device == 'cuda' }} | |
| uses: Oneflow-Inc/get-oneflow/pytest-benchmark@whl-skip-nccl | |
| with: | |
| collect-path: ${{ env.FLOW_VISION_SRC }}/benchmark | |
| container-name: ${{ env.TEST_CONTAINER_NAME }} | |
| unknown-threshold: 30 | |
| error-threshold: 40 | |
| - name: Remove automerge | |
| if: ${{ failure() && contains(matrix.runs-on, 'self-hosted') && cancelled() == false && contains(github.event.pull_request.labels.*.name, 'automerge') }} | |
| uses: actions/github-script@v4 | |
| with: | |
| script: | | |
| github.issues.removeLabel({ | |
| issue_number: context.issue.number, | |
| owner: context.repo.owner, | |
| repo: context.repo.repo, | |
| name: 'automerge' | |
| }) | |
| github.issues.createComment({ | |
| issue_number: context.issue.number, | |
| owner: context.repo.owner, | |
| repo: context.repo.repo, | |
| body: 'CI failed when running job: ${{ matrix.entry }}. PR label automerge has been removed' | |
| }) | |
| - name: Print stacks in all core files | |
| timeout-minutes: 45 | |
| if: ${{ failure() && contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| docker exec ${{ env.TEST_CONTAINER_NAME }} bash ci/test/print_stack_in_all_dirs.sh || true | |
| - name: Query system status | |
| timeout-minutes: 45 | |
| if: ${{ failure() && contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| nvidia-smi || true | |
| docker ps || true | |
| - name: Remove container | |
| timeout-minutes: 45 | |
| if: ${{ always() && contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| docker rm -f ${{ env.TEST_CONTAINER_NAME }} || true | |
| - name: Remove manylinux container | |
| timeout-minutes: 45 | |
| if: ${{ always() && contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| docker rm -f ${{ env.TEST_MANYLINUX_CONTAINER_NAME }} || true | |
| - name: Clean workspace | |
| timeout-minutes: 45 | |
| if: ${{ always() && contains(matrix.runs-on, 'self-hosted') }} | |
| run: | | |
| docker run --rm -v $PWD:$PWD -w $PWD busybox rm -rf * | |
| static_analysis_with_clang_on_diff: | |
| name: Static analysis with clang on diff | |
| runs-on: ubuntu-20.04 | |
| if: github.event.pull_request.draft == false && github.base_ref == 'master' | |
| steps: | |
| - name: Check out OneFlow | |
| uses: actions/checkout@v2 | |
| with: | |
| ref: ${{ github.event.pull_request.head.sha }} | |
| repository: ${{github.event.pull_request.head.repo.full_name}} | |
| fetch-depth: 0 | |
| - uses: Oneflow-Inc/get-oneflow/cache-complete@whl-skip-nccl | |
| name: Save cache if successful | |
| id: save-cache | |
| timeout-minutes: 5 | |
| with: | |
| oneflow-src: . | |
| entry: static_analysis_with_clang_on_diff | |
| digest-type: build | |
| mark-as-completed: ${{ github.event.pull_request.head.repo.full_name == github.repository }} | |
| - name: Install dependencies | |
| if: ${{ !fromJSON(steps.save-cache.outputs.cache-hit) }} | |
| run: | | |
| sudo apt-get update | |
| sudo apt-get install -y libopenblas-dev nasm python3-pip ninja-build ccache | |
| - name: Download OneFlow custom clang-tidy | |
| if: ${{ !fromJSON(steps.save-cache.outputs.cache-hit) }} | |
| run: | | |
| wget https://github.com/Oneflow-Inc/llvm-project/releases/download/maybe-16.0.0/oneflow-clang-tidy-16 | |
| wget https://raw.githubusercontent.com/oneflow-inc/llvm-project/maybe/clang-tools-extra/clang-tidy/tool/clang-tidy-diff.py | |
| chmod +x oneflow-clang-tidy-16 clang-tidy-diff.py | |
| - name: Cache third party dir | |
| uses: actions/cache@v2 | |
| if: ${{ !fromJSON(steps.save-cache.outputs.cache-hit) }} | |
| with: | |
| path: ~/.ccache | |
| key: clang-tidy-diff-third-party-ccache-${{ hashFiles('**/CMakeLists.txt') }}-${{ hashFiles('**/*.cmake') }} | |
| restore-keys: | | |
| clang-tidy-diff-third-party-ccache-${{ hashFiles('**/CMakeLists.txt') }}- | |
| clang-tidy-diff-third-party-ccache- | |
| - name: Build third party libs and generate files | |
| if: ${{ !fromJSON(steps.save-cache.outputs.cache-hit) }} | |
| run: | | |
| export CCACHE_COMPRESS=true | |
| export CCACHE_MAXSIZE=500M | |
| mkdir build | |
| cd build | |
| cmake .. -C ../cmake/caches/international/cpu.cmake \ | |
| -DCMAKE_BUILD_TYPE=Release \ | |
| -DBUILD_TESTING=OFF \ | |
| -DCMAKE_C_COMPILER_LAUNCHER=ccache \ | |
| -DCMAKE_CXX_COMPILER_LAUNCHER=ccache | |
| cmake --build . -j$(nproc) --target oneflow_deps of_protoobj of_functional_obj of_functional_tensor_obj of_op_schema | |
| - name: Fetch upstream | |
| if: ${{ !fromJSON(steps.save-cache.outputs.cache-hit) && github.event.pull_request.head.repo.full_name != github.event.pull_request.base.repo.full_name }} | |
| run: | | |
| git remote add upstream https://github.com/Oneflow-Inc/oneflow | |
| git fetch upstream | |
| - name: Run clang-tidy for modified files | |
| # use clang as compiler for correct compiler flags | |
| if: ${{ !fromJSON(steps.save-cache.outputs.cache-hit) }} | |
| run: | | |
| cd build | |
| rm CMakeCache.txt | |
| cmake .. -C ../cmake/caches/international/cpu.cmake \ | |
| -DCMAKE_C_COMPILER=clang-12 \ | |
| -DCMAKE_CXX_COMPILER=clang++-12 \ | |
| -DCMAKE_BUILD_TYPE=Release \ | |
| -DBUILD_TESTING=OFF \ | |
| -DCMAKE_EXPORT_COMPILE_COMMANDS=ON | |
| cd .. | |
| git diff -U0 ${{ github.event.pull_request.base.sha }} | ./clang-tidy-diff.py -clang-tidy-binary ./oneflow-clang-tidy-16 -path build -allow-enabling-alpha-checkers -j $(nproc) -p1 -extra-arg="-Xclang" -extra-arg="-analyzer-config" -extra-arg="-Xclang" -extra-arg="aggressive-binary-operation-simplification=true" -warnings-as-errors="$(cat ./ci/check/clang_tidy_warnings_as_errors_on_diff)" | |
| - name: Check error message absence in changed files | |
| if: ${{ !fromJSON(steps.save-cache.outputs.cache-hit) && contains(github.event.pull_request.labels.*.name, 'need-check-error-message') }} | |
| run: | | |
| git diff -U0 ${{ github.event.pull_request.base.sha }} | ./clang-tidy-diff.py -clang-tidy-binary ./oneflow-clang-tidy-16 -path build -allow-enabling-alpha-checkers -j $(nproc) -p1 -extra-arg="-Xclang" -extra-arg="-analyzer-config" -extra-arg="-Xclang" -extra-arg="aggressive-binary-operation-simplification=true" -checks=-*,maybe-need-error-msg -warnings-as-errors=* -skip-line-filter | |
| - name: Remove automerge | |
| if: ${{ !fromJSON(steps.save-cache.outputs.cache-hit) && failure() && cancelled() == false && contains(github.event.pull_request.labels.*.name, 'automerge') }} | |
| uses: actions/github-script@v4 | |
| with: | |
| script: | | |
| github.issues.removeLabel({ | |
| issue_number: context.issue.number, | |
| owner: context.repo.owner, | |
| repo: context.repo.repo, | |
| name: 'automerge' | |
| }) | |
| github.issues.createComment({ | |
| issue_number: context.issue.number, | |
| owner: context.repo.owner, | |
| repo: context.repo.repo, | |
| body: 'Static analysis with clang failed. PR label automerge has been removed' | |
| }) |