Merge branch 'main' of https://github.com/oahzxl/ColossalAI into chunk

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -20,6 +20,8 @@ body:
       A clear and concise description of what you expected to happen.
       **Screenshots**
       If applicable, add screenshots to help explain your problem.
+      **Optional: Affiliation**
+      Institution/email information helps better analyze and evaluate users to improve the project. Welcome to establish in-depth cooperation.
     placeholder: |
       A clear and concise description of what the bug is.
   validations:

.github/ISSUE_TEMPLATE/documentation.yml

@@ -17,6 +17,7 @@ body:
       **Expectation** What is your expected content about it?
       **Screenshots** If applicable, add screenshots to help explain your problem.
       **Suggestions** Tell us how we could improve the documentation.
+      **Optional: Affiliation** Institution/email information helps better analyze and evaluate users to improve the project. Welcome to establish in-depth cooperation.
     placeholder: |
       A clear and concise description of the issue.
   validations:

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -22,6 +22,8 @@ body:
       If applicable, add screenshots to help explain your problem.
       **Suggest a potential alternative/fix**
       Tell us how we could improve this project.
+      **Optional: Affiliation** 
+      Institution/email information helps better analyze and evaluate users to improve the project. Welcome to establish in-depth cooperation.
     placeholder: |
       A clear and concise description of your idea.
   validations:

.github/ISSUE_TEMPLATE/proposal.yml

@@ -13,6 +13,7 @@ body:
       - Bumping a critical dependency's major version;
       - A significant improvement in user-friendliness;
       - Significant refactor;
+      - Optional: Affiliation/email information helps better analyze and evaluate users to improve the project. Welcome to establish in-depth cooperation.
       - ...
 
       Please note this is not for feature request or bug template; such action could make us identify the issue wrongly and close it without doing anything.
@@ -43,4 +44,4 @@ body:
 - type: markdown
   attributes:
     value: >
-      Thanks for contributing 🎉!
+      Thanks for contributing 🎉!
\ No newline at end of file

.github/reviewer_list.yml

-addReviewers: true
-
-addAssignees: author
-
-numberOfReviewers: 1
-
-reviewers:
-  - frankleeeee
-  - kurisusnowdeng

.github/workflows/assign_reviewer.yml

-name: Assign Reviewers for Team
-
-on: 
-  pull_request:
-    types: [opened]
-
-jobs:
-  assign_reviewer:
-    name: Assign Reviewer for PR
-    runs-on: ubuntu-latest
-    if: |
-      github.event.pull_request.draft == false && github.base_ref == 'main'
-      && github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI' 
-      && toJson(github.event.pull_request.requested_reviewers) == '[]'
-    steps:
-      - uses: kentaro-m/auto-assign-action@v1.2.1
-        with:
-          configuration-path: '.github/reviewer_list.yml'

.github/workflows/auto_example_check.yml

+name: Test Example
+on:
+  pull_request:
+    # any change in the examples folder will trigger check for the corresponding example.
+    paths:
+      - 'examples/**'
+  # run at 00:00 of every Sunday(singapore time) so here is UTC time Saturday 16:00
+  schedule:
+    - cron:  '0 16 * * 6'
+
+jobs:
+  # This is for changed example files detect and output a matrix containing all the corresponding directory name.
+  detect-changed-example:
+    if: |
+        github.event.pull_request.draft == false &&
+        github.base_ref == 'main' &&
+        github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI' && github.event_name == 'pull_request'
+    runs-on: ubuntu-latest
+    outputs:
+      matrix: ${{ steps.setup-matrix.outputs.matrix }}
+      anyChanged: ${{ steps.setup-matrix.outputs.anyChanged }}
+    name: Detect changed example files
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+          ref: ${{ github.event.pull_request.head.sha }}
+      - name: Get all changed example files
+        id: changed-files
+        uses: tj-actions/changed-files@v35
+        # Using this can trigger action each time a PR is submitted.
+        with:
+          since_last_remote_commit: true
+      - name: setup matrix
+        id: setup-matrix
+        run: |
+          changedFileName=""
+          for file in ${{ steps.changed-files.outputs.all_changed_files  }}; do
+            changedFileName="${file}:${changedFileName}"
+          done
+          echo "$changedFileName was changed"
+          res=`python .github/workflows/scripts/example_checks/detect_changed_example.py --fileNameList $changedFileName`
+          echo "All changed examples are $res"
+
+          if [ "$x" = "[]" ]; then
+            echo "anyChanged=false" >> $GITHUB_OUTPUT
+            echo "matrix=null" >> $GITHUB_OUTPUT
+          else
+            dirs=$( IFS=',' ; echo "${res[*]}" )
+            echo "anyChanged=true" >> $GITHUB_OUTPUT
+            echo "matrix={\"directory\":$(echo "$dirs")}" >> $GITHUB_OUTPUT
+          fi
+
+  # If no file is changed, it will prompt an error and shows the matrix do not have value.
+  check-changed-example:
+    # Add this condition to avoid executing this job if the trigger event is workflow_dispatch.
+    if: |
+        github.event.pull_request.draft == false &&
+        github.base_ref == 'main' &&
+        github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI' && github.event_name == 'pull_request'
+    name: Test the changed example
+    needs: detect-changed-example
+    runs-on: [self-hosted, gpu]
+    strategy:
+      matrix: ${{fromJson(needs.detect-changed-example.outputs.matrix)}}
+    container:
+      image: hpcaitech/pytorch-cuda:1.12.0-11.3.0
+      options: --gpus all --rm -v /data/scratch/examples-data:/data/
+    timeout-minutes: 10
+    steps:
+      - uses: actions/checkout@v3
+      - name: Install Colossal-AI
+        run: |
+          pip install -v .
+      - name: Test the example
+        run: |
+          example_dir=${{ matrix.directory }}
+          cd "${PWD}/examples/${example_dir}"
+          bash test_ci.sh
+        env:
+          NCCL_SHM_DISABLE: 1
+
+  # This is for all files' weekly check. Specifically, this job is to find all the directories.
+  matrix_preparation:
+    if: |
+        github.event.pull_request.draft == false &&
+        github.base_ref == 'main' &&
+        github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI' && github.event_name == 'schedule'
+    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.event.pull_request.draft == false &&
+        github.base_ref == 'main' &&
+        github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI' && github.event_name == 'schedule'
+    name: Weekly check all examples
+    needs: matrix_preparation
+    runs-on: [self-hosted, gpu]
+    strategy:
+      matrix: ${{fromJson(needs.matrix_preparation.outputs.matrix)}}
+    container:
+      image: hpcaitech/pytorch-cuda:1.12.0-11.3.0
+    timeout-minutes: 10
+    steps:
+      - name: 📚 Checkout
+        uses: actions/checkout@v3
+      - name: Install Colossal-AI
+        run: |
+          pip install -v .
+      - name: Traverse all files
+        run: |
+          example_dir=${{ matrix.diretory }}
+          echo "Testing ${example_dir} now"
+          cd "${PWD}/examples/${example_dir}"
+          bash test_ci.sh
+        env:
+          NCCL_SHM_DISABLE: 1

.github/workflows/build.yml

 name: Build
 
-on: 
+on:
   pull_request:
     types: [synchronize, labeled]
 
 jobs:
-  build:
-    name: Build and Test Colossal-AI
+  detect:
+    name: Detect kernel-related file change
     if: |
         github.event.pull_request.draft == false &&
         github.base_ref == 'main' &&
         github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI' &&
         contains( github.event.pull_request.labels.*.name, 'Run Build and Test')
+    outputs:
+      changedFiles: ${{ steps.find-changed-files.outputs.changedFiles }}
+      anyChanged: ${{ steps.find-changed-files.outputs.any_changed }}
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+        with:
+          fetch-depth: 0
+          ref: ${{ github.event.pull_request.head.sha }}
+      - name: Find the changed files
+        id: find-changed-files
+        uses: tj-actions/changed-files@v35
+        with:
+          since_last_remote_commit: true
+          files: |
+            op_builder/**
+            colossalai/kernel/**
+            setup.py
+      - name: List changed files
+        run: |
+          for file in ${{ steps.find-changed-files.outputs.all_changed_files }}; do
+            echo "$file was changed"
+          done
+
+
+  build:
+    name: Build and Test Colossal-AI
+    needs: detect
     runs-on: [self-hosted, gpu]
     container:
       image: hpcaitech/pytorch-cuda:1.11.0-11.3.0
@@ -23,27 +51,38 @@ jobs:
           repository: hpcaitech/TensorNVMe
           ssh-key: ${{ secrets.SSH_KEY_FOR_CI }}
           path: TensorNVMe
+
       - name: Install tensornvme
         run: |
           cd TensorNVMe
           conda install cmake
           pip install -r requirements.txt
           pip install -v .
+
       - uses: actions/checkout@v2
         with:
           ssh-key: ${{ secrets.SSH_KEY_FOR_CI }}
-      - name: Install Colossal-AI      
+
+      - name: Restore cache
+        if: needs.detect.outputs.anyChanged != 'true'
         run: |
-          [ ! -z "$(ls -A /github/home/cuda_ext_cache/)" ] && cp -r /github/home/cuda_ext_cache/* /__w/ColossalAI/ColossalAI/
-          pip install -r requirements/requirements.txt
-          pip install -v -e .
-          cp -r /__w/ColossalAI/ColossalAI/build /github/home/cuda_ext_cache/
-          cp /__w/ColossalAI/ColossalAI/*.so /github/home/cuda_ext_cache/
+          # -p flag is required to preserve the file timestamp to avoid ninja rebuild
+          [ ! -z "$(ls -A /github/home/cuda_ext_cache/)" ] && cp -p -r /github/home/cuda_ext_cache/* /__w/ColossalAI/ColossalAI/
+
+      - name: Install Colossal-AI
+        run: |
+          CUDA_EXT=1 pip install -v -e .
           pip install -r requirements/requirements-test.txt
+
       - name: Unit Testing
         run: |
-          PYTHONPATH=$PWD pytest tests
+          PYTHONPATH=$PWD pytest --cov=. --cov-report lcov tests
         env:
           DATA: /data/scratch/cifar-10
           NCCL_SHM_DISABLE: 1
           LD_LIBRARY_PATH: /github/home/.tensornvme/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
+
+      - name: Store Cache
+        run: |
+          # -p flag is required to preserve the file timestamp to avoid ninja rebuild
+          cp -p -r /__w/ColossalAI/ColossalAI/build /github/home/cuda_ext_cache/

.github/workflows/build_gpu_8.yml

@@ -2,7 +2,7 @@ name: Build on 8 GPUs
 
 on:
   schedule:
-    # run at 00:00 of every Sunday 
+    # run at 00:00 of every Sunday
     - cron:  '0 0 * * *'
   workflow_dispatch:
 
@@ -30,13 +30,11 @@ jobs:
       - uses: actions/checkout@v2
         with:
           ssh-key: ${{ secrets.SSH_KEY_FOR_CI }}
-      - name: Install Colossal-AI      
+      - name: Install Colossal-AI
         run: |
           [ ! -z "$(ls -A /github/home/cuda_ext_cache/)" ] && cp -r /github/home/cuda_ext_cache/* /__w/ColossalAI/ColossalAI/
-          pip install -r requirements/requirements.txt
-          pip install -v -e .
+          CUDA_EXT=1 pip install -v -e .
           cp -r /__w/ColossalAI/ColossalAI/build /github/home/cuda_ext_cache/
-          cp /__w/ColossalAI/ColossalAI/*.so /github/home/cuda_ext_cache/
           pip install -r requirements/requirements-test.txt
       - name: Unit Testing
         run: |
@@ -45,4 +43,3 @@ jobs:
         env:
           DATA: /data/scratch/cifar-10
           LD_LIBRARY_PATH: /github/home/.tensornvme/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64
-          
\ No newline at end of file

.github/workflows/compatibility_test.yml

@@ -70,7 +70,7 @@ jobs:
       - uses: actions/checkout@v2
         with:
           ssh-key: ${{ secrets.SSH_KEY_FOR_CI }}
-      - name: Install Colossal-AI      
+      - name: Install Colossal-AI
         run: |
           pip install -r requirements/requirements.txt
           pip install -v --no-cache-dir .

.github/workflows/dispatch_example_check.yml

+name: Manual Test Example
+on:
+  workflow_dispatch:
+    inputs:
+      example_directory:
+        type: string
+        description: example directory, separated by space. For example, language/gpt, images/vit. Simply input language or simply gpt does not work.
+        required: true
+
+jobs:
+  matrix_preparation:
+    if: |
+        github.event.pull_request.draft == false &&
+        github.base_ref == 'main' &&
+        github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI'
+    name: Check the examples user want
+    runs-on: ubuntu-latest
+    outputs:
+      matrix: ${{ steps.set-matrix.outputs.matrix }}
+    steps:
+    - name: 📚 Checkout
+      uses: actions/checkout@v3
+    - name: Set up matrix
+      id: set-matrix
+      env:
+        check_dir: ${{ inputs.example_directory }}
+      run: |
+        res=`python .github/workflows/scripts/example_checks/check_dispatch_inputs.py --fileNameList $check_dir`
+        if [ res == "failure" ];then
+          exit -1
+        fi
+        dirs="[${check_dir}]"
+        echo "Testing examples in $dirs"
+        echo "matrix={\"directory\":$(echo "$dirs")}" >> $GITHUB_OUTPUT
+
+  test_example:
+    if: |
+        github.event.pull_request.draft == false &&
+        github.base_ref == 'main' &&
+        github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI'
+    name: Manually check example files
+    needs: manual_check_matrix_preparation
+    runs-on: [self-hosted, gpu]
+    strategy:
+      matrix: ${{fromJson(needs.manual_check_matrix_preparation.outputs.matrix)}}
+    container:
+      image: hpcaitech/pytorch-cuda:1.12.0-11.3.0
+      options: --gpus all --rm -v /data/scratch/examples-data:/data/
+    timeout-minutes: 10
+    steps:
+      - name: 📚 Checkout
+        uses: actions/checkout@v3
+      - name: Install Colossal-AI
+        run: |
+          pip install -v .
+      - name: Test the example
+        run: |
+          dir=${{ matrix.directory }}
+          echo "Testing ${dir} now"
+          cd "${PWD}/examples/${dir}"
+          bash test_ci.sh
+        env:
+          NCCL_SHM_DISABLE: 1

.github/workflows/draft_github_release_post.yml

@@ -20,7 +20,7 @@ jobs:
           fetch-depth: 0
       - uses: actions/setup-python@v2
         with:
-          python-version: '3.7.12'
+          python-version: '3.8.14'
       - name: generate draft
         id: generate_draft
         run: |
@@ -42,4 +42,3 @@ jobs:
           body_path: ${{ steps.generate_draft.outputs.path }}
           draft: True
           prerelease: false
-        
\ No newline at end of file

.github/workflows/release_bdist.yml

@@ -64,9 +64,21 @@ jobs:
       - name: Copy scripts and checkout
         run: |
           cp -r ./.github/workflows/scripts/* ./
+
+          # link the cache diretories to current path
+          ln -s /github/home/conda_pkgs ./conda_pkgs
           ln -s /github/home/pip_wheels ./pip_wheels
+
+          # set the conda package path
+          echo "pkgs_dirs:\n  - $PWD/conda_pkgs" > ~/.condarc
+
+          # set safe directory
           git config --global --add safe.directory /__w/ColossalAI/ColossalAI
+
+          # check out
           git checkout $git_ref
+
+          # get cub package for cuda 10.2
           wget https://github.com/NVIDIA/cub/archive/refs/tags/1.8.0.zip
           unzip 1.8.0.zip
         env:

.github/workflows/release_docker.yml

@@ -18,23 +18,17 @@ jobs:
         with:
           fetch-depth: 0
       - name: Build Docker
+        id: build
         run: |
           version=$(cat version.txt)
-          docker build --build-arg http_proxy=http://172.17.0.1:7890 --build-arg https_proxy=http://172.17.0.1:7890 -t hpcaitech/colossalai:$version ./docker
+          tag=hpcaitech/colossalai:$version
+          docker build --build-arg http_proxy=http://172.17.0.1:7890 --build-arg https_proxy=http://172.17.0.1:7890 -t $tag ./docker
+          echo "tag=${tag}" >> $GITHUB_OUTPUT
       - name: Log in to Docker Hub
         uses: docker/login-action@f054a8b539a109f9f41c372932f1ae047eff08c9
         with:
           username: ${{ secrets.DOCKER_USERNAME }}
           password: ${{ secrets.DOCKER_PASSWORD }}
-      - name: Extract metadata (tags, labels) for Docker
-        id: meta
-        uses: docker/metadata-action@98669ae865ea3cffbcbaa878cf57c20bbf1c6c38
-        with:
-          images: hpcaitech/colossalai
-      - name: Build and push Docker image
-        uses: docker/build-push-action@ad44023a93711e3deb337508980b4b5e9bcdc5dc
-        with:
-          context: .
-          push: true
-          tags: ${{ steps.meta.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels }}
+      - name: Push Docker image
+        run: |
+          docker push ${{ steps.build.outputs.tag }}
\ No newline at end of file

.github/workflows/release_nightly.yml

-name: Release bdist wheel for Nightly versions
+name: Publish Nightly Version to PyPI
 
 on:
-  schedule:
-    # run at 00:00 of every Sunday 
-    - cron:  '0 0 * * 6'
   workflow_dispatch:
-  
+  schedule:
+    - cron:  '0 0 * * 6' # release on every Sunday 00:00 UTC time
+
 jobs:
-  matrix_preparation:
-    name: Prepare Container List
+  build-n-publish:
+    if: github.event_name == 'workflow_dispatch' || github.repository == 'hpcaitech/ColossalAI'
+    name: Build and publish Python 🐍 distributions 📦 to PyPI
     runs-on: ubuntu-latest
-    outputs:
-      matrix: ${{ steps.set-matrix.outputs.matrix }}
+    timeout-minutes: 20
     steps:
-    - id: set-matrix
-      run: |
-        matrix="[\"hpcaitech/cuda-conda:11.3\", \"hpcaitech/cuda-conda:10.2\"]"
-        echo $matrix
-        echo "::set-output name=matrix::{\"container\":$(echo $matrix)}"
+    - uses: actions/checkout@v2
 
-  build:
-    name: Release bdist wheels
-    needs: matrix_preparation
-    if: github.repository == 'hpcaitech/ColossalAI' && contains(fromJson('["FrankLeeeee", "ver217", "feifeibear", "kurisusnowdeng"]'), github.actor)
-    runs-on: [self-hosted, gpu]
-    strategy:
-      fail-fast: false
-      matrix: ${{fromJson(needs.matrix_preparation.outputs.matrix)}}
-    container:
-      image: ${{ matrix.container }}
-      options: --gpus all --rm
-    steps:
-      - uses: actions/checkout@v2
-        with:
-          fetch-depth: 0
-      # cub is for cuda 10.2
-      - name: Copy scripts and checkout
-        run: |
-          cp -r ./.github/workflows/scripts/* ./
-          ln -s /github/home/pip_wheels ./pip_wheels
-          wget https://github.com/NVIDIA/cub/archive/refs/tags/1.8.0.zip
-          unzip 1.8.0.zip
-      - name: Build bdist wheel
-        run: |
-          pip install beautifulsoup4 requests packaging
-          python ./build_colossalai_wheel.py --nightly
-      - name: 🚀 Deploy
-        uses: garygrossgarten/github-action-scp@release
-        with:
-          local: all_dist
-          remote: ${{ secrets.PRIVATE_PYPI_NIGHTLY_DIR }}
-          host: ${{ secrets.PRIVATE_PYPI_HOST }}
-          username: ${{ secrets.PRIVATE_PYPI_USER }}
-          password: ${{ secrets.PRIVATE_PYPI_PASSWD }}
-  remove_old_build:
-    name: Remove old nightly build
-    runs-on: ubuntu-latest
-    needs: build
-    steps:
-      - name: executing remote ssh commands using password
-        uses: appleboy/ssh-action@master
-        env:
-          BUILD_DIR: ${{ secrets.PRIVATE_PYPI_NIGHTLY_DIR }}
-        with:
-          host: ${{ secrets.PRIVATE_PYPI_HOST }}
-          username: ${{ secrets.PRIVATE_PYPI_USER }}
-          password: ${{ secrets.PRIVATE_PYPI_PASSWD }}
-          envs: BUILD_DIR
-          script: |
-            cd $BUILD_DIR
-            find . -type f -mtime +0 -exec rm -f {} +
-          script_stop: true
-        
+    - uses: actions/setup-python@v2
+      with:
+        python-version: '3.8.14'
+
+    - run: NIGHTLY=1 python setup.py sdist build
+
+    # publish to PyPI if executed on the main branch
+    - name: Publish package to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1
+      with:
+        user: __token__
+        password: ${{ secrets.PYPI_API_TOKEN }}
+        verbose: true

.github/workflows/release.yml → .github/workflows/release_pypi.yml

 name: Publish to PyPI
 
-on: workflow_dispatch
+on:
+  workflow_dispatch:
+  pull_request:
+    paths:
+      - 'version.txt'
+    types:
+      - closed
 
 jobs:
   build-n-publish:
-    if: github.ref_name == 'main' && github.repository == 'hpcaitech/ColossalAI' && contains(fromJson('["FrankLeeeee", "ver217", "feifeibear", "kurisusnowdeng"]'), github.actor)
+    if: github.event_name == 'workflow_dispatch' || github.repository == 'hpcaitech/ColossalAI' && github.event.pull_request.merged == true && github.base_ref == 'main' 
     name: Build and publish Python 🐍 distributions 📦 to PyPI
     runs-on: ubuntu-latest
     timeout-minutes: 20
     steps:
     - uses: actions/checkout@v2
+
     - uses: actions/setup-python@v2
       with:
-        python-version: '3.7.12'
+        python-version: '3.8.14'
+
     - run: python setup.py sdist build
+    
     # publish to PyPI if executed on the main branch
-    # publish to Test PyPI if executed on the develop branch
     - name: Publish package to PyPI
       uses: pypa/gh-action-pypi-publish@release/v1
       with:

.github/workflows/release_test.yml

-name: Publish to Test PyPI
-
-on: workflow_dispatch
-
-jobs:
-  build-n-publish:
-    if: github.repository == 'hpcaitech/ColossalAI' && contains(fromJson('["FrankLeeeee", "ver217", "feifeibear", "kurisusnowdeng"]'), github.actor)
-    name: Build and publish Python 🐍 distributions 📦 to Test PyPI
-    runs-on: ubuntu-latest
-    timeout-minutes: 20
-    steps:
-    - uses: actions/checkout@v2
-    - uses: actions/setup-python@v2
-      with:
-        python-version: '3.7.12'
-    - run: python setup.py sdist build
-    # publish to PyPI if executed on the main branch
-    # publish to Test PyPI if executed on the develop branch
-    - name: Publish package to Test PyPI
-      uses: pypa/gh-action-pypi-publish@release/v1
-      with:
-        user: __token__
-        password: ${{ secrets.TEST_PYPI_API_TOKEN }}
-        repository_url: https://test.pypi.org/legacy/
-        verbose: true

.github/workflows/scripts/build_colossalai_wheel.py

-from filecmp import cmp
-import requests
-from bs4 import BeautifulSoup
 import argparse
 import os
 import subprocess
-from packaging import version
+from filecmp import cmp
 from functools import cmp_to_key
 
+import requests
+from bs4 import BeautifulSoup
+from packaging import version
+
 WHEEL_TEXT_ROOT_URL = 'https://github.com/hpcaitech/public_assets/tree/main/colossalai/torch_build/torch_wheels'
 RAW_TEXT_FILE_PREFIX = 'https://raw.githubusercontent.com/hpcaitech/public_assets/main/colossalai/torch_build/torch_wheels'
 CUDA_HOME = os.environ['CUDA_HOME']

.github/workflows/scripts/build_colossalai_wheel.sh

@@ -18,7 +18,7 @@ if [ $1 == "pip" ]
 then
     wget -nc -q -O ./pip_wheels/$filename $url
     pip install ./pip_wheels/$filename
-    
+
 elif [ $1 == 'conda' ]
 then
     conda install pytorch==$torch_version cudatoolkit=$cuda_version $flags
@@ -34,8 +34,9 @@ fi
 
 python setup.py bdist_wheel
 mv ./dist/* ./all_dist
+# must remove build to enable compilation for
+# cuda extension in the next build
+rm -rf ./build
 python setup.py clean
 conda deactivate
 conda env remove -n $python_version
-
-

.github/workflows/scripts/example_checks/check_dispatch_inputs.py

+import argparse
+import os
+
+
+def check_inputs(input_list):
+    for path in input_list:
+        real_path = os.path.join('examples', path)
+        if not os.path.exists(real_path):
+            return False
+    return True
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('-f', '--fileNameList', type=str, help="List of file names")
+    args = parser.parse_args()
+    name_list = args.fileNameList.split(",")
+    is_correct = check_inputs(name_list)
+
+    if is_correct:
+        print('success')
+    else:
+        print('failure')
+
+
+if __name__ == '__main__':
+    main()