far

.github/workflows/README.md

@@ -14,7 +14,7 @@
       - [Compatibility Test on Dispatch](#compatibility-test-on-dispatch)
     - [Release](#release)
     - [User Friendliness](#user-friendliness)
-    - [Commmunity](#commmunity)
+    - [Community](#community)
   - [Configuration](#configuration)
   - [Progress Log](#progress-log)
 
@@ -97,7 +97,7 @@ This workflow is triggered by manually dispatching the workflow. It has the foll
 | `Synchronize submodule` | `submodule.yml`         | This workflow will check if any git submodule is updated. If so, it will create a PR to update the submodule pointers.                 |
 | `Close inactive issues` | `close_inactive.yml`    | This workflow will close issues which are stale for 14 days.                                                                           |
 
-### Commmunity
+### Community
 
 | Workflow Name                                | File name                        | Description                                                                      |
 | -------------------------------------------- | -------------------------------- | -------------------------------------------------------------------------------- |

.github/workflows/build_on_pr.yml

@@ -3,24 +3,27 @@ name: Build on PR
 on:
   pull_request:
     types: [synchronize, opened, reopened]
+    branches:
+      - "main"
+      - "develop"
+      - "feature/**"
     paths:
-      - '.github/workflows/build_on_pr.yml' # run command & env variables change
-      - 'colossalai/**' # source code change
-      - '!colossalai/**.md' # ignore doc change
-      - 'op_builder/**' # cuda extension change
-      - '!op_builder/**.md' # ignore doc change
-      - 'requirements/**' # requirements change
-      - 'tests/**' # test change
-      - '!tests/**.md' # ignore doc change
-      - 'pytest.ini' # test config change
-      - 'setup.py' # install command change
+      - ".github/workflows/build_on_pr.yml" # run command & env variables change
+      - "colossalai/**" # source code change
+      - "!colossalai/**.md" # ignore doc change
+      - "op_builder/**" # cuda extension change
+      - "!op_builder/**.md" # ignore doc change
+      - "requirements/**" # requirements change
+      - "tests/**" # test change
+      - "!tests/**.md" # ignore doc change
+      - "pytest.ini" # test config change
+      - "setup.py" # install command change
 
 jobs:
   detect:
     name: Detect file change
     if: |
       github.event.pull_request.draft == false &&
-      github.base_ref == 'main' &&
       github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI'
     outputs:
       changedExtenisonFiles: ${{ steps.find-extension-change.outputs.all_changed_files }}
@@ -133,7 +136,7 @@ jobs:
       - name: Restore Testmon Cache
         run: |
           if [ -d /github/home/testmon_cache ]; then
-            [ ! -z "$(ls -A /github/home/testmon_cache)" ] && cp -p -r /github/home/testmon_cache/.testmondata /__w/ColossalAI/ColossalAI/
+            [ ! -z "$(ls -A /github/home/testmon_cache)" ] && cp -p -r /github/home/testmon_cache/.testmondata* /__w/ColossalAI/ColossalAI/
           fi
 
       - name: Execute Unit Testing
@@ -147,7 +150,7 @@ jobs:
       - name: Store Testmon Cache
         run: |
           [ -d /github/home/testmon_cache ] || mkdir /github/home/testmon_cache
-          cp -p -r /__w/ColossalAI/ColossalAI/.testmondata /github/home/testmon_cache/
+          cp -p -r /__w/ColossalAI/ColossalAI/.testmondata* /github/home/testmon_cache/
 
       - name: Collate artifact
         env:

.github/workflows/compatiblity_test_on_dispatch.yml

@@ -19,26 +19,26 @@ jobs:
     outputs:
       matrix: ${{ steps.set-matrix.outputs.matrix }}
     steps:
-    - id: set-matrix
-      env:
-        TORCH_VERSIONS: ${{ inputs.torch_version }}
-        CUDA_VERSIONS: ${{ inputs.cuda_version }}
-      run: |
-        IFS=','
-        DOCKER_IMAGE=()
+      - id: set-matrix
+        env:
+          TORCH_VERSIONS: ${{ inputs.torch_version }}
+          CUDA_VERSIONS: ${{ inputs.cuda_version }}
+        run: |
+          IFS=','
+          DOCKER_IMAGE=()
 
-        for tv in $TORCH_VERSIONS
-        do
-            for cv in $CUDA_VERSIONS
-            do
-                DOCKER_IMAGE+=("\"hpcaitech/pytorch-cuda:${tv}-${cv}\"")
-            done
-        done
+          for tv in $TORCH_VERSIONS
+          do
+              for cv in $CUDA_VERSIONS
+              do
+                  DOCKER_IMAGE+=("\"hpcaitech/pytorch-cuda:${tv}-${cv}\"")
+              done
+          done
 
-        container=$( IFS=',' ; echo "${DOCKER_IMAGE[*]}" )
-        container="[${container}]"
-        echo "$container"
-        echo "::set-output name=matrix::{\"container\":$(echo "$container")}"
+          container=$( IFS=',' ; echo "${DOCKER_IMAGE[*]}" )
+          container="[${container}]"
+          echo "$container"
+          echo "::set-output name=matrix::{\"container\":$(echo "$container")}"
 
   build:
     name: Test for PyTorch Compatibility
@@ -70,6 +70,17 @@ jobs:
       - uses: actions/checkout@v2
         with:
           ssh-key: ${{ secrets.SSH_KEY_FOR_CI }}
+      - name: Download cub for CUDA 10.2
+        run: |
+          CUDA_VERSION=$(cat $CUDA_HOME/version.txt | grep "CUDA Version" | awk '{print $NF}' | cut -d. -f1,2)
+
+          # check if it is CUDA 10.2
+          # download cub
+          if [ "$CUDA_VERSION" = "10.2" ]; then
+            wget https://github.com/NVIDIA/cub/archive/refs/tags/1.8.0.zip
+            unzip 1.8.0.zip
+            cp -r cub-1.8.0/cub/ colossalai/kernel/cuda_native/csrc/kernels/include/
+          fi
       - name: Install Colossal-AI
         run: |
           pip install -r requirements/requirements.txt

.github/workflows/compatiblity_test_on_pr.yml

@@ -3,8 +3,8 @@ name: Compatibility Test on PR
 on:
   pull_request:
     paths:
-      - 'version.txt'
-      - '.compatibility'
+      - "version.txt"
+      - ".compatibility"
 
 jobs:
   matrix_preparation:
@@ -58,6 +58,18 @@ jobs:
       - uses: actions/checkout@v2
         with:
           ssh-key: ${{ secrets.SSH_KEY_FOR_CI }}
+      - name: Download cub for CUDA 10.2
+        run: |
+          CUDA_VERSION=$(cat $CUDA_HOME/version.txt | grep "CUDA Version" | awk '{print $NF}' | cut -d. -f1,2)
+
+          # check if it is CUDA 10.2
+          # download cub
+          if [ "$CUDA_VERSION" = "10.2" ]; then
+            wget https://github.com/NVIDIA/cub/archive/refs/tags/1.8.0.zip
+            unzip 1.8.0.zip
+            cp -r cub-1.8.0/cub/ colossalai/kernel/cuda_native/csrc/kernels/include/
+          fi
+
       - name: Install Colossal-AI
         run: |
           pip install -v --no-cache-dir .

.github/workflows/doc_build_after_merge.yml → .github/workflows/doc_build_on_schedule_after_release.yml

@@ -1,18 +1,16 @@
-name: Build Documentation After Merge
+name: Build Documentation On Schedule & After Release
 
 on:
   workflow_dispatch:
-  pull_request:
-    paths:
-      - 'version.txt'
-      - 'docs/**'
-    types:
-      - closed
+  schedule:
+    - cron: "0 12 * * *" # build doc every day at 8pm Singapore time (12pm UTC time)
+  release:
+    types: [published]
 
 jobs:
   build-doc:
     name: Trigger Documentation Build Workflow
-    if: ( github.event_name == 'workflow_dispatch' || github.event.pull_request.merged == true ) && github.repository == 'hpcaitech/ColossalAI'
+    if: github.repository == 'hpcaitech/ColossalAI'
     runs-on: ubuntu-latest
     steps:
       - name: trigger workflow in ColossalAI-Documentation

.github/workflows/doc_check_on_pr.yml

@@ -2,47 +2,49 @@ name: Check Documentation on PR
 
 on:
   pull_request:
+    branches:
+      - "main"
+      - "develop"
+      - "feature/**"
     paths:
-      - 'docs/**'
+      - "docs/**"
 
 jobs:
   check-i18n:
     name: Check docs in diff languages
     if: |
-        github.event.pull_request.draft == false &&
-        github.base_ref == 'main' &&
-        github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI'
+      github.event.pull_request.draft == false &&
+      github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI'
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v2
 
       - uses: actions/setup-python@v2
         with:
-          python-version: '3.8.14'
+          python-version: "3.8.14"
 
       - run: python .github/workflows/scripts/check_doc_i18n.py -d docs/source
 
   check-doc-build:
     name: Test if the docs can be built
     if: |
-        github.event.pull_request.draft == false &&
-        github.base_ref == 'main' &&
-        github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI'
+      github.event.pull_request.draft == false &&
+      github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI'
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v2
         with:
-          path: './ColossalAI'
+          path: "./ColossalAI"
           fetch-depth: 0
 
       - uses: actions/checkout@v2
         with:
-          path: './ColossalAI-Documentation'
-          repository: 'hpcaitech/ColossalAI-Documentation'
+          path: "./ColossalAI-Documentation"
+          repository: "hpcaitech/ColossalAI-Documentation"
 
       - uses: actions/setup-python@v2
         with:
-          python-version: '3.8.14'
+          python-version: "3.8.14"
 
       # we use the versions in the main branch as the guide for versions to display
       # checkout will give your merged branch
@@ -57,7 +59,6 @@ jobs:
           git config user.name 'github-actions'
           git config user.email 'github-actions@github.com'
 
-
       - name: Build docs
         run: |
           cache_dir=ColossalAI-Documentation/doc-build/.cache

.github/workflows/doc_test_on_pr.yml

@@ -1,17 +1,20 @@
 name: Test Documentation on PR
 on:
   pull_request:
+    branches:
+      - "main"
+      - "develop"
+      - "feature/**"
     # any change in the examples folder will trigger check for the corresponding example.
     paths:
-      - 'docs/source/**.md'
+      - "docs/source/**.md"
 
 jobs:
   # This is for changed example files detect and output a matrix containing all the corresponding directory name.
   detect-changed-doc:
     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'
+      github.event.pull_request.draft == false &&
+      github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI' && github.event_name == 'pull_request'
     runs-on: ubuntu-latest
     outputs:
       any_changed: ${{ steps.changed-files.outputs.any_changed }}
@@ -26,10 +29,10 @@ jobs:
       - name: Locate base commit
         id: locate-base-sha
         run: |
-            curBranch=$(git rev-parse --abbrev-ref HEAD)
-            commonCommit=$(git merge-base origin/main $curBranch)
-            echo $commonCommit
-            echo "baseSHA=$commonCommit" >> $GITHUB_OUTPUT
+          curBranch=$(git rev-parse --abbrev-ref HEAD)
+          commonCommit=$(git merge-base origin/main $curBranch)
+          echo $commonCommit
+          echo "baseSHA=$commonCommit" >> $GITHUB_OUTPUT
 
       - name: Get all changed example files
         id: changed-files
@@ -43,10 +46,9 @@ jobs:
   check-changed-doc:
     # 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' &&
-        needs.detect-changed-doc.outputs.any_changed == 'true'
+      github.event.pull_request.draft == false &&
+      github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI' && github.event_name == 'pull_request' &&
+      needs.detect-changed-doc.outputs.any_changed == 'true'
     name: Test the changed Doc
     needs: detect-changed-doc
     runs-on: [self-hosted, gpu]
@@ -61,8 +63,8 @@ jobs:
       - name: Checkout ColossalAI-Documentation
         uses: actions/checkout@v2
         with:
-          path: './ColossalAI-Documentation'
-          repository: 'hpcaitech/ColossalAI-Documentation'
+          path: "./ColossalAI-Documentation"
+          repository: "hpcaitech/ColossalAI-Documentation"
 
       - name: Install Docer
         run: |

.github/workflows/example_check_on_pr.yml

@@ -1,17 +1,20 @@
 name: Test Example on PR
 on:
   pull_request:
+    branches:
+      - "main"
+      - "develop"
+      - "feature/**"
     # any change in the examples folder will trigger check for the corresponding example.
     paths:
-      - 'examples/**'
+      - "examples/**"
 
 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'
+      github.event.pull_request.draft == false &&
+      github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI' && github.event_name == 'pull_request'
     runs-on: ubuntu-latest
     outputs:
       matrix: ${{ steps.setup-matrix.outputs.matrix }}
@@ -26,10 +29,10 @@ jobs:
       - name: Locate base commit
         id: locate-base-sha
         run: |
-            curBranch=$(git rev-parse --abbrev-ref HEAD)
-            commonCommit=$(git merge-base origin/main $curBranch)
-            echo $commonCommit
-            echo "baseSHA=$commonCommit" >> $GITHUB_OUTPUT
+          curBranch=$(git rev-parse --abbrev-ref HEAD)
+          commonCommit=$(git merge-base origin/main $curBranch)
+          echo $commonCommit
+          echo "baseSHA=$commonCommit" >> $GITHUB_OUTPUT
 
       - name: Get all changed example files
         id: changed-files
@@ -61,10 +64,9 @@ jobs:
   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' &&
-        needs.detect-changed-example.outputs.anyChanged == 'true'
+      github.event.pull_request.draft == false &&
+      github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI' && github.event_name == 'pull_request' &&
+      needs.detect-changed-example.outputs.anyChanged == 'true'
     name: Test the changed example
     needs: detect-changed-example
     runs-on: [self-hosted, gpu]