[devops] fix concurrency group and compatibility test (#4665)

* [devops] fix concurrency group

* [devops] fix compatibility test

* [devops] fix tensornvme install

* [devops] fix tensornvme install

* [devops] fix colossalai install

.github/workflows/build_on_pr.yml

@@ -61,7 +61,7 @@ jobs:
       run:
         shell: bash
     concurrency:
-      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-repare-cache
       cancel-in-progress: true
     steps:
       - name: Copy testmon cache
@@ -87,7 +87,7 @@ jobs:
       anyLibraryFileChanged: ${{ steps.find-lib-change.outputs.any_changed }}
     runs-on: ubuntu-latest
     concurrency:
-      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-detect-change
       cancel-in-progress: true
     steps:
       - uses: actions/checkout@v2
@@ -147,7 +147,7 @@ jobs:
       run:
         shell: bash
     concurrency:
-      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-run-test
       cancel-in-progress: true
     steps:
       - name: Checkout TensorNVMe

.github/workflows/compatiblity_test_on_dispatch.yml

@@ -64,7 +64,7 @@ jobs:
       - name: Install tensornvme
         run: |
           cd TensorNVMe
-          conda install cmake
+          apt update && apt install -y cmake
           pip install -r requirements.txt
           pip install -v .
       - uses: actions/checkout@v2
@@ -83,8 +83,7 @@ jobs:
           fi
       - name: Install Colossal-AI
         run: |
-          pip install -r requirements/requirements.txt
+          CUDA_EXT=1 pip install -v .
-          pip install -v --no-cache-dir .
           pip install -r requirements/requirements-test.txt
       - name: Unit Testing
         run: |

.github/workflows/compatiblity_test_on_pr.yml

@@ -13,7 +13,7 @@ jobs:
     outputs:
       matrix: ${{ steps.set-matrix.outputs.matrix }}
     concurrency:
-      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-prepare-matrix
       cancel-in-progress: true
     steps:
       - uses: actions/checkout@v3
@@ -44,7 +44,7 @@ jobs:
       options: --gpus all --rm -v /data/scratch/cifar-10:/data/scratch/cifar-10
     timeout-minutes: 120
     concurrency:
-      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-run-test
       cancel-in-progress: true
     steps:
       - name: Install dependencies
@@ -58,7 +58,7 @@ jobs:
       - name: Install tensornvme
         run: |
           cd TensorNVMe
-          conda install cmake
+          apt update && apt install -y cmake
           pip install -r requirements.txt
           pip install -v .
       - uses: actions/checkout@v2
@@ -78,7 +78,7 @@ jobs:
 
       - name: Install Colossal-AI
         run: |
-          pip install -v --no-cache-dir .
+          CUDA_EXT=1 pip install -v .
           pip install -r requirements/requirements-test.txt
       - name: Unit Testing
         run: |

.github/workflows/compatiblity_test_on_schedule.yml

@@ -54,7 +54,7 @@ jobs:
       - name: Install tensornvme
         run: |
           cd TensorNVMe
-          conda install cmake
+          apt update && apt install -y cmake
           pip install -r requirements.txt
           pip install -v .
       - uses: actions/checkout@v2
@@ -75,7 +75,7 @@ jobs:
 
       - name: Install Colossal-AI
         run: |
-          pip install -v --no-cache-dir .
+          CUDA_EXT=1 pip install -v .
           pip install -r requirements/requirements-test.txt
 
       - name: Unit Testing

.github/workflows/doc_check_on_pr.yml

@@ -17,7 +17,7 @@ jobs:
       github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI'
     runs-on: ubuntu-latest
     concurrency:
-      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-check-i18n
       cancel-in-progress: true
     steps:
       - uses: actions/checkout@v2
@@ -35,7 +35,7 @@ jobs:
       github.event.pull_request.base.repo.full_name == 'hpcaitech/ColossalAI'
     runs-on: ubuntu-latest
     concurrency:
-      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-check-doc
       cancel-in-progress: true
     steps:
       - uses: actions/checkout@v2

.github/workflows/doc_test_on_pr.yml

@@ -20,7 +20,7 @@ jobs:
       any_changed: ${{ steps.changed-files.outputs.any_changed }}
       changed_files: ${{ steps.changed-files.outputs.all_changed_files }}
     concurrency:
-      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-detect-change
       cancel-in-progress: true
     name: Detect changed example files
     steps:
@@ -63,7 +63,7 @@ jobs:
       run:
         shell: bash
     concurrency:
-      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-run-doctest
       cancel-in-progress: true
     steps:
       - name: Checkout ColossalAI-Documentation

.github/workflows/example_check_on_pr.yml

@@ -21,7 +21,7 @@ jobs:
       anyChanged: ${{ steps.setup-matrix.outputs.anyChanged }}
     name: Detect changed example files
     concurrency:
-      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-detect-change
       cancel-in-progress: true
     steps:
       - uses: actions/checkout@v3
@@ -81,7 +81,7 @@ jobs:
       options: --gpus all --rm -v /data/scratch/examples-data:/data/
     timeout-minutes: 10
     concurrency:
-      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+      group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-run-example
       cancel-in-progress: true
     steps:
       - uses: actions/checkout@v3