[workflow] refactored compatibility test workflow for maintenability (#2560)

.github/workflows/compatiblity_test_on_dispatch.yml

@@ -1,4 +1,4 @@
-name: Dispatch Compatibility Test
+name: Compatibility Test on Dispatch
 
 on:
   workflow_dispatch:

.github/workflows/compatiblity_test_on_pr.yml

@@ -0,0 +1,71 @@
+name: Compatibility Test on PR
+
+on:
+  pull_request:
+    paths:
+      - 'version.txt'
+      - '.compatibility'
+
+jobs:
+  matrix_preparation:
+    name: Prepare Container List
+    runs-on: ubuntu-latest
+    outputs:
+      matrix: ${{ steps.set-matrix.outputs.matrix }}
+    steps:
+      - uses: actions/checkout@v3
+      - id: set-matrix
+        run: |
+          IFS=','
+          DOCKER_IMAGE=()
+
+          while read tag; do
+            DOCKER_IMAGE+=("\"hpcaitech/pytorch-cuda:${tag}\"")
+          done <.compatibility
+
+          container=$( IFS=',' ; echo "${DOCKER_IMAGE[*]}" )
+          container="[${container}]"
+          echo "$container"
+          echo "::set-output name=matrix::{\"container\":$(echo "$container")}"
+
+  build:
+    name: Test for PyTorch Compatibility
+    needs: matrix_preparation
+    if: github.repository == 'hpcaitech/ColossalAI'
+    runs-on: [self-hosted, gpu]
+    strategy:
+      fail-fast: false
+      matrix: ${{fromJson(needs.matrix_preparation.outputs.matrix)}}
+    container:
+      image: ${{ matrix.container }}
+      options: --gpus all --rm -v /data/scratch/cifar-10:/data/scratch/cifar-10
+    timeout-minutes: 120
+    steps:
+      - name: Install dependencies
+        run: |
+          pip install -U pip setuptools wheel --user
+      - uses: actions/checkout@v2
+        with:
+          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: ${{ secrets.SSH_KEY_FOR_CI }}
+      - name: Install Colossal-AI
+        run: |
+          pip install -v --no-cache-dir .
+          pip install -r requirements/requirements-test.txt
+      - name: Unit Testing
+        run: |
+          PYTHONPATH=$PWD pytest 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

.github/workflows/compatiblity_test_on_schedule.yml

@@ -1,10 +1,6 @@
-name: Compatibility Test
+name: Compatibility Test on Schedule
 
 on:
-  pull_request:
-    paths:
-      - 'version.txt'
-      - '.compatibility'
   # run at 03:00 of every Sunday(singapore time) so here is UTC time Saturday 16:00
   schedule:
     - cron:  '0 19 * * 6'