update

Author: zihugithub

.github/workflows/qa-format.yml

@@ -0,0 +1,32 @@
+name: format_check
+
+on:
+  pull_request:
+    branches: [ "main" ]
+    types: [opened, synchronize, reopened]
+
+jobs:
+  format:
+    runs-on: ubuntu-22.04
+    env:
+      PRID: ${{ github.event.pull_request.number }}
+      BRANCH: main
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.pull_request.base.ref }}
+
+      - name: Merge PR to sub-branch
+        run: |
+          git fetch origin pull/${PRID}/merge
+          git checkout -b test FETCH_HEAD
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+
+      - name: Run pre-commit
+        run: bash ./qa/format.sh

.github/workflows/qa-l0-pytorch-wheel.yml

@@ -5,12 +5,12 @@ on:
     branches: main
     paths:
       - 'qa/L0_pytorch_wheel/**'
-      - '.github/workflows/qa_l0_pytorch_wheel.yml'
+      - '.github/workflows/qa-l0-pytorch-wheel.yml'
   pull_request:
     branches: main
     paths:
       - 'qa/L0_pytorch_wheel/**'
-      - '.github/workflows/qa_l0_pytorch_wheel.yml'
+      - '.github/workflows/qa-l0-pytorch-wheel.yml'
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-${{ github.actor }}

.github/workflows/qa-l0-te-cpp-unittest-pytorch-lint.yml

@@ -4,14 +4,14 @@ on:
   push:
     branches: main
     paths:
-      - '.github/workflows/qa_l0_test.yml'
+      - '.github/workflows/qa-l0-te-cpp-unittest-pytorch-lint.yml'
       - 'qa/L0_pytorch_lint/**'
       - 'transformer_engine/**'
       - 'tests/pytorch/**'
   pull_request:
     branches: main
     paths:
-      - '.github/workflows/qa_l0_test.yml'
+      - '.github/workflows/qa-l0-te-cpp-unittest-pytorch-lint.yml'
       - 'qa/L0_pytorch_lint/**'
       - 'transformer_engine/**'
       - 'tests/pytorch/**'
@@ -58,7 +58,7 @@ jobs:
           set-safe-directory: true
 
       - name: Install Dependencies & Build Transformer Engine
-        timeout-minutes: 60
+        # timeout-minutes: 40
         env:
           NVTE_FRAMEWORK: pytorch
           TE_WITH_NCCL: 1
@@ -92,7 +92,7 @@ jobs:
           python3 -c "import torch; print('CUDA Available:', torch.cuda.is_available()); print('GPU Count:', torch.cuda.device_count())"
 
       - name: Run L0 C++ Unit Tests
-        timeout-minutes: 80
+        # timeout-minutes: 60
         env:
           TE_PATH: .
         run: |
@@ -121,7 +121,7 @@ jobs:
           ctest --test-dir build -j$NUM_PARALLEL_JOBS
 
       - name: PyTorch C++ Lint
-        timeout-minutes: 5
+        # timeout-minutes: 5
         env:
           CPP_ONLY: 1
           TE_PATH: .
@@ -141,7 +141,7 @@ jobs:
         continue-on-error: true
 
       - name: PyTorch Python Lint
-        timeout-minutes: 5
+        # timeout-minutes: 5
         env:
           PYTHON_ONLY: 1
           TE_PATH: .
@@ -174,7 +174,7 @@ jobs:
           bash ./qa/L0_pytorch_debug_unittest/test.sh
 
       - name: Run L0 PyTorch Core Unit Tests
-        # timeout-minutes: 20
+        # timeout-minutes: 10
         env:
           TE_PATH: .
         run: |

.github/workflows/qa-l1-te-cpp-pytorch-tests.yml

@@ -4,7 +4,7 @@ on:
   push:
     branches: main
     paths:
-      - '.github/workflows/qa_l1_test.yml'
+      - '.github/workflows/qa-l1-te-cpp-pytorch-tests.yml'
       - 'qa/L1_cpp_distributed/**'
       - 'tests/cpp_distributed/**'
       - 'qa/L1_pytorch_thunder_integration/**'
@@ -17,7 +17,7 @@ on:
   pull_request:
     branches: main
     paths:
-      - '.github/workflows/qa_l1_test.yml'
+      - '.github/workflows/qa-l1-te-cpp-pytorch-tests.yml'
       - 'qa/L1_cpp_distributed/**'
       - 'tests/cpp_distributed/**'
       - 'qa/L1_pytorch_thunder_integration/**'
@@ -128,6 +128,7 @@ jobs:
           # Run thunder integration tests
           echo "=== Running L1 PyTorch Thunder Integration Tests ==="
           bash ./qa/L1_pytorch_thunder_integration/test.sh
+        # timeout-minutes: 5
 
       - name: Run L1 PyTorch Distributed Unit Tests
         continue-on-error: true
@@ -142,6 +143,7 @@ jobs:
           # Run distributed unit tests
           echo "=== Running L1 PyTorch Distributed Unit Tests ==="
           bash ./qa/L1_pytorch_distributed_unittest/test.sh
+        # timeout-minutes: 5
 
       - name: Run L1 PyTorch ONNX Unit Tests
         env:
@@ -155,3 +157,4 @@ jobs:
           # Run ONNX unit tests
           echo "=== Running L1 PyTorch ONNX Unit Tests ==="
           bash ./qa/L1_pytorch_onnx_unittest/test.sh
+        # timeout-minutes: 60

.github/workflows/qa-l3-te-pytorch-fa-versions-test.yml

@@ -4,13 +4,13 @@ on:
   push:
     branches: main
     paths:
-      - '.github/workflows/qa_l3_test.yml'
+      - '.github/workflows/qa-l3-te-pytorch-fa-versions-test.yml'
       - 'tests/pytorch/attention/test_attention.py'
 
   pull_request:
     branches: main
     paths:
-      - '.github/workflows/qa_l3_test.yml'
+      - '.github/workflows/qa-l3-te-pytorch-fa-versions-test.yml'
       - 'tests/pytorch/attention/test_attention.py'
 
 concurrency:

.github/workflows/te-plugin-tests.yml

@@ -5,12 +5,12 @@ on:
     branches: main
     paths:
       - 'transformer_engine/plugin/**'
-      - '.github/workflows/plugin_test.yml'
+      - '.github/workflows/te-plugin-tests.yml'
   pull_request:
     branches: main
     paths:
       - 'transformer_engine/plugin/**'
-      - '.github/workflows/plugin_test.yml'
+      - '.github/workflows/te-plugin-tests.yml'
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}-${{ github.actor }}