Workflow fixes (#11270)

huggingface · Apr 16, 2021 · 5254220 · 5254220
1 parent dfc6dd8
commit 5254220
Show file tree

Hide file tree

Showing 3 changed files with 46 additions and 2 deletions.
diff --git a/.github/workflows/self-push.yml b/.github/workflows/self-push.yml
@@ -38,6 +38,7 @@ jobs:
           apt -y update && apt install -y libsndfile1-dev
           pip install --upgrade pip
           pip install .[sklearn,testing,onnxruntime,sentencepiece,speech]
+          pip install torch-scatter -f https://pytorch-geometric.com/whl/torch-1.8.0+cu111.html
 
       - name: Are GPUs recognized by our DL frameworks
         run: |
@@ -121,6 +122,7 @@ jobs:
           apt -y update && apt install -y libsndfile1-dev
           pip install --upgrade pip
           pip install .[sklearn,testing,onnxruntime,sentencepiece,speech]
+          pip install torch-scatter -f https://pytorch-geometric.com/whl/torch-1.8.0+cu111.html
 
       - name: Are GPUs recognized by our DL frameworks
         run: |
@@ -220,6 +222,13 @@ jobs:
         if: ${{ always() }}
         run: cat reports/tests_torch_cuda_extensions_gpu_failures_short.txt
 
+      - name: Test suite reports artifacts
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v2
+        with:
+          name: run_tests_torch_cuda_extensions_gpu_test_reports
+          path: reports
+
   run_tests_torch_cuda_extensions_multi_gpu:
     runs-on: [self-hosted, docker-gpu, multi-gpu]
     container:
@@ -253,6 +262,13 @@ jobs:
         if: ${{ always() }}
         run: cat reports/tests_torch_cuda_extensions_multi_gpu_failures_short.txt
 
+      - name: Test suite reports artifacts
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v2
+        with:
+          name: run_tests_torch_cuda_extensions_multi_gpu_test_reports
+          path: reports
+
 
   send_results:
     name: Send results to webhook

diff --git a/.github/workflows/self-scheduled.yml b/.github/workflows/self-scheduled.yml
@@ -33,7 +33,8 @@ jobs:
         run: |
           apt -y update && apt install -y libsndfile1-dev
           pip install --upgrade pip
-          pip install .[sklearn,testing,onnxruntime,sentencepiece,speech,deepspeed]
+          pip install .[sklearn,testing,onnxruntime,sentencepiece,speech]
+          pip install torch-scatter -f https://pytorch-geometric.com/whl/torch-1.8.0+cu111.html
 
       - name: Are GPUs recognized by our DL frameworks
         run: |
@@ -155,7 +156,8 @@ jobs:
         run: |
           apt -y update && apt install -y libsndfile1-dev
           pip install --upgrade pip
-          pip install .[sklearn,testing,onnxruntime,sentencepiece,speech,deepspeed,fairscale]
+          pip install .[sklearn,testing,onnxruntime,sentencepiece,speech]
+          pip install torch-scatter -f https://pytorch-geometric.com/whl/torch-1.8.0+cu111.html
 
       - name: Are GPUs recognized by our DL frameworks
         run: |
@@ -279,6 +281,13 @@ jobs:
         if: ${{ always() }}
         run: cat reports/tests_torch_cuda_extensions_gpu_failures_short.txt
 
+      - name: Test suite reports artifacts
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v2
+        with:
+          name: run_tests_torch_cuda_extensions_gpu_test_reports
+          path: reports
+
   run_all_tests_torch_cuda_extensions_multi_gpu:
     runs-on: [self-hosted, docker-gpu, multi-gpu]
     container:
@@ -312,6 +321,13 @@ jobs:
         if: ${{ always() }}
         run: cat reports/tests_torch_cuda_extensions_multi_gpu_failures_short.txt
 
+      - name: Test suite reports artifacts
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v2
+        with:
+          name: run_tests_torch_cuda_extensions_multi_gpu_test_reports
+          path: reports
+
   send_results:
     name: Send results to webhook
     runs-on: ubuntu-latest

diff --git a/utils/notification_service.py b/utils/notification_service.py
@@ -128,13 +128,25 @@ def format_for_slack(total_results, results, scheduled: bool):
                 "common": "run_all_tests_torch_multi_gpu_test_reports/tests_torch_multi_gpu_[].txt",
                 "pipeline": "run_all_tests_torch_multi_gpu_test_reports/tests_torch_pipeline_multi_gpu_[].txt",
             },
+            "Torch Cuda Extensions Single GPU": {
+                "common": "run_tests_torch_cuda_extensions_gpu_test_reports/tests_torch_cuda_extensions_gpu_[].txt"
+            },
+            "Torch Cuda Extensions Multi GPU": {
+                "common": "run_tests_torch_cuda_extensions_multi_gpu_test_reports/tests_torch_cuda_extensions_multi_gpu_[].txt"
+            },
         }
     else:
         file_paths = {
             "TF Single GPU": {"common": "run_all_tests_tf_gpu_test_reports/tests_tf_gpu_[].txt"},
             "Torch Single GPU": {"common": "run_all_tests_torch_gpu_test_reports/tests_torch_gpu_[].txt"},
             "TF Multi GPU": {"common": "run_all_tests_tf_multi_gpu_test_reports/tests_tf_multi_gpu_[].txt"},
             "Torch Multi GPU": {"common": "run_all_tests_torch_multi_gpu_test_reports/tests_torch_multi_gpu_[].txt"},
+            "Torch Cuda Extensions Single GPU": {
+                "common": "run_tests_torch_cuda_extensions_gpu_test_reports/tests_torch_cuda_extensions_gpu_[].txt"
+            },
+            "Torch Cuda Extensions Multi GPU": {
+                "common": "run_tests_torch_cuda_extensions_multi_gpu_test_reports/tests_torch_cuda_extensions_multi_gpu_[].txt"
+            },
         }
 
     client = WebClient(token=os.environ["CI_SLACK_BOT_TOKEN"])