update

Author: DN6

.github/workflows/nightly_tests.yml

@@ -486,6 +486,56 @@ jobs:
         with:
           name: torch_cuda_${{ matrix.config.backend }}_reports
           path: reports
+          
+  run_nightly_pipeline_level_quantization_tests:
+    name: Torch quantization nightly tests
+    strategy:
+      fail-fast: false
+      max-parallel: 2
+    runs-on:
+      group: aws-g6e-xlarge-plus
+    container:
+      image: diffusers/diffusers-pytorch-cuda
+      options: --shm-size "20gb" --ipc host --gpus 0
+    steps:
+      - name: Checkout diffusers
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 2
+      - name: NVIDIA-SMI
+        run: nvidia-smi
+      - name: Install dependencies
+        run: |
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m uv pip install -e [quality,test]
+          python -m uv pip install -U bitsandbytes optimum_quanto
+          python -m uv pip install pytest-reportlog
+      - name: Environment
+        run: |
+          python utils/print_env.py
+      - name: Pipeline-level quantization tests on GPU
+        env:
+          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
+          CUBLAS_WORKSPACE_CONFIG: :16:8
+          BIG_GPU_MEMORY: 40
+        run: |
+          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+            --make-reports=tests_pipeline_level_quant_torch_cuda \
+            --report-log=tests_pipeline_level_quant_torch_cuda.log \
+            tests/quantization/test_pipeline_level_quantization.py
+      - name: Failure short reports
+        if: ${{ failure() }}
+        run: |
+          cat reports/tests_pipeline_level_quant_torch_cuda_stats.txt
+          cat reports/tests_pipeline_level_quant_torch_cuda_failures_short.txt
+      - name: Test suite reports artifacts
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v4
+        with:
+          name: torch_cuda_pipeline_level_quant_reports
+          path: reports
+
   generate_consolidated_report:
     name: Generate Consolidated Test Report
     needs: [
@@ -494,6 +544,7 @@ jobs:
       run_big_gpu_torch_tests,
       run_nightly_onnx_tests,
       run_nightly_quantization_tests,
+      run_nightly_pipeline_level_quantization_tests,
       run_flax_tpu_tests
     ]
     if: always()
@@ -542,60 +593,6 @@ jobs:
           name: consolidated_test_report
           path: ${{ env.CONSOLIDATED_REPORT_PATH }}
 
-  run_nightly_pipeline_level_quantization_tests:
-    name: Torch quantization nightly tests
-    strategy:
-      fail-fast: false
-      max-parallel: 2
-    runs-on:
-      group: aws-g6e-xlarge-plus
-    container:
-      image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "20gb" --ipc host --gpus 0
-    steps:
-      - name: Checkout diffusers
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 2
-      - name: NVIDIA-SMI
-        run: nvidia-smi
-      - name: Install dependencies
-        run: |
-          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-          python -m uv pip install -e [quality,test]
-          python -m uv pip install -U bitsandbytes optimum_quanto
-          python -m uv pip install pytest-reportlog
-      - name: Environment
-        run: |
-          python utils/print_env.py
-      - name: Pipeline-level quantization tests on GPU
-        env:
-          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
-          CUBLAS_WORKSPACE_CONFIG: :16:8
-          BIG_GPU_MEMORY: 40
-        run: |
-          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            --make-reports=tests_pipeline_level_quant_torch_cuda \
-            --report-log=tests_pipeline_level_quant_torch_cuda.log \
-            tests/quantization/test_pipeline_level_quantization.py
-      - name: Failure short reports
-        if: ${{ failure() }}
-        run: |
-          cat reports/tests_pipeline_level_quant_torch_cuda_stats.txt
-          cat reports/tests_pipeline_level_quant_torch_cuda_failures_short.txt
-      - name: Test suite reports artifacts
-        if: ${{ always() }}
-        uses: actions/upload-artifact@v4
-        with:
-          name: torch_cuda_pipeline_level_quant_reports
-          path: reports
-      - name: Generate Report and Notify Channel
-        if: always()
-        run: |
-          pip install slack_sdk tabulate
-          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
-
 # M1 runner currently not well supported
 # TODO: (Dhruv) add these back when we setup better testing for Apple Silicon
 #  run_nightly_tests_apple_m1: