update

.github/workflows/push_check.yml

@@ -0,0 +1,100 @@
+name: Slow Test Memory Checks
+
+on:
+  push:
+    branches: [ shm-size ]
+
+env:
+  DIFFUSERS_IS_CI: yes
+  HF_HUB_ENABLE_HF_TRANSFER: 1
+  OMP_NUM_THREADS: 8
+  MKL_NUM_THREADS: 8
+  PYTEST_TIMEOUT: 600
+  RUN_SLOW: yes
+  PIPELINE_USAGE_CUTOFF: 50000
+
+jobs:
+  setup_torch_cuda_pipeline_matrix:
+    name: Setup Torch Pipelines CUDA Slow Tests Matrix
+    runs-on: [ self-hosted, intel-cpu, 8-cpu, ci ]
+    container:
+      image: diffusers/diffusers-pytorch-cpu
+    outputs:
+      pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
+    steps:
+      - name: Checkout diffusers
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 2
+      - name: Install dependencies
+        run: |
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m uv pip install -e [quality,test]
+      - name: Environment
+        run: |
+          python utils/print_env.py
+      - name: Fetch Pipeline Matrix
+        id: fetch_pipeline_matrix
+        run: |
+          matrix=$(python utils/fetch_torch_cuda_pipeline_test_matrix.py)
+          echo $matrix
+          echo "pipeline_test_matrix=$matrix" >> $GITHUB_OUTPUT
+      - name: Pipeline Tests Artifacts
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v2
+        with:
+          name: test-pipelines.json
+          path: reports
+
+  torch_pipelines_cuda_tests:
+    name: Torch Pipelines CUDA Slow Tests
+    needs: setup_torch_cuda_pipeline_matrix
+    strategy:
+      max-parallel: 4
+      fail-fast: false
+      matrix:
+        module: ${{ fromJson(needs.setup_torch_cuda_pipeline_matrix.outputs.pipeline_test_matrix) }}
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    container:
+      image: diffusers/diffusers-pytorch-cuda
+      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus 0
+    steps:
+      - name: Checkout diffusers
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 2
+      - name: NVIDIA-SMI
+        run: |
+          nvidia-smi
+      - name: Install dependencies
+        run: |
+          apt-get update && apt-get install libsndfile1-dev libgl1 -y
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m uv pip install -e [quality,test]
+          python -m uv pip install accelerate@git+https://github.com/huggingface/accelerate.git
+          python -m uv pip install hf_transfer
+      - name: Environment
+        run: |
+          python utils/print_env.py
+      - name: Slow PyTorch CUDA checkpoint tests on Ubuntu
+        env:
+          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
+          CUBLAS_WORKSPACE_CONFIG: :16:8
+        run: |
+          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+            -s -v -k "not Flax and not Onnx" \
+            --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
+            tests/pipelines/${{ matrix.module }}
+      - name: Failure short reports
+        if: ${{ failure() }}
+        run: |
+          cat reports/tests_pipeline_${{ matrix.module }}_cuda_stats.txt
+          cat reports/tests_pipeline_${{ matrix.module }}_cuda_failures_short.txt
+
+      - name: Test suite reports artifacts
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v2
+        with:
+          name: pipeline_${{ matrix.module }}_test_reports
+          path: reports

utils/fetch_torch_cuda_pipeline_test_matrix.py

@@ -76,7 +76,6 @@ def fetch_pipeline_modules_to_test():
     test_modules = []
     for pipeline_name in pipeline_objects:
         module = getattr(diffusers, pipeline_name)
-
         test_module = module.__module__.split(".")[-2].strip()
         test_modules.append(test_module)