[CI] Improvements to conditional GPU PR tests (#10859)

* update

* update

* update

* update

* update

* update

* test

* test

* test

* test

* test

* test

* test

* test

* test

* test

* test

* test

* update

.github/workflows/pr_tests_gpu.yml

@@ -0,0 +1,241 @@
+name: Fast GPU Tests on PR 
+
+on:
+  pull_request:
+    branches: main
+    paths:
+      - "src/diffusers/models/modeling_utils.py"
+      - "src/diffusers/models/model_loading_utils.py"
+      - "src/diffusers/pipelines/pipeline_utils.py"
+      - "src/diffusers/pipeline_loading_utils.py"
+      - "src/diffusers/loaders/lora_base.py"
+      - "src/diffusers/loaders/lora_pipeline.py"
+      - "src/diffusers/loaders/peft.py"
+  workflow_dispatch:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+env:
+  DIFFUSERS_IS_CI: yes
+  OMP_NUM_THREADS: 8
+  MKL_NUM_THREADS: 8
+  HF_HUB_ENABLE_HF_TRANSFER: 1
+  PYTEST_TIMEOUT: 600
+  PIPELINE_USAGE_CUTOFF: 1000000000 # set high cutoff so that only always-test pipelines run
+
+jobs:
+  setup_torch_cuda_pipeline_matrix:
+    name: Setup Torch Pipelines CUDA Slow Tests Matrix
+    runs-on:
+      group: aws-general-8-plus
+    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@v4
+        with:
+          name: test-pipelines.json
+          path: reports
+
+  torch_pipelines_cuda_tests:
+    name: Torch Pipelines CUDA Tests
+    needs: setup_torch_cuda_pipeline_matrix
+    strategy:
+      fail-fast: false
+      max-parallel: 8
+      matrix:
+        module: ${{ fromJson(needs.setup_torch_cuda_pipeline_matrix.outputs.pipeline_test_matrix) }}
+    runs-on:
+      group: aws-g4dn-2xlarge
+    container:
+      image: diffusers/diffusers-pytorch-cuda
+      options: --shm-size "16gb" --ipc host --gpus 0
+    steps:
+      - name: Checkout diffusers
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 2
+
+      - name: NVIDIA-SMI
+        run: |
+          nvidia-smi
+      - name: Install dependencies
+        run: |
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m uv pip install -e [quality,test]
+          pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+          pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
+
+      - name: Environment
+        run: |
+          python utils/print_env.py
+      - name: Extract tests
+        id: extract_tests
+        run: |
+          pattern=$(python utils/extract_tests_from_mixin.py --type pipeline)
+          echo "$pattern" > /tmp/test_pattern.txt
+          echo "pattern_file=/tmp/test_pattern.txt" >> $GITHUB_OUTPUT
+
+      - name: PyTorch CUDA checkpoint tests on Ubuntu
+        env:
+          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
+          CUBLAS_WORKSPACE_CONFIG: :16:8
+        run: |
+          pattern=$(cat ${{ steps.extract_tests.outputs.pattern_file }})
+          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+            -s -v -k "not Flax and not Onnx and $pattern" \
+            --make-reports=tests_pipeline_${{ 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: ${{ always() }}
+        uses: actions/upload-artifact@v4
+        with:
+          name: pipeline_${{ matrix.module }}_test_reports
+          path: reports
+
+  torch_cuda_tests:
+    name: Torch CUDA Tests
+    runs-on:
+      group: aws-g4dn-2xlarge
+    container:
+      image: diffusers/diffusers-pytorch-cuda
+      options: --shm-size "16gb" --ipc host --gpus 0
+    defaults:
+      run:
+        shell: bash
+    strategy:
+      fail-fast: false
+      max-parallel: 2
+      matrix:
+        module: [models, schedulers, lora, others]
+    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:$PATH"
+        python -m uv pip install -e [quality,test]
+        python -m uv pip install peft@git+https://github.com/huggingface/peft.git
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+        pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
+
+    - name: Environment
+      run: |
+        python utils/print_env.py
+
+    - name: Extract tests
+      id: extract_tests
+      run: |
+        pattern=$(python utils/extract_tests_from_mixin.py --type ${{ matrix.module }})
+        echo "$pattern" > /tmp/test_pattern.txt
+        echo "pattern_file=/tmp/test_pattern.txt" >> $GITHUB_OUTPUT
+
+    - name: Run PyTorch CUDA tests
+      env:
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+        # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
+        CUBLAS_WORKSPACE_CONFIG: :16:8
+      run: |
+        pattern=$(cat ${{ steps.extract_tests.outputs.pattern_file }})
+        if [ -z "$pattern" ]; then
+          python -m pytest -n 1 -sv --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx" tests/${{ matrix.module }} \
+          --make-reports=tests_torch_cuda_${{ matrix.module }}  
+        else
+          python -m pytest -n 1 -sv --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx and $pattern" tests/${{ matrix.module }} \
+          --make-reports=tests_torch_cuda_${{ matrix.module }}  
+        fi
+
+    - name: Failure short reports
+      if: ${{ failure() }}
+      run: |
+        cat reports/tests_torch_cuda_${{ matrix.module }}_stats.txt
+        cat reports/tests_torch_cuda_${{ matrix.module }}_failures_short.txt
+
+    - name: Test suite reports artifacts
+      if: ${{ always() }}
+      uses: actions/upload-artifact@v4
+      with:
+        name: torch_cuda_test_reports_${{ matrix.module }}
+        path: reports
+
+  run_examples_tests:
+    name: Examples PyTorch CUDA tests on Ubuntu
+        pip uninstall transformers -y && python -m uv pip install -U transformers@git+https://github.com/huggingface/transformers.git --no-deps
+    runs-on:
+      group: aws-g4dn-2xlarge
+
+    container:
+      image: diffusers/diffusers-pytorch-cuda
+      options: --gpus 0 --shm-size "16gb" --ipc host
+    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:$PATH"
+        python -m uv pip install -e [quality,test,training]
+
+    - name: Environment
+      run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python utils/print_env.py
+
+    - name: Run example tests on GPU
+      env:
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+      run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install timm
+        python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v --make-reports=examples_torch_cuda examples/
+
+    - name: Failure short reports
+      if: ${{ failure() }}
+      run: |
+        cat reports/examples_torch_cuda_stats.txt
+        cat reports/examples_torch_cuda_failures_short.txt
+
+    - name: Test suite reports artifacts
+      if: ${{ always() }}
+      uses: actions/upload-artifact@v4
+      with:
+        name: examples_test_reports
+        path: reports
+

.github/workflows/push_tests.yml

@@ -1,13 +1,6 @@
 name: Fast GPU Tests on main
 
 on:
-  pull_request:
-    branches: main
-    paths:
-      - "src/diffusers/models/modeling_utils.py"
-      - "src/diffusers/models/model_loading_utils.py"
-      - "src/diffusers/pipelines/pipeline_utils.py"
-      - "src/diffusers/pipeline_loading_utils.py"
   workflow_dispatch:
   push:
     branches:
@@ -167,7 +160,6 @@ jobs:
         path: reports
 
   flax_tpu_tests:
-    if: ${{ github.event_name != 'pull_request' }}
     name: Flax TPU Tests
     runs-on:
       group: gcp-ct5lp-hightpu-8t
@@ -216,7 +208,6 @@ jobs:
         path: reports
 
   onnx_cuda_tests:
-    if: ${{ github.event_name != 'pull_request' }}
     name: ONNX CUDA Tests
     runs-on:
       group: aws-g4dn-2xlarge
@@ -265,7 +256,6 @@ jobs:
         path: reports
 
   run_torch_compile_tests:
-    if: ${{ github.event_name != 'pull_request' }}
     name: PyTorch Compile CUDA tests
 
     runs-on:
@@ -309,7 +299,6 @@ jobs:
         path: reports
 
   run_xformers_tests:
-    if: ${{ github.event_name != 'pull_request' }}
     name: PyTorch xformers CUDA tests
 
     runs-on:

utils/extract_tests_from_mixin.py

@@ -0,0 +1,61 @@
+import argparse
+import inspect
+import sys
+from pathlib import Path
+from typing import List, Type
+
+
+root_dir = Path(__file__).parent.parent.absolute()
+sys.path.insert(0, str(root_dir))
+
+parser = argparse.ArgumentParser()
+parser.add_argument("--type", type=str, default=None)
+args = parser.parse_args()
+
+
+def get_test_methods_from_class(cls: Type) -> List[str]:
+    """
+    Get all test method names from a given class.
+    Only returns methods that start with 'test_'.
+    """
+    test_methods = []
+    for name, obj in inspect.getmembers(cls):
+        if name.startswith("test_") and inspect.isfunction(obj):
+            test_methods.append(name)
+    return sorted(test_methods)
+
+
+def generate_pytest_pattern(test_methods: List[str]) -> str:
+    """Generate pytest pattern string for the -k flag."""
+    return " or ".join(test_methods)
+
+
+def generate_pattern_for_mixin(mixin_class: Type) -> str:
+    """
+    Generate pytest pattern for a specific mixin class.
+    """
+    if mixin_cls is None:
+        return ""
+    test_methods = get_test_methods_from_class(mixin_class)
+    return generate_pytest_pattern(test_methods)
+
+
+if __name__ == "__main__":
+    mixin_cls = None
+    if args.type == "pipeline":
+        from tests.pipelines.test_pipelines_common import PipelineTesterMixin
+
+        mixin_cls = PipelineTesterMixin
+
+    elif args.type == "models":
+        from tests.models.test_modeling_common import ModelTesterMixin
+
+        mixin_cls = ModelTesterMixin
+
+    elif args.type == "lora":
+        from tests.lora.utils import PeftLoraLoaderMixinTests
+
+        mixin_cls = PeftLoraLoaderMixinTests
+
+    pattern = generate_pattern_for_mixin(mixin_cls)
+    print(pattern)