Merge branch 'main' into fix_flax_use_memory_efficient_attention

Author: sayakpaul

.github/workflows/benchmark.yml

@@ -39,7 +39,7 @@ jobs:
           python utils/print_env.py
       - name: Diffusers Benchmarking
         env:
-            HUGGING_FACE_HUB_TOKEN: ${{ secrets.DIFFUSERS_BOT_TOKEN }}
+            HF_TOKEN: ${{ secrets.DIFFUSERS_BOT_TOKEN }}
             BASE_PATH: benchmark_outputs
         run: |
           export TOTAL_GPU_MEMORY=$(python -c "import torch; print(torch.cuda.get_device_properties(0).total_memory / (1024**3))")

.github/workflows/build_docker_images.yml

@@ -25,17 +25,17 @@ jobs:
     steps:
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v1
-      
+
       - name: Check out code
         uses: actions/checkout@v3
-      
+
       - name: Find Changed Dockerfiles
         id: file_changes
         uses: jitterbit/get-changed-files@v1
         with:
           format: 'space-delimited'
           token: ${{ secrets.GITHUB_TOKEN }}
-      
+
       - name: Build Changed Docker Images
         run: |
           CHANGED_FILES="${{ steps.file_changes.outputs.all }}"
@@ -52,7 +52,7 @@ jobs:
   build-and-push-docker-images:
     runs-on: [ self-hosted, intel-cpu, 8-cpu, ci ]
     if: github.event_name != 'pull_request'
-    
+
     permissions:
       contents: read
       packages: write
@@ -69,6 +69,7 @@ jobs:
           - diffusers-flax-tpu
           - diffusers-onnxruntime-cpu
           - diffusers-onnxruntime-cuda
+          - diffusers-doc-builder
 
     steps:
       - name: Checkout repository

.github/workflows/build_documentation.yml

@@ -21,7 +21,7 @@ jobs:
       package: diffusers
       notebook_folder: diffusers_doc
       languages: en ko zh ja pt
-
+      custom_container: diffusers/diffusers-doc-builder
     secrets:
       token: ${{ secrets.HUGGINGFACE_PUSH }}
       hf_token: ${{ secrets.HF_DOC_BUILD_PUSH }}

.github/workflows/build_pr_documentation.yml

@@ -20,3 +20,4 @@ jobs:
       install_libgl1: true
       package: diffusers
       languages: en ko zh ja pt
+      custom_container: diffusers/diffusers-doc-builder

.github/workflows/nightly_tests.yml

@@ -81,7 +81,7 @@ jobs:
 
       - name: Nightly PyTorch CUDA checkpoint (pipelines) tests
         env:
-          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
@@ -141,7 +141,7 @@ jobs:
     - name: Run nightly PyTorch CUDA tests for non-pipeline modules
       if: ${{ matrix.module != 'examples'}}
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
@@ -154,7 +154,7 @@ jobs:
     - name: Run nightly example tests with Torch
       if: ${{ matrix.module == 'examples' }}
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
@@ -211,7 +211,7 @@ jobs:
 
     - name: Run nightly LoRA tests with PEFT and Torch
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
@@ -269,7 +269,7 @@ jobs:
 
     - name: Run nightly Flax TPU tests
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m pytest -n 0 \
           -s -v -k "Flax" \
@@ -324,7 +324,7 @@ jobs:
 
     - name: Run nightly ONNXRuntime CUDA tests
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "Onnx" \
@@ -390,7 +390,7 @@ jobs:
         shell: arch -arch arm64 bash {0}
         env:
           HF_HOME: /System/Volumes/Data/mnt/cache
-          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
         run: |
           ${CONDA_RUN} python -m pytest -n 1 -s -v --make-reports=tests_torch_mps \
             --report-log=tests_torch_mps.log \

.github/workflows/push_tests.yml

@@ -87,7 +87,7 @@ jobs:
           python utils/print_env.py
       - name: Slow PyTorch CUDA checkpoint tests on Ubuntu
         env:
-          HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
           # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
@@ -144,7 +144,7 @@ jobs:
 
     - name: Run slow PyTorch CUDA tests
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
@@ -194,7 +194,7 @@ jobs:
 
     - name: Run slow PEFT CUDA tests
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
@@ -243,7 +243,7 @@ jobs:
 
     - name: Run slow Flax TPU tests
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m pytest -n 0 \
           -s -v -k "Flax" \
@@ -290,7 +290,7 @@ jobs:
 
     - name: Run slow ONNXRuntime CUDA tests
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "Onnx" \
@@ -337,7 +337,7 @@ jobs:
         python utils/print_env.py
     - name: Run example tests on GPU
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "compile" --make-reports=tests_torch_compile_cuda tests/
     - name: Failure short reports
@@ -378,7 +378,7 @@ jobs:
         python utils/print_env.py
     - name: Run example tests on GPU
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
     - name: Failure short reports
@@ -423,7 +423,7 @@ jobs:
 
     - name: Run example tests on GPU
       env:
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
         python -m uv pip install timm

.github/workflows/push_tests_mps.yml

@@ -59,7 +59,7 @@ jobs:
       shell: arch -arch arm64 bash {0}
       env:
         HF_HOME: /System/Volumes/Data/mnt/cache
-        HUGGING_FACE_HUB_TOKEN: ${{ secrets.HUGGING_FACE_HUB_TOKEN }}
+        HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
         ${CONDA_RUN} python -m pytest -n 0 -s -v --make-reports=tests_torch_mps tests/
 

.github/workflows/run_test_from_pr.yml

@@ -0,0 +1,73 @@
+name: Check running SLOW tests from a PR (only GPU)
+
+on:
+  workflow_dispatch:
+    inputs:
+      docker_image:
+        default: 'diffusers/diffusers-pytorch-cuda'
+        description: 'Name of the Docker image'
+        required: true
+      branch: 
+        description: 'PR Branch to test on'
+        required: true
+      test:
+        description: 'Tests to run (e.g.: `tests/models`).'
+        required: true
+
+env:
+  DIFFUSERS_IS_CI: yes
+  IS_GITHUB_CI: "1"
+  HF_HOME: /mnt/cache
+  OMP_NUM_THREADS: 8
+  MKL_NUM_THREADS: 8
+  PYTEST_TIMEOUT: 600
+  RUN_SLOW: yes
+
+jobs:
+  run_tests:
+    name: "Run a test on our runner from a PR"
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
+    container:
+      image: ${{ github.event.inputs.docker_image }}
+      options: --gpus 0 --privileged --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
+
+    steps:
+      - name: Validate test files input
+        id: validate_test_files
+        env: 
+          PY_TEST: ${{ github.event.inputs.test }}
+        run: |
+          if [[ ! "$PY_TEST" =~ ^tests/ ]]; then
+            echo "Error: The input string must start with 'tests/'."
+            exit 1
+          fi
+          
+          if [[ ! "$PY_TEST" =~ ^tests/(models|pipelines) ]]; then
+            echo "Error: The input string must contain either 'models' or 'pipelines' after 'tests/'."
+            exit 1
+          fi
+          
+          if [[ "$PY_TEST" == *";"* ]]; then
+            echo "Error: The input string must not contain ';'."
+            exit 1
+          fi
+          echo "$PY_TEST"
+
+      - name: Checkout PR branch
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.inputs.branch }}
+          repository: ${{ github.event.pull_request.head.repo.full_name }}
+
+
+      - name: Install pytest 
+        run: | 
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m uv pip install -e [quality,test]
+          python -m uv pip install peft
+      
+      - name: Run tests
+        env: 
+            PY_TEST: ${{ github.event.inputs.test }}
+        run: |
+          pytest "$PY_TEST"

.github/workflows/run_tests_from_a_pr.yml

@@ -25,6 +25,6 @@ jobs:
 
       - name: Update metadata
         env:
-          HUGGING_FACE_HUB_TOKEN: ${{ secrets.SAYAK_HF_TOKEN }}
+          HF_TOKEN: ${{ secrets.SAYAK_HF_TOKEN }}
         run: |
           python utils/update_metadata.py --commit_sha ${{ github.sha }}