Merge branch 'main' into repr-quant-config

Author: sayakpaul

.github/workflows/nightly_tests.yml

@@ -13,8 +13,9 @@ env:
   PYTEST_TIMEOUT: 600
   RUN_SLOW: yes
   RUN_NIGHTLY: yes
-  PIPELINE_USAGE_CUTOFF: 5000
+  PIPELINE_USAGE_CUTOFF: 0
   SLACK_API_TOKEN: ${{ secrets.SLACK_CIFEEDBACK_BOT_TOKEN }}
+  CONSOLIDATED_REPORT_PATH: consolidated_test_report.md
 
 jobs:
   setup_torch_cuda_pipeline_matrix:
@@ -99,11 +100,6 @@ jobs:
         with:
           name: pipeline_${{ matrix.module }}_test_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
 
   run_nightly_tests_for_other_torch_modules:
     name: Nightly Torch CUDA Tests
@@ -142,7 +138,6 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
         CUBLAS_WORKSPACE_CONFIG: :16:8
-        RUN_COMPILE: yes
       run: |
         python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
           -s -v -k "not Flax and not Onnx" \
@@ -175,12 +170,6 @@ jobs:
         name: torch_${{ matrix.module }}_cuda_test_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
-
   run_torch_compile_tests:
     name: PyTorch Compile CUDA tests
 
@@ -224,12 +213,6 @@ jobs:
         name: torch_compile_test_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
-  
   run_big_gpu_torch_tests:
     name: Torch tests on big GPU
     strategy:
@@ -280,12 +263,7 @@ jobs:
         with:
           name: torch_cuda_big_gpu_test_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
-          
+
   torch_minimum_version_cuda_tests:
     name: Torch Minimum Version CUDA Tests
     runs-on:
@@ -342,63 +320,6 @@ jobs:
         with:
           name: torch_minimum_version_cuda_test_reports
           path: reports
- 
-  run_flax_tpu_tests:
-    name: Nightly Flax TPU Tests
-    runs-on:
-      group: gcp-ct5lp-hightpu-8t
-    if: github.event_name == 'schedule'
-
-    container:
-      image: diffusers/diffusers-flax-tpu
-      options: --shm-size "16gb" --ipc host --privileged ${{ vars.V5_LITEPOD_8_ENV}} -v /mnt/hf_cache:/mnt/hf_cache
-    defaults:
-      run:
-        shell: bash
-    steps:
-    - name: Checkout diffusers
-      uses: actions/checkout@v3
-      with:
-        fetch-depth: 2
-
-    - name: Install dependencies
-      run: |
-        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
-        python -m uv pip install -e [quality,test]
-        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-        python -m uv pip install pytest-reportlog
-
-    - name: Environment
-      run: python utils/print_env.py
-
-    - name: Run nightly Flax TPU tests
-      env:
-        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
-      run: |
-        python -m pytest -n 0 \
-          -s -v -k "Flax" \
-          --make-reports=tests_flax_tpu \
-          --report-log=tests_flax_tpu.log \
-          tests/
-
-    - name: Failure short reports
-      if: ${{ failure() }}
-      run: |
-        cat reports/tests_flax_tpu_stats.txt
-        cat reports/tests_flax_tpu_failures_short.txt
-
-    - name: Test suite reports artifacts
-      if: ${{ always() }}
-      uses: actions/upload-artifact@v4
-      with:
-        name: flax_tpu_test_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
 
   run_nightly_onnx_tests:
     name: Nightly ONNXRuntime CUDA tests on Ubuntu
@@ -449,18 +370,12 @@ jobs:
         name: tests_onnx_cuda_reports
         path: reports
 
-    - name: Generate Report and Notify Channel
-      if: always()
-      run: |
-        pip install slack_sdk tabulate
-        python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
-
   run_nightly_quantization_tests:
     name: Torch quantization nightly tests
     strategy:
       fail-fast: false
       max-parallel: 2
-      matrix: 
+      matrix:
         config:
           - backend: "bitsandbytes"
             test_location: "bnb"
@@ -520,12 +435,7 @@ jobs:
         with:
           name: torch_cuda_${{ matrix.config.backend }}_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
-
+          
   run_nightly_pipeline_level_quantization_tests:
     name: Torch quantization nightly tests
     strategy:
@@ -574,12 +484,117 @@ jobs:
         with:
           name: torch_cuda_pipeline_level_quant_reports
           path: reports
-      - name: Generate Report and Notify Channel
-        if: always()
+
+  run_flax_tpu_tests:
+    name: Nightly Flax TPU Tests
+    runs-on:
+      group: gcp-ct5lp-hightpu-8t
+    if: github.event_name == 'schedule'
+
+    container:
+      image: diffusers/diffusers-flax-tpu
+      options: --shm-size "16gb" --ipc host --privileged ${{ vars.V5_LITEPOD_8_ENV}} -v /mnt/hf_cache:/mnt/hf_cache
+    defaults:
+      run:
+        shell: bash
+    steps:
+    - name: Checkout diffusers
+      uses: actions/checkout@v3
+      with:
+        fetch-depth: 2
+
+    - name: Install dependencies
+      run: |
+        python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+        python -m uv pip install -e [quality,test]
+        pip uninstall accelerate -y && python -m uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
+        python -m uv pip install pytest-reportlog
+
+    - name: Environment
+      run: python utils/print_env.py
+
+    - name: Run nightly Flax TPU tests
+      env:
+        HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+      run: |
+        python -m pytest -n 0 \
+          -s -v -k "Flax" \
+          --make-reports=tests_flax_tpu \
+          --report-log=tests_flax_tpu.log \
+          tests/
+
+    - name: Failure short reports
+      if: ${{ failure() }}
+      run: |
+        cat reports/tests_flax_tpu_stats.txt
+        cat reports/tests_flax_tpu_failures_short.txt
+
+    - name: Test suite reports artifacts
+      if: ${{ always() }}
+      uses: actions/upload-artifact@v4
+      with:
+        name: flax_tpu_test_reports
+        path: reports
+
+  generate_consolidated_report:
+    name: Generate Consolidated Test Report
+    needs: [
+      run_nightly_tests_for_torch_pipelines,
+      run_nightly_tests_for_other_torch_modules,
+      run_torch_compile_tests,
+      run_big_gpu_torch_tests,
+      run_nightly_quantization_tests,
+      run_nightly_pipeline_level_quantization_tests,
+      run_nightly_onnx_tests,
+      torch_minimum_version_cuda_tests,
+      run_flax_tpu_tests
+    ]
+    if: always()
+    runs-on:
+      group: aws-general-8-plus
+    container:
+      image: diffusers/diffusers-pytorch-cpu
+    steps:
+      - name: Checkout diffusers
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 2
+
+      - name: Create reports directory
+        run: mkdir -p combined_reports
+
+      - name: Download all test reports
+        uses: actions/download-artifact@v4
+        with:
+          path: artifacts
+
+      - name: Prepare reports
+        run: |
+          # Move all report files to a single directory for processing
+          find artifacts -name "*.txt" -exec cp {} combined_reports/ \;
+
+      - name: Install dependencies
         run: |
+          pip install -e .[test]
           pip install slack_sdk tabulate
-          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
-  
+
+      - name: Generate consolidated report
+        run: |
+          python utils/consolidated_test_report.py \
+            --reports_dir combined_reports \
+            --output_file $CONSOLIDATED_REPORT_PATH \
+            --slack_channel_name diffusers-ci-nightly
+
+      - name: Show consolidated report
+        run: |
+          cat $CONSOLIDATED_REPORT_PATH >> $GITHUB_STEP_SUMMARY
+
+      - name: Upload consolidated report
+        uses: actions/upload-artifact@v4
+        with:
+          name: consolidated_test_report
+          path: ${{ env.CONSOLIDATED_REPORT_PATH }}
+
 # M1 runner currently not well supported
 # TODO: (Dhruv) add these back when we setup better testing for Apple Silicon
 #  run_nightly_tests_apple_m1:

docs/source/en/_toctree.yml

@@ -92,8 +92,6 @@
     title: API Reference
   title: Hybrid Inference
 - sections:
-  - local: using-diffusers/cogvideox
-    title: CogVideoX
   - local: using-diffusers/consisid
     title: ConsisID
   - local: using-diffusers/sdxl
@@ -178,6 +176,8 @@
 - sections:
   - local: optimization/fp16
     title: Accelerate inference
+  - local: optimization/cache
+    title: Caching
   - local: optimization/memory
     title: Reduce memory usage
   - local: optimization/xformers

docs/source/en/api/cache.md

@@ -11,71 +11,19 @@ specific language governing permissions and limitations under the License. -->
 
 # Caching methods
 
-## Pyramid Attention Broadcast
+Cache methods speedup diffusion transformers by storing and reusing intermediate outputs of specific layers, such as attention and feedforward layers, instead of recalculating them at each inference step.
 
-[Pyramid Attention Broadcast](https://huggingface.co/papers/2408.12588) from Xuanlei Zhao, Xiaolong Jin, Kai Wang, Yang You.
-
-Pyramid Attention Broadcast (PAB) is a method that speeds up inference in diffusion models by systematically skipping attention computations between successive inference steps and reusing cached attention states. The attention states are not very different between successive inference steps. The most prominent difference is in the spatial attention blocks, not as much in the temporal attention blocks, and finally the least in the cross attention blocks. Therefore, many cross attention computation blocks can be skipped, followed by the temporal and spatial attention blocks. By combining other techniques like sequence parallelism and classifier-free guidance parallelism, PAB achieves near real-time video generation.
-
-Enable PAB with [`~PyramidAttentionBroadcastConfig`] on any pipeline. For some benchmarks, refer to [this](https://github.com/huggingface/diffusers/pull/9562) pull request.
-
-```python
-import torch
-from diffusers import CogVideoXPipeline, PyramidAttentionBroadcastConfig
-
-pipe = CogVideoXPipeline.from_pretrained("THUDM/CogVideoX-5b", torch_dtype=torch.bfloat16)
-pipe.to("cuda")
-
-# Increasing the value of `spatial_attention_timestep_skip_range[0]` or decreasing the value of
-# `spatial_attention_timestep_skip_range[1]` will decrease the interval in which pyramid attention
-# broadcast is active, leader to slower inference speeds. However, large intervals can lead to
-# poorer quality of generated videos.
-config = PyramidAttentionBroadcastConfig(
-    spatial_attention_block_skip_range=2,
-    spatial_attention_timestep_skip_range=(100, 800),
-    current_timestep_callback=lambda: pipe.current_timestep,
-)
-pipe.transformer.enable_cache(config)
-```
-
-## Faster Cache
-
-[FasterCache](https://huggingface.co/papers/2410.19355) from Zhengyao Lv, Chenyang Si, Junhao Song, Zhenyu Yang, Yu Qiao, Ziwei Liu, Kwan-Yee K. Wong.
-
-FasterCache is a method that speeds up inference in diffusion transformers by:
-- Reusing attention states between successive inference steps, due to high similarity between them
-- Skipping unconditional branch prediction used in classifier-free guidance by revealing redundancies between unconditional and conditional branch outputs for the same timestep, and therefore approximating the unconditional branch output using the conditional branch output
-
-```python
-import torch
-from diffusers import CogVideoXPipeline, FasterCacheConfig
-
-pipe = CogVideoXPipeline.from_pretrained("THUDM/CogVideoX-5b", torch_dtype=torch.bfloat16)
-pipe.to("cuda")
-
-config = FasterCacheConfig(
-    spatial_attention_block_skip_range=2,
-    spatial_attention_timestep_skip_range=(-1, 681),
-    current_timestep_callback=lambda: pipe.current_timestep,
-    attention_weight_callback=lambda _: 0.3,
-    unconditional_batch_skip_range=5,
-    unconditional_batch_timestep_skip_range=(-1, 781),
-    tensor_format="BFCHW",
-)
-pipe.transformer.enable_cache(config)
-```
-
-### CacheMixin
+## CacheMixin
 
 [[autodoc]] CacheMixin
 
-### PyramidAttentionBroadcastConfig
+## PyramidAttentionBroadcastConfig
 
 [[autodoc]] PyramidAttentionBroadcastConfig
 
 [[autodoc]] apply_pyramid_attention_broadcast
 
-### FasterCacheConfig
+## FasterCacheConfig
 
 [[autodoc]] FasterCacheConfig
 

docs/source/en/api/loaders/lora.md

@@ -98,4 +98,8 @@ To learn more about how to load LoRA weights, see the [LoRA](../../using-diffuse
 
 ## LoraBaseMixin
 
-[[autodoc]] loaders.lora_base.LoraBaseMixin
+[[autodoc]] loaders.lora_base.LoraBaseMixin
+
+## WanLoraLoaderMixin
+
+[[autodoc]] loaders.lora_pipeline.WanLoraLoaderMixin