Merge branch 'main' into transformers-v5-pr

Author: sayakpaul

.github/workflows/notify_slack_about_release.yml

@@ -15,7 +15,7 @@ jobs:
     - name: Setup Python
       uses: actions/setup-python@v6
       with:
-        python-version: '3.8'
+        python-version: '3.10'
 
     - name: Notify Slack about the release
       env:

.github/workflows/pr_dependency_test.yml

@@ -22,7 +22,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v6
         with:
-          python-version: "3.8"
+          python-version: "3.10"
       - name: Install dependencies
         run: |
           pip install -e .

.github/workflows/pr_tests.yml

@@ -35,7 +35,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v6
         with:
-          python-version: "3.8"
+          python-version: "3.10"
       - name: Install dependencies
         run: |
           pip install --upgrade pip
@@ -55,7 +55,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v6
         with:
-          python-version: "3.8"
+          python-version: "3.10"
       - name: Install dependencies
         run: |
           pip install --upgrade pip

.github/workflows/pr_tests_gpu.yml

@@ -37,7 +37,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v6
         with:
-          python-version: "3.8"
+          python-version: "3.10"
       - name: Install dependencies
         run: |
           pip install --upgrade pip
@@ -57,7 +57,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v6
         with:
-          python-version: "3.8"
+          python-version: "3.10"
       - name: Install dependencies
         run: |
           pip install --upgrade pip
@@ -206,6 +206,11 @@ jobs:
 
     - name: Install dependencies
       run: |
+        # Install pkgs which depend on setuptools<81 for pkg_resources first with no build isolation
+        uv pip install pip==25.2 setuptools==80.10.2
+        uv pip install --no-build-isolation k-diffusion==0.0.12
+        uv pip install --upgrade pip setuptools
+        # Install the rest as normal
         uv pip install -e ".[quality]"
         uv pip install peft@git+https://github.com/huggingface/peft.git
         uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git

.github/workflows/pr_torch_dependency_test.yml

@@ -22,7 +22,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v6
         with:
-          python-version: "3.8"
+          python-version: "3.10"
       - name: Install dependencies
         run: |
           pip install -e .

.github/workflows/pypi_publish.yaml

@@ -20,7 +20,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@v6
         with:
-          python-version: '3.8'
+          python-version: '3.10'
 
       - name: Fetch latest branch
         id: fetch_latest_branch
@@ -47,7 +47,7 @@ jobs:
       - name: Setup Python
         uses: actions/setup-python@v6
         with:
-          python-version: "3.8"
+          python-version: "3.10"
 
       - name: Install dependencies
         run: |

.github/workflows/stale.yml

@@ -20,7 +20,7 @@ jobs:
     - name: Setup Python
       uses: actions/setup-python@v6
       with:
-        python-version: 3.8
+        python-version: 3.10
 
     - name: Install requirements
       run: |

LICENSE

@@ -144,7 +144,7 @@
       agreed to in writing, Licensor provides the Work (and each
       Contributor provides its Contributions) on an "AS IS" BASIS,
       WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
+      implied, including, without limitation, Any warranties or conditions
       of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
       PARTICULAR PURPOSE. You are solely responsible for determining the
       appropriateness of using or redistributing the Work and assume any

benchmarks/benchmarking_utils.py

@@ -6,7 +6,7 @@
 import threading
 from contextlib import nullcontext
 from dataclasses import dataclass
-from typing import Any, Callable, Dict, Optional, Union
+from typing import Any, Callable
 
 import pandas as pd
 import torch
@@ -91,10 +91,10 @@ def model_init_fn(model_cls, group_offload_kwargs=None, layerwise_upcasting=Fals
 class BenchmarkScenario:
     name: str
     model_cls: ModelMixin
-    model_init_kwargs: Dict[str, Any]
+    model_init_kwargs: dict[str, Any]
     model_init_fn: Callable
     get_model_input_dict: Callable
-    compile_kwargs: Optional[Dict[str, Any]] = None
+    compile_kwargs: dict[str, Any] | None = None
 
 
 @require_torch_gpu
@@ -176,7 +176,7 @@ def run_benchmark(self, scenario: BenchmarkScenario):
             result["fullgraph"], result["mode"] = None, None
         return result
 
-    def run_bencmarks_and_collate(self, scenarios: Union[BenchmarkScenario, list[BenchmarkScenario]], filename: str):
+    def run_bencmarks_and_collate(self, scenarios: BenchmarkScenario | list[BenchmarkScenario], filename: str):
         if not isinstance(scenarios, list):
             scenarios = [scenarios]
         record_queue = queue.Queue()
@@ -214,10 +214,10 @@ def _run_phase(
         *,
         model_cls: ModelMixin,
         init_fn: Callable,
-        init_kwargs: Dict[str, Any],
+        init_kwargs: dict[str, Any],
         get_input_fn: Callable,
-        compile_kwargs: Optional[Dict[str, Any]],
-    ) -> Dict[str, float]:
+        compile_kwargs: dict[str, Any] | None = None,
+    ) -> dict[str, float]:
         # setup
         self.pre_benchmark()
 

examples/cogvideo/train_cogvideox_image_to_video_lora.py

@@ -432,9 +432,9 @@ def get_args():
 class VideoDataset(Dataset):
     def __init__(
         self,
-        instance_data_root: Optional[str] = None,
-        dataset_name: Optional[str] = None,
-        dataset_config_name: Optional[str] = None,
+        instance_data_root: str | None = None,
+        dataset_name: str | None = None,
+        dataset_config_name: str | None = None,
         caption_column: str = "text",
         video_column: str = "video",
         height: int = 480,
@@ -443,8 +443,8 @@ def __init__(
         max_num_frames: int = 49,
         skip_frames_start: int = 0,
         skip_frames_end: int = 0,
-        cache_dir: Optional[str] = None,
-        id_token: Optional[str] = None,
+        cache_dir: str | None = None,
+        id_token: str | None = None,
     ) -> None:
         super().__init__()