Merge branch 'main' into overhaul-release-workflow

.github/workflows/pypi_publish.yaml

@@ -1,73 +1,45 @@
-# Adapted from https://blog.deepjyoti30.dev/pypi-release-github-action
-
 name: PyPI release
 
 on:
   workflow_dispatch:
   push:
     tags:
-      - "*"
+      - "v*"
 
 jobs:
-  find-and-checkout-latest-branch:
+  build-and-test:
     runs-on: ubuntu-22.04
-    outputs:
-      latest_branch: ${{ steps.set_latest_branch.outputs.latest_branch }}
     steps:
-      - name: Checkout Repo
+      - name: Checkout repo
         uses: actions/checkout@v6
 
       - name: Set up Python
         uses: actions/setup-python@v6
         with:
-          python-version: '3.10'
+          python-version: "3.10"
 
-      - name: Fetch latest branch
-        id: fetch_latest_branch
+      - name: Fetch and checkout latest release branch
         run: |
           pip install -U requests packaging
           LATEST_BRANCH=$(python utils/fetch_latest_release_branch.py)
           echo "Latest branch: $LATEST_BRANCH"
-          echo "latest_branch=$LATEST_BRANCH" >> $GITHUB_ENV
+          git fetch origin "$LATEST_BRANCH"
+          git checkout "$LATEST_BRANCH"
 
-      - name: Set latest branch output
-        id: set_latest_branch
-        run: echo "::set-output name=latest_branch::${{ env.latest_branch }}"
-
-  release:
-    needs: find-and-checkout-latest-branch
-    runs-on: ubuntu-22.04
-
-    steps:
-      - name: Checkout Repo
-        uses: actions/checkout@v6
-        with:
-          ref: ${{ needs.find-and-checkout-latest-branch.outputs.latest_branch }}
-
-      - name: Setup Python
-        uses: actions/setup-python@v6
-        with:
-          python-version: "3.10"
-
-      - name: Install dependencies
+      - name: Install build dependencies
         run: |
           python -m pip install --upgrade pip
-          pip install -U setuptools wheel twine
+          pip install -U build
           pip install -U torch --index-url https://download.pytorch.org/whl/cpu
 
       - name: Build the dist files
-        run: python setup.py bdist_wheel && python setup.py sdist
+        run: python -m build
 
-      - name: Publish to the test PyPI
-        env:
-          TWINE_USERNAME: ${{ secrets.TEST_PYPI_USERNAME }}
-          TWINE_PASSWORD: ${{ secrets.TEST_PYPI_PASSWORD }}
-        run: twine upload dist/* -r pypitest --repository-url=https://test.pypi.org/legacy/
+      - name: Install from built wheel
+        run: pip install dist/*.whl
 
       - name: Test installing diffusers and importing
         run: |
-          pip install diffusers && pip uninstall diffusers -y
-          pip install -i https://test.pypi.org/simple/ diffusers
           pip install -U transformers
           python utils/print_env.py
           python -c "from diffusers import __version__; print(__version__)"
@@ -75,8 +47,26 @@ jobs:
           python -c "from diffusers import DiffusionPipeline; pipe = DiffusionPipeline.from_pretrained('hf-internal-testing/tiny-stable-diffusion-pipe', safety_checker=None); pipe('ah suh du')"
           python -c "from diffusers import *"
 
+      - name: Upload build artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: python-dist
+          path: dist/
+
+  publish-to-pypi:
+    needs: build-and-test
+    if: startsWith(github.ref, 'refs/tags/')
+    runs-on: ubuntu-22.04
+    environment: pypi-release
+    permissions:
+      id-token: write
+
+    steps:
+      - name: Download build artifacts
+        uses: actions/download-artifact@v4
+        with:
+          name: python-dist
+          path: dist/
+
       - name: Publish to PyPI
-        env:
-          TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
-          TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
-        run: twine upload dist/* -r pypi
+        uses: pypa/gh-action-pypi-publish@release/v1

tests/models/transformers/test_models_transformer_cosmos.py

@@ -12,46 +12,60 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+import unittest
+
 import torch
 
 from diffusers import CosmosTransformer3DModel
-from diffusers.utils.torch_utils import randn_tensor
 
 from ...testing_utils import enable_full_determinism, torch_device
-from ..testing_utils import (
-    BaseModelTesterConfig,
-    MemoryTesterMixin,
-    ModelTesterMixin,
-    TrainingTesterMixin,
-)
+from ..test_modeling_common import ModelTesterMixin
 
 
 enable_full_determinism()
 
 
-class CosmosTransformerTesterConfig(BaseModelTesterConfig):
-    @property
-    def model_class(self):
-        return CosmosTransformer3DModel
+class CosmosTransformer3DModelTests(ModelTesterMixin, unittest.TestCase):
+    model_class = CosmosTransformer3DModel
+    main_input_name = "hidden_states"
+    uses_custom_attn_processor = True
 
     @property
-    def output_shape(self) -> tuple[int, ...]:
-        return (4, 1, 16, 16)
+    def dummy_input(self):
+        batch_size = 1
+        num_channels = 4
+        num_frames = 1
+        height = 16
+        width = 16
+        text_embed_dim = 16
+        sequence_length = 12
+        fps = 30
 
-    @property
-    def input_shape(self) -> tuple[int, ...]:
-        return (4, 1, 16, 16)
+        hidden_states = torch.randn((batch_size, num_channels, num_frames, height, width)).to(torch_device)
+        timestep = torch.randint(0, 1000, size=(batch_size,)).to(torch_device)
+        encoder_hidden_states = torch.randn((batch_size, sequence_length, text_embed_dim)).to(torch_device)
+        attention_mask = torch.ones((batch_size, sequence_length)).to(torch_device)
+        padding_mask = torch.zeros(batch_size, 1, height, width).to(torch_device)
 
-    @property
-    def main_input_name(self) -> str:
-        return "hidden_states"
-
-    @property
-    def generator(self):
-        return torch.Generator("cpu").manual_seed(0)
-
-    def get_init_dict(self) -> dict[str, int | list | tuple | float | bool | str]:
         return {
+            "hidden_states": hidden_states,
+            "timestep": timestep,
+            "encoder_hidden_states": encoder_hidden_states,
+            "attention_mask": attention_mask,
+            "fps": fps,
+            "padding_mask": padding_mask,
+        }
+
+    @property
+    def input_shape(self):
+        return (4, 1, 16, 16)
+
+    @property
+    def output_shape(self):
+        return (4, 1, 16, 16)
+
+    def prepare_init_args_and_inputs_for_common(self):
+        init_dict = {
             "in_channels": 4,
             "out_channels": 4,
             "num_attention_heads": 2,
@@ -66,68 +80,57 @@ class CosmosTransformerTesterConfig(BaseModelTesterConfig):
             "concat_padding_mask": True,
             "extra_pos_embed_type": "learnable",
         }
-
-    def get_dummy_inputs(self, batch_size: int = 1) -> dict[str, torch.Tensor]:
-        num_channels = 4
-        num_frames = 1
-        height = 16
-        width = 16
-        text_embed_dim = 16
-        sequence_length = 12
-
-        return {
-            "hidden_states": randn_tensor(
-                (batch_size, num_channels, num_frames, height, width), generator=self.generator, device=torch_device
-            ),
-            "timestep": torch.randint(0, 1000, size=(batch_size,), generator=self.generator).to(torch_device),
-            "encoder_hidden_states": randn_tensor(
-                (batch_size, sequence_length, text_embed_dim), generator=self.generator, device=torch_device
-            ),
-            "attention_mask": torch.ones((batch_size, sequence_length)).to(torch_device),
-            "fps": 30,
-            "padding_mask": torch.zeros(batch_size, 1, height, width).to(torch_device),
-        }
-
-
-class TestCosmosTransformer(CosmosTransformerTesterConfig, ModelTesterMixin):
-    """Core model tests for Cosmos Transformer."""
-
-
-class TestCosmosTransformerMemory(CosmosTransformerTesterConfig, MemoryTesterMixin):
-    """Memory optimization tests for Cosmos Transformer."""
-
-
-class TestCosmosTransformerTraining(CosmosTransformerTesterConfig, TrainingTesterMixin):
-    """Training tests for Cosmos Transformer."""
+        inputs_dict = self.dummy_input
+        return init_dict, inputs_dict
 
     def test_gradient_checkpointing_is_applied(self):
         expected_set = {"CosmosTransformer3DModel"}
         super().test_gradient_checkpointing_is_applied(expected_set=expected_set)
 
 
-class CosmosTransformerVideoToWorldTesterConfig(BaseModelTesterConfig):
-    @property
-    def model_class(self):
-        return CosmosTransformer3DModel
+class CosmosTransformer3DModelVideoToWorldTests(ModelTesterMixin, unittest.TestCase):
+    model_class = CosmosTransformer3DModel
+    main_input_name = "hidden_states"
+    uses_custom_attn_processor = True
 
     @property
-    def output_shape(self) -> tuple[int, ...]:
-        return (4, 1, 16, 16)
+    def dummy_input(self):
+        batch_size = 1
+        num_channels = 4
+        num_frames = 1
+        height = 16
+        width = 16
+        text_embed_dim = 16
+        sequence_length = 12
+        fps = 30
 
-    @property
-    def input_shape(self) -> tuple[int, ...]:
-        return (4, 1, 16, 16)
+        hidden_states = torch.randn((batch_size, num_channels, num_frames, height, width)).to(torch_device)
+        timestep = torch.randint(0, 1000, size=(batch_size,)).to(torch_device)
+        encoder_hidden_states = torch.randn((batch_size, sequence_length, text_embed_dim)).to(torch_device)
+        attention_mask = torch.ones((batch_size, sequence_length)).to(torch_device)
+        condition_mask = torch.ones(batch_size, 1, num_frames, height, width).to(torch_device)
+        padding_mask = torch.zeros(batch_size, 1, height, width).to(torch_device)
 
-    @property
-    def main_input_name(self) -> str:
-        return "hidden_states"
-
-    @property
-    def generator(self):
-        return torch.Generator("cpu").manual_seed(0)
-
-    def get_init_dict(self) -> dict[str, int | list | tuple | float | bool | str]:
         return {
+            "hidden_states": hidden_states,
+            "timestep": timestep,
+            "encoder_hidden_states": encoder_hidden_states,
+            "attention_mask": attention_mask,
+            "fps": fps,
+            "condition_mask": condition_mask,
+            "padding_mask": padding_mask,
+        }
+
+    @property
+    def input_shape(self):
+        return (4, 1, 16, 16)
+
+    @property
+    def output_shape(self):
+        return (4, 1, 16, 16)
+
+    def prepare_init_args_and_inputs_for_common(self):
+        init_dict = {
             "in_channels": 4 + 1,
             "out_channels": 4,
             "num_attention_heads": 2,
@@ -142,40 +145,8 @@ class CosmosTransformerVideoToWorldTesterConfig(BaseModelTesterConfig):
             "concat_padding_mask": True,
             "extra_pos_embed_type": "learnable",
         }
-
-    def get_dummy_inputs(self, batch_size: int = 1) -> dict[str, torch.Tensor]:
-        num_channels = 4
-        num_frames = 1
-        height = 16
-        width = 16
-        text_embed_dim = 16
-        sequence_length = 12
-
-        return {
-            "hidden_states": randn_tensor(
-                (batch_size, num_channels, num_frames, height, width), generator=self.generator, device=torch_device
-            ),
-            "timestep": torch.randint(0, 1000, size=(batch_size,), generator=self.generator).to(torch_device),
-            "encoder_hidden_states": randn_tensor(
-                (batch_size, sequence_length, text_embed_dim), generator=self.generator, device=torch_device
-            ),
-            "attention_mask": torch.ones((batch_size, sequence_length)).to(torch_device),
-            "fps": 30,
-            "condition_mask": torch.ones(batch_size, 1, num_frames, height, width).to(torch_device),
-            "padding_mask": torch.zeros(batch_size, 1, height, width).to(torch_device),
-        }
-
-
-class TestCosmosTransformerVideoToWorld(CosmosTransformerVideoToWorldTesterConfig, ModelTesterMixin):
-    """Core model tests for Cosmos Transformer (Video-to-World)."""
-
-
-class TestCosmosTransformerVideoToWorldMemory(CosmosTransformerVideoToWorldTesterConfig, MemoryTesterMixin):
-    """Memory optimization tests for Cosmos Transformer (Video-to-World)."""
-
-
-class TestCosmosTransformerVideoToWorldTraining(CosmosTransformerVideoToWorldTesterConfig, TrainingTesterMixin):
-    """Training tests for Cosmos Transformer (Video-to-World)."""
+        inputs_dict = self.dummy_input
+        return init_dict, inputs_dict
 
     def test_gradient_checkpointing_is_applied(self):
         expected_set = {"CosmosTransformer3DModel"}