[Doc] ruff format some Python examples (#26767)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

docs/contributing/model/multimodal.md

@@ -16,7 +16,7 @@ Further update the model as follows:
             ...
 
             @classmethod
-            def get_placeholder_str(cls, modality: str, i: int) -> Optional[str]:
+            def get_placeholder_str(cls, modality: str, i: int) -> str | None:
                 if modality.startswith("image"):
                     return "<image>"
 
@@ -45,14 +45,14 @@ Further update the model as follows:
             ...
 
             def _process_image_input(self, image_input: YourModelImageInputs) -> torch.Tensor:
-
                 assert self.vision_encoder is not None
                 image_features = self.vision_encoder(image_input)
                 return self.multi_modal_projector(image_features)
 
             def get_multimodal_embeddings(
-                    self, **kwargs: object) -> Optional[MultiModalEmbeddings]:
-
+                self,
+                **kwargs: object,
+            ) -> MultiModalEmbeddings | None:
                 # Validate the multimodal input keyword arguments
                 image_input = self._parse_and_validate_image_input(**kwargs)
                 if image_input is None:
@@ -110,7 +110,7 @@ to return the maximum number of input items for each modality supported by the m
 For example, if the model supports any number of images but only one video per prompt:
 
 ```python
-def get_supported_mm_limits(self) -> Mapping[str, Optional[int]]:
+def get_supported_mm_limits(self) -> Mapping[str, int | None]:
     return {"image": None, "video": 1}
 ```
 
@@ -258,7 +258,7 @@ Assuming that the memory usage increases with the number of tokens, the dummy in
             self,
             seq_len: int,
             mm_counts: Mapping[str, int],
-            mm_options: Optional[Mapping[str, BaseDummyOptions]] = None,
+            mm_options: Mapping[str, BaseDummyOptions] | None = None,
         ) -> MultiModalDataDict:
             num_images = mm_counts.get("image", 0)
 
@@ -421,8 +421,10 @@ Assuming that the memory usage increases with the number of tokens, the dummy in
     ```python
     def get_image_size_with_most_features(self) -> ImageSize:
         image_processor = self.get_image_processor()
-        return ImageSize(width=image_processor.size["width"],
-                            height=image_processor.size["height"])
+        return ImageSize(
+            width=image_processor.size["width"],
+            height=image_processor.size["height"],
+        )
     ```
 
     Fuyu does not expect image placeholders in the inputs to HF processor, so
@@ -452,10 +454,12 @@ Assuming that the memory usage increases with the number of tokens, the dummy in
 
             return {
                 "image":
-                self._get_dummy_images(width=target_width,
-                                    height=target_height,
-                                    num_images=num_images,
-                                    overrides=image_overrides)
+                self._get_dummy_images(
+                    width=target_width,
+                    height=target_height,
+                    num_images=num_images,
+                    overrides=image_overrides,
+                )
             }
         ```
 
@@ -744,8 +748,7 @@ Each [PromptUpdate][vllm.multimodal.processing.PromptUpdate] instance specifies
                 image_width=image_size.width,
                 image_height=image_size.height,
             )
-            image_tokens = ([_IMAGE_TOKEN_ID] * ncols +
-                            [_NEWLINE_TOKEN_ID]) * nrows
+            image_tokens = ([_IMAGE_TOKEN_ID] * ncols + [_NEWLINE_TOKEN_ID]) * nrows
 
             return PromptUpdateDetails.select_token_id(
                 image_tokens + [bos_token_id],
@@ -781,8 +784,7 @@ Each [PromptUpdate][vllm.multimodal.processing.PromptUpdate] instance specifies
                     image_width=image_size.width,
                     image_height=image_size.height,
                 )
-                image_tokens = ([_IMAGE_TOKEN_ID] * ncols +
-                                [_NEWLINE_TOKEN_ID]) * nrows
+                image_tokens = ([_IMAGE_TOKEN_ID] * ncols + [_NEWLINE_TOKEN_ID]) * nrows
 
                 return PromptUpdateDetails.select_token_id(
                     image_tokens + [bos_token_id],
@@ -810,9 +812,11 @@ to register them to the multi-modal registry:
   from vllm.model_executor.models.interfaces import SupportsMultiModal
 + from vllm.multimodal import MULTIMODAL_REGISTRY
 
-+ @MULTIMODAL_REGISTRY.register_processor(YourMultiModalProcessor,
-+                                         info=YourProcessingInfo,
-+                                         dummy_inputs=YourDummyInputsBuilder)
++ @MULTIMODAL_REGISTRY.register_processor(
++     YourMultiModalProcessor,
++     info=YourProcessingInfo,
++     dummy_inputs=YourDummyInputsBuilder,
++ )
   class YourModelForImage2Seq(nn.Module, SupportsMultiModal):
 ```