Fix links in multi-modal model contributing page (#18615)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

Author: hmellor

docs/contributing/model/multimodal.md

@@ -819,7 +819,7 @@ Each [PromptUpdate][vllm.multimodal.processing.PromptUpdate] instance specifies
 After you have defined [BaseProcessingInfo][vllm.multimodal.processing.BaseProcessingInfo] (Step 2),
 [BaseDummyInputsBuilder][vllm.multimodal.profiling.BaseDummyInputsBuilder] (Step 3),
 and [BaseMultiModalProcessor][vllm.multimodal.processing.BaseMultiModalProcessor] (Step 4),
-decorate the model class with {meth}`MULTIMODAL_REGISTRY.register_processor <vllm.multimodal.registry.MultiModalRegistry.register_processor>`
+decorate the model class with [MULTIMODAL_REGISTRY.register_processor][vllm.multimodal.processing.MultiModalRegistry.register_processor]
 to register them to the multi-modal registry:
 
 ```diff

vllm/model_executor/models/interfaces.py

@@ -89,11 +89,22 @@ def get_input_embeddings(
     ) -> Tensor:
         ...
 
+    # TODO: Remove this overload once v0 is deprecated
     @overload
     def get_input_embeddings(
         self,
         input_ids: Tensor,
         multimodal_embeddings: Optional[MultiModalEmbeddings] = None,
+    ) -> Tensor:
+        ...
+
+    def get_input_embeddings(
+        self,
+        input_ids: Tensor,
+        multimodal_embeddings: Optional[MultiModalEmbeddings] = None,
+        # Only necessary so that the v0 overload is valid
+        # TODO: Remove attn_metadata once v0 is deprecated
+        attn_metadata: Optional["AttentionMetadata"] = None,
     ) -> Tensor:
         """
         Returns the input embeddings merged from the text embeddings from