[Misc] add mm_processor_kwargs to extra_body for Qwen2.5-VL (#13533)

vllm/entrypoints/openai/protocol.py

@@ -312,6 +312,10 @@ class ChatCompletionRequest(OpenAIBaseModel):
         description=("Additional kwargs to pass to the template renderer. "
                      "Will be accessible by the chat template."),
     )
+    mm_processor_kwargs: Optional[Dict[str, Any]] = Field(
+        default=None,
+        description=("Additional kwargs to pass to the HF processor."),
+    )
     guided_json: Optional[Union[str, dict, BaseModel]] = Field(
         default=None,
         description=("If specified, the output will follow the JSON schema."),

vllm/entrypoints/openai/serving_engine.py

@@ -451,6 +451,8 @@ class OpenAIServing:
             prompt_token_ids=prompt_inputs["prompt_token_ids"])
         if mm_data is not None:
             engine_prompt["multi_modal_data"] = mm_data
+        if request.mm_processor_kwargs is not None:
+            engine_prompt["mm_processor_kwargs"] = request.mm_processor_kwargs
 
         return conversation, [request_prompt], [engine_prompt]