[fix] add mm_processor_kwargs to extra_body in Chat API.

vllm-project · Feb 19, 2025 · 595ef8a · 595ef8a
1 parent fdc5df6
commit 595ef8a
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 0 deletions.
diff --git a/vllm/entrypoints/openai/protocol.py b/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."),

diff --git a/vllm/entrypoints/openai/serving_engine.py b/vllm/entrypoints/openai/serving_engine.py
@@ -451,6 +451,8 @@ async def _preprocess_chat(
             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]