rebase: adapt to vLLM v0.29 APIs

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

tests/entrypoints/openai_api/test_video_stream_handler.py

@@ -281,7 +281,7 @@ class TestHandleQueryErrors:
     @pytest.mark.asyncio
     async def test_query_returns_error_response(self):
         """create_chat_completion returns ErrorResponse → error forwarded."""
-        from vllm.entrypoints.openai.engine.protocol import ErrorInfo, ErrorResponse
+        from vllm.entrypoints.serve.engine.protocol import ErrorInfo, ErrorResponse
 
         err = ErrorResponse(
             error=ErrorInfo(