Refactor: extract OmniStreamingVideoHandler base and QwenOmniStreamingVideoHandler (#4424)

Signed-off-by: NumberWan <wantszkin2003@gmail.com>
Signed-off-by: lishunyang12 <125541396+lishunyang12@users.noreply.github.com>
Co-authored-by: lishunyang12 <125541396+lishunyang12@users.noreply.github.com>

vllm_omni/entrypoints/openai/api_server.py

@@ -132,7 +132,7 @@ from vllm_omni.entrypoints.openai.serving_video import (
     ReferenceImage,
     ReferenceVideo,
 )
-from vllm_omni.entrypoints.openai.serving_video_stream import OmniStreamingVideoHandler
+from vllm_omni.entrypoints.openai.serving_video_stream import create_streaming_video_handler
 from vllm_omni.entrypoints.openai.stage_params import (
     build_stage_sampling_params_list,
     get_default_sampling_params_list,
@@ -1070,7 +1070,7 @@ async def omni_init_app_state(
         speech_service=state.openai_serving_speech,
     )
     state.openai_streaming_video = (
-        OmniStreamingVideoHandler(
+        create_streaming_video_handler(
             chat_service=state.openai_serving_chat,
             engine_client=engine_client,
         )