From 0da9ffdb0d3023482e1e90d6563a3e379ed6a160 Mon Sep 17 00:00:00 2001 From: Mike Qiu Date: Sun, 17 May 2026 23:05:34 +0800 Subject: [PATCH] Fix output finish reason issue for audio chunk in stream mode (#2849) Signed-off-by: Mike_Qiu Co-authored-by: Mike_Qiu Co-authored-by: Hongsheng Liu --- vllm_omni/entrypoints/openai/serving_chat.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/vllm_omni/entrypoints/openai/serving_chat.py b/vllm_omni/entrypoints/openai/serving_chat.py index 3296c0b4d..66a86e7c9 100644 --- a/vllm_omni/entrypoints/openai/serving_chat.py +++ b/vllm_omni/entrypoints/openai/serving_chat.py @@ -2116,7 +2116,7 @@ class OmniOpenAIServingChat(OpenAIServingChat, AudioMixin): index=output.index, delta=DeltaMessage(role=role, content=audio_base64), logprobs=None, - finish_reason="stop", + finish_reason=output.finish_reason, stop_reason=output.stop_reason, token_ids=(as_list(output.token_ids) if request.return_token_ids else None), ) @@ -2126,7 +2126,7 @@ class OmniOpenAIServingChat(OpenAIServingChat, AudioMixin): message=ChatMessage(role=role, audio=audio_obj), logprobs=None, finish_reason="stop", - stop_reason=None, + stop_reason=output.stop_reason, ) choices.append(choice_data) return choices