From 0e878a92d2b5cb8f6de37bb6320c324e6bc359ea Mon Sep 17 00:00:00 2001
From: Peiqi Yin <60515999+yinpeiqi@users.noreply.github.com>
Date: Tue, 23 Dec 2025 08:52:18 +0800
Subject: [PATCH] [BugFix] raise error when request.stream=True. (#350)

Signed-off-by: yinpe <11810305@mail.sustech.edu.cn>
---
 vllm_omni/entrypoints/openai/serving_chat.py | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

diff --git a/vllm_omni/entrypoints/openai/serving_chat.py b/vllm_omni/entrypoints/openai/serving_chat.py
index ebf947a88..9e8e8dcc7 100644
--- a/vllm_omni/entrypoints/openai/serving_chat.py
+++ b/vllm_omni/entrypoints/openai/serving_chat.py
@@ -263,16 +263,7 @@ class OmniOpenAIServingChat(OpenAIServingChat):
 
         # Streaming response
         if request.stream:
-            return self.chat_completion_stream_generator(
-                request,
-                result_generator,
-                request_id,
-                model_name,
-                conversation,
-                tokenizer,
-                request_metadata,
-                enable_force_include_usage=self.enable_force_include_usage,
-            )
+            raise RuntimeError("Not support streaming output now.")
 
         try:
             return await self.chat_completion_full_generator(