diff --git a/fastdeploy/entrypoints/openai/serving_chat.py b/fastdeploy/entrypoints/openai/serving_chat.py
index 73459c9d4..b7e9555ce 100644
--- a/fastdeploy/entrypoints/openai/serving_chat.py
+++ b/fastdeploy/entrypoints/openai/serving_chat.py
@@ -298,11 +298,6 @@ class OpenAIServingChat:
                             api_server_logger.info(f"Chat Streaming response last send: {chunk.model_dump_json()}")
                         choices = []
 
-                if choices:
-                    chunk.choices = choices
-                    yield f"data: {chunk.model_dump_json(exclude_unset=True)}\n\n"
-                    choices = []
-
             if include_usage:
                 completion_tokens = previous_num_tokens
                 usage = UsageInfo(
diff --git a/fastdeploy/entrypoints/openai/serving_completion.py b/fastdeploy/entrypoints/openai/serving_completion.py
index 0a422d0fa..b4160366f 100644
--- a/fastdeploy/entrypoints/openai/serving_completion.py
+++ b/fastdeploy/entrypoints/openai/serving_completion.py
@@ -352,10 +352,6 @@ class OpenAIServingCompletion:
                             )
                             yield f"data: {usage_chunk.model_dump_json(exclude_unset=True)}\n\n"
                         api_server_logger.info(f"Completion Streaming response last send: {chunk.model_dump_json()}")
-                if choices:
-                    chunk.choices = choices
-                    yield f"data: {chunk.model_dump_json(exclude_unset=True)}\n\n"
-                    choices = []
 
         except Exception as e:
             yield f"data: {ErrorResponse(message=str(e), code=400).model_dump_json(exclude_unset=True)}\n\n"