A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 06:00 UTC
[Bugfix] fix missing 'finish_reason': null in streaming chat (#19662)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Chauncey committed
Jun 16, 2025 at 22:10 UTC
836d4ce140a65a0c5067cca58709cfb86c811b81
1 file changed
+1
-1
vllm/entrypoints/openai/serving_chat.py
+1
-1
@@ -873,7 +873,7 @@ class OpenAIServingChat(OpenAIServing):
873
total_tokens=num_prompt_tokens + completion_tokens,
874
)
875
876
- data = chunk.model_dump_json(exclude_none=True)
876
+ data = chunk.model_dump_json(exclude_unset=True)
877
yield f"data: {data}\n\n"
878
879
# once the final token is handled, if stream_options.include_usage