frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 14:53:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] fix missing 'finish_reason': null in streaming chat (#19662)

Browse Source 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
This commit is contained in:
Chauncey
2025-06-16 22:10:39 +08:00
committed by GitHub
parent c3fec47bb7
commit 836d4ce140
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/entrypoints/openai/serving_chat.py
View File

@ -873,7 +873,7 @@ class OpenAIServingChat(OpenAIServing):
total_tokens=num_prompt_tokens + completion_tokens,
)
data = chunk.model_dump_json(exclude_none=True)
data = chunk.model_dump_json(exclude_unset=True)
yield f"data: {data}\n\n"
# once the final token is handled, if stream_options.include_usage