vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-11 07:44:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: object type for non-streaming response

Browse source
This commit is contained in:
ceerrep 2025-02-18 23:49:51 +08:00
parent 6d45871de8
commit 584c7d5639
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ktransformers/server/api/openai/endpoints/chat.py
View file

@ -33,7 +33,7 @@ async def chat_completion(request:Request,create:ChatCompletionCreate):
yield chunk yield chunk
return chat_stream_response(request,inner()) return chat_stream_response(request,inner())
else: else:
comp = ChatCompletionObject(id=id,object='chat.completion.chunk',created=int(time())) comp = ChatCompletionObject(id=id,object='chat.completion',created=int(time()))
comp.usage = Usage(completion_tokens=1, prompt_tokens=1, total_tokens=2) comp.usage = Usage(completion_tokens=1, prompt_tokens=1, total_tokens=2)
async for token in interface.inference(input_message,id): async for token in interface.inference(input_message,id):
comp.append_token(token) comp.append_token(token)