baalajimaestro/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Remove async from function signature to avoid blocking the server

Browse source
This commit is contained in:
Andrei Betlen 2023-04-11 11:54:31 -04:00
parent 3727ba4d9e
commit 213cc5c340
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
llama_cpp/server/__main__.py
View file

@ -196,7 +196,7 @@ CreateChatCompletionResponse = create_model_from_typeddict(llama_cpp.ChatComplet
"/v1/chat/completions", "/v1/chat/completions",
response_model=CreateChatCompletionResponse, response_model=CreateChatCompletionResponse,
) )
async def create_chat_completion( def create_chat_completion(
request: CreateChatCompletionRequest, request: CreateChatCompletionRequest,
) -> Union[llama_cpp.ChatCompletion, EventSourceResponse]: ) -> Union[llama_cpp.ChatCompletion, EventSourceResponse]:
completion_or_chunks = llama.create_chat_completion( completion_or_chunks = llama.create_chat_completion(