vrr/kvcache-ai-ktransformers
2
0
Fork 0
mirror of https://github.com/kvcache-ai/ktransformers.git synced 2025-09-10 06:14:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: workaround return dummy usage

Browse source
This commit is contained in:
ceerrep 2025-02-18 22:39:49 +08:00
parent db61375f1a
commit 6d45871de8
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
ktransformers/server/api/openai/endpoints/chat.py
View file

@ -5,7 +5,7 @@ from fastapi import APIRouter
from fastapi.requests import Request
from ktransformers.server.utils.create_interface import get_interface
from ktransformers.server.schemas.assistants.streaming import chat_stream_response
from ktransformers.server.schemas.endpoints.chat import ChatCompletionCreate,ChatCompletionChunk,ChatCompletionObject
from ktransformers.server.schemas.endpoints.chat import ChatCompletionCreate,ChatCompletionChunk,ChatCompletionObject, Usage
from ktransformers.server.backend.base import BackendInterfaceBase
from ktransformers.server.config.config import Config
@ -34,6 +34,7 @@ async def chat_completion(request:Request,create:ChatCompletionCreate):
return chat_stream_response(request,inner())
else:
comp = ChatCompletionObject(id=id,object='chat.completion.chunk',created=int(time()))
comp.usage = Usage(completion_tokens=1, prompt_tokens=1, total_tokens=2)
async for token in interface.inference(input_message,id):
comp.append_token(token)
return comp