xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 05:25:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Fix] Change /generate response-type to json for non-streaming (#374)

Browse Source
This commit is contained in:
Nicolas Frenay 2023-07-06 20:15:17 -05:00 committed by GitHub
parent b396cb4998
commit be54f8e5c4
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/entrypoints/api_server.py
View File

@ -3,7 +3,7 @@ import json
from typing import AsyncGenerator from typing import AsyncGenerator
from fastapi import BackgroundTasks, FastAPI, Request from fastapi import BackgroundTasks, FastAPI, Request
from fastapi.responses import Response, StreamingResponse from fastapi.responses import JSONResponse, Response, StreamingResponse
import uvicorn import uvicorn
from vllm.engine.arg_utils import AsyncEngineArgs from vllm.engine.arg_utils import AsyncEngineArgs
@ -64,7 +64,7 @@ async def generate(request: Request) -> Response:
prompt = final_output.prompt prompt = final_output.prompt
text_outputs = [prompt + output.text for output in final_output.outputs] text_outputs = [prompt + output.text for output in final_output.outputs]
ret = {"text": text_outputs} ret = {"text": text_outputs}
return Response(content=json.dumps(ret)) return JSONResponse(ret)
if __name__ == "__main__": if __name__ == "__main__":