yumoqing/llmage
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

bugfix

Browse Source
This commit is contained in:
yumoqing 2026-04-19 14:06:14 +08:00
parent f939349bfa
commit 51b9c87976
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llmage/llmclient.py
View File

@ -154,9 +154,11 @@ async def _inference_generator(request, callerid, callerorgid,
f = partial(async_uapi_request, request, llm, callerid, callerorgid, params_kw=params_kw) f = partial(async_uapi_request, request, llm, callerid, callerorgid, params_kw=params_kw)
elif not params_kw.stream: elif not params_kw.stream:
llm.stream = False llm.stream = False
debug(f'---{params_kw.stream=}, {llm.stream=} ---use sync_uapi_request ')
f = partial(sync_uapi_request, request, llm, callerid, callerorgid, params_kw=params_kw) f = partial(sync_uapi_request, request, llm, callerid, callerorgid, params_kw=params_kw)
else: else:
llm.stream = True llm.stream = True
debug(f'---{params_kw.stream=}, {llm.stream=} ---use sync_uapi_request ')
f = partial(uapi_request, request, llm, callerid, callerorgid, params_kw=params_kw) f = partial(uapi_request, request, llm, callerid, callerorgid, params_kw=params_kw)
async for d in f(): async for d in f():
yield d yield d