scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-06 02:48:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

fix: use logging_obj.start_time for overhead calculation

Browse source 
Previously the call passed start_time=end_time, producing
_response_ms=0 and negative litellm_overhead_time_ms.
Use logging_obj.start_time with end_time fallback instead.
This commit is contained in:
factnn 2026-06-21 13:37:55 +08:00
parent 9f03795b88
commit 78aa0b2ea7
1 changed files with 2 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
litellm/proxy/common_request_processing.py
View file

@ -1437,12 +1437,13 @@ class ProxyBaseLLMRequestProcessing:
update_response_metadata,
)
start_time = logging_obj.start_time or end_time
update_response_metadata(
result=response,
logging_obj=logging_obj,
model=self.data.get("model"),
kwargs=self.data,
start_time=end_time,
start_time=start_time,
end_time=end_time,
)