phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

fix(lowest_latency.py): consistent time calc

Browse source
This commit is contained in:
Krrish Dholakia 2024-02-14 15:03:35 -08:00
parent a6d5d0f714
commit fccacaf91b
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
litellm/router_strategy/lowest_latency.py
View file

@ -168,7 +168,7 @@ class LowestLatencyLoggingHandler(CustomLogger):
if isinstance(response_obj, ModelResponse): if isinstance(response_obj, ModelResponse):
completion_tokens = response_obj.usage.completion_tokens completion_tokens = response_obj.usage.completion_tokens
total_tokens = response_obj.usage.total_tokens total_tokens = response_obj.usage.total_tokens
final_value = float(completion_tokens / response_ms.total_seconds()) final_value = float(response_ms.total_seconds() / completion_tokens)
# ------------ # ------------
# Update usage # Update usage