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

fix(proxy_cli.py): don't double load the router config

Browse source 
was causing callbacks to be instantiated twice - double couting usage in cache
This commit is contained in:
Krrish Dholakia 2024-04-10 13:23:56 -07:00
parent d8da4cf8bb
commit b2741933dc
5 changed files with 12 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

1
litellm/router.py
View file

@ -2374,7 +2374,6 @@ class Router:
"""
Returns the deployment based on routing strategy
"""
# users need to explicitly call a specific deployment, by setting `specific_deployment = True` as completion()/embedding() kwarg
# When this was no explicit we had several issues with fallbacks timing out
if specific_deployment == True: