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

fix(router.py): set cooldown_time: per model

Browse source
This commit is contained in:
Krrish Dholakia 2024-06-25 16:51:55 -07:00
parent e813e984f7
commit d98e00d1e0
6 changed files with 72 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

2
litellm/utils.py
View file

@ -2017,6 +2017,7 @@ def get_litellm_params(
input_cost_per_token=None,
output_cost_per_token=None,
output_cost_per_second=None,
cooldown_time=None,
):
litellm_params = {
"acompletion": acompletion,
@ -2039,6 +2040,7 @@ def get_litellm_params(
"input_cost_per_second": input_cost_per_second,
"output_cost_per_token": output_cost_per_token,
"output_cost_per_second": output_cost_per_second,
"cooldown_time": cooldown_time,
}
return litellm_params