substratusai / lingo

Lightweight ML model proxy and autoscaler for kubernetes
https://www.substratus.ai
Apache License 2.0
102 stars 6 forks source link

Configurable scale down time #32

Closed samos123 closed 7 months ago

samos123 commented 7 months ago

Currently the scale down is hardcoded to 30 seconds or 1 minute. This should be configurable both globally and on a per deployment basis.