lighteval
b68d5bc9
- Autoscaling inference endpoints (#412)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 year ago
Autoscaling inference endpoints (#412) * adding better management for restarts and resizes * upgraded autoscale * added pause option * fix to parallelism manager - no need for endpoint
References
#412 - Autoscaling inference endpoints
Author
clefourrier
Parents
39298254
Loading