llama.cpp
69b398ce
- metrics : add n_busy_slots_per_decode
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 year ago
metrics : add n_busy_slots_per_decode
References
#9283 - server : simplify state machine for slot
Author
ngxson
Parents
fbebf650
Loading
