llama.cpp
e262947d
- common : add command-line arg to disable KV cache offloading
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 years ago
common : add command-line arg to disable KV cache offloading
References
#4309 - llama : per-layer KV cache
Author
ggerganov
Parents
c80b8a2b
Loading