llama.cpp
f3dbfb9f
- llama : offload K shift tensors
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 years ago
llama : offload K shift tensors
References
#4309 - llama : per-layer KV cache
Author
ggerganov
Committer
ggerganov
Parents
986b3da7
Loading
