llama.cpp
3e68df86
- llama : pad KV cache size to 32
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 years ago
llama : pad KV cache size to 32
References
#4280 - llama : pad KV cache size
Author
ggerganov
Committer
ggerganov
Parents
5a7d3125
Loading