llama.cpp
db0fc2da
- simple : improve comments + free batch
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 year ago
simple : improve comments + free batch
References
#3228 - llama : custom attention mask + parallel decoding + no context swaps
Author
ggerganov
Parents
b377bf22
Loading