llama.cpp
llama : add attention weights extraction API [EXPERIMENTAL]
#20086
Open
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
2
Changes
View On
GitHub
Commits
llama : add attention weights extraction API [EXPERIMENTAL]
QuentinFuxa
committed
18 days ago
Use internal cb_eval for attention extraction to eliminate graph splits
QuentinFuxa
committed
18 days ago
Loading