llama.cpp
a1288cfe
- Prepare Q_reg for FP8 FlashAttention in fattn-vec.cuh
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
7 days ago
Prepare Q_reg for FP8 FlashAttention in fattn-vec.cuh
Author
ORippler
Committer
ORippler
Parents
443c2528
Loading