llama.cpp
cb295bf5
- CUDA: extend K-type validation to V-types for flash attention (#24403)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
137 days ago
CUDA: extend K-type validation to V-types for flash attention (#24403) * CUDA: extend K-type validation to V-types for flash attention * reorder
References
#24403 - CUDA: extend K-type validation to V-types for flash attention
Author
sanmai
Parents
bfdf581b
Loading