llama.cpp
a28e0d5e
- CUDA: app option to compile without FlashAttention (#12025)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
299 days ago
CUDA: app option to compile without FlashAttention (#12025)
References
#12025 - CUDA: app option to compile without FlashAttention
Author
JohannesGaessler
Parents
36c258ee
Loading