llama.cpp
8f91ca54
- CUDA: re-use MLA K data for V in MMA FA (#19057)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
5 days ago
CUDA: re-use MLA K data for V in MMA FA (#19057)
References
#19057 - CUDA: re-use MLA K data for V in MMA FA
Author
JohannesGaessler
Parents
81ab64f3
Loading