llama.cpp
ea84d709
- CUDA: optimize Orin single-column MMVQ (#31268)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
4 hours ago
CUDA: optimize Orin single-column MMVQ (#31268) * CUDA: optimize Orin single-column MMVQ * Create a separate Orin branch in `calc_rows_per_block`
References
#31268 - CUDA: optimize Orin single-column MMVQ
Author
meitmt
Parents
9fbe30c2
Loading