llama.cpp
5065da55
- CUDA: loop over ne2*ne3 in case it overflows (#19538)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 days ago
CUDA: loop over ne2*ne3 in case it overflows (#19538) * CUDA: loop over ne2*ne3 in case it overflows * use fastdiv
References
#19538 - CUDA: loop over ne2*ne3 in case it overflows
Author
am17an
Parents
5174d720
Loading