llama.cpp
5eff6ec9
- CUDA: MoE helper in device code, better tile sizes (#15525)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
131 days ago
CUDA: MoE helper in device code, better tile sizes (#15525) * CUDA: MoE helper in device code, better tile sizes * reduce superfluous CUDA blocks
References
#15525 - CUDA: MoE helper in device code, better tile sizes
Author
JohannesGaessler
Parents
dfd9b5f6
Loading