llama.cpp
a72e04ab
- cuda : add F16 kernel support for CONV_2D_DW (#29064)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
11 days ago
cuda : add F16 kernel support for CONV_2D_DW (#29064)
References
#29064 - cuda : add F16 kernel support for CONV_2D_DW
Author
crion99
Parents
8212c780
Loading