llama.cpp
f68669d5
- fix and opt kernel launch
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
113 days ago
fix and opt kernel launch
References
opencl-add-mul-mat-f16-f32-image
#14635 - OpenCL: add `mul_mat_f16_f32_image` kernel
Author
rmatif
Parents
18310bf2
Loading