llama.cpp
a3e6d622
- cuda : alternative q4_q8 kernel
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 years ago
cuda : alternative q4_q8 kernel
References
dequantize-matmul-3-gg
Author
ggerganov
Committer
ggerganov
Parents
e7b9d97b
Loading
