llama.cpp
16b60dd7
- cuda : add F32 sgemm branch
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 year ago
cuda : add F32 sgemm branch
References
#3776 - cuda : improve text-generation and batched decoding performance
Author
ggerganov
Parents
52af7826
Loading