llama.cpp
6a30bf3e
- batched : add NGL arg
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 year ago
batched : add NGL arg
References
#3749 - cuda : add batched cuBLAS GEMM for faster attention
Author
ggerganov
Parents
8fb1be64
Loading
