llama.cpp
4c6744b5
- cuda : remove duplicated cuBLAS GEMM code
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 years ago
cuda : remove duplicated cuBLAS GEMM code
References
#3776 - cuda : improve text-generation and batched decoding performance
Author
ggerganov
Parents
a3c28439
Loading