cturan/llama.cpp

spogulis no https://github.com/cturan/llama.cpp

Autors	SHA1 Ziņojums	Datums
Georgi Gerganov	9c67c2773d ggml : add Flash Attention (#5021)	1 gadu atpakaļ
DAN™	e00b4a8f81 Fix more int overflow during quant (PPL/CUDA). (#6563)	1 gadu atpakaļ
slaren	ae1f211ce2 cuda : refactor into multiple files (#6269)	1 gadu atpakaļ