cturan/llama.cpp

miroir de https://github.com/cturan/llama.cpp

Auteur	SHA1 Message	Date
Johannes Gäßler	133d99c599 CUDA: deduplicate FlashAttention code (#7352)	il y a 1 an
Georgi Gerganov	9cb317f77e ggml : full ALiBi support (#7192)	il y a 1 an
Georgi Gerganov	9c67c2773d ggml : add Flash Attention (#5021)	il y a 1 an
DAN™	e00b4a8f81 Fix more int overflow during quant (PPL/CUDA). (#6563)	il y a 1 an
slaren	ae1f211ce2 cuda : refactor into multiple files (#6269)	il y a 1 an