cturan/llama.cpp @ bbbf5ecccb35286521f735239d499eec4279a840

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

Johannes Gäßler e81b8e4b7f llama: use FA + max. GPU layers by default (#15434)		5 mēneši atpakaļ
..
llama-cpp.h	afa8a9ec9b llama : add `llama_vocab`, functions -> methods, naming (#11110)	1 gadu atpakaļ
llama.h	e81b8e4b7f llama: use FA + max. GPU layers by default (#15434)	5 mēneši atpakaļ