cturan/llama.cpp @ f14f4e421b2177fadcf9d15ebccb0492e5464d86

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

Johannes Gäßler 026d2ad472 llama: fix magic number of 999 for GPU layers (#18266)		1 mēnesi atpakaļ
..
llama-cpp.h	afa8a9ec9b llama : add `llama_vocab`, functions -> methods, naming (#11110)	1 gadu atpakaļ
llama.h	026d2ad472 llama: fix magic number of 999 for GPU layers (#18266)	1 mēnesi atpakaļ