cturan/llama.cpp @ 16bcc1259d311d0fd37fe00fefcc7900324d38cb

зеркало из https://github.com/cturan/llama.cpp

Georgi Gerganov 16bcc1259d kv-cache : pad the cache size to 256 for performance (#17046)		2 месяцев назад
..
llama-cpp.h	afa8a9ec9b llama : add `llama_vocab`, functions -> methods, naming (#11110)	1 год назад
llama.h	16bcc1259d kv-cache : pad the cache size to 256 for performance (#17046)	2 месяцев назад