cturan/llama.cpp @ 2016f07bd106c73699ecbaace80f55db5ed95dac

şunun yansıması https://github.com/cturan/llama.cpp

Ed Addario 71e90e8813 quantize: Handle user-defined quantization levels for additional tensors (#12511)		9 ay önce
..
llama-cpp.h	afa8a9ec9b llama : add `llama_vocab`, functions -> methods, naming (#11110)	1 yıl önce
llama.h	71e90e8813 quantize: Handle user-defined quantization levels for additional tensors (#12511)	9 ay önce