cturan/llama.cpp

mirrorاز https://github.com/cturan/llama.cpp

نویسنده	SHA1 پیام	تاریخ
Georgi Gerganov	8030da7afe ggml : reuse quantum structs across backends (#5943)	1 سال پیش
Kawrakow	44ca159faf 1.5 bit: we can do even better (#5999)	1 سال پیش
Kawrakow	be858f6205 Better 1.5 bit quantization (#5971)	1 سال پیش
Georgi Gerganov	bf47a5eefc ggml : remove __constant__ specifier for CUDA tables (#5940)	1 سال پیش
Georgi Gerganov	8a3012a4ad ggml : add ggml-common.h to deduplicate shared code (#5940)	1 سال پیش