cturan/llama.cpp

kopia lustrzana https://github.com/cturan/llama.cpp

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