cturan/llama.cpp

miroir de https://github.com/cturan/llama.cpp

Auteur	SHA1 Message	Date
Diego Devesa	7cc2d2c889 ggml : move AMX to the CPU backend (#10570)	il y a 1 an
Olivier Chafik	1c641e6aac `build`: rename main → llama-cli, server → llama-server, llava-cli → llama-llava-cli, etc... (#7809)	il y a 1 an
Kawrakow	1bfc153e2f ggml : a faster version for Q4_1 x Q8_0 dot products (#1083)	il y a 2 ans
Kawrakow	5ecff35151 Adding a simple program to measure speed of dot products (#1041)	il y a 2 ans