by wsxiaoys on 9/20/23, 4:15 PM with 1 comments
by wsxiaoys on 9/20/23, 4:23 PM
The Tabby team made a significant contribution by enhancing support for the StarCoder series models (1B/3B/7B) in llama.cpp. This enhancement allows these models to run on Metal, providing comparable performance to that of an NVIDIA GPU.