Re:Llama.cpp: Full CUDA GPU Acceleration
by croes on Tuesday June 13, 2023 @12:19AM
(#36305250)
The others tried with OpenCL to build a more open environment, this will always lose against a single vendor tailoring it's solution for their own lineup.
Think of Apples ecosystem vs Android or MS's Office-Outlook-Teams vs anything else.
Think of Apples ecosystem vs Android or MS's Office-Outlook-Teams vs anything else.