News for hackers. Stuff that matters.
Re:Llama.cpp: Full CUDA GPU Acceleration by gre on Tuesday June 13, 2023 @03:05AM (#36306617)
conda takes up to several minutes to figure out dependencies just to tell you that one library requires an old version of a dependency and another requires a new one, making the whole setup impossible.

mamba can do this much quicker.

Re:Llama.cpp: Full CUDA GPU Acceleration by girvo on Tuesday June 13, 2023 @06:30AM (#36308108)
That’s genuinely good to know! Cheers
Re:Llama.cpp: Full CUDA GPU Acceleration by dekhn on Tuesday June 13, 2023 @11:50AM (#36312045)
as always, a fast no is better than a slow maybe