News for hackers. Stuff that matters.

A comment on Llama.cpp: Full CUDA GPU Acceleration. Parent comment

Re:Llama.cpp: Full CUDA GPU Acceleration by v3ss0n on Tuesday June 13, 2023 @06:56AM (#36308303)
Ridiculous, 10gb binary only if machine learning models involved. I had distributed full stack binaries in 70mb or less.
[ Parent | on HN ]

There are no comments on this comment yet.