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 emmender on Tuesday June 13, 2023 @10:58AM (#36311197)
there is nccl, gpudirect, nvlink and so on and so forth.. It is not just matmul on gpus.
[ Parent | on HN ]

There are no comments on this comment yet.