Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on I built a dual RTX 3090 rig for local AI in 2025 (and lessons learned). Parent comment
Is that important for this workload? I thought most of the effort was spent processing data on the card rather than moving data on or off of it?
There are no comments on this comment yet.
Is that important for this workload? I thought most of the effort was spent processing data on the card rather than moving data on or off of it?