Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Use pytorch2+cu118 with ADA hardware for 50%+ speedup. Parent comment
They know it's a bottleneck for LM training and inference, so they'll want to extract value by reserving it for the professional line cards
There are no comments on this comment yet.
They know it's a bottleneck for LM training and inference, so they'll want to extract value by reserving it for the professional line cards