Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs. Parent comment
Now I see they tried to point out the obvious thing which is to predict multiple tokens ahead, not just two as in your example.
There are no comments on this comment yet.
Now I see they tried to point out the obvious thing which is to predict multiple tokens ahead, not just two as in your example.