Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Serving 70B-Scale LLMs Efficiently on Low-Resource Edge Devices [pdf]. Parent comment
In other words, if I want 100 tokens of output, do I have to wait 2990 seconds? If so, the terminology seems unnecessarily confusing.
There are no comments on this comment yet.
In other words, if I want 100 tokens of output, do I have to wait 2990 seconds? If so, the terminology seems unnecessarily confusing.