Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Nvidia DGX GH200: The First 100 Terabyte GPU Memory System. Parent comment
For LLMs you need to load single row of context size, that's vector of ie. 8k numbers, which is 32kB for single precision floats.
There are no comments on this comment yet.
For LLMs you need to load single row of context size, that's vector of ie. 8k numbers, which is 32kB for single precision floats.