Re:Chiplet ASIC supercomputers for LLMs like GPT-4
by kraken12 on Wednesday July 12, 2023 @03:02PM
(#36700032)
Maybe they could do something like AMD's GPU memory stacking, that is good for scaling, and of course they are using many chips not one chip..
[ Parent
| on HN ]
There are no comments on this comment yet.