
jimmah
@jamesdouma
deep learning dork
ID: 24405165
14-03-2009 18:10:06
9,9K Tweet
49,49K Followers
248 Following











Sawyer Merritt The Samsung fab in Texas will make AI6, not AI5, and the decision regarding using HBM has not been made yet. As the ratio of total parameters to active (frequently used) parameters increases, the cost per unit of useful compute and compute per Watt may favor relatively

Sawyer Merritt You can fit more total RAM on the board if you use “normal” memory than high-bandwidth memory and it is super cheap. Maybe high-bandwidth memory is still the right choice, but using HBM isn’t the slam dunk many people think it is.


