Re:Why DeepSeek is cheap at scale but expensive to run locally
by krapht on Sunday June 01, 2025 @02:44PM
(#44152903)
So the MI300x has 8 different memory domains, and although you can treat it as one flat memory space, if you want to reach their advertised peak memory bandwidth you have to work with it like an 8-socket board.
[ Parent
| on HN ]
Re:Why DeepSeek is cheap at scale but expensive to run locally
by latchkey on Sunday June 01, 2025 @03:30PM
(#44153212)
Here is a good article on it:
https://rocm.blogs.amd.com/software-tools-optimization/compu...