News for hackers. Stuff that matters.
Re:Nvidia announces next-gen RTX 5090 and RTX 5080 GPUs by ryao on Tuesday January 07, 2025 @06:05PM (#42628800)
They are training models that need terabytes of RAM with only 150GB/sec of memory bandwidth. That is compute bound. If you think it is memory bandwidth bound, please explain the algorithms and how they are memory bandwidth bound.

There are no comments on this comment yet.