News for hackers. Stuff that matters.
Re:Groq runs Mixtral 8x7B-32k with 500 T/s by deniz_tekalp on Monday February 19, 2024 @12:47PM (#39432547)
GPUs are notoriously bad on exploiting sparsity. I wonder if this architecture can do a better job. The groq engineers in this thread, if a neural network had say 60% of its weights set to 0, what would it do to cost & speed in your hardware?

There are no comments on this comment yet.