News for hackers. Stuff that matters.
Re:How to make LLMs go fast by D0TheMath on Friday December 22, 2023 @09:08PM (#38740994)
The jury very much still seems out on this. Computationally speaking, I believe Mamba is Turing complete, while transformers aren't (they can't do loops), so technically Mamba is more expressive. But of course, the question is always whether it ends up with lower loss.
Re:How to make LLMs go fast by D0TheMath on Friday December 22, 2023 @09:09PM (#38741003)
(well actually its not turing complete, but it definitely seems closer)