Re:Mercury 2: The fastest reasoning LLM, powered by diffusion
by storus on Wednesday February 25, 2026 @05:52AM
(#47149918)
I'd say using them as draft models for some strong AR model, speeding it up 3x. Diffusion generates a bunch of tokens extremely fast, those can be then passed over to an AR model to accept/reject instead of generating them.
[ Parent
| on HN ]
There are no comments on this comment yet.