Polymorf pushes OMLX inference from 150tps to nearly 200tps within 24 hours of launch

HankYeomans · x · 2026-09-26

X user TheDavidTai reports that Polymorf, less than 24 hours after launch, smashed the 166tps OMLX reference benchmark he had been using—boosting inference speed from 150tps to almost 200tps in one step. Technical details were not elaborated in the post.

Original post →

More from Infra

Infra channel →