Skip to content
VibekollenBETAVibekollen
News briefTechmeme

South Korea-based DeepX tapes out DX-M2, an edge AI chip to run inference of 100B-parameter LLMs on robots and drones, targeting fall 2027 for mass production

eetimes.com via Techmeme

DeepX is targeting edge markets including robotics with its second-generation AI accelerator, which can run large LLMs on device in under 5 W.

A short brief from Techmeme’s public feed, in the source language. The full original article has not been read.

More from Techmeme