Sally Ward-Foxton / EE Times:

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

Sally Ward-Foxton / EE Times:

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

Source: TechMeme
Source Link: https://www.techmeme.com/261113/p8#a261113p8