Primary Source: 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 (Sally Ward-Foxton/EE Times)
DeepX is targeting edge markets including robotics with its second-generation AI accelerator, which can run large LLMs on device in under 5 W.
โก Executive Summary & Key Facts
- [Core Event] Industry Leaders: 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 (Sally Ward-Foxton/EE Times)
- [Context & Motivation] DeepX is targeting edge markets including robotics with its second-generation AI accelerator, which can run large LLMs on device in under 5 W..
- [Key Fact] Sally Ward-Foxton / EE Times:.
๐ค AI Radar Technical Deep-Dive
DeepX is targeting edge markets including robotics with its second-generation AI accelerator, which can run large LLMs on device in under 5 W.
๐ฐ Full In-Depth Coverage
EE Times Full ReportSally 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-gene
