NTT debuts breakthrough AI chip for real-time 4K inference at the edge
NTT announced the world’s first AI inference large-scale integration (LSI) chip for real-time 4K video processing at the edge, designed for low-power and power-constrained devices.
The chip enables real-time AI inference from ultra-high-definition video without requiring compression, improving efficiency and accuracy. It supports applications such as beyond visual line-of-sight drone operations for infrastructure inspections, increasing detection range from 30m to 150m.
The LSI uses an NTT-developed AI inference engine, reducing computational complexity and power consumption to under 20 watts.
“The combination of low-power AI inferencing with ultra-high-definition video holds an enormous amount of potential, from infrastructure inspection to public safety to live sporting events,” says Kazu Gomi, president and CEO of NTT Research. “NTT’s LSI, which we believe to be the first of its kind to achieve such results, represents an important step forward in enabling AI inference at the edge and for power-constrained terminals.”
NTT plans to commercialize the chip by fiscal year 2025 and expand its use cases and supported inference models.
The technology aligns with NTT’s IOWN initiative, leveraging high-speed, low-latency networks to address modern infrastructure challenges.
NTT is collaborating with NTT DATA on integrating the chip with Attribute-Based Encryption (ABE) for secure and flexible data sharing.
NexGen Cloud raises $45M to build Europe’s sovereign AI infrastructure
Article Topics
AI inference | AI/ML | chip | edge computing | NTT | NTT Data | video processing
Comments