CEO Interview: Rebellions’ NPU Leverages Memory-Centric Chiplets

The Korean unicorn packages four NPU dies with 144 GB of HBM3E and bets on an open software stack to serve large language models at lower cost per token.

By Jake Hertz, All About Circuits

The race to build artificial intelligence has become a contest between nations as much as between companies. Right now, the scarcest resources in that contest are energy and silicon.

And, while America’s NVIDIA currently supplies most of the world’s AI compute, South Korea is building a meaningful AI supply chain of its own.

The country already produces most of the world’s high-bandwidth memory through Samsung and SK Hynix, and it is now working to convert that lead into a foothold in AI compute itself. In that effort, Rebellions is undeniable.

Founded in 2020 and transcended to Korea’s first AI-chip unicorn, the company has drawn backing from Samsung, SK Hynix, and Arm, alongside a national growth fund that casts the investment as part of a “K-Nvidia” ambition. With a unique bet on memory-centric design for inference, the company believes that a processor fabricated and funded in Korea can win on cost per token rather than peak compute.

All About Circuits recently sat down in New York City with Rebellions co-founder and CEO Sunghyun Park to learn about the company’s memory-centric approach firsthand.

To read the full article, click here