Semiconductor 'Brain' Combines Transformer's Intelligence and Mamba's Efficiency
3 Articles
3 Articles
Semiconductor 'brain' combines transformer's intelligence and Mamba's efficiency
As recent artificial intelligence (AI) models' capacity to understand and process long, complex sentences grows, the necessity for new semiconductor technologies that can simultaneously boost computation speed and memory efficiency is increasing.
KAIST Develops an AI Semiconductor Brain Combining Transformer's Intelligence and Mamba's Efficiency
As recent Artificial Intelligence (AI) models’ capacity to understand and process long, complex sentences grows, the necessity for new semiconductor technologies that can simultaneously boost computation speed and memory efficiency is increasing.
[Digital Daily Reporter Lee Geon-han] KAIST and an international research team have developed a core AI semiconductor technology that quadruples the inference speed of Large Language Models (LLMs) and reduces power consumption by 2.2 times. Based on a Transformer and Mamba hybrid architecture, it is the world's first implementation that enables direct computation within memory. KAIST announced on the 17th that Professor Jong-se Park's research t…
Coverage Details
Bias Distribution
- 100% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium