Groq LPU ☆

Groq's Language Processing Unit strips out caches and dynamic scheduling: the compiler knows exactly where every byte is every cycle, using 230 MB of on-chip SRAM at 80 TB/s. Made on GlobalFoundries 14 nm — proof that architecture, not process node, drives its speed — LPU racks serve open models at hundreds to thousands of tokens per second. Founded by TPU creator Jonathan Ross; valued in the billions on 2024–25 raises with a major Saudi deployment deal.