At a time when agentic AI is gaining rapid traction, inference is becoming crucial. The world’s most valuable company and GPU leader, Nvidia (NVDA), has often been flagged as a laggard by many in inference. Not willing to cede ground, the Jensen Huang-led company decided to buy its way into the market with the $20 billion acquisition (though the companies said it was a licensing deal) of inference-focused AI infrastructure company Groq late last year.
Now, Nvidia recently revealed Groq 3 LPX, the rack-scale system built around Groq’s LPU technology, is in full-scale production.