The next phase of artificial intelligence may require very different processors
- Mar 20
- 1 min read
THE ECONOMIST — Times are changing fast. Demand for AI computing is shifting from training models to getting them to answer real-world queries, a process known as inference. McKinsey, a consultancy, estimates that by the end of the decade inference will account for three-fifths of demand in AI data centres.
Nvidia appears to recognise the shift. On March 16th it unveiled a new chip designed specifically for inference tasks, the Groq 3 LPX, with an architecture that departs from the traditional GPU.
This time, it will have plenty of competition. A crop of startups is building chips aimed at running AI models faster and more efficiently than Nvidia’s.
Read the full story | THE ECONOMIST
