Nvidia says its next-generation AI chip platform to be rolled out in 2026

By Thomson Reuters Jun 2, 2024 | 7:53 AM

TAIPEI (Reuters) -Nvidia Chief Executive Jensen Huang said on Sunday that the company’s next-generation artificial intelligence (AI) chip platform was called Rubin and would be rolled out in 2026.

The Rubin family of chips will include new graphics (GPU) and central processors (CPU) as well as networking chips, Huang said at National Taiwan University in Taipei as part of the Computex trade show.

However, Huang offered few details.

The new CPU will be called Versa and the new graphics chips that are used to power AI applications will bundle next generation high-bandwidth memory that is made by the likes of SK Hynix, Micron and Samsung.

Huang said the company now plans to release a new family of AI chips every year, accelerating its prior release schedule of roughly every two years.

Dominating roughly 80% of the market for AI chips, Nvidia stands in a unique position as both the largest enabler as well as beneficiary of surging AI development.

(Reporting by Max A Cherney and Ben Blanchard; Editing by Hugh Lawson and Ros Russell)