Alphabet’s Google is in talks with Marvell Technology to develop two new chips aimed at running AI models more efficiently.
One of the chips is a memory processing unit designed to work with Google’s tensor processing units (TPUs), and the other chip is a new TPU purpose-built to run AI models, the report said.
information We reported on Sunday that Google is pushing to make its TPU a viable alternative to Nvidia’s flagship GPU. TPU sales are a key driver of Google’s cloud revenue growth, as the company aims to show investors that its AI investments are paying dividends.
The companies aim to finalize the memory processing unit design as early as next year before moving into test production, according to the report.
The latest news comes after Google recently announced a deal with the Department of Defense will help Alphabet expand its government relationships as the U.S. moves to incorporate artificial intelligence across its operations to reduce costs and speed up administrative tasks.
The Alphabet Inc.-owned platform is negotiating an agreement with the Pentagon that would allow the Pentagon to deploy its Gemini AI model in classified environments, the Intelligencer reported Thursday.
