ChipsThe story, in brief
Google unveils chips for AI training and inference in latest shot at Nvidia
Google just built custom silicon to dethrone Nvidia. Here's why it matters for your AI stack.
The KeyNews take
Why it matters
Google's new dedicated AI training and inference chips with enhanced memory architecture represent a critical shift in the compute supply chain. This directly challenges Nvidia's dominance and gives enterprises an alternative for both model training and inference workloads.
The key facts
5 to knowGoogle unveiled dedicated TPU chips for AI training and inference
New chips feature enhanced static random access memory (SRAM) architecture
Move positions Google as direct competitor to Nvidia in AI compute
Chips address both training and inference use cases in single platform
Published April 22, 2026 on CNBC
Go to the source
CNBC Technologycnbc.com
Publisher excerpt: Google is packing ample amounts of static random access memory into a dedicated chip for running artificial intelligence models, following Nvidia's plans.