k
keynews.ai
keynews.ai
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.

Reporting by CNBC Technology 1 min brief
Paper-cut illustration of an amber microchip with circuit paths extending into a row of data-center cabinets.
The infrastructure powering AI.AI illustration by KeyNews
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 know

  1. Google unveiled dedicated TPU chips for AI training and inference

  2. New chips feature enhanced static random access memory (SRAM) architecture

  3. Move positions Google as direct competitor to Nvidia in AI compute

  4. Chips address both training and inference use cases in single platform

  5. 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.
Read original report
Back to today's editionMore chips news

The wider picture

View all
Paper-cut illustration of an amber microchip with circuit paths extending into a row of data-center cabinets.
AI illustration by KeyNews
Chips01

Google Adds Cycle-Level Kernel Profiling to XProf

A developer-facing tooling improvement that directly enables better TPU utilization and kernel optimization. Practitioners building custom Pallas kernels can now see exactly where cycles are spent, shifting from guesswork to data-driven tuning.

InfoQ AI/ML
Paper-cut illustration of an amber microchip with circuit paths extending into a row of data-center cabinets.
AI illustration by KeyNews
Chips02

Civo unveils first of 40 planned edge data center sites across UK

Edge compute infrastructure is becoming critical for low-latency AI inference and agentic workloads. Civo's distributed network strategy reflects growing demand for regional AI compute capacity outside centralized cloud zones — a structural shift in how AI workloads are deployed.

ITPro
Paper-cut illustration of an amber microchip with circuit paths extending into a row of data-center cabinets.
AI illustration by KeyNews
Chips03

China reviews dependence on Broadcom switches in data centres

China is auditing its reliance on foreign networking hardware for AI data centers as part of a broader push to build domestic alternatives. This reshapes global compute buildout economics and chip supply chains at a moment when AI capacity is the competitive moat.

Financial Times Technology