Google TPU splits training, inference as CPU becomes next focus
As AI model training, inference, and AI agent workloads continue to grow, AI accelerators are increasingly being optimized for different tasks. Amin Vahdat, Google's senior vice president and chief technologist for AI and infrastructure, said at SEMICON Taiwan 2026 that if a specific workload reaches sufficient scale and investment in custom chips is economically viable, Google could develop additional dedicated chips for different computing needs.
Read original article ↗
Related Articles
Rho Invoicing customers can now accept credit card payments on invoices alongside ACH and wire, from the same account th
Google’s Gemini Spark can now manage your Google Photos library
Gemini Spark can edit and curate photo albums, create shared collections, turn photos into calendar events, and handle o
LG to host AI festival with Nvidia, Google, Amazon at Seoul research hub
LG will bring together its top technology executives with representatives from Nvidia, Google, Amazon and Microsoft at a
Acer bets on RTX, GoogleBook as on-site AI demand grows
Acer chairman and chief executive Jason Chen said artificial intelligence deployment is already underway, with enterpris