Google TPU splits training, inference as CPU becomes next focus

DIGITIMESSeptember 4, 2026en

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.

This is a short summary published by AI Global Wire. The full article is owned and hosted by DIGITIMES — open it there to read it in full.

• Google
• Agenter