Google Launches TPU 8tx and TPU 8i Max Chips to Reduce Nvidia Reliance
Google introduces two specialized tensor processing units designed for confidential inference and large-model inference, expanding its in-house chip portfolio.
Google introduces two specialized tensor processing units designed for confidential inference and large-model inference, expanding its in-house chip portfolio.
Google's prototype space data center, carrying four TPUs, successfully ran inference workloads at 1 kW power generation after launching on SpaceX Falcon 9 in late October.