Cloud TPU on Compute Engine generally available
Google Cloud's Tensor Processing Unit (TPU) is now generally available on Compute Engine, offering a unified experience for AI accelerators. Engineers can manage TPU VMs via the Compute Engine and MIG APIs, enabling custom OS configurations and boot disk settings. This integration supports diverse workloads from small-scale experiments to large-scale training and inference.
Features (1) ›
- Cloud TPU Generally available
Generally available : Compute Engine supports Google's custom-developed accelerator Tensor Processing Unit (TPU), providing a converged experience across AI accelerators on Google Cloud. You can use the Compute Engine instance API and managed instance group (MIG) API to create and manage TPU VMs. You can perform standard VM configurations such as using a custom OS or configure boot disk size. Compute Engine APIs support the creation and management of TPU slices across all consumption options, enabling small-scale experimentation and large-scale training and inference workloads. For more inform
https://docs.cloud.google.com/release-notes#June_01_2026
Related releases
- Google Cloud VPC: General Availability for Resolve subnet mask Google Cloud release notes ·
- GKE Optimizations Reduce AI Agent Compute Costs Up To 75% Google Cloud Blog ·
- Cloud SDK 578.0.0: Database Migration default change, AlloyDB backup DR GA, BigQuery improvements Google Cloud release notes ·
- Compute Engine C4D Instances Increase Hyperdisk Throughput Google Cloud release notes ·
- Compute Engine Managed Workload Identities GA Google Cloud release notes ·
- Compute Engine Hyperdisk Balanced Storage IOPS Increased Google Cloud release notes ·