Google launches TPU 8i and TPU 8t for agentic AI workloads
google unveiled two new tensor processing units: tpu 8i for fast inference and autonomous agents, and tpu 8t for training complex models with massive memory pools. these chips support multi-step reasoning and planning workflows. google states this infrastructure will bring responsive agentic ai to the masses.
Google introduced two specialized Tensor Processing Units designed for the agentic era. The TPU 8i prioritizes inference speed for autonomous agents requiring reasoning, planning, and multi-step execution, while the TPU 8t optimizes training by running complex models within a single, large memory pool. These chips integrate with Google's full-stack infrastructure to enable highly responsive agentic AI.