AIARTICLE
AI Agents on GKE: Why a Session Is Not a Request, and How That Cuts Cluster Costs

Article · AI
- Reading
- 1 min
In short
A study using GitHub Copilot traces shows agents wait roughly 80% of session time. Google proposes hibernating those idle sessions to object storage with Agent Substrate and AX, cutting node bill by up to 40% on GKE.
Se você já colocou um agente de coding para rodar em cluster compartilhado, sabe o incômodo... [PLACEHOLDER]
Translated from the Brazilian Portuguese original · Read the original
Read also
AI
Google publishes codesign guide to extract the most from TPUs in AI models
Google released the tpu-codesign guide on Monday (11/16), with eight architecture principles to align LLMs and MoE models with the hardware of Ironwood TPUs and upcoming generations, with measured gains of up to 57% in training throughput.





