GKE 1.37 adds native scale-to-zero, ending reliance on KEDA setups

rseroter · x · 2026-09-24

Google Cloud announced native scale-to-zero in GKE 1.37: sporadic workloads (batch processors, event-driven workers, dev environments) can scale fully to zero replicas, then restart quickly on GKE capacity buffers when demand returns. Compared to KEDA, GKE's managed approach removes extra operators and CRDs (KEDA fleets can exceed 10,000 lines of YAML) and internalizes the scaling signal path to cut cold-start latency. Framed as decoupling always-on infrastructure cost from workload readiness.

Original post →

More from Infra

Infra channel →