GKE Articles

35 min read

DevOps•2026-04-01

Run real-time and async inference on the same infrastructure with GKE Inference Gateway

This post introduces GKE Inference Gateway, a unified platform on Google Kubernetes Engine for running both real-time and async AI inference workloads on shared GPU/TPU infrastructure.

74 min read

DevOps•2026-03-31

Uplevel your workload scaling performance with GKE active buffer

Google Kubernetes Engine (GKE) introduces active buffer, a preview feature that eliminates scale-out latency by maintaining pre-provisioned spare cluster capacity.

05 min read

DevOps•2026-03-25

DRA: A new era of Kubernetes device management with Dynamic Resource Allocation

This post introduces Dynamic Resource Allocation (DRA), a new Kubernetes-native framework for managing hardware accelerators like GPUs and TPUs at scale.

16 min read

DevOps•2026-03-24

The open platform for the AI era: GKE, agents, and OSS innovation at KubeCon EU 2026

Google announces a series of GKE and Kubernetes enhancements at KubeCon EU 2026, positioning Kubernetes as the premier platform for AI workloads and agentic AI.

Open Source

24 min read

DevOps•2026-03-24

Kubernetes as AI Infrastructure: Google Cloud, llm-d, and the CNCF

Google Cloud announces llm-d as an official CNCF Sandbox project, positioning Kubernetes as the foundation for large-scale AI inference infrastructure.

Open Source

23 min read

DevOps•2026-03-17

Introducing multi-cluster GKE Inference Gateway: Scale AI workloads around the world

Google announces the preview of multi-cluster GKE Inference Gateway for scalable AI/ML inference workloads across multiple GKE clusters and regions.

Developers & Practitioners

Networking

35 min read

DevOps•2026-03-05

Grow your own way: Introducing native support for custom metrics in GKE

GKE natively supports custom metrics for HPA, removing the need for complex adapter setups.

55 min read

Architecture•2026-03-04

The AI-native core: Highly resilient telco architecture using Google Kubernetes Engine

This post explores how Google Kubernetes Engine (GKE) serves as a high-performance foundation for modernizing telecommunications network infrastructure with AI-native capabilities.