Kubernetes AI workloads Archives

Autoscaling AI Workloads on Kubernetes With KEDA and What it Means for Agentic Systems

KEDA can scale Kubernetes AI workloads on real demand signals such as queue depth, helping model-serving and agent workloads respond faster while reducing idle compute costs ...

Prometheus, kubernetes, CNCF Promotes Prometheus Container Monitoring

Open Source KServe AI Inference Platform Becomes CNCF Project

The CNCF adopts KServe to strengthen cloud-native AI inference on Kubernetes as platforms like Red Hat OpenShift AI expand model-as-a-service capabilities ...

Mike Vizard | November 13, 2025 | AI gateway, AI inference on Kubernetes, AI model registry, Cloud Native Computing Foundation, CNCF incubator, Edge AI deployment, KServe, KubeCon + CloudNativeCon 2025, Kubeflow, Kubernetes AI workloads, LLM serving on Kubernetes, Model-as-a-service, vLLM

kubernetes, network, logistics, security, Traefik Tigera container security Calico Red Hat Dynatrace

Google Extends Kubernetes Service to Safely Run Agentic AI Workloads

At KubeCon + CloudNativeCon North America 2025, Google unveiled major GKE upgrades — including an AI sandbox, inference gateway, pod snapshots, and 130,000-node clusters — to optimize and secure agentic AI workloads ...

Mike Vizard | November 13, 2025 | agentic AI, AI compute provisioning, AI infrastructure, AI security, AI Workloads, cloud native AI, GKE updates, Google AI platform, Google Cloud, Google Kubernetes Engine, KubeCon 2025, Kubernetes AI, Kubernetes AI workloads, Kubernetes conference, pod snapshots

GPU Resource Management for Kubernetes Workloads: From Monolithic Allocation to Intelligent Sharing

AI and ML workloads in Kubernetes are evolving fast—but traditional GPU allocation leads to massive waste and inefficiency. Learn how intelligent GPU allocation, leveraging technologies like MIG, MPS, and time-slicing, enables smarter, ...

Fitting Square Kubernetes Into the Round AI-Native Apps

Kubernetes tamed cloud-native workloads, but AI-native apps push its limits. Can it evolve for GPU-first, data-intensive AI — or is it time for new control planes? ...