AWS launched EKS Auto Mode at re:Invent 2024 (GA: December 1, 2024), a cluster configuration mode that runs Karpenter as a fully managed, off-cluster service, automating node provisioning, AMI patchin…
According to the Cast AI 2025 Kubernetes Cost Benchmark, teams using Karpenter with partial spot configurations save an average of 59% on compute costs, while all-spot configurations save up to 77%. C…
According to the Cast AI 2026 State of Kubernetes Optimization report, which analyzed 23,000+ clusters, the median CPU utilization across autoscaled EKS clusters is 8%, with 69% of Kubernetes clusters…
Dynamic Resource Allocation (DRA) is now generally available in Kubernetes, replacing the integer-based device plugin API with a declarative API that enables fine-grained GPU scheduling for AI workloa…
AWS raised H200 GPU instance prices by 15% on January 4, 2026, the first GPU price increase in roughly two decades, while average GPU utilization across more than 23,000 Kubernetes clusters sits at ju…
Average GPU utilization in Kubernetes clusters sits at just 5%, according to the Cast AI 2026 State of Kubernetes Optimization Report, with AKS at 2%, EKS at 5%, and GKE at 6%. An idle H100 GPU on AWS…
GPU utilization across production Kubernetes clusters averages just 5%, yet half of GPU cloud providers surveyed by SemiAnalysis report being completely sold out of H100 and H200 capacity, according t…
Kubernetes nodes enter NotReady status when the kubelet fails to renew its Node Lease within 40 seconds, triggering automatic taints and pod evictions after 5 minutes by default, according to Cast AI.…
A Cast AI report finds 69% of Kubernetes clusters are CPU-overprovisioned in 2026, up from 40% in 2024, with average CPU utilization at 8%, and the company advocates for admission-time policies like R…
Graviton ARM instances are approximately 19% cheaper per vCPU than equivalent Intel x86 on-demand, and ARM nodes in Kubernetes clusters grew 3.5x faster than x86 between Q2 2024 and Q4 2025, now accou…
A credible Kubernetes cost optimization case study requires a documented 30-day baseline, multi-metric proof, and a named mechanism, according to Cast AI. The company reports that its customers across…
Average Kubernetes cluster CPU utilization sits at 8%, and a $100K/month compute budget has a reclaim potential of $46K to $64K, according to Cast AI, which developed a Kubernetes cost optimization RF…
Average CPU utilization across 23,000+ Kubernetes clusters sits at just 8%, with CPU overprovisioning rising 40% year-over-year to 69% of clusters, according to the Cast AI 2026 State of Kubernetes Op…
A monthly Kubernetes cost review with engineering and finance prevents the 30-to-60-day erosion of one-time optimization savings, according to Cast AI's 2026 State of Kubernetes Optimization Report co…
WEKA announced NeuralMesh 6 on July 21, calling it the most significant software release in its history, delivering native multi-tenancy, S3 access on NVMe, and Kubernetes-native operations in a singl…
A 15% anomaly spike on a $50,000/month Kubernetes cluster adds $7,500 per month, and undetected over a year that single misconfiguration costs $90,000, according to Cast AI data from 23,000+ productio…
The average Kubernetes cluster uses just 8% of the CPU it pays for, according to the Cast AI 2026 State of Kubernetes Optimization Report, highlighting the need for Kubernetes FinOps to close the gap …
Average GPU utilization in production Kubernetes clusters is just 5%, according to the Cast AI 2026 State of Kubernetes Optimization Report, meaning 95 cents of every GPU dollar goes to idle silicon. …
Average GPU utilization across tens of thousands of production Kubernetes clusters is just 5%, according to the Cast AI 2026 State of Kubernetes Optimization Report. Default Kubernetes scheduling uses…
GPU utilization averages just 5% across production Kubernetes clusters, according to the Cast AI 2026 State of Kubernetes Optimization Report, meaning 95% of provisioned GPU capacity is idle at any mo…