[{"data":1,"prerenderedAt":36},["ShallowReactive",2],{"blog-tag-en-ai":3},[4,16,28],{"path":5,"title":6,"description":7,"date":8,"tags":9},"\u002Fblog\u002Fen\u002Fai-platform-kubernetes-convergence-2026","66% of AI-Driven Companies Choose Kubernetes — Why AI Infrastructure Converges on K8s","CNCF's 2026 survey shows 66% of GenAI organizations run on Kubernetes. From GPU scheduling to multi-tenancy and cost optimization — here's why K8s has become the de facto AI platform, and how managed K8s can cut your build time to zero.","2026-07-10",[10,11,12,13,14,15],"kubernetes","ai","platform-engineering","mlops","k3s","gpu",{"path":17,"title":18,"description":19,"date":20,"tags":21},"\u002Fblog\u002Fen\u002Fproxmox-gpu-passthrough-ai-workloads","Proxmox GPU Passthrough: Configuring for AI\u002FML Workloads","Complete guide to NVIDIA GPU passthrough on Proxmox VE for AI\u002FML workloads, covering IOMMU, VFIO configuration, and running Ollama and vLLM inference.","2026-05-27",[22,15,23,11,24,25,26,27],"proxmox","passthrough","machine-learning","nvidia","vfio","iommu",{"path":29,"title":30,"description":31,"date":32,"tags":33},"\u002Fblog\u002Fen\u002Fkubernetes-ai-gpu-cost-optimization-dra","Satisfied with 20% GPU Utilization? Master Dynamic Resource Management for 50-70% AI Infrastructure Cost Reduction with Kubernetes","Break free from the current state of only 20-30% GPU utilization. Learn the latest 2026 techniques to achieve 50-70% AI infrastructure cost reduction through dynamic resource management with Kubernetes Dynamic Resource Allocation.","2026-05-26",[10,11,15,34,35],"dra","cost-optimization",1792488947336]