#autoscaling

GPU resource management and cost optimization using Karpenter, KEDA, and DRA on EKS

2-Tier GPU autoscaling (KEDA·Karpenter), DRA compatibility, and operational lessons learned from large MoE model (GLM-5·Kimi K2.5) deployments for LLM serving

Node provisioning, scaling signals, readiness, and cost validation with Karpenter v1.13 and EKS Auto Mode

ROSA cluster installation demo - STS-based cluster creation, IAM role configuration, autoscaling setup, and admin access configuration guide