KEDA 기반 Scale-to-Zero 설계로 GPU 비용 65% 절감
I Stopped Paying for Idle GPUs - Scale-to-Zero AI Inference on OKE with KEDA
I Stopped Paying for Idle GPUs - Scale-to-Zero AI Inference on OKE with KEDA
I built an open-source alternative to Microsoft's KAITO that works on ANY Kubernetes cluster
The Gamedev Server That Broke at 300 Concurrent Hunters and How We Fixed It
Production-Ready GPU Inference Autoscaling on EKS with Karpenter, KEDA, and Dragonfly
Code Story: Building a Custom Kubernetes Scheduler with Go 1.24, Scheduler Framework, and KEDA 2.15
War Story: Debugging a Kafka 3.7 Consumer Lag Issue in K8s 1.32 with KEDA 2.14 and Prometheus 2.50
Why Azure Container Apps for AI Workloads
Running Azure Functions in Docker: Why and How