Production LLM Serving on Kubernetes: vLLM + KServe Stack
Deploy vLLM with KServe on Kubernetes: InferenceService CRD, KEDA autoscaling on queue depth, and distributed KV cache with LMCache for production inference.
keda
9 posts
Observability and Troubleshooting for KEDA
Scraping KEDA operator metrics, building Grafana dashboards for scaling events, and diagnosing common ScaledObject issues in production.
KEDA and Karpenter Together — Pod and Node Scaling Synergy
Combining KEDA's event-driven pod scaling with Karpenter's just-in-time node provisioning for a fully reactive, cost-efficient Kubernetes autoscaling stack.
Batch Processing with KEDA ScaledJobs
ScaledJob creates one Kubernetes Job per event, scales dynamically, and lets long-running batch workloads terminate cleanly.
HTTP-Based Autoscaling with the KEDA HTTP Add-on
How the KEDA HTTP Add-on intercepts traffic to scale HTTP workloads to zero, and when the Prometheus scaler is better.
Custom Metrics and Prometheus-Based Scaling with KEDA
Using KEDA's Prometheus scaler to drive autoscaling from any PromQL query — replacing Prometheus Adapter with a simpler, more flexible approach.
Message Queue Scaling with KEDA — Kafka and SQS
How KEDA's Kafka and SQS scalers calculate lag and queue depth, with TriggerAuthentication patterns and production edge cases.
Introduction to KEDA and Event-Driven Autoscaling
How KEDA extends Kubernetes HPA with 65+ scalers, scale-to-zero, and a two-phase architecture for event-driven pod autoscaling.
Agentic AI Workloads on Kubernetes
How kagent, Agent Sandbox, KEDA, and OPA/Kyverno form the production stack for agentic AI on Kubernetes.