Explore Topics Authors

Topic

Autoscaling

1 story

Autoscaling inference with KEDA and custom metrics

Scale on queue depth, not CPU. Your wallet will thank you.

Jun 101 min909Kubernetes

Popular topics

ML Inference7 Kubernetes3 GPU3 Observability3 Cost Optimization3 Security2 LLMOps2 Networking2

Top authors

TBTom Becker377 views · 2 posts
CRCarlos Ruiz364 views · 2 posts
AKAisha Khan306 views · 2 posts
DODaniel Okoro217 views · 2 posts
MLMei Lin182 views · 2 posts

See all authors

Share what you know

Write for KubeInfer. Every story is reviewed by an editor before it goes live.

Become an author

KubeInfer

Engineering stories on running machine-learning inference at scale — Kubernetes, GPUs, autoscaling, and the economics of serving models.

Read

Explore Topics Authors

Write

Become an author Author studio Guidelines

Account

Sign in Settings

© 2026 KubeInfer. A technical publishing platform.

Built with Next.js, Prisma & PostgreSQL.