Library / SDK
Inference & Serving
KServe
1Serverless 2model 3inference 4on 5Kubernetes 6clusters
the six Ws · specification
W1
Who
Maintained by the KServe community (CNCF).
W2
What
Serverless inference for models on Kubernetes.
W3
Where
Runs on a Kubernetes cluster you operate.
W4
When
When you need autoscaling model serving on Kubernetes.
W5
Why
Standard CRDs for deploying, scaling, and routing models.
W6
With
Kubernetes, Knative, and model artifacts.
W7
Watch
Community-governed (CNCF); open-source (Apache-2.0), self-hosted on your cluster; data stays in your environment.
alternatives