EasyDeepLearn

KServe (KFServing) — what does it provide?

medium

Answer

  • Kubernetes-native model serving.
  • Features: (1) autoscaling to zero (serverless).
  • (2) canary + traffic splitting.
  • (3) explainer / transformer sidecars.
  • (4) multi-framework via serving runtimes (Triton, TorchServe, ONNX).
  • (5) built-in metrics + tracing.
  • Built on Knative.
  • Standard for K8s-first orgs.
  • Alternatives: Seldon Core (feature-richer), Ray Serve, custom Deployment + Service.
Check yourself — multiple choice
  • Random
  • K8s-native serving: autoscale-to-zero (serverless) + canary + traffic split + explainer/transformer sidecars + multi-runtime (Triton/TorchServe/ONNX) + metrics/tracing; on Knative; alt Seldon/Ray Serve
  • Just K8s
  • Not real

KServe: K8s + autoscale-to-zero + canary + multi-runtime + Knative.

#serving#infrastructure

Practise MLOps & Data Quality

215 interview questions in this topic.

Related questions