0PricingLogin
MLOps Academy · Lesson

The InferenceService Resource

Declare a model deployment in a single manifest.

Meet KServe

KServe turns a trained model into a production endpoint on Kubernetes. You describe what you want, and it handles serving, scaling, and routing for you. KServe is your serving layer. 🚀

One Resource to Rule Them

Instead of writing raw Deployments and Services by hand, you create a single custom resource. The InferenceService is the one object that defines your whole serving setup.

All lessons in this course

  1. The InferenceService Resource
  2. Scale to Zero and Back Up
  3. Write a Custom Predictor
  4. KServe vs Seldon Core
← Back to MLOps Academy