gen-ai · k8s
Kube + LLM, made readable
Learn
All paths
Practical · model serving

Model serving on Kubernetes

You will know how to pick a model server, declare it with KServe, and deliver weights without baking them into your image.

Progress
0 / 3 lessons
Start
  1. 01
    Anatomy of a model server
    Why you almost never wrap PyTorch in Flask in production
  2. 02
    KServe and model server controllers
    Make 'deploy a model' a one-line declarative resource
  3. 03
    Model data: weights, formats, and Modelcars
    Where do 30 GB of weights actually live, and how do they get to the GPU?
Lock it in
Multi-tenant fine-tuned serving

20 tenants, each with their own LoRA adapter on the same 7B base.

Try the scenario