KFServing aims to solve production model serving use cases by providing performant, high abstraction interfaces for common ML frameworks like Tensorflow, XGBoost, ScikitLearn, PyTorch, and ONNX.
This charm encompasses the Kubernetes Python operator for KFServing (see CharmHub).
The KFServing operator is a Python script that wrap the latest released version of KFServing, providing lifecycle management and handling events such as install, upgrade, integrate, and remove.
To install KFServing, run:
juju deploy kfserving
For more information, see https://juju.is/docs