mlserving is a framework for developing a realtime model-inference service.

Allows you to easily set-up an inference-endpoint for your ML Model.

mlserving emphasizes on high performance and allows easy integration with other model servers such as TensorFlow Serving

Docs can found here: https://mlserving.readthedocs.io/en/latest/

Data Scientists usually struggle with integrating their ML-models to production.

mlserving is here to make the development of model-servers easy for everyone.

$ pip install mlserving