The use of ML models in production is a delicate process full of challenges. You can deploy a model through a REST API, on an edge device, or as an offline unit used for batch processing. You can build the deployment pipeline from scratch or use ML deployment frameworks.

In this video, you will learn about the different strategies to implement ML in production. I'll give a brief overview of the major ML deployment tools on the market (TensorFlow Serving, MLFlow Model, Seldon Deploy, KServe by Kubeflow). I also present BentoM – the focus of this miniseries – and describe its features in detail.

1st The Sound of AI Hackathon (register here!):
https://musikalkemist.github.io/thesoundofaihackathon/

Join the Sound Of AI Slack community:
https://valeriovelardo.com/the-sound-of-ai-community/

Interested in hiring me as a consultant/freelancer?
https://valeriovelardo.com/

Connect with Valerio on Linkedin:
https://www.linkedin.com/in/valeriovelardo

Follow Valerio on Facebook:
https://www.facebook.com/TheSoundOfAI

Follow Valerio on Twitter:
https://twitter.com/muziekalkemis​

Contents:

0:00 Introduction
0:36 ML implementation strategies
1:32 Basic ML implementation
3:27 Disadvantages of simple ML implementation
4:57 Overview of ML implementation tools
9:54 BentoML
2:00 PM What's next?

Please take the opportunity to connect and share this video with your friends and family if you find it helpful.