What's in the Box: Automatic ML Model Containerization

Speaker:
Clayton Davis, Head of Data Science, Modzy
Clayton Davis is the Head of Data Science at Modzy. He holds undergraduate and graduate degrees in Physics. Clayton has 15 years of experience developing solutions across the spectrum of Data Science from training deep learning neural nets, to building analytics for petabyte-level Spark clusters. At Modzy, he leads the development of model-agnostic insight and governance tools for data scientists, and oversees the development of open-source technology such as Chassis.ml.

Saumil Dave, Head of ML Engineering, Modzy
Saumil Dave is the Head of ML Engineering at Modzy and a core maintainer of chassis.ml, an open-source MLOps project. He leads Modzy’s ML engineering team in developing tools that make it easier and faster to get machine learning models into production. Saumil holds a Master of Science in Computer Science from the University of Southern California and a Bachelor of Science in Chemical Engineering from the University of California, Los Angeles.
Abstract:
This talk will include a deep dive on building machine learning (ML) models into container images to run in production for inference. Based on our experience setting up ML container builds for many customers, we’ll share a set of best practices for ensuring secure, multi-tenant image builds that avoid lock-in, and we’ll also cover some tooling (chassis.ml) and a standard (Open Model Interface (OMI)) to execute this process. Data scientists and developers will walk away with an understanding of the merits of a standard container specification that allows for interoperability, portability, and security for models to seamlessly be integrated into production applications.

Видео What's in the Box: Automatic ML Model Containerization канала Toronto Machine Learning Society (TMLS)