Taking deep learning models to production and doing so reliably is one of the next frontiers of MLOps. With the advent of Redis modules and the availability of C APIs for the major deep learning frameworks, it is now possible to turn Redis into a reliable runtime for deep learning workloads, providing a simple solution for a model serving microservice. RedisAI is shipped with several cool features such as support for multiple frameworks, CPU and GPU backend, auto batching, DAGing, and soon will be with automatic monitoring abilities. In this talk, we'll explore some of these features of RedisAI and see how easy it is to integrate MLflow and RedisAI to build an efficient productionization pipeline.
[Originally aired as part of the Data+AI Online Meetup ([ Ссылка ]) and Bay Area MLflow meetup]
**
* About Sherin, the speaker
*/
Sherin Thomas is a software engineer, deep learning consultant, author, and international speaker who is currently working at tensorwerk, a deep learning infrastructure company. He helps to build tools for an end-to-end deep learning pipeline such as RedisAI - a high performant deep learning runtime, Hangar, and Stockroom - version control for software 2.0. He is also an active contributor to deep learning ecosystem tools such as PyTorch, MLflow, etc. He is an author, speaker, and co-created fullstackengineering.ai, a deep learning mentorship platform. Databricks is proud to announce that Gartner has named us a Leader in both the 2021 Magic Quadrant for Cloud Database Management Systems and the 2021 Magic Quadrant for Data Science and Machine Learning Platforms. Download the reports here. [ Ссылка ]
![](https://s2.save4k.ru/pic/ZIqHGjiSff4/mqdefault.jpg)