Demystifying MLOPs and Kubernetes

We had a discussion on MLOps yesterday, in the learning carnival. You can find the codebase used to in session here.

Description

Central thoughts:

  • ML model lifecycle.
  • ML model serving patterns & deployment strategies.
  • Serving a sentiment analysis model in "model-as-service" pattern using FastAPI & docker.
  • Load & Stress testing of the same model service, checking latency and TAT using JMeter.
  • Scale-up the same model to cater 10000+ users using Kubernetes and load-balancing.

Dependencies

Any operating system with docker installed, For kubernetes: any cloud based kubernetes service.

Authors

Contributors names and contact info

Sumit Tyagi @tyagi.py