Skills Application
Skills application
CompleteDesigning a cost-effective ML/AI platform
In this skills application, you will simulate dynamic auto-scaling for a machine learning inference workload using a real-world inspired request dataset. You will:
- Implement basic auto-scaling rules using Python.
- Calculate the cost of a fixed vs. dynamic scaling setup.
- Visualise how the number of active instances changes over time.
Important access information
Please set aside 30 uninterrupted minutesto complete the lab before opening it. Your lab attempt will expire after 30 minutes. While you are welcome to restart, please keep in mind that you are limited to amaximum of five attemptsat the labwithin 90 daysfrom your initial attempt.
Context
You are part of the ML infrastructure team at SnapCart, a mid-sized e-commerce platform. Your team manages the deployment of a computer vision model used to auto-tag products in customer-uploaded images.
This model is served behind an API and experiences variable traffic throughout the day.
To reduce cloud costs without compromising performance, you are tasked with implementing basic dynamic auto-scaling based on incoming request rates.
Success criteria
To complete the skills application, you must complete the following Skillable Lab.