EKS ML Deployment Quiz

5 questions Pass: 70% +25 pts (50 with Pro)

Quiz covering Advanced Deployment

What you'll be asked

  1. Which AWS service is most commonly used to provide persistent storage for ML model artifacts when deploying to Amazon EKS?
  2. When deploying an ML model on EKS, which strategy allows you to shift traffic between different versions of your model without downtime?
  3. You need to automatically scale your ML inference pods based on custom GPU utilization metrics. Which Kubernetes component should you use?
  4. What is the primary benefit of using a 'Sidecar' container pattern for an ML model deployment on EKS?
  5. When configuring GPU-accelerated inference on EKS, what is the required step to ensure pods are scheduled only on nodes with available NVIDIA GPUs?

Answers and explanations come after you submit.