Lambda ML Inference Quiz

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

Quiz covering Advanced Deployment

What you'll be asked

  1. What is the primary reason for using container images instead of ZIP files when deploying ML models to AWS Lambda?
  2. When deploying an ML model on Lambda, how can you mitigate the 'cold start' latency caused by loading large model weights into memory?
  3. You are hosting a model that requires significant CPU power for inference. Which Lambda configuration setting will most directly improve inference speed?
  4. If your inference code requires loading a model from an S3 bucket during initialization, where should this code be placed to optimize performance?
  5. You are deploying a custom ML model using a Docker image on Lambda. During the build process, you notice the image exceeds the 10 GB limit. Which strategy is most effective for reducing image size while maintaining inference capability?

Answers and explanations come after you submit.