nerdexam
Microsoft

DP-100 · Question #183

You train a machine learning model. You must deploy the model as a real-time inference service for testing. The service requires low CPU utilization and less than 48 MB of RAM. The compute target…

The correct answer is A. Azure Container Instance (ACI). Azure Container Instances (ACI) are suitable only for small models less than 1 GB in size. Use it for low-scale CPU-based workloads that require less than 48 GB of RAM. Note: Microsoft recommends using single-node Azure Kubernetes Service (AKS) clusters for dev- test of larger…

Train and deploy models

Question

You train a machine learning model. You must deploy the model as a real-time inference service for testing. The service requires low CPU utilization and less than 48 MB of RAM. The compute target for the deployed service must initialize automatically while minimizing cost and administrative overhead. Which compute target should you use?

Options

  • AAzure Container Instance (ACI)
  • Battached Azure Databricks cluster
  • CAzure Kubernetes Service (AKS) inference cluster
  • DAzure Machine Learning compute cluster

How the community answered

(48 responses)
  • A
    77% (37)
  • B
    4% (2)
  • C
    13% (6)
  • D
    6% (3)

Explanation

Azure Container Instances (ACI) are suitable only for small models less than 1 GB in size. Use it for low-scale CPU-based workloads that require less than 48 GB of RAM. Note: Microsoft recommends using single-node Azure Kubernetes Service (AKS) clusters for dev- test of larger models. https://docs.microsoft.com/id-id/azure/machine-learning/how-to-deploy-and-where

Topics

#Model Deployment#Real-time Inference#Azure Container Instance (ACI)#Compute Target Selection

Community Discussion

No community discussion yet for this question.

Sign up to join the discussion
Full DP-100 Practice