Answer-first summary for fast verification
Answer: Azure Container Instance (ACI)
Azure Container Instance (ACI) is the optimal choice because it aligns with all requirements: it automatically initializes compute targets, minimizes cost (as it's pay-per-second with no cluster management fees), and reduces administrative overhead (no need to manage clusters or nodes). ACI is specifically designed for small-scale, low-resource workloads like this testing scenario with low CPU utilization and minimal RAM (48 MB is well below ACI's 48 GB limit). While AKS supports real-time inference, it incurs higher costs and administrative overhead due to cluster management, making it less suitable for this testing-focused, cost-minimizing requirement. Azure Databricks and Azure ML compute clusters are not designed for real-time inference deployment and would introduce unnecessary complexity and cost.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
You are deploying a machine learning model as a real-time inference service for testing. The service has low CPU utilization and requires less than 48 MB of RAM. The compute target must initialize automatically, minimize cost, and reduce administrative overhead.
Which compute target should you use?
A
Azure Container Instance (ACI)
B
attached Azure Databricks cluster
C
Azure Kubernetes Service (AKS) inference cluster
D
Azure Machine Learning compute cluster
No comments yet.