AWS Certified Machine Learning – Specialty — Question 77

A Machine Learning Specialist wants to determine the appropriate SageMakerVariantInvocationsPerInstance setting for an endpoint automatic scaling configuration. The Specialist has performed a load test on a single instance and determined that peak requests per second (RPS) without service degradation is about 20 RPS. As this is the first deployment, the Specialist intends to set the invocation safety factor to 0.5.
Based on the stated parameters and given that the invocations per instance setting is measured on a per-minute basis, what should the Specialist set as the
SageMakerVariantInvocationsPerInstance setting?

Answer options

• A. 10
• B. 30
• C. 600
• D. 2,400

Correct answer: C

Explanation

The correct answer is C, as the Specialist has determined that with a peak of 20 RPS and applying a safety factor of 0.5, the safe invocation rate becomes 10 RPS. Since this is measured per minute, multiplying 10 RPS by 60 seconds results in 600 invocations per minute. Options A, B, and D do not accurately reflect the calculations based on the given parameters.