Exam AWS Certified Machine Learning Engineer - Associate MLA-C01 topic 1 question 110 discussion

Exam question from Amazon's AWS Certified Machine Learning Engineer - Associate MLA-C01

Question #: 110
Topic #: 1

[All AWS Certified Machine Learning Engineer - Associate MLA-C01 Questions]

An ML engineer has deployed an Amazon SageMaker model to a serverless endpoint in production. The model is invoked by the InvokeEndpoint API operation.

The model's latency in production is higher than the baseline latency in the test environment. The ML engineer thinks that the increase in latency is because of model startup time.

What should the ML engineer do to confirm or deny this hypothesis?

A. Schedule a SageMaker Model Monitor job. Observe metrics about model quality.
B. Schedule a SageMaker Model Monitor job with Amazon CloudWatch metrics enabled.
C. Enable Amazon CloudWatch metrics. Observe the ModelSetupTime metric in the SageMaker namespace.
D. Enable Amazon CloudWatch metrics. Observe the ModelLoadingWaitTime metric in the SageMaker namespace.

Show Suggested Answer

Suggested Answer: C 🗳️

by chris_spencer at March 12, 2025, 12:46 p.m.

Disclaimers:

- ExamTopics website is not related to, affiliated with, endorsed or authorized by Amazon.
- Trademarks, certification & product names are used for reference only and belong to Amazon.

Comments

Submit Cancel

snna4

Highly Voted 3 months, 3 weeks ago

Selected Answer: C

C. ModelSetupTime because we have single model. Not D, because it relates to Multi-Model Endpoint Model Loading Metrics see https://docs.aws.amazon.com/sagemaker/latest/dg/monitoring-cloudwatch.html for ModelSetupTime in "Endpoint Invocation Metrics" and ModelLoadingWaitTime in "Multi-Model Endpoint Model Loading Metrics"

upvoted 6 times

...

eesa

Highly Voted 4 months, 3 weeks ago

Selected Answer: C

C. Enable Amazon CloudWatch metrics. Observe the ModelSetupTime metric in the SageMaker namespace. ✅ Correct: This metric will show if model startup time is contributing to the latency. ✅ Directly confirms or denies the cold start hypothesis. ModelSetupTime The time it takes to launch new compute resources for a serverless endpoint. The time can vary depending on the model size, how long it takes to download the model, and the start-up time of the container. Units: Microseconds Valid statistics: Average, Min, Max, Sample Count, Percentiles https://docs.aws.amazon.com/sagemaker/latest/dg/monitoring-cloudwatch.html

upvoted 6 times

...

67495ef

Most Recent 1 month ago

Selected Answer: D

ModelSetupTime is not a valid CloudWatch metric in SageMaker for measuring serverless endpoint latency components. The relevant metric for startup time is ModelLoadingWaitTime.

upvoted 2 times

...

rebobe1958

1 month, 2 weeks ago

Selected Answer: C

C correct.

upvoted 4 times

...

postbox4me

1 month, 3 weeks ago

Selected Answer: D

This metric specifically measures how long the request waited for the model to load into memory before inference could begin. It is directly tied to cold start time and is the most accurate metric to confirm if startup time is causing latency.

upvoted 2 times

...

snna4

3 months, 3 weeks ago

Selected Answer: D

ModelSetupTime - The time it takes to launch new compute resources for a serverless endpoint. The time can vary depending on the model size, how long it takes to download the model, and the start-up time of the container. see https://docs.aws.amazon.com/sagemaker/latest/dg/monitoring-cloudwatch.html

upvoted 1 times