easyMultiple Choice
MLA-C01 Practice Question: A company deploys a deep learning model to a…
A company deploys a deep learning model to a real-time SageMaker endpoint. After deployment, users report high inference latency. Which action is the MOST effective first step to reduce latency?
⚠ Common exam trap
Many exam-takers confuse latency reduction with throughput improvement, incorrectly choosing horizontal scaling (Option D) or vertical scaling (Option A) as the first step, when model optimization via compilation is the most direct and cost-effective approach.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Compile the model using SageMaker Neo to optimize for the target instance.
SageMaker Neo compiles the trained model to optimize it for the target instance hardware, reducing inference latency without requiring additional resources. This is the most effective first step because it directly addresses model execution efficiency, often yielding significant speedups for deep learning models.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Switch to a larger instance type with more GPU memory.
Why it's wrong here
A larger GPU instance may help, but the question asks for the most effective first step; latency often stems from model size or inference configuration, so optimisation or a smaller model is typically addressed first. Larger instances raise cost and may not fix the bottleneck.
- ✓
Compile the model using SageMaker Neo to optimize for the target instance.
Why this is correct
SageMaker Neo compiles the model into optimised machine code for the target instance's specific processor architecture, cutting inference latency on the existing endpoint. This directly addresses the reported latency without redeploying to different hardware, making it the most effective first step for the deployed deep learning model.
- ✗
Enable SageMaker Model Monitor to capture inference data.
Why it's wrong here
Model Monitor captures data and detects drift; it does not reduce inference latency. It is tempting because monitoring is a standard operational step, but it addresses data quality, not response time. Latency reduction requires changing the endpoint's compute or model configuration, not enabling data capture.
- ✗
Increase the number of instances in the endpoint to handle more requests.
Why it's wrong here
Adding instances scales throughput for concurrent requests, not per-request latency. It is tempting because horizontal scaling handles load, but if each inference is slow, more instances do not speed a single response. Latency stems from model or instance compute, addressed by instance type or optimisation.
Go deeper
Related to this question
About these practice questions
This MLA-C01 question is part of Courseiva's 665-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This MLA-C01 practice question is part of Courseiva's free Amazon Web Services certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the MLA-C01 exam.