easyMultiple ChoiceObjective-mapped
MLA-C01 Practice Question: Deploying a real-time inference endpoint for a…
A company is deploying a real-time inference endpoint for a natural language processing model using Amazon SageMaker. The model is a fine-tuned BERT variant. The endpoint has been running for two weeks with acceptable latency (average 200 ms). However, over the past 24 hours, the latency has increased to an average of 800 ms, and the number of simultaneous requests has doubled. The team expects traffic to continue to grow. The current endpoint configuration uses a single ml.m5.large instance. The model is loaded into memory once, and the inference framework is PyTorch. The team needs to maintain latency under 500 ms. Which course of action should the team take to address the latency increase while minimizing cost?
⚠ Common exam trap
Many exam-takers assume a larger single instance (Option B) is the simplest fix, but they overlook that concurrency scaling requires horizontal scaling to avoid queue buildup, not just vertical scaling.
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
✓
Enable automatic scaling for the endpoint with a target average latency of 500 ms and use multiple ml.m5.large instances.
The latency increase is caused by a doubling of simultaneous requests overwhelming a single ml.m5.large instance. Enabling automatic scaling with a target average latency of 500 ms allows SageMaker to add more ml.m5.large instances as traffic grows, distributing the load and keeping latency under the threshold. This approach minimizes cost by scaling only when needed, rather than over-provisioning a larger instance.
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 ml.c5.large instances because CPU-optimized instances provide better inference performance for NLP models.
Why it's wrong here
Incorrect: BERT models are often memory-intensive; c5 instances have less memory per vCPU and may not improve latency; also, this doesn't add scaling.
- ✗
Increase the instance size to ml.m5.xlarge and keep a single instance.
Why it's wrong here
Incorrect: A larger single instance may handle current load but does not scale for future growth and is a single point of failure.
- ✓
Enable automatic scaling for the endpoint with a target average latency of 500 ms and use multiple ml.m5.large instances.
Why this is correct
Correct: Auto scaling adds instances based on latency, distributing load and maintaining under 500 ms, and minimizes cost by scaling only when needed.
- ✗
Implement a multi-model endpoint with multiple ml.m5.large instances and use Amazon Elastic Inference (EI) accelerators.
Why it's wrong here
Incorrect: Multi-model endpoints are for serving multiple models, not for scaling a single model. EI can accelerate but not address scaling directly.
Go deeper
Related to this question
About these practice questions
This MLA-C01 question is part of Courseiva's 835-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.