easyMultiple Choice
MLA-C01 Practice Question: A data science team needs to deploy a PyTorch…
A data science team needs to deploy a PyTorch model for real-time inference with low latency. The model requires GPU acceleration. Which SageMaker endpoint configuration should they use?
⚠ Common exam trap
It's easy for candidates to confuse batch transform jobs or serverless endpoints with real-time inference, overlooking the explicit GPU requirement and the need for persistent, low-latency compute resources.
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
✓
Create a real-time endpoint using an ml.p3.2xlarge instance
Real-time SageMaker endpoints with GPU instances like ml.p3.2xlarge are specifically designed for low-latency, synchronous inference with GPU acceleration. PyTorch models requiring GPU must use instance types that support NVIDIA CUDA, and the ml.p3 family provides the necessary GPU compute for real-time predictions.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Create a multi-model endpoint using ml.m5.large instances
Why it's wrong here
Multi-model endpoints share a single GPU across multiple models, which introduces contention and unpredictable latency, failing the low-latency real-time requirement. This option is tempting because multi-model endpoints reduce cost by hosting several models on one instance, making them ideal for scenarios with infrequent or variable inference traffic where throughput can be traded for lower infrastructure expense.
- ✗
Create a serverless endpoint with memory set to 6144 MB
Why it's wrong here
Serverless inference does not provision GPU instances, so the PyTorch model cannot receive the acceleration it requires; it runs on CPU only. Serverless endpoints suit intermittent, bursty CPU workloads where cold-start latency is tolerable and traffic is unpredictable, which is the opposite of this continuous low-latency GPU requirement.
- ✗
Create a batch transform job using an ml.c5.xlarge instance
Why it's wrong here
Batch transform processes an entire dataset offline and cannot serve real-time requests; ml.c5.xlarge is a CPU instance lacking GPU acceleration. Batch transform is correct for scoring large stored datasets asynchronously, not for low-latency interactive inference.
- ✓
Create a real-time endpoint using an ml.p3.2xlarge instance
Why this is correct
An ml.p3.2xlarge instance provides NVIDIA V100 GPU acceleration, satisfying the stem's GPU requirement, and real-time endpoints deliver the low-latency synchronous inference the team needs. SageMaker real-time endpoints keep the model loaded and respond in milliseconds, unlike serverless or asynchronous options that cap resources or add queuing delay.
Go deeper
Related to this question
About these practice questions
Courseiva writes every MLA-C01 question from scratch — 665 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or 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.