Reducing Inference Latency for SageMaker Endpoints
Which THREE actions can help reduce the inference latency of a SageMaker endpoint? (Choose three.)
Quick Answer
This is a 'choose three' style question, and the answers work by attacking different portions of the total request time rather than competing with each other. Enabling data compression reduces the size of the payload traveling over the network for each inference request, and since total request latency includes network transfer time in addition to model computation time, shrinking the payload directly cuts that transfer portion of the latency, independent of anything happening inside the model itself. A separate, complementary lever is using a larger instance type with more CPU or GPU resources: SageMaker endpoints can be scaled vertically as well as horizontally, and more compute per instance means each individual inference request is processed faster, which reduces the computation portion of latency. Because these two levers act on different segments of the request lifecycle, data transfer versus actual model execution, they can be combined with other techniques without one diminishing the effect of the other, which is exactly why a well-designed latency-reduction strategy tends to include multiple approaches rather than one fix. The general pattern worth internalizing is to break total latency down into its component parts, network transfer, queueing, and compute, and match each proposed action to the specific segment it improves. When an exam question asks for multiple actions that reduce latency together, look for a combination that spans payload size, compute capacity, and possibly other stages, rather than three variations on the same single fix.
⚠ Common exam trap
The MLS-C01 exam often tests the distinction between improving throughput (horizontal scaling) versus reducing latency (vertical scaling or optimization), and candidates mistakenly assume that adding more instances will speed up individual requests.
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
✓
Use a larger instance type with more CPU/GPU
Using a larger instance type with more CPU or GPU resources directly increases the computational capacity available for inference. This reduces the time required to process each prediction request, thereby lowering inference latency. SageMaker endpoints scale horizontally and vertically, and vertical scaling (larger instances) is a straightforward way to improve per-request performance.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Use a larger instance type with more CPU/GPU
Why this is correct
More compute power reduces per-request latency.
- ✓
Enable SageMaker Batch Transform to process predictions offline
Why this is correct
Batch Transform is asynchronous and can handle large loads without affecting real-time latency.
- ✓
Enable data compression to reduce payload size
Why this is correct
Smaller payloads reduce network transfer time.
- ✗
Use a multi-model endpoint to share instances across models
Why it's wrong here
Multi-model endpoints optimize memory, not latency.
- ✗
Increase the number of instances in the endpoint
Why it's wrong here
More instances improve throughput but not per-request latency.
Go deeper
Related to this question
About these practice questions
One of 1,672 original MLS-C01 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
Same concept, more angles
2 more ways this is tested on MLS-C01
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. Which TWO actions can help reduce inference latency for a SageMaker endpoint?
medium- A.Switch to batch transform
- ✓ B.Use SageMaker Neo to optimize the model
- C.Use a larger instance type
- D.Enable SageMaker Endpoint Cache
- E.Use a multi-model endpoint
Why B: SageMaker Neo optimizes trained models for a specific target hardware platform by compiling the model graph, fusing operations, and applying quantization and pruning techniques. This reduces the model's memory footprint and computational requirements, directly decreasing inference latency at the endpoint. Option D, 'Enable SageMaker Endpoint Cache,' is not a real SageMaker feature; there is no managed endpoint cache service. Batch transform (A) is used for offline inference, not for reducing endpoint latency. Larger instance types (C) primarily increase throughput and may not improve per-request latency. Multi-model endpoints (E) reduce model loading overhead but do not directly affect inference latency.
Variation 2. Which TWO actions can reduce inference latency for a SageMaker real-time endpoint? (Choose 2.)
medium- ✓ A.Choose a larger instance type with more compute capacity.
- B.Add more instances behind the endpoint.
- C.Use batch transform instead.
- ✓ D.Compile the model using SageMaker Neo.
- E.Switch to asynchronous inference.
Why A: Choosing a larger instance type with more compute capacity (Option A) reduces inference latency because it provides more CPU/GPU and memory resources, enabling the model to process each request faster. This directly decreases the time per inference, which is the primary driver of latency for real-time endpoints.
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This MLS-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 MLS-C01 exam.