The answer is a target architecture mismatch between the SageMaker Neo compilation step and the endpoint instance type. SageMaker Neo compiles a model into an optimized binary specifically for a declared target device architecture, such as ARM, x86, or a GPU accelerator. When you deploy that compiled model to a SageMaker endpoint, the underlying instance must have a CPU or accelerator that matches that exact architecture; otherwise, the Neo-optimized runtime cannot interpret the binary, causing the "RuntimeError: Unable to load model." On the AWS Certified Machine Learning Engineer Associate MLA-C01 exam, this tests your understanding that Neo compilation is not a one-size-fits-all optimization—it is hardware-specific. A common trap is assuming any instance can run a Neo-compiled model, or forgetting to specify the correct target_device_family in the compilation job. To remember: think of Neo as a key cut for a specific lock—the endpoint instance is the lock, and if the key doesn't match, the door won't open.
MLA-C01 Deployment and Orchestration of ML Workflows Practice Question
This MLA-C01 practice question tests your understanding of deployment and orchestration of ml workflows. The scenario asks you to isolate a root cause — eliminate options that address a different problem before choosing. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
A team uses SageMaker Neo to compile a model for deployment on a target device. After compilation, they deploy the compiled model to a SageMaker endpoint using the Neo-optimized container. The endpoint fails to start with error "RuntimeError: Unable to load model". What could be the issue?
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
The target device architecture during compilation does not match the endpoint instance architecture.
Option D is correct because SageMaker Neo compiles a model for a specific target architecture (e.g., ARM, x86, GPU). When deploying the compiled model to a SageMaker endpoint, the endpoint instance type must have a CPU or accelerator architecture that matches the target device specified during compilation. If they do not match, the Neo-optimized runtime cannot load the compiled binary, resulting in a 'RuntimeError: Unable to load model'.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
✗
The compiled model was not uploaded to the correct S3 path.
Why it's wrong here
Incorrect path would cause a file not found error.
✗
The Neo compilation job failed silently.
Why it's wrong here
A failed compilation would produce an error during compilation, not at deployment.
✗
The endpoint instance type does not support Neo.
Why it's wrong here
Neo supports many instance types; unsupported types would cause a different error.
✓
The target device architecture during compilation does not match the endpoint instance architecture.
Why this is correct
Neo models are compiled for specific architectures; mismatch causes load failure.
Related concept
Read the scenario before looking for a memorised answer.
Common exam traps
Common exam trap: answer the scenario, not the keyword
AWS often tests the misconception that Neo compilation is a generic optimization that works on any endpoint instance, when in fact the target architecture must exactly match the deployment instance's hardware.
Detailed technical explanation
How to think about this question
SageMaker Neo uses Apache TVM to compile a model into a lightweight, hardware-specific binary. The compilation target is specified via the 'TargetDevice' or 'TargetPlatform' parameter, which defines the instruction set (e.g., 'ml_c5' for Intel Xeon, 'lambda' for ARM). The Neo-optimized container includes a TVM runtime that loads the compiled binary; if the runtime detects a mismatch between the compiled binary's target architecture and the actual CPU/GPU features of the endpoint instance, it throws a load error. This is a common pitfall when teams compile for a GPU target (e.g., 'ml_p2') but deploy on a CPU-only instance (e.g., 'ml_c5').
KKey Concepts to Remember
Read the scenario before looking for a memorised answer.
Find the constraint that changes the correct option.
Eliminate answers that are true in general but not in this case.
TExam Day Tips
→Watch for words such as best, first, most likely and least administrative effort.
→Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
A media company stores terabytes of video archives that are accessed once a year for audit purposes. Moving these objects to a cold storage tier (Azure Archive, S3 Glacier, or Google Nearline) costs a fraction of hot storage. Questions like this test whether you understand storage tiers, access frequency tradeoffs, and retrieval latency requirements.
What to study next
Got this wrong? Here's your next step.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
Deployment and Orchestration of ML Workflows — This question tests Deployment and Orchestration of ML Workflows — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: The target device architecture during compilation does not match the endpoint instance architecture. — Option D is correct because SageMaker Neo compiles a model for a specific target architecture (e.g., ARM, x86, GPU). When deploying the compiled model to a SageMaker endpoint, the endpoint instance type must have a CPU or accelerator architecture that matches the target device specified during compilation. If they do not match, the Neo-optimized runtime cannot load the compiled binary, resulting in a 'RuntimeError: Unable to load model'.
What should I do if I get this MLA-C01 question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
What is the key concept behind this question?
Read the scenario before looking for a memorised answer.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
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.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.