mediumMultiple Select
MLA-C01 Practice Question: Deploy a PyTorch model on SageMaker for real-time…
A company wants to deploy a PyTorch model on SageMaker for real-time inference. Which two steps are required? (Select TWO.)
⚠ Common exam trap
Candidates often confuse the optional Model Registry step (B) as mandatory for deployment, or mistakenly think uploading training data (A) is needed for inference, when in fact only the model artifact packaging (C) and endpoint configuration (D) are the two required steps for real-time inference on SageMaker.
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
✓
Package the model artifacts into a tar.gz file.
Option C is correct because SageMaker requires model artifacts to be packaged as a tar.gz archive (typically containing the model files and an inference script in a directory structure like model.tar.gz) before they can be deployed to a hosting container. Option D is correct because deploying a real-time inference endpoint requires creating an endpoint configuration that specifies the production variant, including the instance type (e.g., ml.m5.large) and the model to serve, which is then used to create the endpoint. Option A is incorrect because uploading training data to S3 is part of the training workflow, not a required step for deploying an already-trained PyTorch model for inference. Option B is incorrect because the SageMaker Model Registry is optional for governance and versioning; you can deploy a model directly without registering it. Option E is incorrect because a SageMaker Notebook instance is only a development tool and is not required to host a real-time inference endpoint.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Upload the training data to an S3 bucket.
Why it's wrong here
Training data in S3 is required for training jobs, not for deploying an existing PyTorch model to a real-time endpoint. Uploading training data would be a required step when running a SageMaker training job to produce model artefacts before deployment.
- ✗
Register the model in the SageMaker Model Registry.
Why it's wrong here
Registering in the Model Registry catalogues versions and approvals; it does not create the deployable endpoint configuration. Real-time inference requires a SageMaker model plus an endpoint configuration, so registration is optional governance. It would be correct when the scenario demands model versioning, approval workflows, or lineage tracking before production release.
- ✓
Package the model artifacts into a tar.gz file.
Why this is correct
SageMaker requires model artefacts in a compressed tar.gz archive in Amazon S3 before deployment; the inference container extracts and loads them. Packaging the PyTorch model this way satisfies the deployment prerequisite for hosting on an endpoint.
- ✓
Create a SageMaker endpoint configuration with the desired instance type.
Why this is correct
An endpoint configuration specifies the production variant's instance type, initial instance count and model name. SageMaker uses it to provision hosting resources, so creating one is mandatory before deploying the PyTorch model for real-time inference.
- ✗
Set up a SageMaker Notebook instance.
Why it's wrong here
A notebook instance is an optional development environment for authoring and testing code; deployment proceeds from model artefacts in S3 via a SageMaker model and endpoint configuration. A notebook instance would be the right choice when interactively developing or debugging training and inference code.
Quick reference
AWS S3 Storage Class Comparison
| Storage Class | Min Duration | Retrieval | Use Case |
|---|---|---|---|
| S3 Standard | None | Immediate | Frequently accessed data |
| S3 Standard-IA | 30 days | Immediate | Infrequent access, rapid retrieval |
| S3 One Zone-IA | 30 days | Immediate | Non-critical infrequent data |
| S3 Intelligent-Tiering | None | Immediate–hours | Unknown or changing access patterns |
| S3 Glacier Instant | 90 days | Milliseconds | Archive with instant retrieval |
| S3 Glacier Flexible | 90 days | Minutes–hours | Archive, flexible retrieval |
| S3 Glacier Deep Archive | 180 days | Hours | Long-term compliance archive |
Go deeper
Related to this question
About these practice questions
One of 665 original MLA-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 →
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.