PMLE Scaling Prototypes into ML Models Practice Question

You want to use Vertex AI JumpStart to quickly deploy a pre-built foundation model for text summarization. Which action is required?

⚠ Common exam trap

PMLE often tests the distinction between JumpStart's one-click Model Garden deployment and the manual custom-container or training-from-scratch paths, so candidates overthink and pick the container option.

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

✓

Select the model from Model Garden and deploy it to a Vertex AI endpoint

Vertex AI JumpStart provides pre-built foundation models in Model Garden that can be deployed directly to a Vertex AI endpoint with minimal configuration. Selecting the model from Model Garden and deploying it to an endpoint is the standard JumpStart workflow for getting a foundation model into production for tasks like text summarization. No training, containerization, or batch export is required because JumpStart handles the deployment plumbing.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✓
Select the model from Model Garden and deploy it to a Vertex AI endpoint
Why this is correct
JumpStart models are accessed through Model Garden, and deploying the selected foundation model to a Vertex AI endpoint is what provisions it for inference. This satisfies the stem's requirement to quickly deploy a pre-built summarisation model.
✗
Train the model from scratch using Vertex AI Training
Why it's wrong here
JumpStart provides pre-trained foundation models ready for deployment; training from scratch contradicts its purpose and wastes resources. Custom training is tempting when fine-tuning is needed, but JumpStart's value is avoiding that. The required action is selecting and deploying a model from the JumpStart catalogue.
✗
Export the model to a Cloud Storage bucket and use batch prediction
Why it's wrong here
Exporting to Cloud Storage suits custom models needing batch inference, not JumpStart deployment. JumpStart deploys models directly to an endpoint for online prediction. Export is tempting because it is a standard Vertex AI workflow, but it bypasses the managed deployment JumpStart provides.
✗
Build a custom Docker container with the model and deploy to Vertex AI
Why it's wrong here
JumpStart supplies deployable model containers and endpoints, so building a custom Docker image duplicates work it already performs. Custom containers suit bespoke models or preprocessing pipelines absent from the model garden, not pre-built foundation models offered through JumpStart's one-click deployment.

Go deeper

PMLE Scaling Prototypes into ML Models Practice Question

Why each option matters

Option-by-option breakdown

Related to this question