PMLE Practice Question: Collaborating Within and Across Teams to Manage Data and Models
An ML engineer has a model trained in Vertex AI and wants to deploy it to an endpoint with autoscaling and traffic splitting for canary testing. They have the model artifact stored in Vertex AI Model Registry with alias 'champion'. What is the correct sequence of steps?
⚠ Common exam trap
PMLE often tests the deployment sequence — candidates reverse the order (endpoint before model) or assume models can be deployed directly from GCS, missing the mandatory Model Registry upload step.
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
✓
Upload model to registry, create endpoint, then deploy model to endpoint with traffic split.
The correct sequence is: upload the model to Vertex AI Model Registry (creating a model resource with the 'champion' alias), create an endpoint, then deploy the model to the endpoint with traffic split for canary testing. The model must exist in the registry before it can be deployed, and the endpoint must exist before deployment.
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 model to registry, create endpoint, then deploy model to endpoint with traffic split.
Why this is correct
Deployment requires the model in the registry first, then an endpoint, then deploying that model to the endpoint where traffic splits are configured. This sequence satisfies the canary traffic-splitting constraint, since traffic allocation is set at deploy time on the endpoint, not during upload.
- ✗
Create endpoint, upload model to registry, then deploy model to endpoint with traffic split.
Why it's wrong here
Uploading the model again after it already exists in the registry with the 'champion' alias is redundant and can create a duplicate version rather than referencing the existing artefact. Registry upload is for registering new models; here the model is already registered, so deployment should reference the alias directly.
- ✗
Create endpoint, deploy model directly from Cloud Storage, then add traffic split.
Why it's wrong here
Deploying directly from Cloud Storage bypasses the Model Registry, so the 'champion' alias cannot be referenced and version tracking is lost. Direct GCS deployment suits quick one-off serving of an unregistered artefact, not alias-based canary deployment requiring registry-managed versions.
- ✗
Upload model to registry, then create endpoint and deploy in one command using gcloud ai endpoints deploy-model.
Why it's wrong here
The gcloud ai endpoints deploy-model command creates the endpoint and deploys in one step, but it cannot configure the canary traffic split across two model versions in that same invocation. Traffic splitting requires a separate update, so the single-command sequence omits the required split configuration.
Go deeper
Related to this question
About these practice questions
Courseiva writes every PMLE question from scratch — 775 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 and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Google Cloud exam blueprint
This PMLE practice question is part of Courseiva's free Google Cloud 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 PMLE exam.