hardMultiple Select
PMLE Practice Question: Which TWO statements are true about canary…
Which TWO statements are true about canary deployments for Vertex AI endpoints?
⚠ Common exam trap
PMLE often tests the misconception that canary deployments require specific model types or the Model Registry; candidates may incorrectly believe that prebuilt frameworks cannot use traffic splitting or that the Model Registry is mandatory.
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
✓
You can roll back a canary by resetting traffic to 0% for the new version.
Option B is correct because in Vertex AI traffic splitting, a canary version is simply a DeployedModel receiving a percentage of prediction traffic; setting that version's traffic split to 0% (and returning 100% to the stable version) effectively rolls back the canary without undeploying it. Option C is correct because Vertex AI endpoints support traffic splitting where you assign each deployed model a percentage from 0 to 100, letting you gradually shift traffic from the existing version to the new version in controlled increments. Option A is wrong because canary/traffic splitting works with any deployed model on an endpoint, including AutoML and prebuilt-framework models, not only custom containers. Option D is wrong because traffic splitting operates on DeployedModels on an endpoint and does not require the model to be registered in Vertex AI Model Registry. Option E is wrong because traffic percentages are configurable at any time up to 100%, so a canary at 50% can be increased further.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Canary deployments are only supported for custom containers, not prebuilt frameworks.
Why it's wrong here
Canary deployment on Vertex AI endpoints works with any deployed Model, including prebuilt-framework models imported from Model Garden or AutoML, since the split is applied at the endpoint's DeployedModel level. Restricting it to custom containers confuses deployment packaging with traffic routing.
- ✓
You can roll back a canary by resetting traffic to 0% for the new version.
Why this is correct
Traffic splitting is reversible: setting the new version's split to 0% routes all requests back to the stable version, effectively rolling back the canary. This satisfies the rollback requirement without redeploying or deleting the endpoint.
- ✓
You can use traffic splitting to gradually shift 1-100% of traffic to a new version.
Why this is correct
Vertex AI endpoints support traffic splitting, letting you route any percentage from 1% to 100% to a new model version. This enables gradual canary progression, satisfying the requirement to shift traffic incrementally while monitoring the new version.
- ✗
Canary deployments require the use of Vertex AI Model Registry.
Why it's wrong here
Vertex AI canary deployments operate on DeployedModel resources within an endpoint; a model need not be registered in Vertex AI Model Registry first, as models can be uploaded and deployed directly. The registry is optional for versioning and lineage, not a prerequisite for traffic splitting.
- ✗
Once a canary receives 50% traffic, you cannot increase it further.
Why it's wrong here
Vertex AI allows the canary traffic split to be adjusted at any time, including raising it beyond 50%, up to 100% for full rollout. The 50% figure is simply a common midpoint, not a ceiling, so the stated restriction misrepresents the configurable trafficSplit percentage.
Go deeper
Related to this question
About these practice questions
One of 775 original PMLE 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 PMLE
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. You run the above command to deploy a new model version to an existing endpoint. After deployment, you observe that the endpoint's previous model version is still receiving 100% of traffic. What is the most likely reason for this?
medium- A.The new model is still in the 'creating' state and hasn't been activated.
- B.The model ID provided does not exist in the endpoint.
- ✓ C.The --traffic-split flag is specified incorrectly; it should use model IDs, not '0-100'.
- D.The min-replica-count is too high, preventing traffic splitting.
Why C: The traffic-split flag syntax is incorrect. The correct syntax for Vertex AI is --traffic-split=<model-id>=<percentage> for each model. Without correct model IDs, the flag is ignored, and no traffic split is applied, so the existing version continues to receive all traffic.
Variation 2. After deploying a new version of a model to a Vertex AI Endpoint, the team notices that predictions are still returning results from the old version. The deployment command used a traffic split of 100% to the new version. What is the most likely cause?
medium- A.The model artifact uploaded was identical to the old version.
- ✓ B.The traffic split was not properly updated; the endpoint is still routing 100% to the old version.
- C.The new model version failed health checks and was automatically rolled back.
- D.The prediction client is caching the old model response.
Why B: When deploying a model to a Vertex AI Endpoint, the traffic split must be explicitly applied to the deployed model via the deployedModels[].trafficSplit or the dedicated update command. If the split was not actually committed to the endpoint (e.g., the command targeted the wrong deployed model ID or the split was set on the model resource rather than the endpoint), the endpoint continues routing 100% to the old version despite the intent.
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.