Implement generative AI solutions →hardMultiple ChoiceObjective-mapped

AI-102 Implement generative AI solutions Practice Question

Exhibit

Refer to the exhibit. {
  "type": "Microsoft.MachineLearningServices/workspaces/onlineEndpoints/deployments",
  "apiVersion": "2023-04-01-preview",
  "name": "deploy-gen-model",
  "location": "eastus",
  "properties": {
    "model": {
      "assetId": "/subscriptions/.../models/gen-model/versions/1"
    },
    "requestSettings": {
      "requestTimeout": "PT30S",
      "maxConcurrentRequestsPerInstance": 10
    },
    "environmentVariables": {
      "MODEL_CACHE_SIZE": "10"
    },
    "scaleSettings": {
      "scaleType": "Manual",
      "instanceCount": 2
    }
  }
}

Refer to the exhibit. You are deploying a generative AI model as an online endpoint in Azure Machine Learning. You receive complaints that the endpoint returns 503 errors during peak hours. What is the most likely cause?

⚠ Common exam trap

Microsoft often tests the distinction between HTTP status codes (503 vs. 408/504) to mislead candidates into confusing timeout-related errors with capacity-related errors.

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

✓

The manual scale setting with 2 instances may be insufficient for peak traffic.

503 errors during peak hours indicate that the endpoint is overwhelmed by the request volume. With manual scaling set to only 2 instances, the compute capacity is insufficient to handle the increased traffic, causing the service to reject requests. Azure Machine Learning online endpoints require sufficient instance count or autoscaling to absorb traffic spikes.

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 manual scale setting with 2 instances may be insufficient for peak traffic.
Why this is correct
Manual scaling does not automatically adjust; if traffic exceeds capacity, requests are rejected with 503.
✗
The request timeout of 30 seconds is too short.
Why it's wrong here
30 seconds is a standard timeout; longer timeouts may cause resource exhaustion, not 503.
✗
The environment variable MODEL_CACHE_SIZE is set too low.
Why it's wrong here
This may affect performance but not directly cause 503 errors; 503 is typically due to capacity.
✗
The model version is not specified correctly.
Why it's wrong here
The assetId correctly references a model version.

Go deeper

AI-102 Implement generative AI solutions Practice Question

Exhibit

Why each option matters

Option-by-option breakdown

Related to this question