DP-100 Question #247: Real Exam Question with Answer & Explanation

Question

You use the Azure Machine Learning designer to create and run a training pipeline. You then create a real-time inference pipeline. You must deploy the real-time inference pipeline as a web service. What must you do before you deploy the real-time inference pipeline?

Options

• ARun the real-time inference pipeline.
• BCreate a batch inference pipeline.
• CClone the training pipeline.
• DCreate an Azure Machine Learning compute cluster.

Explanation

{"question_number": 9, "correct_answer": "D", "explanation": "Before deploying a real-time inference pipeline as a web service, an inference compute target must exist to host the deployed endpoint. For real-time web services in Azure ML, this is an AKS-based inference cluster. Without a suitable compute target, the Deploy option is unavailable. Running the inference pipeline (option A) is also a prerequisite-the pipeline must be run successfully at least once before the Deploy button becomes active-but the question identifies the compute infrastructure as the key prerequisite to create. Creating a batch inference pipeline or cloning the training pipeline are not required steps.", "generated_by": "claude-sonnet", "llm_judge_score": 4}

No community discussion yet for this question.