DP-100 Question #244: Real Exam Question with Answer & Explanation

Question

You create and register a model in an Azure Machine Learning workspace. You must use the Azure Machine Learning SDK to implement a batch inference pipeline that uses a ParallelRunStep to score input data using the model. You must specify a value for the ParallelRunConfig compute_target setting of the pipeline step. You need to create the compute target. Which class should you use?

Options

• ABatchCompute
• BAdlaCompute
• DAksCompute

Explanation

{"question_number": 6, "correct_answer": "C (AmlCompute)", "explanation": "ParallelRunStep requires an AmlCompute cluster (Azure Machine Learning managed compute) as its compute_target. AmlCompute clusters are designed for scalable, distributed batch workloads such as batch inference. BatchCompute links to Azure Batch pools, which is a different service not used by ParallelRunStep. AdlaCompute links to Azure Data Lake Analytics, a SQL-based analytics service that cannot run Python scoring scripts. AksCompute is an Azure Kubernetes Service cluster used for real-time online inference endpoints, not batch scoring pipelines. Note: Option C was not fully displayed in the choices but is the correct class.", "generated_by": "claude-sonnet", "llm_judge_score": 4}

No community discussion yet for this question.