azureml-contrib-pipeline-steps 1.8.0

Azure Machine Learning Parallel Run Step

## Note As Batch Inference has been fully released, the project has moved to [azureml-pipeline-steps](https://pypi.org/project/azureml-pipeline-steps/). Please refer to the release notes.

# Azure Machine Learning Batch Inference

Azure Machine Learning Batch Inference targets large inference jobs that are not time-sensitive. Batch Inference provides cost-effective inference compute scaling, with unparalleled throughput for asynchronous applications. It is optimized for high-throughput, fire-and-forget inference over large collections of data.

# Getting Started with Batch Inference Public Preview

Batch inference public preview offers a platform in which to do large inference or generic parallel map-style operations. Please visit [Azure Machine Learning Notebooks](https://github.com/Azure/MachineLearningNotebooks) to find tutorials on how to leverage this service.