components batch_score_llm

Batch Score Large Language Models

batch_score_llm

Overview

Version: 1.1.7

View in Studio: https://ml.azure.com/registries/azureml/components/batch_score_llm/version/1.1.7

Inputs

Predefined arguments for parallel job:

https://learn.microsoft.com/en-us/azure/machine-learning/reference-yaml-job-parallel?source=recommendations#predefined-arguments-for-parallel-job

Name	Description	Type	Default	Optional	Enum
resume_from	The pipeline run id to resume from	string		True

PRS preview feature

Name	Description	Type	Default	Optional	Enum
async_mode	Whether to use PRS mini-batch streaming feature, which allows each PRS processor to process multiple mini-batches at a time.	boolean	False	True

Custom arguments

Name	Description	Type	Default	Optional	Enum
configuration_file	Configures the behavior of batch scoring.	uri_file		False
data_input_table	The data to be split and scored in parallel.	mltable		False

Outputs

Name	Description	Type
job_output_path		uri_file
mini_batch_results_output_directory		uri_folder