Pipeline Deployment

Organizations manage model deployments through pipelines.

Pipelines represent how data is submitted to your uploaded Machine Learning (ML) models. Pipelines allow you to:

• Submit information through an uploaded file or through the Pipeline’s Deployment URL.
• Have the Pipeline submit the information to one or more models in sequence.
• Once complete, output the result from the model(s).

Creating a pipeline follows these steps:

• Build Pipeline Steps: Set the model(s) used in the pipeline in the order of inference.
• Set Hardware Configuration: Allocate the hardware resources in the form of cpus, gpus, memory, replicas, etc.
• Deploy the Pipeline: Deploy the pipeline on the model’s targeted architecture in cloud, multi-cloud or edge environments.