A processor is a package that contains online prediction logic, including model loading logic and request prediction logic. If the official processors of Elastic Algorithm Service (EAS) cannot meet the model deployment requirements, you can create a custom processor based on the processor development standard.
Develop custom processors
You can use the following programming languages to develop custom processors:
C or C++. For more information, see Develop custom processors by using C or C++.
Java. For more information, see Develop custom processors by using Java.
Python. For more information, see Develop custom processors by using Python.
Deploy a model service by using a custom processor
We recommend that you debug a custom processor before you use the processor to deploy a model service. You can deploy a model service in the Machine Learning Platform for AI (PAI) console or by using the EASCMD client.
Upload and deploy a model in the PAI console
Select Custom Processor for the Processor Type parameter when you deploy the model service. For more information, see Model service deployment by using the PAI console.
Deploy a model by using the EASCMD client
Set the resource field to the ID of the dedicated resource group that you purchased. For more information, see Run commands to use the EASCMD client.