Compute requirements for batch deployment jobs in Watson Machine Learning

The compute configuration for a batch deployment refers to the CPU and memory size that is allocated for a job. Learn about the predefined hardware specifications for your batch deployments.

Programmatically, this information must be specified in the hardware_spec API parameter of the deployment payload or deployment jobs payload.

Compute configurations must be a reference to a predefined hardware specification. You can specify a hardware specification by name or ID with hardware_spec or hybrid_pipeline_hardware_specs (for AutoAI). You can access the list and details about the predefined hardware specifications through the watsonx.ai Python client or the Data and AI Common Core API.