configure runtime
Last updated
Last updated
The configure runtime command configures a runtime job. It is used to deploy a runtime resource. In the notebook, you will be guided through a template form that will prompt you for various inputs, such as the runtime name, whether it is for Model Training or Model Serving, and the Python pip install requirements.
To create a runtime job:
Select New from the Runtime drop-down list. Specify a name for the runtime job in the Runtime Name field.
Select the type, which is either Model Training or Model Serving.
Select a pip install requirements file, if applicable.
If applicable, select a trained model name and version to make available within the runtime:
For Model Training, select datasets to make available within the runtime, if applicable.
For Model Serving, select a Python module file (.py), and select the function names within the file that are to be served as FastAPI endpoints for inference.
Click the Save Configuration button to save the runtime job.
