Do machine learning models run within an AWS IoT Greengrass group or on an AWS IoT Greengrass core?

Question

According to the[ AWS IoT Greengrass developer guide](https://docs.aws.amazon.com/greengrass/v1/developerguide/deployments.html), you need to configure ML inference at the AWS IoT Greengrass group level. In [the sample at GitHub](https://github.com/aws-samples/aws-greengrass-ml-deployment-sample), I see that an AWS Lambda function and an ML model are exported to an AWS IoT Greengrass core.

Do ML models run within an AWS IoT Greengrass group or on an AWS IoT Greengrass core?

Accepted Answer

[AWS IoT Greengrass ML inferences](https://aws.amazon.com/greengrass/ml/) run on [AWS IoT Greengrass core](https://docs.aws.amazon.com/greengrass/v1/developerguide/gg-core.html) edge devices, not in the cloud. AWS IoT Greengrass ML inference configuration is done within the cloud at the AWS IoT Greengrass group level. Then, the ML inference is run on an AWS IoT Greengrass core edge device.

For more information, see [Setting up AWS IoT Greengrass core devices](https://docs.aws.amazon.com/greengrass/v2/developerguide/setting-up.html).

Do machine learning models run within an AWS IoT Greengrass group or on an AWS IoT Greengrass core?

Relevant content