[Python] Possibility to enable multi model endpoint with DeepAR on SageMaker

I am working with SageMaker and have a deployed separate real-time endpoints and models for DEV and PROD.

To save costs, I am trying to put both models behind the same endpoint.

While this worked for the AWS RandomCutForest, I am struggling to replicate the process for DeepAR models.

I get the following error:

ClientError: An error occurred (ValidationException) when calling the CreateModel operation: Your Ecr Image XXXX.amazonaws.com/forecasting-deepar:1 does not contain required com.amazonaws.sagemaker.capabilities.multi-models=true Docker label(s).


My understanding is, that the DeepAR model does not have the necessary capabilities. Does a possibility exist to adjust this or is there a workaround?

I have seen a similar question regarding the RandomCutForest model, , but this seems to be resolved.

Continue reading...