I’ve re-trained a model and want to deployed to existing SageMaker endpoint, so that application don’t need to make any change on the SageMaker Endpoint.
I use PyTorchModel from sagemaker.pytorch
When calling pytorch_model.deploy(instance_type='ml.m5d.large', initial_instance_count=1, endpoint_name="some-existing-endpoint")
Get an Error
botocore.exceptions.ClientError: An error occurred (ValidationException) when calling the CreateEndpointConfig operation: Cannot create already existing endpoint configuration "arn:aws:sagemaker:us-east-1:xxxxxxxx:endpoint-config/some-existing-endpoint".
I have seen a suggestion using update_endpoint=True,
But seems like doesn’t have this options, with error:
TypeError: _create_sagemaker_model() got an unexpected keyword argument 'update_endpoint'
Anyone know how to deploy PyTorchModel to existing SageMaker endpoint?
2