Estimator.delete_endpoint does not delete the Model or Endpoint Configuration

[mvsusp]

Please fill out the form below.

System Information

• Framework (e.g. TensorFlow) / Algorithm (e.g. KMeans):
  Any Framework Container
• Python Version:
  2 and 3
• Python SDK Version:
  1.12

Describe the problem

Issue found by @andrewcking here #402

In SageMaker Hosting, the process to create an endpoint requires to create an model, an endpoint configuration, and an endpoint.

SageMaker Python SDK abstract these 3 layers for you. These are the lines where this process happens

        container_def = self.prepare_container_def(instance_type)
        self.name = self.name or name_from_image(container_def['Image'])
        self.sagemaker_session.create_model(self.name, self.role, container_def, vpc_config=self.vpc_config)
        production_variant = sagemaker.production_variant(self.name, instance_type, initial_instance_count)
        self.endpoint_name = endpoint_name or self.name
        self.sagemaker_session.endpoint_from_production_variants(self.endpoint_name, [production_variant], tags)

To be able to use Python SDK to create an endpoint with the same name, you will have to delete the model, the endpoint_config, and the endpoint. SageMaker Python SDK delete_endpoint() only deletes the endpoint, which is why the issue is happening.

Minimal repro / logs

Please provide any logs and a bare minimum reproducible test case, as this will be helpful to diagnose the problem. If including tracebacks, please include the full traceback. Large logs and files should be attached.

• Exact command to reproduce:

from sagemaker.pytorch import PyTorch

# create estimator
estimator = PyTorch(entry_point='train.py', 
                    role='SageMakerRole', 
                    framework_version='0.4.0', 
                    train_instance_count=1, 
                    train_instance_type='ml.c5.xlarge', 
                    source_dir='source', 
                    hyperparameters={'epochs': 6,})

# fit estimator
estimator.fit('s3://sagemaker-sample-data-us-west-2/spark/mnist/train/')

# deploy estimator (except it doesn't deploy your new estimator if a previously used endpoint name is specified)
estimator.deploy(instance_type='ml.c5.xlarge'', initial_instance_count=1)

# delete endpoint
estimator.delete_endpoint()

# deploy again
estimator.deploy(instance_type='ml.c5.xlarge'', initial_instance_count=1, endpoint_name=estimator.last_training_job.name)

[ChoiByungWook]

These features are being worked on in the following PRs:

• Add new APIs to clean up resources from predictor and transformer. #630
• Model linkage #638

The ability to delete endpoint configurations has been merged.

[chuyang-deng]

The change has been merged, waiting on release.