breaking: deprecate update_endpoint arg in deploy()

src/sagemaker/automl/automl.py

@@ -343,7 +343,6 @@ def deploy(
         endpoint_name=None,
         tags=None,
         wait=True,
-        update_endpoint=False,
         vpc_config=None,
         enable_network_isolation=False,
         model_kms_key=None,
@@ -372,11 +371,6 @@ def deploy(
                 specific endpoint.
             wait (bool): Whether the call should wait until the deployment of
                 model completes (default: True).
-            update_endpoint (bool): Flag to update the model in an existing
-                Amazon SageMaker endpoint. If True, this will deploy a new
-                EndpointConfig to an already existing endpoint and delete
-                resources corresponding to the previous EndpointConfig. If
-                False, a new endpoint will be created. Default: False
             vpc_config (dict): Specifies a VPC that your training jobs and hosted models have
                 access to. Contents include "SecurityGroupIds" and "Subnets".
             enable_network_isolation (bool): Isolates the training container. No inbound or
@@ -414,7 +408,6 @@ def deploy(
             endpoint_name=endpoint_name,
             tags=tags,
             wait=wait,
-            update_endpoint=update_endpoint,
         )
 
     def _check_problem_type_and_job_objective(self, problem_type, job_objective):

src/sagemaker/estimator.py

@@ -640,7 +640,6 @@ def deploy(
         accelerator_type=None,
         endpoint_name=None,
         use_compiled_model=False,
-        update_endpoint=False,
         wait=True,
         model_name=None,
         kms_key=None,
@@ -670,11 +669,6 @@ def deploy(
                 used.
             use_compiled_model (bool): Flag to select whether to use compiled
                 (optimized) model. Default: False.
-            update_endpoint (bool): Flag to update the model in an existing
-                Amazon SageMaker endpoint. If True, this will deploy a new
-                EndpointConfig to an already existing endpoint and delete
-                resources corresponding to the previous EndpointConfig. Default:
-                False
             wait (bool): Whether the call should wait until the deployment of
                 model completes (default: True).
             model_name (str): Name to use for creating an Amazon SageMaker
@@ -728,7 +722,6 @@ def deploy(
             initial_instance_count=initial_instance_count,
             accelerator_type=accelerator_type,
             endpoint_name=endpoint_name,
-            update_endpoint=update_endpoint,
             tags=tags or self.tags,
             wait=wait,
             kms_key=kms_key,

src/sagemaker/model.py

@@ -411,7 +411,6 @@ def deploy(
         instance_type,
         accelerator_type=None,
         endpoint_name=None,
-        update_endpoint=False,
         tags=None,
         kms_key=None,
         wait=True,
@@ -444,11 +443,6 @@ def deploy(
                 https://docs.aws.amazon.com/sagemaker/latest/dg/ei.html
             endpoint_name (str): The name of the endpoint to create (default:
                 None). If not specified, a unique endpoint name will be created.
-            update_endpoint (bool): Flag to update the model in an existing
-                Amazon SageMaker endpoint. If True, this will deploy a new
-                EndpointConfig to an already existing endpoint and delete
-                resources corresponding to the previous EndpointConfig. If
-                False, a new endpoint will be created. Default: False
             tags (List[dict[str, str]]): The list of tags to attach to this
                 specific endpoint.
             kms_key (str): The ARN of the KMS key that is used to encrypt the
@@ -497,29 +491,14 @@ def deploy(
         if data_capture_config is not None:
             data_capture_config_dict = data_capture_config._to_request_dict()
 
-        if update_endpoint:
-            endpoint_config_name = self.sagemaker_session.create_endpoint_config(
-                name=self.name,
-                model_name=self.name,
-                initial_instance_count=initial_instance_count,
-                instance_type=instance_type,
-                accelerator_type=accelerator_type,
-                tags=tags,
-                kms_key=kms_key,
-                data_capture_config_dict=data_capture_config_dict,
-            )
-            self.sagemaker_session.update_endpoint(
-                self.endpoint_name, endpoint_config_name, wait=wait
-            )
-        else:
-            self.sagemaker_session.endpoint_from_production_variants(
-                name=self.endpoint_name,
-                production_variants=[production_variant],
-                tags=tags,
-                kms_key=kms_key,
-                wait=wait,
-                data_capture_config_dict=data_capture_config_dict,
-            )
+        self.sagemaker_session.endpoint_from_production_variants(
+            name=self.endpoint_name,
+            production_variants=[production_variant],
+            tags=tags,
+            kms_key=kms_key,
+            wait=wait,
+            data_capture_config_dict=data_capture_config_dict,
+        )
 
         if self.predictor_cls:
             return self.predictor_cls(self.endpoint_name, self.sagemaker_session)

src/sagemaker/multidatamodel.py

@@ -144,7 +144,6 @@ def deploy(
         instance_type,
         accelerator_type=None,
         endpoint_name=None,
-        update_endpoint=False,
         tags=None,
         kms_key=None,
         wait=True,
@@ -179,11 +178,6 @@ def deploy(
                 https://docs.aws.amazon.com/sagemaker/latest/dg/ei.html
             endpoint_name (str): The name of the endpoint to create (default:
                 None). If not specified, a unique endpoint name will be created.
-            update_endpoint (bool): Flag to update the model in an existing
-                Amazon SageMaker endpoint. If True, this will deploy a new
-                EndpointConfig to an already existing endpoint and delete
-                resources corresponding to the previous EndpointConfig. If
-                False, a new endpoint will be created. Default: False
             tags (List[dict[str, str]]): The list of tags to attach to this
                 specific endpoint.
             kms_key (str): The ARN of the KMS key that is used to encrypt the
@@ -241,29 +235,14 @@ def deploy(
         if data_capture_config is not None:
             data_capture_config_dict = data_capture_config._to_request_dict()
 
-        if update_endpoint:
-            endpoint_config_name = self.sagemaker_session.create_endpoint_config(
-                name=self.name,
-                model_name=self.name,
-                initial_instance_count=initial_instance_count,
-                instance_type=instance_type,
-                accelerator_type=accelerator_type,
-                tags=tags,
-                kms_key=kms_key,
-                data_capture_config_dict=data_capture_config_dict,
-            )
-            self.sagemaker_session.update_endpoint(
-                self.endpoint_name, endpoint_config_name, wait=wait
-            )
-        else:
-            self.sagemaker_session.endpoint_from_production_variants(
-                name=self.endpoint_name,
-                production_variants=[production_variant],
-                tags=tags,
-                kms_key=kms_key,
-                wait=wait,
-                data_capture_config_dict=data_capture_config_dict,
-            )
+        self.sagemaker_session.endpoint_from_production_variants(
+            name=self.endpoint_name,
+            production_variants=[production_variant],
+            tags=tags,
+            kms_key=kms_key,
+            wait=wait,
+            data_capture_config_dict=data_capture_config_dict,
+        )
 
         if predictor:
             return predictor(self.endpoint_name, self.sagemaker_session)

src/sagemaker/tensorflow/model.py

@@ -201,7 +201,6 @@ def deploy(
         instance_type,
         accelerator_type=None,
         endpoint_name=None,
-        update_endpoint=False,
         tags=None,
         kms_key=None,
         wait=True,
@@ -217,7 +216,6 @@ def deploy(
             instance_type=instance_type,
             accelerator_type=accelerator_type,
             endpoint_name=endpoint_name,
-            update_endpoint=update_endpoint,
             tags=tags,
             kms_key=kms_key,
             wait=wait,

tests/integ/test_mxnet_train.py

@@ -247,43 +247,6 @@ def test_deploy_model_and_update_endpoint(
         assert new_config["ProductionVariants"][0]["InitialInstanceCount"] == 1
 
 
-def test_deploy_model_with_update_non_existing_endpoint(
-    mxnet_training_job,
-    sagemaker_session,
-    mxnet_full_version,
-    mxnet_full_py_version,
-    cpu_instance_type,
-    alternative_cpu_instance_type,
-):
-    endpoint_name = "test-mxnet-deploy-model-{}".format(sagemaker_timestamp())
-    expected_error_message = (
-        'Endpoint with name "{}" does not exist; '
-        "please use an existing endpoint name".format(endpoint_name)
-    )
-
-    with timeout_and_delete_endpoint_by_name(endpoint_name, sagemaker_session):
-        desc = sagemaker_session.sagemaker_client.describe_training_job(
-            TrainingJobName=mxnet_training_job
-        )
-        model_data = desc["ModelArtifacts"]["S3ModelArtifacts"]
-        script_path = os.path.join(DATA_DIR, "mxnet_mnist", "mnist.py")
-        model = MXNetModel(
-            model_data,
-            "SageMakerRole",
-            entry_point=script_path,
-            py_version=mxnet_full_py_version,
-            sagemaker_session=sagemaker_session,
-            framework_version=mxnet_full_version,
-        )
-        model.deploy(1, alternative_cpu_instance_type, endpoint_name=endpoint_name)
-        sagemaker_session.sagemaker_client.describe_endpoint(EndpointName=endpoint_name)
-
-        with pytest.raises(ValueError, message=expected_error_message):
-            model.deploy(
-                1, cpu_instance_type, update_endpoint=True, endpoint_name="non-existing-endpoint"
-            )
-
-
 @pytest.mark.canary_quick
 @pytest.mark.regional_testing
 @pytest.mark.skipif(

tests/unit/sagemaker/automl/test_auto_ml.py

@@ -563,7 +563,6 @@ def test_deploy_optional_args(candidate_estimator, sagemaker_session, candidate_
         endpoint_name=JOB_NAME,
         tags=TAGS,
         wait=False,
-        update_endpoint=True,
         vpc_config=VPC_CONFIG,
         enable_network_isolation=True,
         model_kms_key=OUTPUT_KMS_KEY,
@@ -591,7 +590,6 @@ def test_deploy_optional_args(candidate_estimator, sagemaker_session, candidate_
         endpoint_name=JOB_NAME,
         tags=TAGS,
         wait=False,
-        update_endpoint=True,
     )
 
 

tests/unit/sagemaker/model/test_deploy.py

@@ -266,69 +266,3 @@ def test_deploy_predictor_cls(production_variant, sagemaker_session):
     assert isinstance(predictor, sagemaker.predictor.Predictor)
     assert predictor.endpoint_name == endpoint_name
     assert predictor.sagemaker_session == sagemaker_session
-
-
-def test_deploy_update_endpoint(sagemaker_session):
-    model = Model(MODEL_IMAGE, MODEL_DATA, role=ROLE, sagemaker_session=sagemaker_session)
-    model.deploy(
-        instance_type=INSTANCE_TYPE, initial_instance_count=INSTANCE_COUNT, update_endpoint=True
-    )
-    sagemaker_session.create_endpoint_config.assert_called_with(
-        name=model.name,
-        model_name=model.name,
-        initial_instance_count=INSTANCE_COUNT,
-        instance_type=INSTANCE_TYPE,
-        accelerator_type=None,
-        tags=None,
-        kms_key=None,
-        data_capture_config_dict=None,
-    )
-    config_name = sagemaker_session.create_endpoint_config(
-        name=model.name,
-        model_name=model.name,
-        initial_instance_count=INSTANCE_COUNT,
-        instance_type=INSTANCE_TYPE,
-        accelerator_type=ACCELERATOR_TYPE,
-    )
-    sagemaker_session.update_endpoint.assert_called_with(model.name, config_name, wait=True)
-    sagemaker_session.create_endpoint.assert_not_called()
-
-
-def test_deploy_update_endpoint_optional_args(sagemaker_session):
-    endpoint_name = "endpoint-name"
-    tags = [{"Key": "Value"}]
-    kms_key = "foo"
-    data_capture_config = Mock()
-
-    model = Model(MODEL_IMAGE, MODEL_DATA, role=ROLE, sagemaker_session=sagemaker_session)
-    model.deploy(
-        instance_type=INSTANCE_TYPE,
-        initial_instance_count=INSTANCE_COUNT,
-        update_endpoint=True,
-        endpoint_name=endpoint_name,
-        accelerator_type=ACCELERATOR_TYPE,
-        tags=tags,
-        kms_key=kms_key,
-        wait=False,
-        data_capture_config=data_capture_config,
-    )
-    sagemaker_session.create_endpoint_config.assert_called_with(
-        name=model.name,
-        model_name=model.name,
-        initial_instance_count=INSTANCE_COUNT,
-        instance_type=INSTANCE_TYPE,
-        accelerator_type=ACCELERATOR_TYPE,
-        tags=tags,
-        kms_key=kms_key,
-        data_capture_config_dict=data_capture_config._to_request_dict(),
-    )
-    config_name = sagemaker_session.create_endpoint_config(
-        name=model.name,
-        model_name=model.name,
-        initial_instance_count=INSTANCE_COUNT,
-        instance_type=INSTANCE_TYPE,
-        accelerator_type=ACCELERATOR_TYPE,
-        wait=False,
-    )
-    sagemaker_session.update_endpoint.assert_called_with(endpoint_name, config_name, wait=False)
-    sagemaker_session.create_endpoint.assert_not_called()

tests/unit/test_estimator.py

@@ -2081,7 +2081,6 @@ def test_generic_to_deploy_kms(create_model, sagemaker_session):
         initial_instance_count=INSTANCE_COUNT,
         accelerator_type=None,
         endpoint_name=endpoint_name,
-        update_endpoint=False,
         tags=None,
         wait=True,
         kms_key=kms_key,
@@ -2190,29 +2189,6 @@ def test_generic_deploy_accelerator_type(sagemaker_session):
     assert args["production_variants"][0]["InstanceType"] == INSTANCE_TYPE
 
 
-def test_deploy_with_update_endpoint(sagemaker_session):
-    estimator = Estimator(
-        IMAGE_NAME,
-        ROLE,
-        INSTANCE_COUNT,
-        INSTANCE_TYPE,
-        output_path=OUTPUT_PATH,
-        sagemaker_session=sagemaker_session,
-    )
-    estimator.set_hyperparameters(**HYPERPARAMS)
-    estimator.fit({"train": "s3://bucket/training-prefix"})
-    endpoint_name = "endpoint-name"
-    estimator.deploy(
-        INSTANCE_COUNT, INSTANCE_TYPE, endpoint_name=endpoint_name, update_endpoint=True
-    )
-
-    update_endpoint_args = sagemaker_session.update_endpoint.call_args[0]
-    assert update_endpoint_args[0] == endpoint_name
-    assert update_endpoint_args[1].startWith(IMAGE_NAME)
-
-    sagemaker_session.create_endpoint.assert_not_called()
-
-
 def test_deploy_with_model_name(sagemaker_session):
     estimator = Estimator(
         IMAGE_NAME,