Merge branch 'master' into master

Author: chuyang-deng

src/sagemaker/local/local_session.py

@@ -343,7 +343,6 @@ def invoke_endpoint(
         Accept=None,
         CustomAttributes=None,
         TargetModel=None,
-        TargetVariant=None,
     ):
         """
 
@@ -371,9 +370,6 @@ def invoke_endpoint(
         if TargetModel is not None:
             headers["X-Amzn-SageMaker-Target-Model"] = TargetModel
 
-        if TargetVariant is not None:
-            headers["X-Amzn-SageMaker-Target-Variant"] = TargetVariant
-
         r = self.http.request("POST", url, body=Body, preload_content=False, headers=headers)
 
         return {"Body": r, "ContentType": Accept}

src/sagemaker/predictor.py

@@ -83,7 +83,7 @@ def __init__(
         self._endpoint_config_name = self._get_endpoint_config_name()
         self._model_names = self._get_model_names()
 
-    def predict(self, data, initial_args=None, target_model=None, target_variant=None):
+    def predict(self, data, initial_args=None, target_model=None):
         """Return the inference from the specified endpoint.
 
         Args:
@@ -98,9 +98,6 @@ def predict(self, data, initial_args=None, target_model=None, target_variant=Non
             target_model (str): S3 model artifact path to run an inference request on,
                 in case of a multi model endpoint. Does not apply to endpoints hosting
                 single model (Default: None)
-            target_variant (str): The name of the production variant to run an inference
-            request on (Default: None). Note that the ProductionVariant identifies the model
-            you want to host and the resources you want to deploy for hosting it.
 
         Returns:
             object: Inference for the given input. If a deserializer was specified when creating
@@ -109,7 +106,7 @@ def predict(self, data, initial_args=None, target_model=None, target_variant=Non
                 as is.
         """
 
-        request_args = self._create_request_args(data, initial_args, target_model, target_variant)
+        request_args = self._create_request_args(data, initial_args, target_model)
         response = self.sagemaker_session.sagemaker_runtime_client.invoke_endpoint(**request_args)
         return self._handle_response(response)
 
@@ -126,13 +123,12 @@ def _handle_response(self, response):
         response_body.close()
         return data
 
-    def _create_request_args(self, data, initial_args=None, target_model=None, target_variant=None):
+    def _create_request_args(self, data, initial_args=None, target_model=None):
         """
         Args:
             data:
             initial_args:
             target_model:
-            target_variant:
         """
         args = dict(initial_args) if initial_args else {}
 
@@ -148,9 +144,6 @@ def _create_request_args(self, data, initial_args=None, target_model=None, targe
         if target_model:
             args["TargetModel"] = target_model
 
-        if target_variant:
-            args["TargetVariant"] = target_variant
-
         if self.serializer is not None:
             data = self.serializer(data)