simplify and refactor djl model for latest container releases

Author: siddvenk

src/sagemaker/djl_inference/__init__.py

@@ -13,8 +13,5 @@
 """Placeholder docstring"""
 from __future__ import absolute_import
 
-from sagemaker.djl_inference.model import DJLPredictor  # noqa: F401
+from sagemaker.djl_inference.djl_predictor import DJLPredictor  # noqa: F401
 from sagemaker.djl_inference.model import DJLModel  # noqa: F401
-from sagemaker.djl_inference.model import DeepSpeedModel  # noqa: F401
-from sagemaker.djl_inference.model import HuggingFaceAccelerateModel  # noqa: F401
-from sagemaker.djl_inference.model import FasterTransformerModel  # noqa: F401

src/sagemaker/djl_inference/defaults.py

@@ -0,0 +1,44 @@
+from sagemaker.predictor import Predictor
+from sagemaker import Session
+from sagemaker.serializers import BaseSerializer, JSONSerializer
+from sagemaker.deserializers import BaseDeserializer, JSONDeserializer
+
+
+class DJLPredictor(Predictor):
+    """A Predictor for inference against DJL Model Endpoints.
+
+    This is able to serialize Python lists, dictionaries, and numpy arrays to
+    multidimensional tensors for DJL inference.
+    """
+
+    def __init__(
+        self,
+        endpoint_name: str,
+        sagemaker_session: Session = None,
+        serializer: BaseSerializer = JSONSerializer(),
+        deserializer: BaseDeserializer = JSONDeserializer(),
+        component_name=None,
+    ):
+        """Initialize a ``DJLPredictor``
+
+        Args:
+            endpoint_name (str): The name of the endpoint to perform inference
+                on.
+            sagemaker_session (sagemaker.session.Session): Session object that
+                manages interactions with Amazon SageMaker APIs and any other
+                AWS services needed. If not specified, the estimator creates one
+                using the default AWS configuration chain.
+            serializer (sagemaker.serializers.BaseSerializer): Optional. Default
+                serializes input data to json format.
+            deserializer (sagemaker.deserializers.BaseDeserializer): Optional.
+                Default parses the response from json format to dictionary.
+            component_name (str): Optional. Name of the Amazon SageMaker inference
+                component corresponding the predictor.
+        """
+        super(DJLPredictor, self).__init__(
+            endpoint_name,
+            sagemaker_session,
+            serializer=serializer,
+            deserializer=deserializer,
+            component_name=component_name,
+        )