[fix] Update dtype logic for huggingface backend for new containers

Author: siddvenk

src/sagemaker/djl_inference/model.py

@@ -854,11 +854,13 @@ def generate_serving_properties(self, serving_properties=None) -> Dict[str, str]
         if self.low_cpu_mem_usage:
             serving_properties["option.low_cpu_mem_usage"] = self.low_cpu_mem_usage
         # This is a workaround due to a bug in our built in handler for huggingface
-        # TODO: This needs to be fixed when new dlc is published
+        # TODO: Remove this logic whenever 0.20.0 image is out of service
         if (
             serving_properties["option.entryPoint"] == "djl_python.huggingface"
             and self.dtype
             and self.dtype != "auto"
+            and self.djl_version
+            and int(self.djl_version.split('.')[1]) < 21
         ):
             serving_properties["option.dtype"] = "auto"
             serving_properties.pop("option.load_in_8bit", None)

tests/unit/test_djl_inference.py

@@ -454,7 +454,7 @@ def test_generate_serving_properties_with_valid_configurations(
         "option.entryPoint": "djl_python.huggingface",
         "option.s3url": VALID_UNCOMPRESSED_MODEL_DATA,
         "option.tensor_parallel_degree": 1,
-        "option.dtype": "auto",
+        "option.dtype": "fp32",
         "option.device_id": 4,
         "option.device_map": "balanced",
     }