Improve debuggability during model load and inference failures

[namannandan]

Describe the feature you'd like
Enable logging errors with traceback during model load and inference to help with debugging.

Current implementation:

sagemaker-pytorch-inference-toolkit/src/sagemaker_inference/transformer.py

Lines 159 to 168 in c7365b9

	except Exception as e: # pylint: disable=broad-except
	trace = traceback.format_exc()
	if isinstance(e, BaseInferenceToolkitError):
	return self.handle_error(context, e, trace)
	else:
	return self.handle_error(
	context,
	GenericInferenceToolkitError(http_client.INTERNAL_SERVER_ERROR, str(e)),
	trace,
	)

How would this feature be used? Please describe.
Errors during model loading and inference will be logged.

Describe alternatives you've considered
N/A

Additional context
This is useful in scenarios where there's no direct access to an endpoint where a model is deployed, for ex: Sagemaker Endpoint, where we only have access to logs.