Example code to use sagemaker-spark for our own model

Please fill out the form below.

### System Information
- **Spark or PySpark**: PySpark
- **SDK Version**: Any or most recent
- **Spark Version**: Any or most recent
- **Algorithm (e.g. KMeans)**: Any - in our case, PyTorch models

### Describe the problem
Is there example code of sagemaker-spark to perform inference on a spark dataframe using our own ML model using a GPU inference endpoint spun up by sagemaker? In our case we are bringing over our own PyTorch model.

### Minimal repo / logs
Please provide any logs and a bare minimum reproducible test case, as this will be helpful to diagnose the problem. If including tracebacks, please include the full traceback. Large logs and files should be attached.
N/A
- **Exact command to reproduce**:
N/A

No files, tests, or entry points are named. Start by reviewing the repository's existing SageMaker Spark examples and inference entry points, then determine how a PySpark DataFrame can use a custom PyTorch model through a SageMaker GPU endpoint; done means a working example covering that flow.

Written by the indexing model from the issue text.