DJLModel doesn't support ml.p4d.24xlarge for deployment

[andjsmi]

Describe the bug
A clear and concise description of what the bug is.
The ml.p4d.* and ml.p4de.* instances are not supported for the DJLModel for deploying as they aren't included in allowed instance families.

To reproduce
A clear, step-by-step set of instructions to reproduce the bug.
Deploy a SageMaker Endpoint with an ml.p4d.24xlarge from a DJLModel.

Expected behavior
A clear and concise description of what you expected to happen.
Endpoint deploys successfully as ml.p4d.24xlarge is sufficiently large enough.

Screenshots or logs
If applicable, add screenshots or logs to help explain your problem.

System information
A description of your system. Please provide:

• SageMaker Python SDK version: 2.140.1
• Framework name (eg. PyTorch) or algorithm (eg. KMeans): Deep Java Library
• Framework version:
• Python version: 3.8.13
• CPU or GPU: CPU
• Custom Docker image (Y/N): N

Additional context
Add any other context about the problem here.

[siddvenk]

Thanks for raising this issue - I have created a PR to fix this bug. I also noticed that some other instance families needed to be fixed, so now p3dn, p4d, and p4de instances should all work.