Make GPU resource name configurable for MIG support

[cpierce-deepgram]

Proposed changes

Types of changes

What types of changes does your code introduce to the Deepgram self-hosted resources?
Put an x in the boxes that apply

• Bugfix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update or tests (if none of the other choices apply)

Checklist

Put an x in the boxes that apply. You can also fill these out after creating the PR. If you're unsure about any of them, don't hesitate to ask. We're here to help! This is simply a reminder of what we are going to look for before merging your code.

• I have read the CONTRIBUTING doc
• I have tested my changes in my local self-hosted environment
  • Please describe your testing setup and methodology here
• I have added necessary documentation (if appropriate)

Further comments

[bnogas]

This change adds support for MIG; for reference here is naming convention of nvidia.com resources created when MIG is enabled https://docs.nvidia.com/datacenter/tesla/mig-user-guide/mig-device-names.html

I have tested my changes in my local self-hosted environment
Please describe your testing setup and methodology here

I'm currently running a deepgram deployment with MIG on H100/H200 using this change

I have added necessary documentation (if appropriate)

I believe the docs for helm chart are autogenerated