feat(vllm): add GPU container image build pipeline

[nathan-weinberg]

Summary

Add Containerfile, GitHub Actions workflow, and Dependabot config for building CUDA-based vLLM GPU inference images with models baked in at build time

Related issue

Closes #692

Validation

N/A

Checklist

• I reviewed every changed line and can explain the change.
• New capabilities include an example config and functional example test.
• User-facing behavior and generated documentation are updated.
• Performance-sensitive changes include appropriate benchmark or load-test evidence.
• Commits are signed and include a Signed-off-by trailer.

Breaking changes

N/A

[praxis-bot-app]

Unsigned commits: 9c71dba. Please sign your commits.

[nathan-weinberg]

Currently blocked by ongoing work to determine how we will get our GPU runners for GHA - this is denoted in the PR code by TODO-GPU-RUNNER-LABEL

Once that is resolved, I will update that label and move this out of draft state