Support yololite object detection in inference_models with ONNX backend

[leeclemnet]

What does this PR do?

Adds support for yololite object detection in inference_models, ONNX backend only to start

We will not do the same for legacy inference, since traffic is no longer being routed there.

Type of Change

• New feature (non-breaking change that adds functionality)

Testing

• I have tested this change locally
• I have added/updated tests for this change

Test details:

• Added integration test with canned model package
• Tested inferencing yololite-edge-n model trained on platform (staging) using local build of x86.cu124.base.dockerfile - outputs as expected

• Tested Object Detection workflow block with yololite-edge-n model with local Dockerfile.onnx.gpu.dev build and USE_INFERENCE_MODELS=True

Checklist

• My code follows the style guidelines of this project
• I have performed a self-review of my own code
• I have commented my code where necessary, particularly in hard-to-understand areas
• My changes generate no new warnings or errors
• I have updated the documentation accordingly (if applicable)

Additional Context

[PawelPeczek-Roboflow]

LGTM so far. -let me know do you need anything as support moving forward