Add FiftyOne dataset inference example + multi-GPU inference

[GeorgePearse]

Summary

• Add a FiftyOne (Voxel51) dataset example to the inference User Guide.
• Support single-process multi-GPU inference via init_detector(device=...) plus batched inference_detector.
• Add an MMDataParallel wrapper and unit test for device parsing.

Testing

• python3 -m pytest -q tests/test_runtime/test_inference_device_parsing.py

[github-actions]

🤖 Multi-Model Consensus Review

Model	Status
Claude Sonnet 4	✅
GPT-4o	✅
Gemini 2.0 Flash	✅

✅ tests/test_runtime/test_inference_device_parsing.py

Pass Rate: 3/3 models

✅ visdet/apis/inference.py

Pass Rate: 3/3 models

✅ visdet/engine/model/__init__.py

Pass Rate: 3/3 models

✅ visdet/engine/model/wrappers/__init__.py

Pass Rate: 3/3 models

✅ visdet/engine/model/wrappers/distributed.py

Pass Rate: 3/3 models

[github-actions]

✅ Skylos Scan: No dead code or security issues detected.