Inference: default to all GPUs

[GeorgePearse]

Summary

• Change init_detector(..., device=...) default from "cuda:0" to "cuda".
• When device="cuda", auto-detect available GPUs and use all of them for single-process inference.
• Log an info message: found X GPUs.

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

[github-actions]

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