Requirements updates:
- Default to CUDA 13 with TensorRT 10.14.1.48 (requirements.txt)
- Add cuda-toolkit version constraints (>=13.0.0,<13.1.0)
- Rename requirements_cu13.txt -> requirements_cu12.txt for legacy support
- Add cuda-toolkit constraint for CUDA 12 (>=12.8.0,<13.0.0)
CUDA toolkit detection:
- Add _setup_cuda_dll_path() to auto-detect CUDA installation
- Check CUDA_PATH, CUDA_HOME, and default Windows install paths
- Handle CUDA 13+ bin/x64 subdirectory for cudart64.dll
- Display download link if CUDA not found
Engine building updates:
- Add resolution profiles (small: 480-896px, medium: 720-1280px)
- Add 'custom' profile with CustomResolutionConfig node
- Include profile name in engine filename for separate caching
- Reduce default VRAM usage from ~15GB to ~2-3GB