Load model synchronously before Gradio launch (fix HF gcTimeout kill)

Refactor: load Lyra-2 model once at startup, reuse across requests

Shorter runtime copy

Update runtime copy to reflect real ~75min/request timing on A100

Soften macOS viewer copy to 'coming soon' until LyraViewerMac is public

README: raise sleep_time to 7200s (2h) — DCP load + inference needs ~1h on A100

Initial Dockerfile + Gradio UI

initial commit