v9: footer URLs corrected — Gradio 5 uses /gradio_api/call/, not /api/

v8: api_name= on click handlers + background model preload + status indicator

v3: install llama-cpp-python from prebuilt wheel (HF dataset, no source build)

v2: pin py3.12 + add inference tab on TinyLlama Q4_K_M

initial: TurboQuant visualizer (rotation effect on quantization)