Simplify to non-streaming render for ZeroGPU compatibility

Wrap streaming inference in @spaces.GPU, yield chunks after

Remove warmup - no GPU at startup on ZeroGPU

Revert to float32 model loading - codec needs float32, dtype casts in model.py handle ZeroGPU SDPA

Load model in bfloat16 natively

Fix dtype mismatch for ZeroGPU SDPA patching

Add streaming audio generation with Web Audio player

trying to cast

trying to cast

trying to cast

trying to cast

trying to cast

trying to cast

trying to cast

Fixed serving

Trying to fix kvcache

Trying to fix kvcache

wip

wip

Trying to fix kvcache

Trying to fix kvcache

wip

Merge branch 'main' of hf.co:spaces/fluxions/vui-space

tryin relative imports

Update README.md

tryin relative imports

INIT

initial commit