Add bf16 precision option for ViTMatte (--precision, default fp32)

bf16 halves the matting model's activation memory -- its full-resolution
attention is the pipeline's memory peak -- with visually identical alpha
(measured: 0 px alpha deviation > 0.25 on samples; cross-check veto
behaviour unchanged, region IoU 0.984).

Guarded by a hardware check so it never lands on a slow emulation path:
CUDA requires torch.cuda.is_bf16_supported(); CPU requires the same
oneDNN native-bf16 gate PyTorch uses for matmul routing (AVX512-BF16/
AMX). Without support it warns and falls back to fp32 -- on a Zen2 EPYC
the fallback kernels measured 17-370x slower than fp32, so silent bf16
there would be a performance landmine.

Segmentation stays fp32: torchvision deform_conv2d (used by BiRefNet)
has no bf16 CPU kernel, and the segmenter is not the memory peak.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

configs/default.yaml

@@ -8,6 +8,9 @@ model:
   device: cpu
   matting_method: vitmatte
   fallback_to_chroma_alpha: false
+  # "bf16" halves ViTMatte activation memory (visually identical alpha); needs
+  # bf16-capable hardware (modern GPU / AVX512-BF16 CPU), else falls back to fp32.
+  precision: fp32
 
 segmentation:
   # enabled: true  = single-segmenter pipeline (one seg model drives the trimap)