deps: bump bitsandbytes to >=0.50.2 (fix 4-bit load on transformers 5.12)

bitsandbytes 0.49.2's Params4bit.__new__ has no **kwargs and rejects the
_is_hf_initialized kwarg that transformers 5.12 passes during 4-bit weight
init, so every load_in_4bit model crashed with:
  Params4bit.__new__() got an unexpected keyword argument '_is_hf_initialized'
In production this turned a single default-model chat request (Qwen3.5-9B,
load_in_4bit) into a ~2h internal 60-retry storm. bnb 0.50.2 adds **kwargs to
Params4bit.__new__ (absorbs _is_hf_initialized); verified end-to-end: a
transformers load_in_4bit load now succeeds on cuda:0 (torch 2.11/cu130), and a
GPU 4-bit quantize/dequantize round-trips. Image rebuilt with bnb 0.50.2.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Mw2KQiswmD69T45fTfjKwW

requirements-nvidia.txt

@@ -58,7 +58,10 @@ insightface>=0.7.3
 onnxruntime-gpu>=1.20.0        # GPU-accelerated ONNX runtime for insightface
 
 # Optional: for better performance with NVIDIA GPUs
-bitsandbytes>=0.41.0
+# >=0.50.2 required: earlier bnb (e.g. 0.49.2) Params4bit.__new__ rejects the
+# _is_hf_initialized kwarg that transformers 5.12+ passes on 4-bit load, breaking
+# every load_in_4bit model (Params4bit.__new__() got an unexpected keyword argument).
+bitsandbytes>=0.50.2
 sentencepiece>=0.1.99
 tiktoken>=0.5.0
 tokenizers>=0.15.0