Add NaN guard to audio code generation path

Revert camera prompt changes; add NaN guard and CUDA sync; add engineering challenges doc

Cast logits to float32 before softmax/sampling to prevent fp16 overflow

Fix from_pretrained: use SenseVoice/Siglip encoder wrappers instead of raw models

Convert omni-o.pth to HF format + add from_pretrained support

Fix generate() to return last text tokens instead of (None, audio_frame) tuple

docs: update README and docs for model_type rename, RoPE guard fix, config paths

rename minimind→omni in model_type, eval/convert scripts, and docs

Flatten src layout: drop omni namespace, modules live directly under src/