Adding Qwen3-Omni inference

[dannigt]

Adds Qwen3-Omni-30B-A3B-Instruct as a MLLM baseline under the name qwen3_omni.

Changes

• New model file baselines/models/mllm/qwen3_omni.py
• Registered in baselines/main.py

Example usage

python main.py \
  --model qwen3_omni \
  --lang en \
  --track long \
  --modality audio \
  --prompt fixed \
  --in_data_folder $PATH2DATA \
  --out_folder ./baseline

Notes

• Requires flash_attention_2 and sufficient VRAM for a 30B MoE model