Describe the bug
RuntimeError: Tensor on device meta is not on the expected device cuda:0!

Expected behavior
No error happens and quantized weight could be obtained

Environment
Include all relevant environment information:

1. OS [Ubuntu 20.04]:Ubuntu 20.04
2. Python version [3.10.12]: 3.10.12
3. LLM Compressor version or commit hash [e.g. 0.1.0, f7245c8]:
4. ML framework version(s) [torch 2.7.1]: torch 2.7.1
5. Other Python package versions [e.g. vLLM, compressed-tensors, numpy, ONNX]:
6. Other relevant environment information [CUDA version]: 12.6

To Reproduce
cd /llm-compressor/examples/multimodal_audio
python3 whisper_example.py

Errors

Additional context
Add any other context about the problem here. Also include any relevant files.