fix: update cleanup logic for quantized model path in tests

[xin3he]

Description

FAILED test_cuda/quantization/test_mxfp_nvfp.py::TestAutoRound::test_qwen_moe_quant_infer - RuntimeError: Error(s) in loading state_dict for Linear:
size mismatch for weight: copying a param with shape torch.Size([102400, 2048]) from checkpoint, the shape in current model is torch.Size([151936, 2048])

Type of Change

• Bug fix
• New feature
• Documentation update
• Performance improvement
• Code refactoring
• Other (please specify):

Related Issues

Fixes or relates to #1227

Checklist Before Submitting

• My code has been tested locally.
• Documentation has been updated as needed.
• New or updated tests are included where applicable.

[Copilot]

Pull request overview

Updates test cleanup to remove the actual quantized model output directory rather than a hard-coded path, reducing test artifact leakage.

Changes:

• Replace hard-coded ./saved cleanup with quantized_model_path cleanup in test_nvfp4_llmcompressor_format.
• Add cleanup of quantized_model_path after quantized model saves in two additional NVFP4 MoE tests.