[Bug]: error encountered when trying to quantize model with modelslim

[fataswellassad]

Your current environment

I know this isn't strictly vllm-ascend but it's heavily related.
I was trying to follow the instructions from https://vllm-ascend.readthedocs.io/en/latest/user_guide/feature_guide/quantization.html.

🐛 Describe the bug

However, when I run the script, (cmd: python3 msit/msmodelslim/example/Qwen/quant_qwen.py --model_path Qwen2.5-32B-Instruct --model_type qwen2 --save_directory Qwen2.5-32B-Instruct-W8A16 --a_bit 16 --w_bit 8 --tp_size 2), it shows:

That file msmodelslim.pytorch.llm_ptq.anti_outlier.anti_utils doesn't even exist (for this tag at least). How do I work around this?

Thx in advance.