Thanks for sending an issue! Please fill in the following template to help quickly solve your problem.

Describe the current behavior / 问题描述 (Mandatory / 必填)

RT，在310p上量化Qwen2.5-7b-Instruct时出现报错：
TypeError: fake_quantize_save() got an unexpected keyword argument 'max_bound'

File "/usr/local/lib/python3.11/site-packages/msmodelslim/pytorch/llm_ptq/llm_ptq_tools/quant_tools.py", line 566, in save
self._save(output_path, safetensors_name, json_name, save_type, part_file_size)
File "/usr/local/lib/python3.11/site-packages/msmodelslim/pytorch/llm_ptq/llm_ptq_tools/quant_tools.py", line 930, in _save
self._save_weights_of_model(quantifier, saver)
File "/usr/local/lib/python3.11/site-packages/msmodelslim/pytorch/llm_ptq/llm_ptq_tools/quant_tools.py", line 937, in _save_weights_of_model
for name, meta, tensor in weight_collector:
File "/usr/local/lib/python3.11/site-packages/msmodelslim/pytorch/llm_ptq/llm_ptq_tools/quant_tools.py", line 577, in generate_weight_of_model
yield from weight_of_module_generator(name, module)
File "/usr/local/lib/python3.11/site-packages/msmodelslim/pytorch/llm_ptq/llm_ptq_tools/save/complex_quantifier.py", line 223, in generate_weight_of_module
yield from self.generate_weight_of_linear_module(name, module, model_quant_type)
File "/usr/local/lib/python3.11/site-packages/msmodelslim/pytorch/llm_ptq/llm_ptq_tools/save/complex_quantifier.py", line 301, in generate_weight_of_linear_module
quant_weight, fp_weight, weight_scale, weight_offset = self.get_param_from_quantizer(module)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib64/python3.11/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.11/site-packages/msmodelslim/pytorch/llm_ptq/llm_ptq_tools/save/complex_quantifier.py", line 454, in get_param_from_quantizer
quant_weight, _ = fake_quantize_save(fp_weight, weight_scale, weight_offset, bit=module.cfg.w_bit,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "quant_funcs.py", line 157, in quant_funcs.fake_quantize_save
TypeError: fake_quantize_save() got an unexpected keyword argument 'max_bound'

Environment / 环境信息 (Mandatory / 必填)

310P 在mindie容器内操作
CANN 8.0.0，MindIE 1.0.0 和 ATB-Models 1.0.0

Steps to reproduce the issue / 重现步骤 (Mandatory / 必填)

bash examples/models/qwen/convert_quant_weight.sh -src /models/Qwen2.5-7B-Instruct -dst /models/Qwen2.5-7B-W8A8 -type qwen_w8a8

Describe the expected behavior / 预期结果 (Mandatory / 必填)

正确量化

Related log / screenshot / 日志 / 截图 (Mandatory / 必填)

Special notes for this issue/备注 (Optional / 选填)