[root@rhel8 data]# pip list|grep torch
torch 2.9.0+cpu
torch_npu 2.9.0.post1+gitee7ba04
torchaudio 2.9.0
torchvision 0.24.0
[root@rhel8 data]# pip list|grep msmodelslim
msmodelslim 26.0.0a1
[root@rhel8 data]# pip list|grep transformers
transformers 4.57.6
[root@rhel8 data]# pip list|grep vllm
vllm 0.18.0+empty /vllm-workspace/vllm
vllm_ascend 0.18.0rc1 /vllm-workspace/vllm-ascend
[root@rhel8 data]# msmodelslim quant --model_path ./Qwen3.6-35B-A3B --save_path ./Qwen3.6-35B-A3B-w8a8 --model_type Qwen3.5-35B-A3B --quant_type w8a8
/usr/local/python3.11.14/lib/python3.11/site-packages/torch_npu/contrib/transfer_to_npu.py:347: ImportWarning:
*************************************************************************************************************
The torch.Tensor.cuda and torch.nn.Module.cuda are replaced with torch.Tensor.npu and torch.nn.Module.npu now..
The torch.cuda.DoubleTensor is replaced with torch.npu.FloatTensor cause the double type is not supported now..
The backend in torch.distributed.init_process_group set to hccl now..
The torch.cuda.* and torch.cuda.amp.* are replaced with torch.npu.* and torch.npu.amp.* now..
The device parameters have been replaced with npu in the function below:
torch.logspace, torch.randint, torch.hann_window, torch.rand, torch.full_like, torch.ones_like, torch.rand_like, torch.randperm, torch.arange, torch.frombuffer, torch.normal, torch._empty_per_c hannel_affine_quantized, torch.empty_strided, torch.empty_like, torch.scalar_tensor, torch.tril_indices, torch.bartlett_window, torch.ones, torch.sparse_coo_tensor, torch.randn, torch.kaiser_window , torch.tensor, torch.triu_indices, torch.as_tensor, torch.zeros, torch.randint_like, torch.full, torch.eye, torch._sparse_csr_tensor_unsafe, torch.empty, torch._sparse_coo_tensor_unsafe, torch.bla ckman_window, torch.zeros_like, torch.range, torch.sparse_csr_tensor, torch.randn_like, torch.from_file, torch._cudnn_init_dropout_state, torch._empty_affine_quantized, torch.linspace, torch.hammin g_window, torch.empty_quantized, torch._pin_memory, torch.load, torch.set_default_device, torch.get_device_module, torch.sparse_compressed_tensor, torch.Tensor.new_empty, torch.Tensor.new_empty_str ided, torch.Tensor.new_full, torch.Tensor.new_ones, torch.Tensor.new_tensor, torch.Tensor.new_zeros, torch.Tensor.to, torch.Tensor.pin_memory, torch.nn.Module.to, torch.nn.Module.to_empty
*************************************************************************************************************
warnings.warn(msg, ImportWarning)
/usr/local/python3.11.14/lib/python3.11/site-packages/torch_npu/contrib/transfer_to_npu.py:276: RuntimeWarning: torch.jit.script and torch.jit.script_method will be disabled by transfer_to_npu, whi ch currently does not support them, if you need to enable them, please do not use transfer_to_npu.
warnings.warn(msg, RuntimeWarning)
2026-04-28 01:08:09,839 - msmodelslim.app.naive_quantization - WARNING - write directory not exists, creating directory './Qwen3.6-35B-A3B-w8a8'
2026-04-28 01:08:09,840 - msmodelslim.app.naive_quantization - INFO - quantization with following parameters:
2026-04-28 01:08:09,840 - msmodelslim.app.naive_quantization - INFO - model_type: Qwen3.5-35B-A3B
2026-04-28 01:08:09,840 - msmodelslim.app.naive_quantization - INFO - model_path: /data/Qwen3.6-35B-A3B
2026-04-28 01:08:09,840 - msmodelslim.app.naive_quantization - INFO - save_path: /data/Qwen3.6-35B-A3B-w8a8
2026-04-28 01:08:09,840 - msmodelslim.app.naive_quantization - INFO - device_type: DeviceType.NPU
2026-04-28 01:08:09,841 - msmodelslim.app.naive_quantization - INFO - using single device (default): npu
2026-04-28 01:08:09,841 - msmodelslim.app.naive_quantization - INFO - quant_type: QuantType.W8A8
2026-04-28 01:08:09,841 - msmodelslim.app.naive_quantization - INFO - trust_remote_code: False
2026-04-28 01:08:09,841 - msmodelslim.app.naive_quantization - INFO - ===========ANALYSE MODEL===========
2026-04-28 01:08:09,862 - msmodelslim.app.naive_quantization - INFO - Found 63 model adapters: ['DeepSeek-R1', 'DeepSeek-R1-0528', 'DeepSeek-R1-Distill-Qwen-1.5B', 'DeepSeek-R1-Distill-Qwen-7B', 'D eepSeek-V3', 'DeepSeek-V3-0324', 'DeepSeek-V3.1', 'DeepSeek-V3.2', 'DeepSeek-V3.2-Exp', 'DeepSeek-V4-Flash', 'FLUX.1-dev', 'GLM-4.5', 'GLM-4.6', 'GLM-4.6V', 'GLM-4.7', 'GLM-5', 'HunyuanVideo', 'Kim i-K2-Instruct-0905', 'Kimi-K2-Thinking', 'Kimi-K2.5', 'QwQ-32B', 'Qwen-Image-Edit-2509', 'Qwen-QwQ-32B', 'Qwen1.5-110B', 'Qwen2-72B', 'Qwen2-7B', 'Qwen2-7B-Instruct', 'Qwen2.5-32B-Instruct', 'Qwen2 .5-72B-Instruct', 'Qwen2.5-7B-Instruct', 'Qwen2.5-Coder-7B-Instruct', 'Qwen2.5-Omni-7B', 'Qwen2.5-VL-32B-Instruct', 'Qwen2.5-VL-72B-Instruct', 'Qwen2.5-VL-7B-Instruct', 'Qwen3-14B', 'Qwen3-235B', ' Qwen3-30B', 'Qwen3-32B', 'Qwen3-8B', 'Qwen3-Coder-480B-A35B', 'Qwen3-Next-80B-A3B-Instruct', 'Qwen3-Omni-30B-A3B-Instruct', 'Qwen3-Omni-30B-A3B-Thinking', 'Qwen3-VL-235B-A22B', 'Qwen3-VL-30B-A3B', 'Qwen3-VL-32B-Instruct', 'Qwen3-VL-4B-Instruct', 'Qwen3.5-122B-A10B', 'Qwen3.5-27B', 'Qwen3.5-35B-A3B', 'Qwen3.5-397B-A17B', 'Wan2.1', 'Wan2.2', 'Wan2.2-I2V-A14B', 'Wan2.2-T2V-A14B', 'Wan2.2-TI2V-5 B', 'Wan2_1', 'Wan2_2', 'default', 'hunyuan-video', 'hunyuan_video', 'hunyuanvideo']
2026-04-28 01:08:09,891 - msmodelslim.app.naive_quantization - ERROR - [UnexpectedError] Code: 500, Message: Unexpected error., TIP: Please report this issue to the msModelSlim developers. Reposito ry: https://gitcode.com/Ascend/msmodelslim Q&A: https://gitcode.com/Ascend/msmodelslim/blob/master/docs/zh/appendix/faq.md
2026-04-28 01:08:09,891 - msmodelslim.app.naive_quantization - ERROR - Original exception: ImportError("cannot import name 'Qwen3_5MoeForConditionalGeneration' from 'transformers' (/usr/local/pytho n3.11.14/lib/python3.11/site-packages/transformers/__init__.py)")
2026-04-28 01:08:09,894 - msmodelslim.app.naive_quantization - ERROR - Traceback: Traceback (most recent call last): File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/utils/ exception_decorator.py", line 178, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/app/naive_q uantization/application.py", line 420, in quant self._quant( File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/utils/logging.py", line 307, in wrapper return func(*a rgs, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/app/naive_quantization/application.py", line 438, in _quant model_adapt er = self.model_factory.create( ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/model/plugin_factory.py", line 84, in create adapter_class = model_map[model_type].load() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/importlib_metadata/__init__.py", lin e 221, in load module = import_module(self.module) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/importlib/__init__.py", line 126, in import_module return _bootstrap._gcd_import(name[level:], package, level) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "<frozen importlib._bootstrap>", line 1204, in _gcd_import File "<frozen importlib._bootstrap>", line 1176, in _find_and_load File "<frozen importlib._bootstrap>", line 1126, in _find_and_load_unlocked File "<frozen importlib._bootstrap>", line 241, in _ca ll_with_frames_removed File "<frozen importlib._bootstrap>", line 1204, in _gcd_import File "<frozen importlib._bootstrap>", line 1176, in _find_and_load File "<frozen importlib._bootstrap>", line 1147, in _find_and_load_unlocked File "<frozen importlib._bootstrap>", line 690, in _load_unlocked File "<frozen importlib._bootstrap_external>", line 940, in exec_module File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/model/qwen3_5_moe/__init__.py", line 39, in <module> fro m .model_adapter import Qwen3_5ModelAdapter File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/model/qwen3_5_moe/model_adapter.py", line 37, in <module> from transformers import Qwen3_5MoeForConditionalGeneration, Qwen3_5ForConditionalGeneration ImportError: cannot import name 'Qwen3_5MoeForConditionalGeneration' from 'transformers' (/usr/local/python3.11.14/lib/py thon3.11/site-packages/transformers/__init__.py)
Traceback (most recent call last):
File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/utils/exception_decorator.py", line 178, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/app/naive_quantization/application.py", line 420, in quant
self._quant(
File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/utils/logging.py", line 307, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/app/naive_quantization/application.py", line 438, in _quant
model_adapter = self.model_factory.create(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/model/plugin_factory.py", line 84, in create
adapter_class = model_map[model_type].load()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/python3.11.14/lib/python3.11/site-packages/importlib_metadata/__init__.py", line 221, in load
module = import_module(self.module)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/python3.11.14/lib/python3.11/importlib/__init__.py", line 126, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "<frozen importlib._bootstrap>", line 1204, in _gcd_import
File "<frozen importlib._bootstrap>", line 1176, in _find_and_load
File "<frozen importlib._bootstrap>", line 1126, in _find_and_load_unlocked
File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
File "<frozen importlib._bootstrap>", line 1204, in _gcd_import
File "<frozen importlib._bootstrap>", line 1176, in _find_and_load
File "<frozen importlib._bootstrap>", line 1147, in _find_and_load_unlocked
File "<frozen importlib._bootstrap>", line 690, in _load_unlocked
File "<frozen importlib._bootstrap_external>", line 940, in exec_module
File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/model/qwen3_5_moe/__init__.py", line 39, in <module>
from .model_adapter import Qwen3_5ModelAdapter
File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/model/qwen3_5_moe/model_adapter.py", line 37, in <module>
from transformers import Qwen3_5MoeForConditionalGeneration, Qwen3_5ForConditionalGeneration
ImportError: cannot import name 'Qwen3_5MoeForConditionalGeneration' from 'transformers' (/usr/local/python3.11.14/lib/python3.11/site-packages/transformers/__init__.py)
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/usr/local/python3.11.14/bin/msmodelslim", line 6, in <module>
sys.exit(main())
^^^^^^
File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/cli/__main__.py", line 128, in main
quant_main(args)
File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/cli/naive_quantization/__main__.py", line 91, in main
app.quant(
File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/utils/logging.py", line 307, in wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/utils/exception_decorator.py", line 189, in wrapper
raise unexpected_error from e
msmodelslim.utils.exception.UnexpectedError: Code: 500, Message: Unexpected error.
TIP: Please report this issue to the msModelSlim developers. Repository: https://gitcode.com/Ascend/msmodelslim Q&A: https://gitcode.com/Ascend/msmodelslim/blob/master/docs/zh/appendix/faq.md
[ERROR] 2026-04-28-01:08:09 (PID:47250, Device:-1, RankID:-1) ERR99999 UNKNOWN applicaiton exception
点赞
收藏
回复
分享
举报
已解决
报错信息如下
[root@rhel8 data]# pip list|grep torch torch 2.9.0+cpu torch_npu 2.9.0.post1+gitee7ba04 torchaudio 2.9.0 torchvision 0.24.0 [root@rhel8 data]# pip list|grep msmodelslim msmodelslim 26.0.0a1 [root@rhel8 data]# pip list|grep transformers transformers 4.57.6 [root@rhel8 data]# pip list|grep vllm vllm 0.18.0+empty /vllm-workspace/vllm vllm_ascend 0.18.0rc1 /vllm-workspace/vllm-ascend [root@rhel8 data]# msmodelslim quant --model_path ./Qwen3.6-35B-A3B --save_path ./Qwen3.6-35B-A3B-w8a8 --model_type Qwen3.5-35B-A3B --quant_type w8a8 /usr/local/python3.11.14/lib/python3.11/site-packages/torch_npu/contrib/transfer_to_npu.py:347: ImportWarning: ************************************************************************************************************* The torch.Tensor.cuda and torch.nn.Module.cuda are replaced with torch.Tensor.npu and torch.nn.Module.npu now.. The torch.cuda.DoubleTensor is replaced with torch.npu.FloatTensor cause the double type is not supported now.. The backend in torch.distributed.init_process_group set to hccl now.. The torch.cuda.* and torch.cuda.amp.* are replaced with torch.npu.* and torch.npu.amp.* now.. The device parameters have been replaced with npu in the function below: torch.logspace, torch.randint, torch.hann_window, torch.rand, torch.full_like, torch.ones_like, torch.rand_like, torch.randperm, torch.arange, torch.frombuffer, torch.normal, torch._empty_per_c hannel_affine_quantized, torch.empty_strided, torch.empty_like, torch.scalar_tensor, torch.tril_indices, torch.bartlett_window, torch.ones, torch.sparse_coo_tensor, torch.randn, torch.kaiser_window , torch.tensor, torch.triu_indices, torch.as_tensor, torch.zeros, torch.randint_like, torch.full, torch.eye, torch._sparse_csr_tensor_unsafe, torch.empty, torch._sparse_coo_tensor_unsafe, torch.bla ckman_window, torch.zeros_like, torch.range, torch.sparse_csr_tensor, torch.randn_like, torch.from_file, torch._cudnn_init_dropout_state, torch._empty_affine_quantized, torch.linspace, torch.hammin g_window, torch.empty_quantized, torch._pin_memory, torch.load, torch.set_default_device, torch.get_device_module, torch.sparse_compressed_tensor, torch.Tensor.new_empty, torch.Tensor.new_empty_str ided, torch.Tensor.new_full, torch.Tensor.new_ones, torch.Tensor.new_tensor, torch.Tensor.new_zeros, torch.Tensor.to, torch.Tensor.pin_memory, torch.nn.Module.to, torch.nn.Module.to_empty ************************************************************************************************************* warnings.warn(msg, ImportWarning) /usr/local/python3.11.14/lib/python3.11/site-packages/torch_npu/contrib/transfer_to_npu.py:276: RuntimeWarning: torch.jit.script and torch.jit.script_method will be disabled by transfer_to_npu, whi ch currently does not support them, if you need to enable them, please do not use transfer_to_npu. warnings.warn(msg, RuntimeWarning) 2026-04-28 01:08:09,839 - msmodelslim.app.naive_quantization - WARNING - write directory not exists, creating directory './Qwen3.6-35B-A3B-w8a8' 2026-04-28 01:08:09,840 - msmodelslim.app.naive_quantization - INFO - quantization with following parameters: 2026-04-28 01:08:09,840 - msmodelslim.app.naive_quantization - INFO - model_type: Qwen3.5-35B-A3B 2026-04-28 01:08:09,840 - msmodelslim.app.naive_quantization - INFO - model_path: /data/Qwen3.6-35B-A3B 2026-04-28 01:08:09,840 - msmodelslim.app.naive_quantization - INFO - save_path: /data/Qwen3.6-35B-A3B-w8a8 2026-04-28 01:08:09,840 - msmodelslim.app.naive_quantization - INFO - device_type: DeviceType.NPU 2026-04-28 01:08:09,841 - msmodelslim.app.naive_quantization - INFO - using single device (default): npu 2026-04-28 01:08:09,841 - msmodelslim.app.naive_quantization - INFO - quant_type: QuantType.W8A8 2026-04-28 01:08:09,841 - msmodelslim.app.naive_quantization - INFO - trust_remote_code: False 2026-04-28 01:08:09,841 - msmodelslim.app.naive_quantization - INFO - ===========ANALYSE MODEL=========== 2026-04-28 01:08:09,862 - msmodelslim.app.naive_quantization - INFO - Found 63 model adapters: ['DeepSeek-R1', 'DeepSeek-R1-0528', 'DeepSeek-R1-Distill-Qwen-1.5B', 'DeepSeek-R1-Distill-Qwen-7B', 'D eepSeek-V3', 'DeepSeek-V3-0324', 'DeepSeek-V3.1', 'DeepSeek-V3.2', 'DeepSeek-V3.2-Exp', 'DeepSeek-V4-Flash', 'FLUX.1-dev', 'GLM-4.5', 'GLM-4.6', 'GLM-4.6V', 'GLM-4.7', 'GLM-5', 'HunyuanVideo', 'Kim i-K2-Instruct-0905', 'Kimi-K2-Thinking', 'Kimi-K2.5', 'QwQ-32B', 'Qwen-Image-Edit-2509', 'Qwen-QwQ-32B', 'Qwen1.5-110B', 'Qwen2-72B', 'Qwen2-7B', 'Qwen2-7B-Instruct', 'Qwen2.5-32B-Instruct', 'Qwen2 .5-72B-Instruct', 'Qwen2.5-7B-Instruct', 'Qwen2.5-Coder-7B-Instruct', 'Qwen2.5-Omni-7B', 'Qwen2.5-VL-32B-Instruct', 'Qwen2.5-VL-72B-Instruct', 'Qwen2.5-VL-7B-Instruct', 'Qwen3-14B', 'Qwen3-235B', ' Qwen3-30B', 'Qwen3-32B', 'Qwen3-8B', 'Qwen3-Coder-480B-A35B', 'Qwen3-Next-80B-A3B-Instruct', 'Qwen3-Omni-30B-A3B-Instruct', 'Qwen3-Omni-30B-A3B-Thinking', 'Qwen3-VL-235B-A22B', 'Qwen3-VL-30B-A3B', 'Qwen3-VL-32B-Instruct', 'Qwen3-VL-4B-Instruct', 'Qwen3.5-122B-A10B', 'Qwen3.5-27B', 'Qwen3.5-35B-A3B', 'Qwen3.5-397B-A17B', 'Wan2.1', 'Wan2.2', 'Wan2.2-I2V-A14B', 'Wan2.2-T2V-A14B', 'Wan2.2-TI2V-5 B', 'Wan2_1', 'Wan2_2', 'default', 'hunyuan-video', 'hunyuan_video', 'hunyuanvideo'] 2026-04-28 01:08:09,891 - msmodelslim.app.naive_quantization - ERROR - [UnexpectedError] Code: 500, Message: Unexpected error., TIP: Please report this issue to the msModelSlim developers. Reposito ry: https://gitcode.com/Ascend/msmodelslim Q&A: https://gitcode.com/Ascend/msmodelslim/blob/master/docs/zh/appendix/faq.md 2026-04-28 01:08:09,891 - msmodelslim.app.naive_quantization - ERROR - Original exception: ImportError("cannot import name 'Qwen3_5MoeForConditionalGeneration' from 'transformers' (/usr/local/pytho n3.11.14/lib/python3.11/site-packages/transformers/__init__.py)") 2026-04-28 01:08:09,894 - msmodelslim.app.naive_quantization - ERROR - Traceback: Traceback (most recent call last): File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/utils/ exception_decorator.py", line 178, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/app/naive_q uantization/application.py", line 420, in quant self._quant( File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/utils/logging.py", line 307, in wrapper return func(*a rgs, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/app/naive_quantization/application.py", line 438, in _quant model_adapt er = self.model_factory.create( ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/model/plugin_factory.py", line 84, in create adapter_class = model_map[model_type].load() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/importlib_metadata/__init__.py", lin e 221, in load module = import_module(self.module) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/importlib/__init__.py", line 126, in import_module return _bootstrap._gcd_import(name[level:], package, level) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "<frozen importlib._bootstrap>", line 1204, in _gcd_import File "<frozen importlib._bootstrap>", line 1176, in _find_and_load File "<frozen importlib._bootstrap>", line 1126, in _find_and_load_unlocked File "<frozen importlib._bootstrap>", line 241, in _ca ll_with_frames_removed File "<frozen importlib._bootstrap>", line 1204, in _gcd_import File "<frozen importlib._bootstrap>", line 1176, in _find_and_load File "<frozen importlib._bootstrap>", line 1147, in _find_and_load_unlocked File "<frozen importlib._bootstrap>", line 690, in _load_unlocked File "<frozen importlib._bootstrap_external>", line 940, in exec_module File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/model/qwen3_5_moe/__init__.py", line 39, in <module> fro m .model_adapter import Qwen3_5ModelAdapter File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/model/qwen3_5_moe/model_adapter.py", line 37, in <module> from transformers import Qwen3_5MoeForConditionalGeneration, Qwen3_5ForConditionalGeneration ImportError: cannot import name 'Qwen3_5MoeForConditionalGeneration' from 'transformers' (/usr/local/python3.11.14/lib/py thon3.11/site-packages/transformers/__init__.py) Traceback (most recent call last): File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/utils/exception_decorator.py", line 178, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/app/naive_quantization/application.py", line 420, in quant self._quant( File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/utils/logging.py", line 307, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/app/naive_quantization/application.py", line 438, in _quant model_adapter = self.model_factory.create( ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/model/plugin_factory.py", line 84, in create adapter_class = model_map[model_type].load() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/importlib_metadata/__init__.py", line 221, in load module = import_module(self.module) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/importlib/__init__.py", line 126, in import_module return _bootstrap._gcd_import(name[level:], package, level) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "<frozen importlib._bootstrap>", line 1204, in _gcd_import File "<frozen importlib._bootstrap>", line 1176, in _find_and_load File "<frozen importlib._bootstrap>", line 1126, in _find_and_load_unlocked File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed File "<frozen importlib._bootstrap>", line 1204, in _gcd_import File "<frozen importlib._bootstrap>", line 1176, in _find_and_load File "<frozen importlib._bootstrap>", line 1147, in _find_and_load_unlocked File "<frozen importlib._bootstrap>", line 690, in _load_unlocked File "<frozen importlib._bootstrap_external>", line 940, in exec_module File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/model/qwen3_5_moe/__init__.py", line 39, in <module> from .model_adapter import Qwen3_5ModelAdapter File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/model/qwen3_5_moe/model_adapter.py", line 37, in <module> from transformers import Qwen3_5MoeForConditionalGeneration, Qwen3_5ForConditionalGeneration ImportError: cannot import name 'Qwen3_5MoeForConditionalGeneration' from 'transformers' (/usr/local/python3.11.14/lib/python3.11/site-packages/transformers/__init__.py) The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/usr/local/python3.11.14/bin/msmodelslim", line 6, in <module> sys.exit(main()) ^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/cli/__main__.py", line 128, in main quant_main(args) File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/cli/naive_quantization/__main__.py", line 91, in main app.quant( File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/utils/logging.py", line 307, in wrapper return func(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.14/lib/python3.11/site-packages/msmodelslim/utils/exception_decorator.py", line 189, in wrapper raise unexpected_error from e msmodelslim.utils.exception.UnexpectedError: Code: 500, Message: Unexpected error. TIP: Please report this issue to the msModelSlim developers. Repository: https://gitcode.com/Ascend/msmodelslim Q&A: https://gitcode.com/Ascend/msmodelslim/blob/master/docs/zh/appendix/faq.md [ERROR] 2026-04-28-01:08:09 (PID:47250, Device:-1, RankID:-1) ERR99999 UNKNOWN applicaiton exception