python：3.11

cann：8.2.RC1

torch: 2.3.1

torch-npu: 2.3.1

/usr/local/python3/lib/python3.11/site-packages/torch_npu/contrib/transfer_to_npu.py:294: 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_channel_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.blackman_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.hamming_window, torch.empty_quantized, torch._pin_memory, torch.autocast, torch.load, torch.Generator, torch.set_default_device, torch.Tensor.new_empty, torch.Tensor.new_empty_strided, 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/lib/python3.11/site-packages/torch_npu/contrib/transfer_to_npu.py:249: RuntimeWarning: torch.jit.script and torch.jit.script_method will be disabled by transfer_to_npu, which currently does not support them, if you need to enable them, please do not use transfer_to_npu. 

  warnings.warn(msg, RuntimeWarning) 

failed to import ttsfrd, use WeTextProcessing instead 

/usr/local/python3/lib/python3.11/site-packages/diffusers/models/lora.py:393: FutureWarning: `LoRACompatibleLinear` is deprecated and will be removed in version 1.0.0. Use of `LoRACompatibleLinear` is deprecated. Please switch to PEFT backend by installing PEFT: `pip install peft`. 

  deprecate("LoRACompatibleLinear", "1.0.0", deprecation_message) 

[INFO] input frame rate=25 

/usr/local/python3/lib/python3.11/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py:65: UserWarning: Specified provider 'CUDAExecutionProvider' is not in available provider names.Available providers: 'CPUExecutionProvider' 

  warnings.warn( 

2025-08-15 20:08:55,687 WETEXT INFO building fst for zh_normalizer ... 

[INFO] building fst for zh_normalizer ... 

2025-08-15 20:09:16,979 WETEXT INFO done 

[INFO] done 

2025-08-15 20:09:16,979 WETEXT INFO fst path: /usr/local/python3/lib/python3.11/site-packages/tn/zh_tn_tagger.fst 

[INFO] fst path: /usr/local/python3/lib/python3.11/site-packages/tn/zh_tn_tagger.fst 

2025-08-15 20:09:16,979 WETEXT INFO           /usr/local/python3/lib/python3.11/site-packages/tn/zh_tn_verbalizer.fst 

[INFO]           /usr/local/python3/lib/python3.11/site-packages/tn/zh_tn_verbalizer.fst 

2025-08-15 20:09:16,983 WETEXT INFO found existing fst: /usr/local/python3/lib/python3.11/site-packages/tn/en_tn_tagger.fst 

[INFO] found existing fst: /usr/local/python3/lib/python3.11/site-packages/tn/en_tn_tagger.fst 

2025-08-15 20:09:16,983 WETEXT INFO                     /usr/local/python3/lib/python3.11/site-packages/tn/en_tn_verbalizer.fst 

[INFO]                     /usr/local/python3/lib/python3.11/site-packages/tn/en_tn_verbalizer.fst 

2025-08-15 20:09:16,983 WETEXT INFO skip building fst for en_normalizer ... 

[INFO] skip building fst for en_normalizer ... 

[WARN] acl repeat initialize 

[INFO] acl init success 

[INFO] open device 0 success 

[INFO] get current context 

[INFO] load model CosyVoice/CosyVoice2-0.5B/flow_linux_x86_64.om success 

[INFO] create model description success 

[INFO] create new context 

[INFO] load model CosyVoice/CosyVoice2-0.5B/flow_static.om success 

[INFO] create model description success 

[INFO] create new context 

[INFO] load model CosyVoice/CosyVoice2-0.5B/speech_linux_x86_64.om success 

[INFO] create model description success 

Removing weight norm... 

Traceback (most recent call last): 

  File "/home/jsh/cos/ModelZoo-PyTorch/ACL_PyTorch/built-in/audio/CosyVoice2/infer.py", line 103, in <module> 

    cosyvoice.model.hift.remove_weight_norm() 

  File "/home/jsh/cos/ModelZoo-PyTorch/ACL_PyTorch/built-in/audio/CosyVoice2/CosyVoice/cosyvoice/hifigan/generator.py", line 323, in remove_weight_norm 

    remove_parametrizations(l, 'weight') 

  File "/usr/local/python3/lib/python3.11/site-packages/torch/nn/utils/parametrize.py", line 664, in remove_parametrizations 

    t = getattr(module, tensor_name) 

        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 

  File "/usr/local/python3/lib/python3.11/site-packages/torch/nn/utils/parametrize.py", line 368, in get_parametrized 

    return parametrization() 

           ^^^^^^^^^^^^^^^^^ 

  File "/usr/local/python3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl 

    return self._call_impl(*args, **kwargs) 

           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 

  File "/usr/local/python3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl 

    return forward_call(*args, **kwargs) 

           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 

  File "/usr/local/python3/lib/python3.11/site-packages/torch/nn/utils/parametrize.py", line 268, in forward 

    x = self[0](*originals) 

        ^^^^^^^^^^^^^^^^^^^ 

  File "/usr/local/python3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl 

    return self._call_impl(*args, **kwargs) 

           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 

  File "/usr/local/python3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl 

    return forward_call(*args, **kwargs) 

           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 

  File "/usr/local/python3/lib/python3.11/site-packages/torch/nn/utils/parametrizations.py", line 300, in forward 

    return torch._weight_norm(weight_v, weight_g, self.dim) 

           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ 

RuntimeError: call aclnnNorm failed, detail:EZ9999: Inner Error! 

EZ9999: [PID: 2343468] 2025-08-15-20:09:44.003.537 Parse dynamic kernel config fail. 

        TraceBack (most recent call last): 

       AclOpKernelInit failed opType 

       LpNormV2 ADD_TO_LAUNCHER_LIST_AICORE failed. 

 

[ERROR] 2025-08-15-20:09:44 (PID:2343468, Device:0, RankID:-1) ERR01100 OPS call acl api failed 

[W npu_sys_ctrl.cpp:234] Warning: NPU warning, error code is 107003[Error]:  

[Error]: The stream is not in the current context. 

        Check whether the context where the stream is located is the same as the current context. 

EE9999: Inner Error! 

EE9999: [PID: 2343468] 2025-08-15-20:09:44.016.652 Stream destroy failed, stream is not in current ctx, stream_id=2.[FUNC:StreamDestroy][FILE:api_impl.cc][LINE:1378] 

        TraceBack (most recent call last): 

       rtStreamDestroyForce execute failed, reason=[stream not in current context][FUNC:FuncErrorReason][FILE:error_message_manage.cc][LINE:53] 

       destroy stream force failed, runtime result = 107003[FUNC:ReportCallError][FILE:log_inner.cpp][LINE:161] 

 (function operator()) 

[INFO] unload model success, model Id is 2147483649 

[INFO] unload model success, model Id is 2147483648 

[INFO] unload model success, model Id is 2 

[WARN] acl repeat destroy