[INFO] create model description success

[INFO] create new context

[INFO] load model ./CosyVoice2-0.5B/speech_linux_aarch64.om success

[INFO] create model description success

Removing weight norm...

warm up start

  0%|                                                                                                                                  | 0/1 [00:00<?, ?it/s]                                                 [INFO] synthesis text 收到好友从远方寄来的生日礼物，那份意外的惊喜和深深的祝福，让我心中充满了甜蜜的快乐，笑容如花儿般绽放。

  0%|                                                                                                                                  | 0/1 [00:00<?, ?it/s]

Traceback (most recent call last):

  File "/home/yaowenjie/ModelZoo-PyTorch/ACL_PyTorch/built-in/audio/CosyVoice2/CosyVoice/infer.py", line 118, in <module>

    no_stream_input_inference(args, cosyvoice, prompt_txt)

  File "/home/yaowenjie/ModelZoo-PyTorch/ACL_PyTorch/built-in/audio/CosyVoice2/CosyVoice/infer.py", line 26, in no_stream_input_inference

    for _ in enumerate(cosyvoice.inference_sft(prompt_txt[0], '中文女', stream=args.stream_out)):

  File "/home/yaowenjie/ModelZoo-PyTorch/ACL_PyTorch/built-in/audio/CosyVoice2/CosyVoice/cosyvoice/cli/cosyvoice.py", line 74, in inference_sft

    for model_output in self.model.tts(**model_input, stream=stream, speed=speed):

  File "/home/yaowenjie/ModelZoo-PyTorch/ACL_PyTorch/built-in/audio/CosyVoice2/CosyVoice/cosyvoice/cli/model.py", line 380, in tts

    for i in self.llm.inference(text=text.to(self.device),

  File "/usr/local/lib64/python3.11/site-packages/torch/utils/_contextlib.py", line 35, in generator_context

    response = gen.send(None)

               ^^^^^^^^^^^^^^

  File "/home/yaowenjie/ModelZoo-PyTorch/ACL_PyTorch/built-in/audio/CosyVoice2/CosyVoice/cosyvoice/llm/llm.py", line 338, in inference

    y_pred, cache = self.llm.forward_one_step(lm_input,

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

  File "/home/yaowenjie/ModelZoo-PyTorch/ACL_PyTorch/built-in/audio/CosyVoice2/CosyVoice/cosyvoice/llm/llm.py", line 234, in forward_one_step

    outs = self.model(

           ^^^^^^^^^^^

  File "/usr/local/lib64/python3.11/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl

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

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

  File "/usr/local/lib64/python3.11/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl

    return forward_call(*args, **kwargs)

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

  File "/home/yaowenjie/ModelZoo-PyTorch/ACL_PyTorch/built-in/audio/CosyVoice2/CosyVoice/transformers/src/transformers/models/qwen2/modeling_qwen2.py", line                                                  846, in forward

    outputs, logits = self.model(

                      ^^^^^^^^^^^

  File "/usr/local/lib64/python3.11/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl

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

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

  File "/usr/local/lib64/python3.11/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl

    return forward_call(*args, **kwargs)

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

  File "/home/yaowenjie/ModelZoo-PyTorch/ACL_PyTorch/built-in/audio/CosyVoice2/CosyVoice/transformers/src/transformers/models/qwen2/modeling_qwen2.py", line                                                  476, in forward

    return self.cached_first_prefill(

           ^^^^^^^^^^^^^^^^^^^^^^^^^^

  File "/usr/local/lib64/python3.11/site-packages/torch_npu/dynamo/torchair/inference/_cache_compiler.py", line 551, in __call__

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

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

  File "/usr/local/lib64/python3.11/site-packages/torch_npu/dynamo/torchair/inference/_cache_compiler.py", line 476, in __call__

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

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

  File "/usr/local/lib64/python3.11/site-packages/torch/_dynamo/eval_frame.py", line 451, in _fn

    return fn(*args, **kwargs)

           ^^^^^^^^^^^^^^^^^^^

  File "/usr/local/lib64/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 921, in catch_errors

    return callback(frame, cache_entry, hooks, frame_state, skip=1)

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

  File "/usr/local/lib64/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 400, in _convert_frame_assert

    return _compile(

           ^^^^^^^^^

  File "/usr/lib64/python3.11/contextlib.py", line 81, in inner

    return func(*args, **kwds)

           ^^^^^^^^^^^^^^^^^^^

  File "/usr/local/lib64/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 703, in _compile

    raise InternalTorchDynamoError(str(e)).with_traceback(

  File "/usr/local/lib64/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 676, in _compile

    guarded_code = compile_inner(code, one_graph, hooks, transform)

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

  File "/usr/local/lib64/python3.11/site-packages/torch/_dynamo/utils.py", line 262, in time_wrapper

    r = func(*args, **kwargs)

        ^^^^^^^^^^^^^^^^^^^^^

  File "/usr/local/lib64/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 535, in compile_inner

    out_code = transform_code_object(code, transform)

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

  File "/usr/local/lib64/python3.11/site-packages/torch/_dynamo/bytecode_transformation.py", line 1036, in transform_code_object

    transformations(instructions, code_options)

  File "/usr/local/lib64/python3.11/site-packages/torch/_dynamo/convert_frame.py", line 160, in _fn

    cuda_rng_state = torch.cuda.get_rng_state()

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

  File "/usr/local/lib64/python3.11/site-packages/torch_npu/npu/random.py", line 32, in get_rng_state

    return default_generator.get_state()

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

torch._dynamo.exc.InternalTorchDynamoError: currentStreamCaptureStatusMayInitCtx:build/CMakeFiles/torch_npu.dir/compiler_depend.ts:77 NPU function error: c10                                                 _npu::acl::AclmdlRICaptureGetInfo(s.stream(false), &is_capturing, &model_ri), error code is 107003

[ERROR] 2025-08-16-19:49:58 (PID:182183, Device:0, RankID:-1) ERR00100 PTA call acl api failed

[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: 182183] 2025-08-16-19:49:58.467.052 stream is not in current ctx, stream_id=161.[FUNC:StreamGetCaptureInfo][FILE:api_impl.cc][LINE:7889]

        TraceBack (most recent call last):

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

You can suppress this exception and fall back to eager by setting:

    import torch._dynamo

    torch._dynamo.config.suppress_errors = True

[W compiler_depend.ts: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: 182183] 2025-08-16-19:49:58.489.491 Stream destroy failed, stream is not in current ctx, stream_id=161.[FUNC:StreamDestroy][FILE:api_impl.cc][L                                                 INE: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