300IDuo 跑Cosyvoice2 出现attention相关的错误

一、问题现象（附报错日志上下文）：
root@k8s-master:/home/work/pcr/cz2/CosVoice2/CosyVoice# bash infer.sh
/usr/local/python3.11.10/lib/python3.11/site-packages/torch_npu/contrib/transfer_to_npu.py:291: 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.nn.Module.to, torch.nn.Module.to_empty
    *************************************************************************************************************

warnings.warn(msg, ImportWarning)
/usr/local/python3.11.10/lib/python3.11/site-packages/torch_npu/contrib/transfer_to_npu.py:246: 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)
2025-04-27 08:17:06,756 - modelscope - INFO - PyTorch version 2.4.0 Found.
2025-04-27 08:17:06,757 - modelscope - INFO - Loading ast index from /root/.cache/modelscope/ast_indexer
2025-04-27 08:17:06,819 - modelscope - INFO - Loading done! Current index file version is 1.15.0, with md5 d9b2fb29d4a982bfb7209e3708098c33 and a total number of 980 components indexed
failed to import ttsfrd, use WeTextProcessing instead
/usr/local/python3.11.10/lib/python3.11/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: '/usr/local/python3.11.10/lib/python3.11/site-packages/torchvision/image.so: undefined symbol: _ZN3c1017RegisterOperatorsD1Ev'If you don't plan on using image functionality from `torchvision.io`, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have `libjpeg` or `libpng` installed before building `torchvision` from source?
  warn(
/usr/local/python3.11.10/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/python3.11.10/lib/python3.11/site-packages/librosa/core/intervals.py:15: DeprecationWarning: path is deprecated. Use files() instead. Refer to https://importlib-resources.readthedocs.io/en/latest/using.html#migrating-from-legacy for migration advice.
  with resources.path("librosa.core", "intervals.msgpack") as imsgpack:
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
/usr/local/python3.11.10/lib/python3.11/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py:69: UserWarning: Specified provider 'CUDAExecutionProvider' is not in available provider names.Available providers: 'AzureExecutionProvider, CPUExecutionProvider'
  warnings.warn(
2025-04-27 08:17:29,304 WETEXT INFO building fst for zh_normalizer ...
[INFO] building fst for zh_normalizer ...
2025-04-27 08:18:16,056 WETEXT INFO done
[INFO] done
2025-04-27 08:18:16,056 WETEXT INFO fst path: /usr/local/python3.11.10/lib/python3.11/site-packages/tn/zh_tn_tagger.fst
[INFO] fst path: /usr/local/python3.11.10/lib/python3.11/site-packages/tn/zh_tn_tagger.fst
2025-04-27 08:18:16,056 WETEXT INFO           /usr/local/python3.11.10/lib/python3.11/site-packages/tn/zh_tn_verbalizer.fst
[INFO]           /usr/local/python3.11.10/lib/python3.11/site-packages/tn/zh_tn_verbalizer.fst
2025-04-27 08:18:16,064 WETEXT INFO found existing fst: /usr/local/python3.11.10/lib/python3.11/site-packages/tn/en_tn_tagger.fst
[INFO] found existing fst: /usr/local/python3.11.10/lib/python3.11/site-packages/tn/en_tn_tagger.fst
2025-04-27 08:18:16,064 WETEXT INFO                     /usr/local/python3.11.10/lib/python3.11/site-packages/tn/en_tn_verbalizer.fst
[INFO]                     /usr/local/python3.11.10/lib/python3.11/site-packages/tn/en_tn_verbalizer.fst
2025-04-27 08:18:16,064 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 /home/work/model-weight/CosyVoice/CosyVoice2-0.5B//flow_linux_aarch64.om success
[INFO] create model description success
[INFO] create new context
[INFO] load model /home/work/model-weight/CosyVoice/CosyVoice2-0.5B//flow_static.om success
[INFO] create model description success
[INFO] create new context
[INFO] load model /home/work/model-weight/CosyVoice/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 [00:32<?, ?it/s]
Traceback (most recent call last):
  File "/usr/local/python3.11.10/lib/python3.11/site-packages/torch_npu/dynamo/torchair/_utils/error_code.py", line 43, in wapper
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/python3.11.10/lib/python3.11/site-packages/torch_npu/dynamo/torchair/core/_backend.py", line 133, in run
    return super(TorchNpuGraph, self).run((inputs, assigned_outputs, stream))
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: EZ1001: [PID: 122813] 2025-04-27-08:19:41.034.956 PromptFlashAttention LaunchAicore failed.
        TraceBack (most recent call last):
        attention mask must be NULL, when Qs,Kvs is unAlign or Qs is not equal to Kvs, Qs = 53, Kvs = 53[FUNC:RunBigKernelTilingWithParams][FILE:prompt_flash_attention_tiling.cpp][LINE:2446]
        Tiling failed
        Tiling Failed.
        Kernel GetWorkspace failed. opType: 18
        PromptFlashAttention LaunchAicore failed.
        call aclnnPromptFlashAttentionV3 failed:[FUNC:PromptHostExecuteFunc][FILE:fallback_prompt_flash_attention.cpp][LINE:116]
        api_ret faild:4294967295[FUNC:PromptHostExecuteFunc][FILE:fallback_prompt_flash_attention.cpp][LINE:119]
        Assert ((op_execute_func(op_execute_context)) == ge::SUCCESS) failed[FUNC:ExecuteOpFunc][FILE:aclnn_op_execute_kernel.cc][LINE:46]
        Failed to execute rt v2 model for graph graph_1_0, model_id 2.[FUNC:ExecuteWithStreamAsync][FILE:hybrid_model_rt_v2_executor.cc][LINE:964]
        GraphManager ExecuteGrapWithStreamhAsync failed,session id = 1, graph id = 0, stream = 0xaaab632b73e0.[FUNC:ExecuteGraphWithStreamAsync][FILE:inner_session.cc][LINE:625]
        Execute graph with stream async failed, error code:1343225857, session_id:1, graph_id:0, stream:0xaaab632b73e0.[FUNC:ExecuteGraphWithStreamAsync][FILE:ge_api.cc][LINE:844]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/work/pcr/cz2/CosVoice2/CosyVoice/infer.py", line 51, in <module>
    next(cosyvoice.inference_sft(prompt_txt, '中文女', stream=args.stream))
  File "/home/work/pcr/cz2/CosVoice2/CosyVoice/cosyvoice/cli/cosyvoice.py", line 73, in inference_sft
    for model_output in self.model.tts(**model_input, stream=stream, speed=speed):
  File "/home/work/pcr/cz2/CosVoice2/CosyVoice/cosyvoice/cli/model.py", line 368, in tts
    for i in self.llm.inference(text=text.to(self.device),
  File "/usr/local/python3.11.10/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 36, in generator_context
    response = gen.send(None)
               ^^^^^^^^^^^^^^
  File "/home/work/pcr/cz2/CosVoice2/CosyVoice/cosyvoice/llm/llm.py", line 329, in inference
    y_pred, cache = self.llm.forward_one_step(lm_input,
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/work/pcr/cz2/CosVoice2/CosyVoice/cosyvoice/llm/llm.py", line 234, in forward_one_step
    outs = self.model(
           ^^^^^^^^^^^
  File "/usr/local/python3.11.10/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/python3.11.10/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/work/pcr/cz2/CosVoice2/CosyVoice/transformers/src/transformers/models/qwen2/modeling_qwen2.py", line 774, in forward
    outputs, logits = self.model(
                      ^^^^^^^^^^^
  File "/usr/local/python3.11.10/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/python3.11.10/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/work/pcr/cz2/CosVoice2/CosyVoice/transformers/src/transformers/models/qwen2/modeling_qwen2.py", line 456, in forward
    return self.cached_prefill(
           ^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/python3.11.10/lib/python3.11/site-packages/torch_npu/dynamo/torchair/inference/_cache_compiler.py", line 503, in __call__
    return self._compiled_model(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/python3.11.10/lib/python3.11/site-packages/torch_npu/dynamo/torchair/inference/_cache_compiler.py", line 247, in compiled_method
    return compiled_fn(model, *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/work/pcr/cz2/CosVoice2/CosyVoice/transformers/src/transformers/models/qwen2/modeling_qwen2.py", line 520, in prefill
    def prefill(
  File "/usr/local/python3.11.10/lib/python3.11/site-packages/torch_npu/dynamo/torchair/inference/_cache_compiler.py", line 229, in compiled_fn
    return ge_kernel(*full_args)
           ^^^^^^^^^^^^^^^^^^^^^
  File "<string>", line 339, in kernel
  File "/usr/local/python3.11.10/lib/python3.11/site-packages/torch_npu/dynamo/torchair/ge/_ge_graph.py", line 659, in run
    return self._executor.run(inputs, assigned_outputs, stream)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/python3.11.10/lib/python3.11/site-packages/torch_npu/dynamo/torchair/_utils/error_code.py", line 46, in wapper
    raise type(e)("\n".join(msg))
RuntimeError: EZ1001: [PID: 122813] 2025-04-27-08:19:41.034.956 PromptFlashAttention LaunchAicore failed.
        TraceBack (most recent call last):
        attention mask must be NULL, when Qs,Kvs is unAlign or Qs is not equal to Kvs, Qs = 53, Kvs = 53[FUNC:RunBigKernelTilingWithParams][FILE:prompt_flash_attention_tiling.cpp][LINE:2446]
        Tiling failed
        Tiling Failed.
        Kernel GetWorkspace failed. opType: 18
        PromptFlashAttention LaunchAicore failed.
        call aclnnPromptFlashAttentionV3 failed:[FUNC:PromptHostExecuteFunc][FILE:fallback_prompt_flash_attention.cpp][LINE:116]
        api_ret faild:4294967295[FUNC:PromptHostExecuteFunc][FILE:fallback_prompt_flash_attention.cpp][LINE:119]
        Assert ((op_execute_func(op_execute_context)) == ge::SUCCESS) failed[FUNC:ExecuteOpFunc][FILE:aclnn_op_execute_kernel.cc][LINE:46]
        Failed to execute rt v2 model for graph graph_1_0, model_id 2.[FUNC:ExecuteWithStreamAsync][FILE:hybrid_model_rt_v2_executor.cc][LINE:964]
        GraphManager ExecuteGrapWithStreamhAsync failed,session id = 1, graph id = 0, stream = 0xaaab632b73e0.[FUNC:ExecuteGraphWithStreamAsync][FILE:inner_session.cc][LINE:625]
        Execute graph with stream async failed, error code:1343225857, session_id:1, graph_id:0, stream:0xaaab632b73e0.[FUNC:ExecuteGraphWithStreamAsync][FILE:ge_api.cc][LINE:844]

Traceback (most recent call last):
  File "/usr/local/python3.11.10/lib/python3.11/site-packages/torch_npu/dynamo/torchair/_utils/error_code.py", line 43, in wapper
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/python3.11.10/lib/python3.11/site-packages/torch_npu/dynamo/torchair/core/_backend.py", line 133, in run
    return super(TorchNpuGraph, self).run((inputs, assigned_outputs, stream))
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: EZ1001: [PID: 122813] 2025-04-27-08:19:41.034.956 PromptFlashAttention LaunchAicore failed.
        TraceBack (most recent call last):
        attention mask must be NULL, when Qs,Kvs is unAlign or Qs is not equal to Kvs, Qs = 53, Kvs = 53[FUNC:RunBigKernelTilingWithParams][FILE:prompt_flash_attention_tiling.cpp][LINE:2446]
        Tiling failed
        Tiling Failed.
        Kernel GetWorkspace failed. opType: 18
        PromptFlashAttention LaunchAicore failed.
        call aclnnPromptFlashAttentionV3 failed:[FUNC:PromptHostExecuteFunc][FILE:fallback_prompt_flash_attention.cpp][LINE:116]
        api_ret faild:4294967295[FUNC:PromptHostExecuteFunc][FILE:fallback_prompt_flash_attention.cpp][LINE:119]
        Assert ((op_execute_func(op_execute_context)) == ge::SUCCESS) failed[FUNC:ExecuteOpFunc][FILE:aclnn_op_execute_kernel.cc][LINE:46]
        Failed to execute rt v2 model for graph graph_1_0, model_id 2.[FUNC:ExecuteWithStreamAsync][FILE:hybrid_model_rt_v2_executor.cc][LINE:964]
        GraphManager ExecuteGrapWithStreamhAsync failed,session id = 1, graph id = 0, stream = 0xaaab632b73e0.[FUNC:ExecuteGraphWithStreamAsync][FILE:inner_session.cc][LINE:625]
        Execute graph with stream async failed, error code:1343225857, session_id:1, graph_id:0, stream:0xaaab632b73e0.[FUNC:ExecuteGraphWithStreamAsync][FILE:ge_api.cc][LINE:844]

[ERROR] 2025-04-27-08:19:41 (PID:122813, Device:0, RankID:-1) ERR03005 GRAPH internal error
[INFO] unload model success, model Id is 2147483649
[INFO] unload model success, model Id is 2147483648
[INFO] unload model success, model Id is 1
[WARN] acl repeat destroy
root@k8s-master:/home/work/pcr/cz2/CosVoice2/CosyVoice# ^C

二、软件版本:
 
--docker-images：swr.cn-south-1.myhuaweicloud.com/ascendhub/mindie:1.0.0-300I-Duo-py311-openeuler24.03-lts
--Pytorch 版本:torch                       2.4.0
              torch-npu                   2.4.0.post2

--Python 版本 (e.g., Python 3.11.10):
--操作系统版本 (e.g., Ubuntu 18.04):

三、测试步骤：
正常按照ModelZoo-Pytorch CosyVoice仓库CosyVoice2相关代码进行测试，模型转化和ACL初始化成功，随后出现
RuntimeError: EZ1001: [PID: 122813] 2025-04-27-08:19:41.034.956 PromptFlashAttention LaunchAicore failed.
        TraceBack (most recent call last):
        attention mask must be NULL, when Qs,Kvs is unAlign or Qs is not equal to Kvs, Qs = 53, Kvs = 53[FUNC:RunBigKernelTilingWithParams][FILE:prompt_flash_attention_tiling.cpp][LINE:2446]
        Tiling failed
        Tiling Failed.
        Kernel GetWorkspace failed. opType: 18
        PromptFlashAttention LaunchAicore failed.
        call aclnnPromptFlashAttentionV3 failed:[FUNC:PromptHostExecuteFunc][FILE:fallback_prompt_flash_attention.cpp][LINE:116]
        api_ret faild:4294967295[FUNC:PromptHostExecuteFunc][FILE:fallback_prompt_flash_attention.cpp][LINE:119]
        Assert ((op_execute_func(op_execute_context)) == ge::SUCCESS) failed[FUNC:ExecuteOpFunc][FILE:aclnn_op_execute_kernel.cc][LINE:46]
        Failed to execute rt v2 model for graph graph_1_0, model_id 2.[FUNC:ExecuteWithStreamAsync][FILE:hybrid_model_rt_v2_executor.cc][LINE:964]
        GraphManager ExecuteGrapWithStreamhAsync failed,session id = 1, graph id = 0, stream = 0xaaab632b73e0.[FUNC:ExecuteGraphWithStreamAsync][FILE:inner_session.cc][LINE:625]
        Execute graph with stream async failed, error code:1343225857, session_id:1, graph_id:0, stream:0xaaab632b73e0.[FUNC:ExecuteGraphWithStreamAsync][FILE:ge_api.cc][LINE:844]

[ERROR] 2025-04-27-08:19:41 (PID:122813, Device:0, RankID:-1) ERR03005 GRAPH internal error

四、日志信息:

export ASDOPS_LOG_LEVEL=ERROR
export ASDOPS_LOG_TO_STDOUT=1
/root/ascend/log/debug/plog

[ERROR] OP(123766,python3):2025-04-27-08:35:57.111.020 [prompt_flash_attention_tiling.cpp:2446][OP_TILING][RunBigKernelTilingWithParams][123766] OpName:[GetBasicShape310P] "attention mask must be NULL, when Qs,Kvs is unAlign or Qs is not equal to Kvs, Qs = 53, Kvs = 53"
[ERROR] OP(123766,python3):2025-04-27-08:35:57.111.154 [kernel_workspace.cpp:144][NNOP][Tiling][123766] errno[561000] OpName:[aclnnInnerPromptFlashAttention_318_PromptFlashAttention] Tiling failed
[ERROR] OP(123766,python3):2025-04-27-08:35:57.111.242 [kernel_workspace.cpp:685][NNOP][GetWorkspace][123766] errno[561103] OpName:[aclnnInnerPromptFlashAttention_318_PromptFlashAttention] Tiling Failed.
[ERROR] OP(123766,python3):2025-04-27-08:35:57.111.264 [kernel_workspace.cpp:101][NNOP][GetWorkspace][123766] errno[561103] OpName:[aclnnInnerPromptFlashAttention_318_PromptFlashAttention] Kernel GetWorkspace failed. opType: 18
[ERROR] OP(123766,python3):2025-04-27-08:35:57.111.299 [prompt_flash_attention_base_aclnn.cpp:91][NNOP][PromptFlashAttention][123766] errno[161002] OpName:[aclnnInnerPromptFlashAttention_318_PromptFlashAttention] PromptFlashAttention LaunchAicore failed.
[ERROR] OP(123766,python3):2025-04-27-08:35:57.111.324 [aclnn_prompt_flash_attention_inner.cpp:660][NNOP][aclnnInnerPromptFlashAttentionGetWorkspaceSize][123766] errno[561000] OpName:[aclnnInnerPromptFlashAttention_318] check l0AttentionOutOut != nullptr failed.
[ERROR] OP(123766,python3):2025-04-27-08:35:57.111.331 [acl_rfft1d.cpp:164][NNOP][~UniqueExecutor][123766] errno[561102] OpName:[aclnnInnerPromptFlashAttention_318] When aclnnInnerPromptFlashAttentionGetWorkspaceSize do success, ReleaseTo(executor) should be called before return.
[ERROR] OP(123766,python3):2025-04-27-08:35:57.111.340 [fallback_prompt_flash_attention.cpp:116][OP_TILING][PromptHostExecuteFunc][123766] OpName:[aclnnfallback] "call aclnnPromptFlashAttentionV3 failed:"
[ERROR] OP(123766,python3):2025-04-27-08:35:57.111.356 [fallback_prompt_flash_attention.cpp:119][OP_TILING][PromptHostExecuteFunc][123766] OpName:[aclnnfallback] "api_ret faild:4294967295"
[ERROR] GE(123766,python3):2025-04-27-08:35:57.111.455 [aclnn_op_execute_kernel.cc:46]123766 ExecuteOpFunc: ErrorNo: 4294967295(failed) [COMP][DEFAULT]Assert ((op_execute_func(op_execute_context)) == ge::SUCCESS) failed
[ERROR] GE(123766,python3):2025-04-27-08:35:57.111.461 [aclnn_op_execute_kernel.cc:46]123766 ExecuteOpFunc: ErrorNo: 4294967295(failed) [COMP][DEFAULT]Assert ((op_execute_func(op_execute_context)) == ge::SUCCESS) failed
[ERROR] GE(123766,python3):2025-04-27-08:35:57.111.542 [hybrid_model_rt_v2_executor.cc:964]123766 ExecuteWithStreamAsync: ErrorNo: 4294967295(failed) [COMP][DEFAULT]Failed to execute rt v2 model for graph graph_1_0, model_id 2.
[ERROR] GE(123766,python3):2025-04-27-08:35:57.111.552 [model_executor.cc:552]123766 ExecuteGraphWithStream: ErrorNo: 1343225857(Parameter invalid!) [COMP][DEFAULT][Execute][Graph] With Stream failed, graph id = 0, stream = 0xaaab96343990.
[ERROR] GE(123766,python3):2025-04-27-08:35:57.111.560 [inner_session.cc:624]123766 ExecuteGraphWithStreamAsync: ErrorNo: 1343225857(Parameter invalid!) [COMP][DEFAULT][Execute][GraphWithStreamAsync]failed,session id = 1, graph id = 0, stream = 0xaaab96343990.
[ERROR] GE(123766,python3):2025-04-27-08:35:57.111.587 [ge_api.cc:844]123766 ExecuteGraphWithStreamAsync: ErrorNo: 4294967295(failed) [COMP][DEFAULT]Execute graph with stream async failed, error code:1343225857, session_id:1, graph_id:0, stream:0xaaab96343990.

日志提供方式:
将日志打包后作为附件上传。若日志大小超出附件限制，则可上传至外部网盘后提供链接。

获取方法请参考wiki：
https://gitee.com/ascend/modelzoo/wikis/%E5%A6%82%E4%BD%95%E8%8E%B7%E5%8F%96%E6%97%A5%E5%BF%97%E5%92%8C%E8%AE%A1%E7%AE%97%E5%9B%BE?sort_id=4097825

遇到了一样的报错，请问你解决了嘛

Ascend/ModelZoo-PyTorch

内容风险标识

评论 (1)

Ascend/ModelZoo-PyTorch .gitee-modal { width: 500px !important; }

内容风险标识