FAQ

• “Segmentation fault”错误
  
• 运行报错：RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device(‘cpu’) to map your storages to the CPU
  
• 对于引用库找不到的问题
  
• 运行报错：Unsupport data type: at::ScalarType::Double.
  
• 运行报错：IndexError: invalid index of a 0-dim tensor. Use tensor.item() in Python or tensor.item<T>() in C++ to convert a 0-dim tensor to a number
  
• 对于报错 “No supported Ops kernel and engine are found for [ReduceStdV2A], optype [ReduceStdV2A]”，算子ReduceStdV2A不支持的问题。
  
• Muls算子不支持INT64
  
• 运行报错：Could not run ‘aten::empty_with_format’ with arguments from the ‘CPUTensorId’ backend. ‘aten::empty_with_format’ is only available for these backend “CUDA、NPU”
  
• 运行报错：options.device().type() == DeviceType::NPU INTERNAL ASSERT FAILED xxx:
  
• 运行报错：Attempting to deserialize object on a CUDA device but torch.cuda.is_availabel() is False.