Ascend310 不支持

README.MD文件中的代码运行提示：RuntimeError: Unsupported soc version: Ascend310

```
[root@localhost guchao]# python
Python 3.9.9 (main, May 18 2023, 18:12:40) 
[GCC 10.3.1] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import torch
>>> import torch_npu
/usr/local/lib64/python3.9/site-packages/torch_npu/dynamo/__init__.py:18: UserWarning: Register eager implementation for the 'npu' backend of dynamo, as torch_npu was not compiled with torchair.
  warnings.warn(
>>> x = torch.randn(2, 2).npu()
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/usr/local/lib64/python3.9/site-packages/torch/utils/backend_registration.py", line 153, in wrap_tensor_to
    device_idx = _normalization_device(custom_backend_name, device)
  File "/usr/local/lib64/python3.9/site-packages/torch/utils/backend_registration.py", line 109, in _normalization_device
    return _get_current_device_index()
  File "/usr/local/lib64/python3.9/site-packages/torch/utils/backend_registration.py", line 103, in _get_current_device_index
    return getattr(getattr(torch, custom_backend_name), _get_device_index)()
  File "/usr/local/lib64/python3.9/site-packages/torch_npu/npu/utils.py", line 51, in current_device
    torch_npu.npu._lazy_init()
  File "/usr/local/lib64/python3.9/site-packages/torch_npu/npu/__init__.py", line 203, in _lazy_init
    torch_npu._C._npu_init()
RuntimeError: Unsupported soc version: Ascend310
>>> y = torch.randn(2, 2).npu()
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/usr/local/lib64/python3.9/site-packages/torch/utils/backend_registration.py", line 153, in wrap_tensor_to
    device_idx = _normalization_device(custom_backend_name, device)
  File "/usr/local/lib64/python3.9/site-packages/torch/utils/backend_registration.py", line 109, in _normalization_device
    return _get_current_device_index()
  File "/usr/local/lib64/python3.9/site-packages/torch/utils/backend_registration.py", line 103, in _get_current_device_index
    return getattr(getattr(torch, custom_backend_name), _get_device_index)()
  File "/usr/local/lib64/python3.9/site-packages/torch_npu/npu/utils.py", line 51, in current_device
    torch_npu.npu._lazy_init()
  File "/usr/local/lib64/python3.9/site-packages/torch_npu/npu/__init__.py", line 203, in _lazy_init
    torch_npu._C._npu_init()
RuntimeError: Initialize:torch_npu/csrc/core/npu/sys_ctrl/npu_sys_ctrl.cpp:120 NPU error, error code is 100002
[Error]: Repeated initialization or repeated loading.
        Check whether the corresponding interface is repeatedly invoked for initialization or loading.
```

环境：
Python 3.9.9
torch 2.1.0
torch-npu 2.1.0
CANN 8.0.RC1.alpha001

Ascend/pytorch
暂停

内容风险标识

评论 (1)

Ascend/pytorch暂停 .gitee-modal { width: 500px !important; }

内容风险标识