验证torch_npu报错

300IDUO卡推理服务器，操作系统为麒麟v10 arm版本，容器部署了1.0.0-300I-Duo-py311-openeuler24.03-lts，服务化部署蒸馏版deepseek-32B，但是torch报错

运行torch_npu.npu.is_available()，返回True
运行a=torch.rand(3,4).npu()，a=a+a,print(a)时，返回如下信息：

[2025-5-25 9:33:33] [ERROR] [ascend310p] 737efd3b48fb8dd663e2cebfdb38ba722ae46b20b4aedccb351d75c8e3615948_te In file included from /usr/local/Ascend/ascend-toolkit/8.0.0/opp/built-in/op_impl/ai_core/tbe/impl/dynamic/../ascendc/is_finite/is_finite.cpp:22:

In file included from /usr/local/Ascend/ascend-toolkit/8.0.0/opp/built-in/op_impl/ai_core/tbe/impl/dynamic/../ascendc/is_finite/is_finite.h:24:

In file included from /usr/local/Ascend/ascend-toolkit/8.0.0/aarch64-linux/tikcpp/tikcfw/kernel_operator.h:24:

In file included from /usr/local/Ascend/ascend-toolkit/8.0.0/aarch64-linux/tikcpp/tikcfw/impl/kernel_tpipe_impl.h:23:

In file included from /usr/local/Ascend/ascend-toolkit/8.0.0/aarch64-linux/tikcpp/tikcfw/interface/kernel_tpipe.h:23:

In file included from /usr/local/Ascend/ascend-toolkit/8.0.0/aarch64-linux/tikcpp/tikcfw/impl/kernel_tpipe_base.h:23:

In file included from /usr/local/Ascend/ascend-toolkit/8.0.0/aarch64-linux/tikcpp/tikcfw/impl/kernel_tensor_impl.h:23:

In file included from /usr/local/Ascend/ascend-toolkit/8.0.0/aarch64-linux/tikcpp/tikcfw/interface/kernel_tensor.h:24:

In file included from /usr/local/Ascend/ascend-toolkit/8.0.0/aarch64-linux/tikcpp/tikcfw/impl/kernel_utils.h:23:

In file included from /usr/local/Ascend/ascend-toolkit/8.0.0/aarch64-linux/tikcpp/tikcfw/impl/utils/kernel_utils_macros.h:33:

/usr/local/Ascend/ascend-toolkit/8.0.0/aarch64-linux/tikcpp/tikcfw/impl/kernel_macros.h:24:10: fatal error: 'cstdint' file not found

#include <cstdint>

^~~~~~~~~

1 error generated.

Traceback (most recent call last):

File "<stdin>", line 1, in <module>

File "/usr/local/lib64/python3.11/site-packages/torch/_tensor.py", line 431, in __repr__

return torch._tensor_str._str(self, tensor_contents=tensor_contents)

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

File "/usr/local/lib64/python3.11/site-packages/torch/_tensor_str.py", line 664, in _str

return _str_intern(self, tensor_contents=tensor_contents)

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

File "/usr/local/lib64/python3.11/site-packages/torch/_tensor_str.py", line 595, in _str_intern

tensor_str = _tensor_str(self, indent)

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

File "/usr/local/lib64/python3.11/site-packages/torch/_tensor_str.py", line 347, in _tensor_str

formatter = _Formatter(get_summarized_data(self) if summarize else self)

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

File "/usr/local/lib64/python3.11/site-packages/torch/_tensor_str.py", line 138, in __init__

tensor_view, torch.isfinite(tensor_view) & tensor_view.ne(0)

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

RuntimeError: InnerRun:build/CMakeFiles/torch_npu.dir/compiler_depend.ts:218 OPS function error: IsFinite, error code is 500002

[ERROR] 2025-02-23-18:56:12 (PID:118, Device:0, RankID:-1) ERR01100 OPS call acl api failed

[Error]: A GE error occurs in the system.

Rectify the fault based on the error information in the ascend log.

E40021: [PID: 118] 2025-02-23-18:56:12.834.755 Failed to compile Op [IsFinite1]. (oppath: [Compile /usr/local/Ascend/ascend-toolkit/8.0.0/opp/built-in/op_impl/ai_core/tbe/impl/dynamic/is_finite.py failed with errormsg/stack: File "/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/tbe/tikcpp/compile_op.py", line 530, in dump_build_log

raise Exception("An error occurred during compile phases of {}, msg is {}".\

Exception: An error occurred during compile phases of CompileStage.PRECOMPILE, msg is In file included from /usr/local/Ascend/ascend-toolkit/8.0.0/opp/built-in/op_impl/ai_core/tbe/impl/dynamic/../ascendc/is_finite/is_finite.cpp:22: