ImportError: /root/miniconda3/envs/py3.10/lib/python3.10/site-packages/mmcv/_ext.cpython-310-aarch64-linux-gnu.so: undefined symbol: _ZNK3c105Error4whatEv

时间: 2025-08-21 21:14:48 AIGC 浏览: 39
<think>好的,我现在需要解决用户遇到的Python中mmcv库的ImportError错误,具体是undefined symbol: _ZNK3c105Error4whatEv,系统是py3.10 aarch64-linux-gnu架构。首先,我得分析这个问题的可能原因。这个错误通常出现在动态链接库找不到某个符号的时候,尤其是在C++扩展中。符号_ZNK3c105Error4whatEv对应的是c10::Error::what() const,属于PyTorch库的一部分,所以问题可能和PyTorch与mmcv的版本不兼容有关。 接下来,我需要考虑用户的环境是否安装了正确版本的PyTorch。用户提到使用的是Python 3.10和aarch64架构,也就是ARM架构,比如NVIDIA Jetson或者树莓派等设备。ARM架构下的PyTorch安装可能需要特定的版本,因为官方预编译的版本可能不支持,或者用户可能通过pip安装的PyTorch和mmcv的依赖不匹配。 另外,mmcv的安装方式是否正确也是一个关键点。mmcv分为mmcv-full(现在可能改名为mmcv)和mmcv-lite,用户如果是从源码编译的话,可能需要安装正确的依赖项,比如正确的CUDA版本,或者对应的PyTorch版本。如果用户通过pip安装的mmcv是预编译的,可能不支持ARM架构,导致链接到错误的PyTorch符号。 还可能存在的问题包括系统中安装了多个版本的PyTorch,或者虚拟环境中的路径没有正确设置,导致动态链接器找不到正确的库文件。另外,C++运行库的版本不一致也可能导致符号未找到的错误。 接下来,我需要整理解决方案的步骤。首先建议用户检查PyTorch的版本,并确保安装的是与mmcv兼容的版本。然后确认mmcv是否支持ARM架构,可能需要从源码编译。最后,检查系统依赖项,比如是否有必要的开发库安装,如libopenblas-dev等。 还需要考虑用户是否使用虚拟环境,环境是否激活,或者是否在安装过程中混用了pip和conda,这可能导致库路径冲突。此外,检查PyTorch是否正确安装,是否有权限问题导致库文件未被正确加载。 可能还需要指导用户如何从源码编译mmcv,包括安装所需的依赖项,设置正确的环境变量,比如TORCH_CUDA_ARCH_LIST等,特别是针对ARM架构的调整。此外,用户可能需要更新setuptools和wheel,确保编译工具是最新的。 最后,如果用户的问题仍未解决,可能需要查看详细的错误日志,或者尝试在社区寻求帮助,比如mmcv的GitHub仓库或论坛,看看是否有其他用户遇到类似的问题以及他们的解决方法。</think>### 解决Python中mmcv库的ImportError: undefined symbol问题 #### 1. 问题分析 错误`ImportError: undefined symbol: _ZNK3c105Error4whatEv`表明动态链接器在加载mmcv时无法找到PyTorch库中的符号`c10::Error::what()`。这通常由以下原因导致: - **PyTorch版本不匹配**:mmcv对PyTorch版本有严格依赖,ARM架构(aarch64)可能需特定编译版本[^1] - **mmcv安装方式错误**:预编译的mmcv包可能未适配ARM架构或当前PyTorch版本 - **ABI兼容性问题**:C++编译器版本或编译参数不一致导致符号表差异 #### 2. 分步解决方案 **步骤1:验证PyTorch安装** ```bash python -c "import torch; print(torch.__version__)" ``` - 确认输出为PyTorch官方支持的aarch64版本(如v2.0+) - ARM推荐安装方式: ```bash pip3 install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cpu ``` **步骤2:源码编译mmcv** ```bash git clone https://github.com/open-mmlab/mmcv.git cd mmcv MMCV_WITH_OPS=1 pip install -e . # 启用CUDA支持需先安装CUDA Toolkit ``` - 编译前确保安装依赖: ```bash sudo apt-get install -y libssl-dev libopenblas-dev g++-aarch64-linux-gnu ``` **步骤3:检查ABI兼容性** ```bash # 查看PyTorch使用的CXXABI版本 python -c "import torch; print(torch._C._GLIBCXX_USE_CXX11_ABI)" ``` - 若输出为`1`,编译mmcv时需添加: ```bash export CXXFLAGS="-D_GLIBCXX_USE_CXX11_ABI=1" ``` **步骤4:验证符号链接** ```bash ldd $(python -c "import mmcv; print(mmcv.__file__)") | grep libc10.so ``` - 确认输出路径指向正确版本的PyTorch库 #### 3. 架构特定配置 对于Jetson等ARM设备: ```bash # 设置CUDA架构 export TORCH_CUDA_ARCH_LIST="5.3;6.2;7.2" # Jetson TX2/Xavier参数 export FORCE_CUDA=1 ``` #### 4. 版本组合建议 | mmcv版本 | PyTorch版本 | Python版本 | |----------|-------------|------------| | 2.0.0 | 1.12.0+ | 3.8-3.10 | | 1.7.1 | 1.9.0+ | 3.7-3.9 | [^1]: PyTorch官方从v1.8开始提供aarch64预编译包
阅读全文

相关推荐

(li) lenovo@lenovo-ThinkStation-P920:/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan$ pip install -v --no-cache-dir --force-reinstall . 2>&1 | tee build.log Using pip 25.1 from /home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/pip (python 3.10) Looking in indexes: https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple Processing /media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan Preparing metadata (setup.py): started Running command python setup.py egg_info A module that was compiled using NumPy 1.x cannot be run in NumPy 2.2.6 as it may crash. To support both 1.x and 2.x versions of NumPy, modules must be compiled with NumPy 2.0. Some module may need to rebuild instead e.g. with 'pybind11>=2.12'. If you are a user of the module, the easiest solution will be to downgrade to 'numpy<2' or try to upgrade the affected module. We expect that some modules will need time to support NumPy 2. Traceback (most recent call last): File "<string>", line 2, in <module> File "", line 35, in <module> File "/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/setup.py", line 17, in <module> import torch File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/__init__.py", line 1471, in <module> from .functional import * # noqa: F403 File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/functional.py", line 9, in <module> import torch.nn.functional as F File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/nn/__init__.py", line 1, in <module> from .modules import * # noqa: F403 File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/nn/modules/__init__.py", line 35, in <module> from .transformer import TransformerEncoder, TransformerDecoder, \ File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/nn/modules/transformer.py", line 20, in <module> device: torch.device = torch.device(torch._C._get_default_device()), # torch.device('cpu'), /home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/nn/modules/transformer.py:20: UserWarning: Failed to initialize NumPy: _ARRAY_API not found (Triggered internally at ../torch/csrc/utils/tensor_numpy.cpp:84.) device: torch.device = torch.device(torch._C._get_default_device()), # torch.device('cpu'), torch.__version__ = 2.2.0+cu118 CUDA_HOME = /home/lenovo/anaconda3/envs/li CUDA version: 11.8 /home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/dist.py:759: SetuptoolsDeprecationWarning: License classifiers are deprecated. !! ******************************************************************************** Please consider removing the following classifiers in favor of a SPDX license expression: License :: OSI Approved :: BSD License See https://packaging.python.org/en/latest/guides/writing-pyproject-toml/#license for details. ******************************************************************************** !! self._finalize_license_expression() running egg_info creating /tmp/pip-pip-egg-info-w2djvsss/selective_scan.egg-info writing /tmp/pip-pip-egg-info-w2djvsss/selective_scan.egg-info/PKG-INFO writing dependency_links to /tmp/pip-pip-egg-info-w2djvsss/selective_scan.egg-info/dependency_links.txt writing requirements to /tmp/pip-pip-egg-info-w2djvsss/selective_scan.egg-info/requires.txt writing top-level names to /tmp/pip-pip-egg-info-w2djvsss/selective_scan.egg-info/top_level.txt writing manifest file '/tmp/pip-pip-egg-info-w2djvsss/selective_scan.egg-info/SOURCES.txt' reading manifest file '/tmp/pip-pip-egg-info-w2djvsss/selective_scan.egg-info/SOURCES.txt' writing manifest file '/tmp/pip-pip-egg-info-w2djvsss/selective_scan.egg-info/SOURCES.txt' Preparing metadata (setup.py): finished with status 'done' Collecting torch (from selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/0a/7c/0a5b3aee977596459ec45be2220370fde8e017f651fecc40522fd478cb1e/torch-2.7.1-cp310-cp310-manylinux_2_28_x86_64.whl (821.2 MB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 821.2/821.2 MB 1.1 MB/s eta 0:00:00 Collecting packaging (from selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/20/12/38679034af332785aac8774540895e234f4d07f7545804097de4b666afd8/packaging-25.0-py3-none-any.whl (66 kB) Collecting ninja (from selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/eb/7a/455d2877fe6cf99886849c7f9755d897df32eaf3a0fba47b56e615f880f7/ninja-1.11.1.4-py3-none-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (422 kB) Collecting einops (from selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/87/62/9773de14fe6c45c23649e98b83231fffd7b9892b6cf863251dc2afa73643/einops-0.8.1-py3-none-any.whl (64 kB) Collecting filelock (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/4d/36/2a115987e2d8c300a974597416d9de88f2444426de9571f4b59b2cca3acc/filelock-3.18.0-py3-none-any.whl (16 kB) Collecting typing-extensions>=4.10.0 (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/69/e0/552843e0d356fbb5256d21449fa957fa4eff3bbc135a74a691ee70c7c5da/typing_extensions-4.14.0-py3-none-any.whl (43 kB) Collecting sympy>=1.13.3 (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/a2/09/77d55d46fd61b4a135c444fc97158ef34a095e5681d0a6c10b75bf356191/sympy-1.14.0-py3-none-any.whl (6.3 MB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 6.3/6.3 MB 946.1 kB/s eta 0:00:00 Link requires a different Python (3.10.18 not in: '>=3.11'): https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/eb/8d/776adee7bbf76365fdd7f2552710282c79a4ead5d2a46408c9043a2b70ba/networkx-3.5-py3-none-any.whl (from https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple/networkx/) (requires-python:>=3.11) Link requires a different Python (3.10.18 not in: '>=3.11'): https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/6c/4f/ccdb8ad3a38e583f214547fd2f7ff1fc160c43a75af88e6aec213404b96a/networkx-3.5.tar.gz (from https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple/networkx/) (requires-python:>=3.11) Link requires a different Python (3.10.18 not in: '>=3.11'): https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/3f/a1/46c1b6e202e3109d2a035b21a7e5534c5bb233ee30752d7f16a0bd4c3989/networkx-3.5rc0-py3-none-any.whl (from https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple/networkx/) (requires-python:>=3.11) Link requires a different Python (3.10.18 not in: '>=3.11'): https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/90/7e/0319606a20ced20730806b9f7fe91d8a92f7da63d76a5c388f87d3f7d294/networkx-3.5rc0.tar.gz (from https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple/networkx/) (requires-python:>=3.11) Collecting networkx (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/b9/54/dd730b32ea14ea797530a4479b2ed46a6fb250f682a9cfb997e968bf0261/networkx-3.4.2-py3-none-any.whl (1.7 MB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.7/1.7 MB 883.3 kB/s eta 0:00:00 Collecting jinja2 (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/62/a1/3d680cbfd5f4b8f15abc1d571870c5fc3e594bb582bc3b64ea099db13e56/jinja2-3.1.6-py3-none-any.whl (134 kB) Collecting fsspec (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/bb/61/78c7b3851add1481b048b5fdc29067397a1784e2910592bc81bb3f608635/fsspec-2025.5.1-py3-none-any.whl (199 kB) Collecting nvidia-cuda-nvrtc-cu12==12.6.77 (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/75/2e/46030320b5a80661e88039f59060d1790298b4718944a65a7f2aeda3d9e9/nvidia_cuda_nvrtc_cu12-12.6.77-py3-none-manylinux2014_x86_64.whl (23.7 MB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 23.7/23.7 MB 1.1 MB/s eta 0:00:00 Collecting nvidia-cuda-runtime-cu12==12.6.77 (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/e1/23/e717c5ac26d26cf39a27fbc076240fad2e3b817e5889d671b67f4f9f49c5/nvidia_cuda_runtime_cu12-12.6.77-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (897 kB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 897.7/897.7 kB 1.7 MB/s eta 0:00:00 Collecting nvidia-cuda-cupti-cu12==12.6.80 (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/49/60/7b6497946d74bcf1de852a21824d63baad12cd417db4195fc1bfe59db953/nvidia_cuda_cupti_cu12-12.6.80-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (8.9 MB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 8.9/8.9 MB 1.1 MB/s eta 0:00:00 Collecting nvidia-cudnn-cu12==9.5.1.17 (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/2a/78/4535c9c7f859a64781e43c969a3a7e84c54634e319a996d43ef32ce46f83/nvidia_cudnn_cu12-9.5.1.17-py3-none-manylinux_2_28_x86_64.whl (571.0 MB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 571.0/571.0 MB 1.1 MB/s eta 0:00:00 Collecting nvidia-cublas-cu12==12.6.4.1 (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/af/eb/ff4b8c503fa1f1796679dce648854d58751982426e4e4b37d6fce49d259c/nvidia_cublas_cu12-12.6.4.1-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (393.1 MB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 393.1/393.1 MB 889.2 kB/s eta 0:00:00 Collecting nvidia-cufft-cu12==11.3.0.4 (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/8f/16/73727675941ab8e6ffd86ca3a4b7b47065edcca7a997920b831f8147c99d/nvidia_cufft_cu12-11.3.0.4-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (200.2 MB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 200.2/200.2 MB 761.5 kB/s eta 0:00:00 Collecting nvidia-curand-cu12==10.3.7.77 (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/73/1b/44a01c4e70933637c93e6e1a8063d1e998b50213a6b65ac5a9169c47e98e/nvidia_curand_cu12-10.3.7.77-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (56.3 MB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 56.3/56.3 MB 1.1 MB/s eta 0:00:00 Collecting nvidia-cusolver-cu12==11.7.1.2 (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/f0/6e/c2cf12c9ff8b872e92b4a5740701e51ff17689c4d726fca91875b07f655d/nvidia_cusolver_cu12-11.7.1.2-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (158.2 MB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 158.2/158.2 MB 881.4 kB/s eta 0:00:00 Collecting nvidia-cusparse-cu12==12.5.4.2 (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/06/1e/b8b7c2f4099a37b96af5c9bb158632ea9e5d9d27d7391d7eb8fc45236674/nvidia_cusparse_cu12-12.5.4.2-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (216.6 MB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 216.6/216.6 MB 1.4 MB/s eta 0:00:00 Collecting nvidia-cusparselt-cu12==0.6.3 (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/3b/9a/72ef35b399b0e183bc2e8f6f558036922d453c4d8237dab26c666a04244b/nvidia_cusparselt_cu12-0.6.3-py3-none-manylinux2014_x86_64.whl (156.8 MB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 156.8/156.8 MB 887.6 kB/s eta 0:00:00 Collecting nvidia-nccl-cu12==2.26.2 (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/67/ca/f42388aed0fddd64ade7493dbba36e1f534d4e6fdbdd355c6a90030ae028/nvidia_nccl_cu12-2.26.2-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (201.3 MB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 201.3/201.3 MB 1.1 MB/s eta 0:00:00 Collecting nvidia-nvtx-cu12==12.6.77 (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/56/9a/fff8376f8e3d084cd1530e1ef7b879bb7d6d265620c95c1b322725c694f4/nvidia_nvtx_cu12-12.6.77-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (89 kB) Collecting nvidia-nvjitlink-cu12==12.6.85 (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/9d/d7/c5383e47c7e9bf1c99d5bd2a8c935af2b6d705ad831a7ec5c97db4d82f4f/nvidia_nvjitlink_cu12-12.6.85-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl (19.7 MB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 19.7/19.7 MB 1.9 MB/s eta 0:00:00 Collecting nvidia-cufile-cu12==1.11.1.6 (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/b2/66/cc9876340ac68ae71b15c743ddb13f8b30d5244af344ec8322b449e35426/nvidia_cufile_cu12-1.11.1.6-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (1.1 MB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.1/1.1 MB 1.9 MB/s eta 0:00:00 Collecting triton==3.3.1 (from torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/8d/a9/549e51e9b1b2c9b854fd761a1d23df0ba2fbc60bd0c13b489ffa518cfcb7/triton-3.3.1-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (155.6 MB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 155.6/155.6 MB 758.4 kB/s eta 0:00:00 Collecting setuptools>=40.8.0 (from triton==3.3.1->torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/a3/dc/17031897dae0efacfea57dfd3a82fdd2a2aeb58e0ff71b77b87e44edc772/setuptools-80.9.0-py3-none-any.whl (1.2 MB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.2/1.2 MB 872.9 kB/s eta 0:00:00 Collecting mpmath<1.4,>=1.1.0 (from sympy>=1.13.3->torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/43/e3/7d92a15f894aa0c9c4b49b8ee9ac9850d6e63b03c9c32c0367a13ae62209/mpmath-1.3.0-py3-none-any.whl (536 kB) ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 536.2/536.2 kB 919.5 kB/s eta 0:00:00 Collecting MarkupSafe>=2.0 (from jinja2->torch->selective_scan==0.0.2) Downloading https://mirrors.tuna.tsinghua.edu.cn/pypi/web/packages/22/35/137da042dfb4720b638d2937c38a9c2df83fe32d20e8c8f3185dbfef05f7/MarkupSafe-3.0.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (20 kB) Building wheels for collected packages: selective_scan DEPRECATION: Building 'selective_scan' using the legacy setup.py bdist_wheel mechanism, which will be removed in a future version. pip 25.3 will enforce this behaviour change. A possible replacement is to use the standardized build interface by setting the --use-pep517 option, (possibly combined with --no-build-isolation), or adding a pyproject.toml file to the source tree of 'selective_scan'. Discussion can be found at https://github.com/pypa/pip/issues/6334 Building wheel for selective_scan (setup.py): started Running command python setup.py bdist_wheel A module that was compiled using NumPy 1.x cannot be run in NumPy 2.2.6 as it may crash. To support both 1.x and 2.x versions of NumPy, modules must be compiled with NumPy 2.0. Some module may need to rebuild instead e.g. with 'pybind11>=2.12'. If you are a user of the module, the easiest solution will be to downgrade to 'numpy<2' or try to upgrade the affected module. We expect that some modules will need time to support NumPy 2. Traceback (most recent call last): File "<string>", line 2, in <module> File "", line 35, in <module> File "/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/setup.py", line 17, in <module> import torch File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/__init__.py", line 1471, in <module> from .functional import * # noqa: F403 File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/functional.py", line 9, in <module> import torch.nn.functional as F File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/nn/__init__.py", line 1, in <module> from .modules import * # noqa: F403 File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/nn/modules/__init__.py", line 35, in <module> from .transformer import TransformerEncoder, TransformerDecoder, \ File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/nn/modules/transformer.py", line 20, in <module> device: torch.device = torch.device(torch._C._get_default_device()), # torch.device('cpu'), /home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/nn/modules/transformer.py:20: UserWarning: Failed to initialize NumPy: _ARRAY_API not found (Triggered internally at ../torch/csrc/utils/tensor_numpy.cpp:84.) device: torch.device = torch.device(torch._C._get_default_device()), # torch.device('cpu'), torch.__version__ = 2.2.0+cu118 CUDA_HOME = /home/lenovo/anaconda3/envs/li CUDA version: 11.8 /home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/dist.py:759: SetuptoolsDeprecationWarning: License classifiers are deprecated. !! ******************************************************************************** Please consider removing the following classifiers in favor of a SPDX license expression: License :: OSI Approved :: BSD License See https://packaging.python.org/en/latest/guides/writing-pyproject-toml/#license for details. ******************************************************************************** !! self._finalize_license_expression() running bdist_wheel running build running build_ext /home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/utils/cpp_extension.py:425: UserWarning: There are no g++ version bounds defined for CUDA version 11.8 warnings.warn(f'There are no {compiler_name} version bounds defined for CUDA version {cuda_str_version}') building 'selective_scan_cuda_core' extension creating /media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/build/temp.linux-x86_64-cpython-310/csrc/selective_scan/cus Emitting ninja build file /media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/build/temp.linux-x86_64-cpython-310/build.ninja... Compiling objects... Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) [1/3] c++ -MMD -MF '/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/build/temp.linux-x86_64-cpython-310/csrc/selective_scan/cus/selective_scan.o'.d -pthread -B /home/lenovo/anaconda3/envs/li/compiler_compat -Wno-unused-result -Wsign-compare -DNDEBUG -fwrapv -O2 -Wall -fPIC -O2 -isystem /home/lenovo/anaconda3/envs/li/include -fPIC -O2 -isystem /home/lenovo/anaconda3/envs/li/include -fPIC '-I/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/csrc/selective_scan' -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include/torch/csrc/api/include -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include/TH -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include/THC -I/home/lenovo/anaconda3/envs/li/include -I/home/lenovo/anaconda3/envs/li/include/python3.10 -c -c '/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/csrc/selective_scan/cus/selective_scan.cpp' -o '/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/build/temp.linux-x86_64-cpython-310/csrc/selective_scan/cus/selective_scan.o' -O3 -std=c++17 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=selective_scan_cuda_core -D_GLIBCXX_USE_CXX11_ABI=0 FAILED: /media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/build/temp.linux-x86_64-cpython-310/csrc/selective_scan/cus/selective_scan.o c++ -MMD -MF '/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/build/temp.linux-x86_64-cpython-310/csrc/selective_scan/cus/selective_scan.o'.d -pthread -B /home/lenovo/anaconda3/envs/li/compiler_compat -Wno-unused-result -Wsign-compare -DNDEBUG -fwrapv -O2 -Wall -fPIC -O2 -isystem /home/lenovo/anaconda3/envs/li/include -fPIC -O2 -isystem /home/lenovo/anaconda3/envs/li/include -fPIC '-I/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/csrc/selective_scan' -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include/torch/csrc/api/include -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include/TH -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include/THC -I/home/lenovo/anaconda3/envs/li/include -I/home/lenovo/anaconda3/envs/li/include/python3.10 -c -c '/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/csrc/selective_scan/cus/selective_scan.cpp' -o '/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/build/temp.linux-x86_64-cpython-310/csrc/selective_scan/cus/selective_scan.o' -O3 -std=c++17 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=selective_scan_cuda_core -D_GLIBCXX_USE_CXX11_ABI=0 In file included from /home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include/ATen/cuda/CUDAContext.h:3, from /media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/csrc/selective_scan/cus/selective_scan.cpp:5: /home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include/ATen/cuda/CUDAContextLight.h:6:10: fatal error: cuda_runtime_api.h: 没有那个文件或目录 6 | #include <cuda_runtime_api.h> | ^~~~~~~~~~~~~~~~~~~~ compilation terminated. [2/3] /home/lenovo/anaconda3/envs/li/bin/nvcc --generate-dependencies-with-compile --dependency-output '/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/build/temp.linux-x86_64-cpython-310/csrc/selective_scan/cus/selective_scan_core_fwd.o'.d '-I/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/csrc/selective_scan' -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include/torch/csrc/api/include -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include/TH -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include/THC -I/home/lenovo/anaconda3/envs/li/include -I/home/lenovo/anaconda3/envs/li/include/python3.10 -c -c '/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/csrc/selective_scan/cus/selective_scan_core_fwd.cu' -o '/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/build/temp.linux-x86_64-cpython-310/csrc/selective_scan/cus/selective_scan_core_fwd.o' -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ -U__CUDA_NO_BFLOAT16_OPERATORS__ -U__CUDA_NO_BFLOAT16_CONVERSIONS__ -U__CUDA_NO_BFLOAT162_OPERATORS__ -U__CUDA_NO_BFLOAT162_CONVERSIONS__ --expt-relaxed-constexpr --expt-extended-lambda --use_fast_math --ptxas-options=-v -lineinfo -arch=sm_86 --threads 4 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=selective_scan_cuda_core -D_GLIBCXX_USE_CXX11_ABI=0 FAILED: /media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/build/temp.linux-x86_64-cpython-310/csrc/selective_scan/cus/selective_scan_core_fwd.o /home/lenovo/anaconda3/envs/li/bin/nvcc --generate-dependencies-with-compile --dependency-output '/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/build/temp.linux-x86_64-cpython-310/csrc/selective_scan/cus/selective_scan_core_fwd.o'.d '-I/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/csrc/selective_scan' -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include/torch/csrc/api/include -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include/TH -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include/THC -I/home/lenovo/anaconda3/envs/li/include -I/home/lenovo/anaconda3/envs/li/include/python3.10 -c -c '/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/csrc/selective_scan/cus/selective_scan_core_fwd.cu' -o '/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/build/temp.linux-x86_64-cpython-310/csrc/selective_scan/cus/selective_scan_core_fwd.o' -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ -U__CUDA_NO_BFLOAT16_OPERATORS__ -U__CUDA_NO_BFLOAT16_CONVERSIONS__ -U__CUDA_NO_BFLOAT162_OPERATORS__ -U__CUDA_NO_BFLOAT162_CONVERSIONS__ --expt-relaxed-constexpr --expt-extended-lambda --use_fast_math --ptxas-options=-v -lineinfo -arch=sm_86 --threads 4 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=selective_scan_cuda_core -D_GLIBCXX_USE_CXX11_ABI=0 <command-line>: fatal error: cuda_runtime.h: 没有那个文件或目录 compilation terminated. <command-line>: fatal error: cuda_runtime.h: 没有那个文件或目录 compilation terminated. fatal : Could not open input file /tmp/tmpxft_00005756_00000000-7_selective_scan_core_fwd.cpp1.ii [3/3] /home/lenovo/anaconda3/envs/li/bin/nvcc --generate-dependencies-with-compile --dependency-output '/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/build/temp.linux-x86_64-cpython-310/csrc/selective_scan/cus/selective_scan_core_bwd.o'.d '-I/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/csrc/selective_scan' -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include/torch/csrc/api/include -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include/TH -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include/THC -I/home/lenovo/anaconda3/envs/li/include -I/home/lenovo/anaconda3/envs/li/include/python3.10 -c -c '/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/csrc/selective_scan/cus/selective_scan_core_bwd.cu' -o '/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/build/temp.linux-x86_64-cpython-310/csrc/selective_scan/cus/selective_scan_core_bwd.o' -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ -U__CUDA_NO_BFLOAT16_OPERATORS__ -U__CUDA_NO_BFLOAT16_CONVERSIONS__ -U__CUDA_NO_BFLOAT162_OPERATORS__ -U__CUDA_NO_BFLOAT162_CONVERSIONS__ --expt-relaxed-constexpr --expt-extended-lambda --use_fast_math --ptxas-options=-v -lineinfo -arch=sm_86 --threads 4 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=selective_scan_cuda_core -D_GLIBCXX_USE_CXX11_ABI=0 FAILED: /media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/build/temp.linux-x86_64-cpython-310/csrc/selective_scan/cus/selective_scan_core_bwd.o /home/lenovo/anaconda3/envs/li/bin/nvcc --generate-dependencies-with-compile --dependency-output '/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/build/temp.linux-x86_64-cpython-310/csrc/selective_scan/cus/selective_scan_core_bwd.o'.d '-I/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/csrc/selective_scan' -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include/torch/csrc/api/include -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include/TH -I/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/include/THC -I/home/lenovo/anaconda3/envs/li/include -I/home/lenovo/anaconda3/envs/li/include/python3.10 -c -c '/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/csrc/selective_scan/cus/selective_scan_core_bwd.cu' -o '/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/build/temp.linux-x86_64-cpython-310/csrc/selective_scan/cus/selective_scan_core_bwd.o' -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O3 -std=c++17 -U__CUDA_NO_HALF_OPERATORS__ -U__CUDA_NO_HALF_CONVERSIONS__ -U__CUDA_NO_BFLOAT16_OPERATORS__ -U__CUDA_NO_BFLOAT16_CONVERSIONS__ -U__CUDA_NO_BFLOAT162_OPERATORS__ -U__CUDA_NO_BFLOAT162_CONVERSIONS__ --expt-relaxed-constexpr --expt-extended-lambda --use_fast_math --ptxas-options=-v -lineinfo -arch=sm_86 --threads 4 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=selective_scan_cuda_core -D_GLIBCXX_USE_CXX11_ABI=0 <command-line>: fatal error: cuda_runtime.h: 没有那个文件或目录 compilation terminated. <command-line>: fatal error: cuda_runtime.h: 没有那个文件或目录 compilation terminated. fatal : Could not open input file /tmp/tmpxft_00005755_00000000-7_selective_scan_core_bwd.cpp1.ii ninja: build stopped: subcommand failed. Traceback (most recent call last): File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/utils/cpp_extension.py", line 2096, in _run_ninja_build subprocess.run( File "/home/lenovo/anaconda3/envs/li/lib/python3.10/subprocess.py", line 526, in run raise CalledProcessError(retcode, process.args, subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1. The above exception was the direct cause of the following exception: Traceback (most recent call last): File "<string>", line 2, in <module> File "", line 35, in <module> File "/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/setup.py", line 146, in <module> setup( File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/__init__.py", line 117, in setup return distutils.core.setup(**attrs) File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/_distutils/core.py", line 186, in setup return run_commands(dist) File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/_distutils/core.py", line 202, in run_commands dist.run_commands() File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/_distutils/dist.py", line 1002, in run_commands self.run_command(cmd) File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/dist.py", line 1104, in run_command super().run_command(command) File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/_distutils/dist.py", line 1021, in run_command cmd_obj.run() File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/command/bdist_wheel.py", line 370, in run self.run_command("build") File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/_distutils/cmd.py", line 357, in run_command self.distribution.run_command(command) File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/dist.py", line 1104, in run_command super().run_command(command) File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/_distutils/dist.py", line 1021, in run_command cmd_obj.run() File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/_distutils/command/build.py", line 135, in run self.run_command(cmd_name) File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/_distutils/cmd.py", line 357, in run_command self.distribution.run_command(command) File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/dist.py", line 1104, in run_command super().run_command(command) File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/_distutils/dist.py", line 1021, in run_command cmd_obj.run() File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/command/build_ext.py", line 99, in run _build_ext.run(self) File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/_distutils/command/build_ext.py", line 368, in run self.build_extensions() File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/utils/cpp_extension.py", line 871, in build_extensions build_ext.build_extensions(self) File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/_distutils/command/build_ext.py", line 484, in build_extensions self._build_extensions_serial() File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/_distutils/command/build_ext.py", line 510, in _build_extensions_serial self.build_extension(ext) File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/command/build_ext.py", line 264, in build_extension _build_ext.build_extension(self, ext) File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/_distutils/command/build_ext.py", line 565, in build_extension objects = self.compiler.compile( File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/utils/cpp_extension.py", line 684, in unix_wrap_ninja_compile _write_ninja_file_and_compile_objects( File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/utils/cpp_extension.py", line 1774, in _write_ninja_file_and_compile_objects _run_ninja_build( File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/utils/cpp_extension.py", line 2112, in _run_ninja_build raise RuntimeError(message) from e RuntimeError: Error compiling objects for extension error: subprocess-exited-with-error × python setup.py bdist_wheel did not run successfully. │ exit code: 1 ╰─> See above for output. note: This error originates from a subprocess, and is likely not a problem with pip. full command: /home/lenovo/anaconda3/envs/li/bin/python3.10 -u -c ' exec(compile('"'"''"'"''"'"' # This is -- a caller that pip uses to run setup.py # # - It imports setuptools before invoking setup.py, to enable projects that directly # import from distutils.core to work with newer packaging standards. # - It provides a clear error message when setuptools is not installed. # - It sets sys.argv[0] to the underlying setup.py, when invoking setup.py so # setuptools doesn'"'"'t think the script is -c. This avoids the following warning: # manifest_maker: standard file '"'"'-c'"'"' not found". # - It generates a shim setup.py, for handling setup.cfg-only projects. import os, sys, tokenize, traceback try: import setuptools except ImportError: print( "ERROR: Can not execute setup.py since setuptools failed to import in " "the build environment with exception:", file=sys.stderr, ) traceback.print_exc() sys.exit(1) __file__ = %r sys.argv[0] = __file__ if os.path.exists(__file__): filename = __file__ with tokenize.open(__file__) as f: setup_py_code = f.read() else: filename = "<auto-generated setuptools caller>" setup_py_code = "from setuptools import setup; setup()" exec(compile(setup_py_code, filename, "exec")) '"'"''"'"''"'"' % ('"'"'/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/setup.py'"'"',), "", "exec"))' bdist_wheel -d /tmp/pip-wheel-fm2tmb40 cwd: /media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/ Building wheel for selective_scan (setup.py): finished with status 'error' ERROR: Failed building wheel for selective_scan Running setup.py clean for selective_scan Running command python setup.py clean A module that was compiled using NumPy 1.x cannot be run in NumPy 2.2.6 as it may crash. To support both 1.x and 2.x versions of NumPy, modules must be compiled with NumPy 2.0. Some module may need to rebuild instead e.g. with 'pybind11>=2.12'. If you are a user of the module, the easiest solution will be to downgrade to 'numpy<2' or try to upgrade the affected module. We expect that some modules will need time to support NumPy 2. Traceback (most recent call last): File "<string>", line 2, in <module> File "", line 35, in <module> File "/media/lenovo/PHILIPS/Mamba_20250409_ torch22_cuda118/VMamba-main/kernels/selective_scan/setup.py", line 17, in <module> import torch File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/__init__.py", line 1471, in <module> from .functional import * # noqa: F403 File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/functional.py", line 9, in <module> import torch.nn.functional as F File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/nn/__init__.py", line 1, in <module> from .modules import * # noqa: F403 File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/nn/modules/__init__.py", line 35, in <module> from .transformer import TransformerEncoder, TransformerDecoder, \ File "/home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/nn/modules/transformer.py", line 20, in <module> device: torch.device = torch.device(torch._C._get_default_device()), # torch.device('cpu'), /home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/torch/nn/modules/transformer.py:20: UserWarning: Failed to initialize NumPy: _ARRAY_API not found (Triggered internally at ../torch/csrc/utils/tensor_numpy.cpp:84.) device: torch.device = torch.device(torch._C._get_default_device()), # torch.device('cpu'), torch.__version__ = 2.2.0+cu118 CUDA_HOME = /home/lenovo/anaconda3/envs/li CUDA version: 11.8 /home/lenovo/anaconda3/envs/li/lib/python3.10/site-packages/setuptools/dist.py:759: SetuptoolsDeprecationWarning: License classifiers are deprecated. !! ******************************************************************************** Please consider removing the following classifiers in favor of a SPDX license expression: License :: OSI Approved :: BSD License See https://packaging.python.org/en/latest/guides/writing-pyproject-toml/#license for details. ******************************************************************************** !! self._finalize_license_expression() running clean removing 'build/temp.linux-x86_64-cpython-310' (and everything under it) 'build/lib.linux-x86_64-cpython-310' does not exist -- can't clean it 'build/bdist.linux-x86_64' does not exist -- can't clean it 'build/scripts-3.10' does not exist -- can't clean it removing 'build' Failed to build selective_scan ERROR: Failed to build installable wheels for some pyproject.toml based projects (selective_scan)

大家在看

recommend-type

信贷管理系统需求规格说明书

目录 第1章 1.1 背景概括 …………………………………………………… 5 1.2 可行性分析……………………………………………………… 7 (1) 经济可行性………………………………………………… 7 (2)操作可行性………………………………………………… 8 (3)技术可行性………………………………………………… (4)系统特点……………………………………………………… 8 第2章 需求分析………………………………………………………… 9 4.1 功能……………………………………………… 11 4.2 目标 4.3 业务流程设计……………………………………………… 11 (1) 存款管理……………………………………………………… 9 (2) 贷款管理…………………………………………………… 10 4.4 业务流程重组 4.5 数据流程图………………………………………………… 13 第3章 总体设计………………………………………………………… 11 第6章 详细设计………………………………………………………… 16 6.1 模块设计 ……………………………………………………… 16 6.2 代码设计……………………………………………………… 20 6.3 输入输出设计 ……………………………………………… 20 结束语 ……………………………………………………………………… 21 致谢 …………………………………………………………………………… 22 参考文献……………………………………………………………………… 23
recommend-type

genetic-algorithms:(python)01背包问题和平衡分配问题的遗传算法

这是遗传算法的python实现,用于对0/1背包问题进行组合优化,并将其与本地搜索(爬坡)进行混合,以解决平衡分配问题。
recommend-type

基于赛灵思的FPGA 支持 10-100Gbit/s 的 TCP/IP、RoCEv2、UDP/IP 的可扩展网络堆栈

赛灵思 Vivado 2019.1 cmake 3.0 或更高版本 支持的板 赛灵思VC709 赛灵思VCU118 阿尔法数据ADM-PCIE-7V3 文件内有详细说明
recommend-type

keras-gp:硬+高斯过程

Keras的高斯过程 KGP通过高斯过程(GP)层扩展了 。 它允许人们使用由Keras构建的网络构造的内核构建灵活的GP模型。 模型的结构化部分(神经网络)在或上运行。 GP层使用基于库的自定义后端,并基于和构建。 可以使用批量或半随机优化方法分阶段或联合训练模型(请参见)。 有关深度内核学习和KISS-GP的其他资源和教程,请参阅 KGP兼容:Python 2.7-3.5 。 特别是,此程序包实现了本文中描述的方法: 学习具有递归结构的可扩展深核Maruan Al-Shedivat,Andrew Gordon Wilson,Yunus Saatchi,Huzhiting Hu,Eric P.Xing ,2017。 入门 KGP允许使用功能性API以与Keras相同的方式构建模型。 例如,只需几行代码即可构建和编译一个简单的GP-RNN模型: from keras . layer
recommend-type

易语言CPU优化

易语言CPU优化,改下进程名字即可。。一起学习,一起进步。

最新推荐

recommend-type

indispensable-tvosx64-3.14.0-javadoc.jar

indispensable-tvosx64-3.14.0-javadoc.jar
recommend-type

Node.js构建的运动咖啡馆RESTful API介绍

标题《sportscafeold:体育咖啡馆》指出了项目名称为“体育咖啡馆”,这个名字暗示了该项目可能是一个结合了运动和休闲主题的咖啡馆相关的网络服务平台。该项目运用了多种技术栈,核心的开发语言为JavaScript,这从标签中可以得到明确的信息。 从描述中可以提取以下知识点: 1. **Node.js**:体育咖啡馆项目使用了Node.js作为服务器端运行环境。Node.js是一个基于Chrome V8引擎的JavaScript运行环境,它能够使得JavaScript应用于服务器端开发。Node.js的事件驱动、非阻塞I/O模型使其适合处理大量并发连接,这对于RESTFUL API的构建尤为重要。 2. **Express Framework**:项目中使用了Express框架来创建RESTFUL API。Express是基于Node.js平台,快速、灵活且极简的Web应用开发框架。它提供了构建Web和移动应用的强大功能,是目前最流行的Node.js Web应用框架之一。RESTFUL API是一组遵循REST原则的应用架构,其设计宗旨是让Web服务通过HTTP协议进行通信,并且可以使用各种语言和技术实现。 3. **Mongoose ORM**:这个项目利用了Mongoose作为操作MongoDB数据库的接口。Mongoose是一个对象文档映射器(ODM),它为Node.js提供了MongoDB数据库的驱动。通过Mongoose可以定义数据模型,进行数据库操作和查询,从而简化了对MongoDB数据库的操作。 4. **Passport.js**:项目中采用了Passport.js库来实现身份验证系统。Passport是一个灵活的Node.js身份验证中间件,它支持多种验证策略,例如用户名和密码、OAuth等。它提供了标准化的方法来为用户登录提供认证,是用户认证功能的常用解决方案。 5. **版权信息**:项目的版权声明表明了Sportscafe 2015是版权所有者,这表明项目或其相关内容最早发布于2015年或之前。这可能表明该API背后有商业实体的支持或授权使用。 从【压缩包子文件的文件名称列表】中我们可以了解到,该文件的版本控制仓库使用的是“master”分支。在Git版本控制系统中,“master”分支通常用于存放当前可部署的稳定版本代码。在“master”分支上进行的更改通常都是经过测试且准备发布到生产环境的。 综上所述,我们可以知道体育咖啡馆项目是一个利用现代JavaScript技术栈搭建的后端服务。它包含了处理HTTP请求的Express框架、连接MongoDB数据库的Mongoose库和实现用户身份验证的Passport.js中间件。该项目可用于构建提供体育信息、咖啡馆菜单信息、预约服务等的Web应用或API服务,这为体育咖啡馆的营销、用户体验和数据管理提供了可能。 考虑到文档资料的提及,该项目的安装和API文档应该包含在项目资料中,可能在项目的README文件或其他说明文档中。对于项目的使用者或者开发者而言,这部分文档非常重要,因为它们可以提供详细的信息和指导,帮助用户快速部署和使用该API。 总结来说,这是一套针对体育咖啡馆相关业务的后端解决方案,它使用了流行的开源技术栈,可以灵活地应用于体育咖啡馆的网络服务中,如信息发布、在线预约、会员管理等。
recommend-type

【LNR优化与用户体验】:一文看透互操作优化如何提升用户感知

# 摘要 LNR(邻区关系优化)是提升移动通信网络性能与用户体验的关键技术。本文系统阐述了LNR优化的基本概念、理论基础与技术实现路径,构建了包括信道质量评估、干扰建模及关键性能指标分析在内的数学模型,并探讨了参数配置、邻区管理及AI与大数据在LNR优化中的应用。通过量化用户感知指标,分析了LNR优化对视频流畅度、页面加载速度及切换性能的实际改善效果,并结合典型场景验证了其优化成效。本文进一步展望了LNR技术在5G及未来网络中的发展趋势与技术挑战。
recommend-type

Java1.8 的编程语言、使用场景、版本号、厂商、是否开源、发行日期、终止日期、可替代产品、推荐产品是什么

以下是关于 **Java 1.8** 的全面信息汇总,涵盖其编程语言特性、使用场景、版本号、厂商、是否开源、发行日期、终止支持日期、可替代产品和推荐产品。 --- ## ✅ Java 1.8 综合信息表 | 项目 | 内容 | |------|------| | **编程语言** | Java | | **版本号** | Java 1.8(也称为 Java 8) | | **厂商** | Oracle、Adoptium、Amazon(Corretto)、Azul(Zulu)、Red Hat、IBM 等 | | **是否开源** | ✅ 是(OpenJDK 1.8 是开源的,Oracle
recommend-type

Java开发的教区牧民支持系统介绍

根据给定文件信息,下面将详细阐述相关知识点: ### 标题知识点 #### catecumenus-java: 教区牧民支持系统 - **Java技术栈应用**:标题提到的“catecumenus-java”表明这是一个使用Java语言开发的系统。Java是目前最流行的编程语言之一,广泛应用于企业级应用、Web开发、移动应用等,尤其是在需要跨平台运行的应用中。Java被设计为具有尽可能少的实现依赖,所以它可以在多种处理器上运行。 - **教区牧民支持系统**:从标题来看,这个系统可能面向的是教会管理或教区管理,用来支持牧民(教会领导者或牧师)的日常管理工作。具体功能可能包括教友信息管理、教区活动安排、宗教教育资料库、财务管理、教堂资源调配等。 ### 描述知识点 #### 儿茶类 - **儿茶素(Catechin)**:描述中提到的“儿茶类”可能与“catecumenus”(新信徒、教徒)有关联,暗示这个系统可能与教会或宗教教育相关。儿茶素是一类天然的多酚类化合物,常见于茶、巧克力等植物中,具有抗氧化、抗炎等多种生物活性,但在系统标题中可能并无直接关联。 - **系统版本号**:“0.0.1”表示这是一个非常初期的版本,意味着该系统可能刚刚开始开发,功能尚不完善。 ### 标签知识点 #### Java - **Java语言特点**:标签中明确提到了“Java”,这暗示了整个系统都是用Java编程语言开发的。Java的特点包括面向对象、跨平台(即一次编写,到处运行)、安全性、多线程处理能力等。系统使用Java进行开发,可能看重了这些特点,尤其是在构建可扩展、稳定的后台服务。 - **Java应用领域**:Java广泛应用于企业级应用开发中,包括Web应用程序、大型系统后台、桌面应用以及移动应用(Android)。所以,此系统可能也会涉及这些技术层面。 ### 压缩包子文件的文件名称列表知识点 #### catecumenus-java-master - **Git项目结构**:文件名称中的“master”表明了这是Git版本控制系统中的一个主分支。在Git中,“master”分支通常被用作项目的主干,是默认的开发分支,所有开发工作都是基于此分支进行的。 - **项目目录结构**:在Git项目中,“catecumenus-java”文件夹应该包含了系统的源代码、资源文件、构建脚本、文档等。文件夹可能包含各种子文件夹和文件,比如src目录存放Java源代码,lib目录存放相关依赖库,以及可能的build.xml文件用于构建过程(如Ant或Maven构建脚本)。 ### 结合以上信息的知识点整合 综合以上信息,我们可以推断“catecumenus-java: 教区牧民支持系统”是一个使用Java语言开发的系统,可能正处于初级开发阶段。这个系统可能是为了支持教会内部管理,提供信息管理、资源调度等功能。其使用Java语言的目的可能是希望利用Java的多线程处理能力、跨平台特性和强大的企业级应用支持能力,以实现一个稳定和可扩展的系统。项目结构遵循了Git版本控制的规范,并且可能采用了模块化的开发方式,各个功能模块的代码和资源文件都有序地组织在不同的子文件夹内。 该系统可能采取敏捷开发模式,随着版本号的增加,系统功能将逐步完善和丰富。由于是面向教会的内部支持系统,对系统的用户界面友好性、安全性和数据保护可能会有较高的要求。此外,考虑到宗教性质的敏感性,系统的开发和使用可能还需要遵守特定的隐私和法律法规。
recommend-type

LNR切换成功率提升秘籍:参数配置到网络策略的全面指南

# 摘要 LNR(LTE to NR)切换技术是5G网络部署中的关键环节,直接影
recommend-type

How to install watt toolkit in linux ?

安装 Watt Toolkit(原名 Steam++)在 Linux 系统上通常可以通过编译源码或者使用预编译的二进制文件来完成。Watt Toolkit 是一个开源工具,主要用于加速 Steam 平台的下载速度,支持跨平台运行,因此在 Linux 上也能够很好地工作。 ### 安装步骤 #### 方法一:使用预编译的二进制文件 1. 访问 [Watt Toolkit 的 GitHub 仓库](https://github.com/BeyondDimension/SteamTools) 并下载适用于 Linux 的最新版本。 2. 解压下载的压缩包。 3. 给予可执行权限: ```
recommend-type

PHP实现用户墙上帖子与评论的分享功能

根据给定文件信息,我们可以推导出与“userwallposts”相关的知识点。这里涉及的关键概念包括用户墙面墙(User Wall)、帖子(Posts)和评论(Comments),以及它们在编程语言PHP中的实现方式。用户墙是一种允许用户发布信息,并让他们的朋友或跟随者查看并参与讨论的功能,常见于社交网站。 ### 用户墙概念 用户墙类似于现实生活中的一面墙,用户可以在上面贴上“帖子”来分享自己的想法、照片、视频等信息。其他用户可以在这些帖子下面进行“评论”,类似于在墙上留言。这种互动方式构建了一个社区式的交流环境,增加了用户之间的互动性和参与感。 ### 用户墙的实现 在PHP中实现用户墙功能需要处理前端用户界面和后端服务器逻辑。前端负责展示用户墙、帖子和评论的界面,而后端则负责存储、检索和管理这些数据。 1. **前端实现**:前端可以使用HTML、CSS和JavaScript来构建用户墙的界面。使用AJAX技术可以让用户无需刷新页面即可提交和获取新的帖子和评论。此外,可能还会用到模板引擎(如Twig或Smarty)来动态生成页面内容。 2. **后端实现**:后端PHP代码将负责处理前端发送的请求,如帖子和评论的添加、删除和检索。数据库(如MySQL)将用于存储用户信息、帖子内容、评论以及它们之间的关联关系。 3. **数据库设计**: - 用户表(users):存储用户信息,例如用户名、密码(加密存储)、用户状态等。 - 帖子表(posts):存储帖子信息,例如帖子ID、帖子内容、发帖时间、所属用户ID等。 - 评论表(comments):存储评论信息,包括评论ID、评论内容、评论时间、所属帖子ID和用户ID等。 4. **PHP与数据库交互**:使用PDO(PHP Data Objects)或mysqli扩展来执行SQL语句与数据库进行交互。PDO提供了数据库访问的抽象层,可以连接多种数据库系统,而mysqli则针对MySQL进行了优化。 5. **安全性**: - 输入验证:为了防止SQL注入等安全问题,需要对用户输入进行验证和清理。 - 输出编码:在将数据输出到浏览器之前,应将特殊字符转换为HTML实体。 - 用户认证:用户登录系统时,应采取安全措施如使用会话管理(session management)和防止跨站请求伪造(CSRF)。 6. **功能实现细节**: - 发布帖子:用户输入帖子内容并提交,后端接收并存储到帖子表中。 - 显示帖子:从帖子表中检索所有帖子并展示在用户墙上,包括帖子标题、内容、发布时间和发帖人等信息。 - 发布评论:用户对特定帖子发表评论,后端接收评论信息并将其存储到评论表中。 - 显示评论:为每个帖子显示其下的所有评论,包括评论内容、时间、评论者等。 ### 开源项目实践 “userwallposts-master”暗示了可能存在一个与用户墙帖子和评论相关的开源项目或代码库。这个项目可能包含预设的代码和文件结构,允许开发者下载、安装和配置来创建他们自己的用户墙功能。开发人员可以使用这个项目作为起点,根据自己的需求进一步定制和扩展功能。 在实际开发过程中,还需要考虑系统的可扩展性和维护性。例如,可以设计RESTful API让前端和后端分离,或者使用现代的PHP框架(如Laravel、Symfony等)来简化开发流程和提高代码的组织性。 在总结上述内容后,我们可以了解到用户墙是社交平台中常见的一种功能,其核心功能包括发布帖子和评论。在PHP环境下实现这样的功能需要对前端界面和后端逻辑有深入的理解,以及对数据库设计和交互的安全性有一定的认识。开源项目如“userwallposts-master”可能提供了一个基础框架,帮助开发者快速构建和部署一个用户墙系统。
recommend-type

【LNR信令深度解析】:MR-DC双连接建立全过程技术揭秘

# 摘要 本文系统探讨了LNR信令与MR-DC双连接技术的基本原理、架构组成及其关键信令流程。深入分析了MR-DC的网络架构分类、核心网元功能、无线承载管理机制以及双连接建立过程中的关键信令交互路径。同时,文章解析了LNR信令消息的结构特征与关键字段,探讨了MR-DC场景下的性能评估指标与优化策略,包括信令压缩、负载均衡及节能调度机制。最后,文章展望了MR-DC技术在5G
recommend-type

计算机类:得全方位考,不能局限软考这句话的含义

计算机类考试的全面性要求考生不仅要掌握理论知识,还要具备实践能力、分析能力和对行业发展趋势的理解。考试内容通常涵盖计算机基础、核心技术和应用、前沿技术以及行业标准和规范。考生需要全方位掌握知识体系,不能仅限于软考(软件水平考试)的内容,还需结合实际应用场景和新兴技术的发展。 在计算机类考试中,基础知识的掌握是关键。例如IP地址的分类(如引用[1]中提到的A、B、C、D和E类地址),需要理解其划分规则、网络ID和主机ID的表示方式以及如何根据需求选择合适的IP地址类别。这类知识是网络设计和管理的基础,考试中可能会涉及实际案例分析,要求考生能够灵活运用这些知识解决具体问题。 此外,随着信息技术