diff options
author | CoprDistGit <infra@openeuler.org> | 2024-01-27 12:48:10 +0000 |
---|---|---|
committer | CoprDistGit <infra@openeuler.org> | 2024-01-27 12:48:10 +0000 |
commit | 96f14f3e83529ed27128ed1a4b7d7b5ba9ec6881 (patch) | |
tree | 60cc99b5fef59411567516dbecd65fec2d430e55 | |
parent | 3e9add293255a2865fea7f245b9cfe79f59f2e79 (diff) |
automatic import of DeepSpeedopeneuler23.09
-rw-r--r-- | .gitignore | 1 | ||||
-rw-r--r-- | DeepSpeed.spec | 96 | ||||
-rw-r--r-- | sources | 1 |
3 files changed, 98 insertions, 0 deletions
@@ -0,0 +1 @@ +/DeepSpeed-0.12.2.tar.gz diff --git a/DeepSpeed.spec b/DeepSpeed.spec new file mode 100644 index 0000000..b070592 --- /dev/null +++ b/DeepSpeed.spec @@ -0,0 +1,96 @@ +%global _empty_manifest_terminate_build 0 +%define debug_package %{nil} +Name: DeepSpeed +Version: 0.12.2 +Release: 2 +Summary: Tensors and Dynamic neural networks in Python with strong GPU acceleration +License: BSD-3 +URL: https://github.com/microsoft/DeepSpeed +Source0: https://atomgit.com/havefun/DeepSpeed/raw/master/DeepSpeed-0.12.2.tar.gz + +BuildRequires: g++ +Requires: python3-future +Requires: python3-numpy + +%description +PyTorch is a Python package that provides two high-level features: +- Tensor computation (like NumPy) with strong GPU acceleration +- Deep neural networks built on a tape-based autograd system +You can reuse your favorite Python packages such as NumPy, SciPy and Cython to extend PyTorch when needed. + +%package -n python3-DeepSpeed +Summary: Tensors and Dynamic neural networks in Python with strong GPU acceleration +Provides: python-DeepSpeed +BuildRequires: python3-devel +BuildRequires: python3-setuptools +BuildRequires: python3-setuptools_scm +BuildRequires: python3-pbr +BuildRequires: python3-pip +BuildRequires: python3-wheel +BuildRequires: python3-hatchling + +BuildRequires: python3-astunparse +BuildRequires: python3-numpy +BuildRequires: python3-pyyaml +BuildRequires: cmake +BuildRequires: python3-typing-extensions +BuildRequires: python3-requests +BuildRequires: python3-pytorch + +AutoReqProv: no + +%description -n python3-DeepSpeed +PyTorch is a Python package that provides two high-level features: +- Tensor computation (like NumPy) with strong GPU acceleration +- Deep neural networks built on a tape-based autograd system +You can reuse your favorite Python packages such as NumPy, SciPy and Cython to extend PyTorch when needed. + +%package help +Summary: Development documents and examples for torch +Provides: python3-DeepSpeed-doc +%description help +PyTorch is a Python package that provides two high-level features: +- Tensor computation (like NumPy) with strong GPU acceleration +- Deep neural networks built on a tape-based autograd system +You can reuse your favorite Python packages such as NumPy, SciPy and Cython to extend PyTorch when needed. + +%prep +%autosetup -p1 -n %{name}-%{version} + +%build +%py3_build +#python3 setup.py build + +%install +%define _unpackaged_files_terminate_build 0 +%py3_install +#python3 setup.py install + +%files -n python3-DeepSpeed +%doc *.md +%license LICENSE +%{python3_sitelib}/* +/usr/bin/deepspeed + + +%changelog +* Thu Aug 17 2023 Dongxing Wang <dxwangk@isoftstone.com> - 2.0.1-2 +- Fix the EulerMaker failure for verion 2.0.1 + +* Mon Jul 24 2023 Dongxing Wang <dxwangk@isoftstone.com> - 2.0.1-1 +- upgrade to 2.0.1 + +* Thu Feb 16 2023 Dongxing Wang <dxwangk@isoftstone.com> - 1.11.0-2 +- fixes: error: the CXX 11 compiler error (linux.cc flexible array member not at end of struct) + +* Mon Jun 13 2022 Zhipeng Xie <xiezhipeng1@huawei.com> - 1.11.0-1 +- upgrade to 1.11.0 + +* Mon Jun 28 2021 wulei <wulei80@huawei.com> - 1.6.0-3 +- fixes: error: the CXX compiler identification is unknown + +* Thu Feb 4 2021 Zhipeng Xie<xiezhipeng1@huawei.com> - 1.6.0-2 +- disable SVE to fix compile error in gcc 9 + +* Sun Sep 27 2020 Zhipeng Xie<xiezhipeng1@huawei.com> - 1.6.0-1 +- Package init @@ -0,0 +1 @@ +521d71d77c5f3333f55d4855f70779f1 DeepSpeed-0.12.2.tar.gz |