%global _empty_manifest_terminate_build 0
%define debug_package %{nil}
Name:           onnxruntime
Version:        1.17.0
Release:        2
Summary:        ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
License:        BSD-3
URL:            https://github.com/pytorch/onnxruntime
Source0:        https://atomgit.com/havefun/onnxruntime/raw/master/onnxruntime-1.17.0.tar.gz

BuildRequires:  g++
Requires:       python3-future
Requires:       python3-numpy

%description
ONNX Runtime is a cross-platform inference and training machine-learning accelerator.
ONNX Runtime inference can enable faster customer experiences and lower costs, supporting models from deep learning frameworks such as PyTorch and TensorFlow/Keras as well as classical machine learning libraries such as scikit-learn, LightGBM, XGBoost, etc. ONNX Runtime is compatible with different hardware, drivers, and operating systems, and provides optimal performance by leveraging hardware accelerators where applicable alongside graph optimizations and transforms. 

%package -n python3-onnxruntime
Summary:        ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Provides:       python-onnxruntime
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-onnxruntime
ONNX Runtime is a cross-platform inference and training machine-learning accelerator.
ONNX Runtime inference can enable faster customer experiences and lower costs, supporting models from deep learning frameworks such as PyTorch and TensorFlow/Keras as well as classical machine learning libraries such as scikit-learn, LightGBM, XGBoost, etc. ONNX Runtime is compatible with different hardware, drivers, and operating systems, and provides optimal performance by leveraging hardware accelerators where applicable alongside graph optimizations and transforms. 

%package help
Summary:        Development documents and examples for torch
Provides:       python3-onnxruntime-doc
%description help
ONNX Runtime is a cross-platform inference and training machine-learning accelerator.
ONNX Runtime inference can enable faster customer experiences and lower costs, supporting models from deep learning frameworks such as PyTorch and TensorFlow/Keras as well as classical machine learning libraries such as scikit-learn, LightGBM, XGBoost, etc. ONNX Runtime is compatible with different hardware, drivers, and operating systems, and provides optimal performance by leveraging hardware accelerators where applicable alongside graph optimizations and transforms. 

%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-onnxruntime
%doc *.md
%license LICENSE
%{python3_sitelib}/*


%changelog
* Tue April 15 2024 Hongyu Li<543306408@qq.com>
- Package init