%global _empty_manifest_terminate_build 0
Name:		python-onnxruntime
Version:	1.16.3
Release:	1
Summary:	Tensors and Dynamic neural networks in Python with strong GPU acceleration
License:	MIT
URL:		https://onnxruntime.ai/
Source0:	https://github.com/microsoft/onnxruntime/archive/refs/tags/v1.16.3.tar.gz#/%{name}-%{version}.tar.gz

%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.
ONNX Runtime training can accelerate the model training time on multi-node NVIDIA GPUs for transformer models with a one-line addition for existing PyTorch training scripts.

%package -n python3-onnxruntime
Summary:	Tensors and Dynamic neural networks in Python with strong GPU acceleration
Provides:	python-torch
BuildRequires:	python3-devel
BuildRequires:	python3-setuptools
BuildRequires:	python3-setuptools_scm
BuildRequires:	python3-pip
BuildRequires:	python3-wheel
BuildRequires:	python3-hatchling

%description -n python3-onnxruntime
ONNX Runtime is a cross-platform inference and training machine-learning accelerator.

%package help
Summary:	Development documents and examples for onnxruntime
Provides:	python3-onnxruntime-doc
%description help
help documents for python3 onnxruntime

%prep
%autosetup -p1 -n onnxruntime-%{version}

%build
%pyproject_build

%install
%pyproject_install
install -d -m755 %{buildroot}/%{_pkgdocdir}

%files -n python3-onnxruntime
%doc *.md
%license LICENSE
#%{_bindir}/torchrun
#%{python3_sitearch}/*

%changelog
* Fri Jan 26 2024 menma <1316818279@qq.com> - 1.6.3-1
- Package init