Fri, 20 Nov 2026 01:58:36 UTC Log in
Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation built by guoguo completed Thu, 29 Oct 2026 23:34:34 UTC

Description

This library provides ordinary differential equation (ODE) solvers implemented in PyTorch. Backpropagation through ODE solutions is supported using the adjoint method for constant memory cost. For usage of ODE solvers in deep learning applications. As the solvers are implemented in PyTorch, algorithms in this repository are fully supported to run on the GPU.

RPMs

No RPMs

Changelog

* Tue Aug 11 2026 Tom Rix <Tom.Rix@amd.com> - 0.2.5-10
- Disable testing

* Thu Jul 16 2026 Fedora Release Engineering <releng@fedoraproject.org> - 0.2.5-9
- Rebuilt for https://fedoraproject.org/wiki/Fedora_45_Mass_Rebuild

* Sat Jun 06 2026 Python Maint <python-maint@redhat.com> - 0.2.5-8
- Rebuilt for Python 3.15

* Sat Jan 17 2026 Fedora Release Engineering <releng@fedoraproject.org> - 0.2.5-7
- Rebuilt for https://fedoraproject.org/wiki/Fedora_44_Mass_Rebuild

* Fri Sep 19 2025 Python Maint <python-maint@redhat.com> - 0.2.5-6
- Rebuilt for Python 3.14.0rc3 bytecode

* Fri Aug 15 2025 Python Maint <python-maint@redhat.com> - 0.2.5-5
- Rebuilt for Python 3.14.0rc2 bytecode

* Fri Jul 25 2025 Fedora Release Engineering <releng@fedoraproject.org> - 0.2.5-4
- Rebuilt for https://fedoraproject.org/wiki/Fedora_43_Mass_Rebuild

* Sat Jan 18 2025 Fedora Release Engineering <releng@fedoraproject.org> - 0.2.5-3
- Rebuilt for https://fedoraproject.org/wiki/Fedora_42_Mass_Rebuild

* Mon Jan 06 2025 Tom Rix <Tom.Rix@amd.com> - 0.2.5-2
- Improve packaged docs

* Sun Jan 05 2025 Tom Rix <Tom.Rix@amd.com> - 0.2.5-1
- Initial package