RecursiveAI.OneModel 1.0.0

.NET 10.0 This package targets .NET 10.0. The package is compatible with this framework or higher. 
dotnet add package RecursiveAI.OneModel --version 1.0.0
                    


                    

                
NuGet\Install-Package RecursiveAI.OneModel -Version 1.0.0
This command is intended to be used within the Package Manager Console in Visual Studio, as it uses the NuGet module's version of Install-Package. 
<PackageReference Include="RecursiveAI.OneModel" Version="1.0.0" />
For projects that support PackageReference, copy this XML node into the project file to reference the package. 
<PackageVersion Include="RecursiveAI.OneModel" Version="1.0.0" />
                    


                            Directory.Packages.props
                        

                    

                
<PackageReference Include="RecursiveAI.OneModel" />
                    


                            Project file
For projects that support Central Package Management (CPM), copy this XML node into the solution Directory.Packages.props file to version the package. 
paket add RecursiveAI.OneModel --version 1.0.0
                    


                    

                
#r "nuget: RecursiveAI.OneModel, 1.0.0"
#r directive can be used in F# Interactive and Polyglot Notebooks. Copy this into the interactive tool or source code of the script to reference the package. 
#:package RecursiveAI.OneModel@1.0.0
#:package directive can be used in C# file-based apps starting in .NET 10 preview 4. Copy this into a .cs file before any lines of code to reference the package. 
#addin nuget:?package=RecursiveAI.OneModel&version=1.0.0
                    


                            Install as a Cake Addin
                        

                    

                
#tool nuget:?package=RecursiveAI.OneModel&version=1.0.0
                    


                            Install as a Cake Tool

OneModel

A neural-network runtime for .NET in pure managed C#, with no native binaries and no dependency beyond the shared framework.

  • RecursiveAI.OneModel: ONNX import, graph optimization and SIMD CPU kernels (AVX2, AVX-512, NEON, portable SIMD) for inference in fp32, fp16/bf16 and int8; thread-safe sessions; an opt-in exact mode with bit-identical results on every platform; its own memory-mappable model format. NativeAOT-, trim- and WebAssembly-compatible.
  • RecursiveAI.OneModel.Training: reverse-mode autodiff, modules, losses, SGD/Adam/AdamW, data loading, checkpoints, and tracing a trained module into a graph.
using RecursiveAI.OneModel;

using var m = Model.Load("model.onnx");
float[] v = m.Run(tokens);   // names and shapes come from the model

Several inputs, tensors, exact mode, training, tracing and migration notes from ONNX Runtime and TorchSharp: the usage guide.

using RecursiveAI.OneModel;
using RecursiveAI.OneModel.Graph;
using RecursiveAI.OneModel.Tensors;

using var session = Session.Load("model.onnx", new ModelOptions { Mode = ArithmeticMode.Exact });
using Tensor x = Tensor.FromSpan<float>(values, 2, 16);
using SessionOutputs outputs = session.Run(new Dictionary<string, Tensor> { ["x"] = x });
float[] y = outputs["y"].ToArray<float>();

The public API follows Semantic Versioning. Documentation, supported operators, source and issues: https://github.com/recursive-ai-oss/onemodel-csharp.

Licensed MIT OR Apache-2.0.

Product Compatible and additional computed target framework versions.
.NET net10.0 is compatible.  net10.0-android was computed.  net10.0-browser was computed.  net10.0-ios was computed.  net10.0-maccatalyst was computed.  net10.0-macos was computed.  net10.0-tvos was computed.  net10.0-windows was computed. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

  • net10.0

    • No dependencies.

NuGet packages (1)

Showing the top 1 NuGet packages that depend on RecursiveAI.OneModel:

Package Downloads
RecursiveAI.OneModel.Training

Training for the OneModel runtime, on the tensor layer's reverse-mode autodiff: modules (linear, convolution, batch and layer norm, embedding, dropout, multi-head attention, transformer encoder layer), losses, SGD, Adam and AdamW with gradient clipping and learning-rate schedules, bit-exact checkpoints, and gradient checking.

GitHub repositories

This package is not used by any popular GitHub repositories.

Version Downloads Last Updated
1.0.0 78 10/31/2026
0.3.0-preview.1 235 10/30/2026

See CHANGELOG.md in the repository.