ORT 1.0.0
See the version list below for details.
dotnet add package ORT --version 1.0.0
NuGet\Install-Package ORT -Version 1.0.0
<PackageReference Include="ORT" Version="1.0.0" />
<PackageVersion Include="ORT" Version="1.0.0" />
<PackageReference Include="ORT" />
paket add ORT --version 1.0.0
#r "nuget: ORT, 1.0.0"
#:package ORT@1.0.0
#addin nuget:?package=ORT&version=1.0.0
#tool nuget:?package=ORT&version=1.0.0
ORT
A clean, minimal ONNX Runtime package for Windows x64 — same binaries, same API, none of the bloat.
ORT is a repack of the official ONNX Runtime 1.31.0 binaries with one goal: when you install it, your output directory stays clean. The official Microsoft.ML.OnnxRuntime ships native payloads for Android, iOS, Linux, macOS and ARM64 (160 MB package); ORT keeps only what a Windows desktop app actually needs (~6.7 MB).
What's inside
| Asset | Source |
|---|---|
lib/net8.0/Microsoft.ML.OnnxRuntime.dll |
Official managed assembly (net8.0 build) |
lib/net461/Microsoft.ML.OnnxRuntime.dll |
Official managed assembly (netstandard2.0 build, .NET Framework 4.6.1 compatible) |
runtimes/win-x64/native/onnxruntime.dll |
Official win-x64 native binary |
runtimes/win-x64/native/onnxruntime_providers_shared.dll |
Official win-x64 native binary |
The managed API is 100 % identical to Microsoft.ML.OnnxRuntime — your existing code works unchanged; only the package reference differs.
Requirements
- Windows x64 (the official 1.31 release no longer ships win-x86 binaries)
- net8.0 or .NET Framework 4.6.1+
- PackageReference-style references
- For .NET Framework projects: use
AnyCPU(uncheck "Prefer 32-bit") orx64. Building for x86 produces a clear build-time error instead of a runtime failure.
Quick start
using Microsoft.ML.OnnxRuntime;
using Microsoft.ML.OnnxRuntime.Tensors;
using var session = new InferenceSession("model.onnx");
var input = new DenseTensor<float>(new[] { 1f, 2f, 3f }, new[] { 1, 3 });
var inputs = new[] { NamedOnnxValue.CreateFromTensor("input", input) };
using var results = session.Run(inputs);
Dependencies (System.Memory, and System.Numerics.Tensors on net8.0) are pulled in automatically.
When to use which package
- Building a Windows x64 desktop/service app and tired of every platform's native dlls flooding your output? → ORT
- Need Linux, macOS, ARM64 or mobile targets? → use the official
Microsoft.ML.OnnxRuntimeinstead
License & attribution
This package contains unmodified ONNX Runtime binaries, released under the MIT License, © Microsoft Corporation. Source and original license: https://github.com/microsoft/onnxruntime Repackaged by GreatBear.
| Product | Versions Compatible and additional computed target framework versions. |
|---|---|
| .NET | net5.0 was computed. net5.0-windows was computed. net6.0 was computed. net6.0-android was computed. net6.0-ios was computed. net6.0-maccatalyst was computed. net6.0-macos was computed. net6.0-tvos was computed. net6.0-windows was computed. net7.0 was computed. net7.0-android was computed. net7.0-ios was computed. net7.0-maccatalyst was computed. net7.0-macos was computed. net7.0-tvos was computed. net7.0-windows was computed. net8.0 is compatible. net8.0-android was computed. net8.0-browser was computed. net8.0-ios was computed. net8.0-maccatalyst was computed. net8.0-macos was computed. net8.0-tvos was computed. net8.0-windows was computed. net9.0 was computed. net9.0-android was computed. net9.0-browser was computed. net9.0-ios was computed. net9.0-maccatalyst was computed. net9.0-macos was computed. net9.0-tvos was computed. net9.0-windows was computed. net10.0 was computed. 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. |
| .NET Core | netcoreapp2.0 was computed. netcoreapp2.1 was computed. netcoreapp2.2 was computed. netcoreapp3.0 was computed. netcoreapp3.1 was computed. |
| .NET Standard | netstandard2.0 is compatible. netstandard2.1 was computed. |
| .NET Framework | net461 is compatible. net462 was computed. net463 was computed. net47 was computed. net471 was computed. net472 was computed. net48 was computed. net481 was computed. |
| MonoAndroid | monoandroid was computed. |
| MonoMac | monomac was computed. |
| MonoTouch | monotouch was computed. |
| Tizen | tizen40 was computed. tizen60 was computed. |
| Xamarin.iOS | xamarinios was computed. |
| Xamarin.Mac | xamarinmac was computed. |
| Xamarin.TVOS | xamarintvos was computed. |
| Xamarin.WatchOS | xamarinwatchos was computed. |
-
.NETFramework 4.6.1
- System.Memory (>= 4.5.5)
-
net8.0
- System.Memory (>= 4.5.5)
- System.Numerics.Tensors (>= 9.0.0)
NuGet packages (2)
Showing the top 2 NuGet packages that depend on ORT:
| Package | Downloads |
|---|---|
|
VisionFlow
视觉流程图框架:流程图引擎([FlowNode] 节点注册、JSON 序列化、拓扑执行、配方)+ WinForms 编辑器控件 + csx 脚本 / .cs 源码 / DLL 算子包四种扩展载体。内置视觉算子(旋转模板匹配/综合测量/OCR/读码/颜色抽取/深度学习目标检测)随包自动部署,装一个包即可用。 |
|
|
PPOCR
PP-OCRv5 文字检测+识别引擎(ONNX CPU):检测、批量识别、中英文双模型、旋转 ROI 拉正、同行碎片拼接、词间空格补偿。模型字典内嵌 DLL,装包即用零文件释放。 |
GitHub repositories
This package is not used by any popular GitHub repositories.