Microsoft.ML.OnnxRuntime 1.21.0

Prefix Reserved
.NET 8.0 This package targets .NET 8.0. The package is compatible with this framework or higher. .NET Standard 2.0 This package targets .NET Standard 2.0. The package is compatible with this framework or higher. 
dotnet add package Microsoft.ML.OnnxRuntime --version 1.21.0
                    


                    

                
NuGet\Install-Package Microsoft.ML.OnnxRuntime -Version 1.21.0
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="Microsoft.ML.OnnxRuntime" Version="1.21.0" />
For projects that support PackageReference, copy this XML node into the project file to reference the package. 
<PackageVersion Include="Microsoft.ML.OnnxRuntime" Version="1.21.0" />
                    


                            Directory.Packages.props
                        

                    

                
<PackageReference Include="Microsoft.ML.OnnxRuntime" />
                    


                            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 Microsoft.ML.OnnxRuntime --version 1.21.0
                    


                    

                
#r "nuget: Microsoft.ML.OnnxRuntime, 1.21.0"
#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. 
#addin nuget:?package=Microsoft.ML.OnnxRuntime&version=1.21.0
                    


                            Install Microsoft.ML.OnnxRuntime as a Cake Addin
                        

                    

                
#tool nuget:?package=Microsoft.ML.OnnxRuntime&version=1.21.0
                    


                            Install Microsoft.ML.OnnxRuntime as a Cake Tool

About

ONNX Runtime Logo

ONNX Runtime is a cross-platform machine-learning inferencing accelerator.

ONNX Runtime 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.

Learn more → here

NuGet Packages

ONNX Runtime Native packages

Microsoft.ML.OnnxRuntime
Microsoft.ML.OnnxRuntime.Gpu
Microsoft.ML.OnnxRuntime.DirectML
Microsoft.ML.OnnxRuntime.QNN
Intel.ML.OnnxRuntime.OpenVino

Other packages

Microsoft.ML.OnnxRuntime.Managed
  • C# language bindings
Microsoft.ML.OnnxRuntime.Extensions
Product 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 was computed.  net8.0-android was computed.  net8.0-android31.0 is compatible.  net8.0-browser was computed.  net8.0-ios was computed.  net8.0-ios15.4 is compatible.  net8.0-maccatalyst was computed.  net8.0-maccatalyst14.0 is compatible.  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. 
.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 is compatible. 
.NET Framework net461 was computed.  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. 
native native is compatible. 
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. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

NuGet packages (112)

Showing the top 5 NuGet packages that depend on Microsoft.ML.OnnxRuntime:

Package Downloads
Aspose.OCR

Powerful and developer-friendly OCR API for extracting text from images and creating searchable PDFs. Add optical character recognition to on-premises solutions, web sites, cloud services, and serverless functions with just a few lines of native .NET code. Effortlessly transform scanned pages, photos, screenshots, handwritten memos, and other images into machine-readable text, regardless of the font, layout and styles. Find and compare text on images. Bulk-recognize all images from folders and archives; read multi-page PDF documents and TIFF images. Aspose.OCR is a universal solution for document processing, data extraction, and content digitization on a global scale. Supporting over 130 European, Middle East, Asian, African and American languages, the library allows you to recognize texts in Latin, Cyrillic, Arabic, Chinese, and Hindi scrips, including text in mixed languages. The library can be used virtually everywhere, catering to both small and medium businesses as well as multinational corporations. With Aspose.OCR, optical character recognition becomes a trivial and straightforward task, even for developers new to the technology. You can focus at business task rather than complex maths, neural networks, and other technical intricacies. Powerful image processing and customizable content structure detection algorithms enable text extraction from virtually any image, ranging from high-quality scans to street photos. Aspose.OCR for .NET can work with virtually any file you can get from a scanner or camera, including PDF document and multi-page TIFF images. Recognition results are returned in the most popular file and data exchange formats that can be saved, imported to a database, or analyzed in real time. Changelog: - Added Markdown (.md) as a new save format - Improved DOCX export: images are now extracted and embedded - Added support for automatic language detection during recognition Check for details at https://releases.aspose.com/ocr/net/release-notes/2025/aspose-ocr-for-net-25-4-0-release-notes/ Resources: Product page: https://products.aspose.com/ocr/net/ Advanced OCR models: https://github.com/aspose-ocr/resources Online documentation: https://docs.aspose.com/ocr/net/ Solutions: https://docs.aspose.com/ocr/net/use-cases/ Free support forum: https://forum.aspose.com/c/ocr/16
GroupDocs.Parser

GroupDocs.Parser for .NET is a useful parsing class library which allows to extract different data from documents of various formats. The data extraction API supports PDF, DOC, DOCX, PPT, PPTX, XLS, XLSX and many more formats.
GroupDocs.Search

GroupDocs.Search for .NET is a easy to use document search library which performs search operations over various file formats - DOC, XLS, PPT, ODP and many others. The search API allows to create search index with flexible settings with different requirements: quick and lightweight document search or advanced document search features. Customize search index with custom fields and search your custom data along with document text and metadata.
Microsoft.ML.OnnxRuntimeGenAI

ONNX Runtime Generative AI Native Package
our1314.work

Package Description

GitHub repositories (19)

Showing the top 19 popular GitHub repositories that depend on Microsoft.ML.OnnxRuntime:

Repository Stars
microsoft/semantic-kernel
Integrate cutting-edge LLM technology quickly and easily into your apps
rocksdanister/lively
Free and open-source software that allows users to set animated desktop wallpapers and screensavers powered by WinUI 3.
dotnet/machinelearning
ML.NET is an open source and cross-platform machine learning framework for .NET.
stakira/OpenUtau
Open singing synthesis platform / Open source UTAU successor
Webreaper/Damselfly
Damselfly is a server-based Photograph Management app. The goal of Damselfly is to index an extremely large collection of images, and allow easy search and retrieval of those images, using metadata such as the IPTC keyword tags, as well as the folder and file names. Damselfly includes support for object/face detection.
wangfreexx/wangfreexx-tianruoocr-cl-paddle
天若ocr开源版本的本地版，采用Chinese-lite和paddleocr识别框架
codeproject/CodeProject.AI-Server
CodeProject.AI Server is a self contained service that software developers can include in, and distribute with, their applications in order to augment their apps with the power of AI.
rocksdanister/weather
Windows native weather app powered by DirectX12 animations
microsoft/psi
Platform for Situated Intelligence
redis/redis-om-dotnet
Object mapping, and more, for Redis and .NET
dme-compunet/YoloSharp
🚀 Use YOLO11 in real-time for object detection tasks, with edge performance ⚡️ powered by ONNX-Runtime.
techwingslab/yolov5-net
YOLOv5 object detection with C#, ML.NET, ONNX
microsoft/CryptoNets
CryptoNets is a demonstration of the use of Neural-Networks over data encrypted with Homomorphic Encryption. Homomorphic Encryptions allow performing operations such as addition and multiplication over data while it is encrypted. Therefore, it allows keeping data private while outsourcing computation (see here and here for more about Homomorphic E
unoplatform/Uno.Samples
A collection of code samples for the Uno Platform
Azure/azure-stream-analytics
Azure Stream Analytics
FaceONNX/FaceONNX
Face recognition and analytics library based on deep neural networks and ONNX runtime
Vincentzyx/VinXiangQi
Xiangqi syncing tool based on Yolov5 / 基于Yolov5的中国象棋连线工具
deepakkumar1984/MxNet.Sharp
.NET Standard bindings for Apache MxNet with Imperative, Symbolic and Gluon Interface for developing, training and deploying Machine Learning models in C#. https://mxnet.tech-quantum.com/
Lyrcaxis/KokoroSharp
Fast local TTS inference engine in C# with ONNX runtime. Multi-speaker, multi-platform and multilingual. Integrate on your .NET projects using a plug-and-play NuGet package, complete with all voices.
Version Downloads Last updated
1.21.0 50,390 a month ago
1.20.1 312,822 5 months ago
1.20.0 66,977 5 months ago
1.19.2 203,367 7 months ago
1.19.1 86,498 8 months ago
1.19.0 23,161 8 months ago
1.18.1 410,324 10 months ago
1.18.0 193,814 5/17/2024
1.17.3 114,135 4/10/2024
1.17.1 326,732 2/25/2024
1.17.0 225,296 1/31/2024
1.16.3 448,234 11/20/2023
1.16.2 31,575 11/9/2023
1.16.1 132,946 10/11/2023
1.16.0 187,186 9/19/2023
1.15.1 409,492 6/16/2023
1.15.0 75,304 5/24/2023
1.15.0-rc 5,119 5/17/2023
1.15.0-alpha 5,041 5/12/2023
1.14.1 217,570 2/27/2023
1.14.0 112,390 2/10/2023
1.13.1 277,360 10/24/2022
1.12.1 319,234 8/4/2022
1.12.0 23,276 7/22/2022
1.11.0 407,390 3/25/2022
1.10.0 230,704 12/7/2021
1.9.0 132,249 9/22/2021
1.8.1 160,523 7/7/2021
1.8.0 61,360 6/3/2021
1.7.0 256,073 3/2/2021
1.6.0 141,315 12/10/2020
1.5.2 91,402 10/15/2020
1.5.1 29,058 9/29/2020
1.4.0 133,282 7/17/2020
1.3.0 106,259 5/18/2020
1.2.0 76,039 3/10/2020
1.1.2 9,525 2/21/2020
1.1.1 21,653 1/24/2020
1.1.0 12,656 12/19/2019
1.0.0 92,305 10/30/2019
0.5.1 182,373 10/12/2019
0.5.0 17,347 8/1/2019
0.4.0 70,472 5/2/2019
0.3.1 6,168 4/9/2019
0.3.0 40,602 3/14/2019
0.2.1 41,513 2/1/2019
0.1.5 12,549 12/1/2018

Release Def:
Branch: refs/heads/rel-1.21.0
Commit: e0b66cad282043d4377cea5269083f17771b6dfc
Build: https://aiinfra.visualstudio.com/Lotus/_build/results?buildId=704036