Microsoft AI Infra and Tools team
NuGet publisher profile
Packages (30)
Microsoft.ML.OnnxRuntime
This package contains native shared library artifacts for all supported platforms of ONNX Runtime.
Microsoft.ML.OnnxRuntime.Gpu.Linux
This package contains Linux native shared library artifacts for ONNX Runtime with CUDA.
Microsoft.ML.OnnxRuntime.Managed
This package contains ONNX Runtime for .Net platforms
Microsoft.ML.OnnxRuntime.Gpu
This package contains native shared library artifacts for all supported platforms of ONNX Runtime.
Microsoft.ML.OnnxRuntimeGenAI.Managed
ONNX Runtime Generative AI Managed Package
Microsoft.ML.OnnxRuntime.DirectML
This package contains native shared library artifacts for all supported platforms of ONNX Runtime.
Microsoft.ML.OnnxRuntime.Gpu.Windows
This package contains Windows native shared library artifacts for ONNX Runtime with CUDA.
Microsoft.ML.OnnxRuntimeGenAI
ONNX Runtime Generative AI Native Package
Microsoft.ML.OnnxRuntime.MKLML
This package contains native shared library artifacts for all supported platforms of ONNX Runtime.
Microsoft.AI.Foundry.Local
Microsoft AI Foundry Local SDK for .NET
Microsoft.ML.OnnxRuntimeGenAI.Foundry
ONNX Runtime Generative AI Native Package
Microsoft.ML.OnnxRuntime.Foundry
This package contains native shared library artifacts for all supported platforms of ONNX Runtime.
Microsoft.ML.OnnxRuntimeGenAI.DirectML
ONNX Runtime Generative AI Native Package
Microsoft.ML.OnnxRuntimeGenAI.Cuda
ONNX Runtime Generative AI Native Package
Microsoft.ML.OnnxRuntime.Extensions
ONNX Runtime Extensions NuGet Package
Microsoft.AI.MachineLearning
This package contains Windows ML binaries.
Microsoft.AI.Foundry.Local.Core
Microsoft Foundry Local Core native library - Native AOT compiled multi-platform AI inference library
Microsoft.ML.Scoring
Microsoft Machine Learning Scoring library for deep learning model inference. Current version of the library supports inferencing on ONNX v1.3 and TensorFlow v1.10.0 models. The library supports CPU execution with MKL/MKLDNN acceleration. Also supports CUDA GPU devices. For CPU execution of ONNX models, no extra libraries are required. However for scoring TensorFlow models, the CUDA libraries are needed for both CPU and GPU execution. Download and install CUDA 9.2 toolkit, CUDNN and device drivers separately. This package provides a .Net standard 1.3 compatible module for maximum portability. Currently supported platforms include x64 CPU on Windows OS only.
Microsoft.ML.OnnxRuntime.QNN
This package contains native shared library artifacts for all supported platforms of ONNX Runtime.
Microsoft.AI.Foundry.Local.Core.WinML
Microsoft Foundry Local Core WinML native library - Native AOT compiled Windows AI inference library with WinML support
Microsoft.ML.OnnxRuntimeGenAI.WinML
ONNX Runtime Generative AI Native Package
Microsoft.AI.Foundry.Local.WinML
Microsoft AI Foundry Local SDK for .NET
Microsoft.ML.OnnxRuntime.Training
The onnxruntime-training native shared library artifacts are designed to efficiently train and infer a wide range of ONNX models on edge devices, such as client machines, gaming consoles, and other portable devices with a focus on minimizing resource usage and maximizing accuracy.See https://github.com/microsoft/onnxruntime-training-examples/tree/master/on_device_training for more details.
Microsoft.ML.OnnxRuntimeGenAI.QNN
ONNX Runtime Generative AI Native Package
Microsoft.ML.OnnxRuntime.Extensions.Dummy
ONNX Runtime Extensions Dummy NuGet Package
Microsoft.ML.OnnxRuntime.NoOpenMP
This package contains native shared library artifacts for all supported platforms of ONNX Runtime.
Microsoft.ML.OnnxRuntime.OpenMP
This package contains native shared library artifacts for all supported platforms of ONNX Runtime.
Microsoft.ML.OnnxRuntime.Azure
This package contains native shared library artifacts for all supported platforms of ONNX Runtime.
Microsoft.ML.OnnxRuntime.Snpe
This package contains native shared library artifacts for all supported platforms of ONNX Runtime.
Microsoft.ML.OnnxRuntime.EP.WebGpu
ONNX Runtime WebGPU Plugin Execution Provider.