Unofficial.OnnxRuntime
1.24.9
dotnet add package Unofficial.OnnxRuntime --version 1.24.9
NuGet\Install-Package Unofficial.OnnxRuntime -Version 1.24.9
<PackageReference Include="Unofficial.OnnxRuntime" Version="1.24.9" />
<PackageVersion Include="Unofficial.OnnxRuntime" Version="1.24.9" />
<PackageReference Include="Unofficial.OnnxRuntime" />
paket add Unofficial.OnnxRuntime --version 1.24.9
#r "nuget: Unofficial.OnnxRuntime, 1.24.9"
#:package Unofficial.OnnxRuntime@1.24.9
#addin nuget:?package=Unofficial.OnnxRuntime&version=1.24.9
#tool nuget:?package=Unofficial.OnnxRuntime&version=1.24.9
ONNX Runtime native bundle with Aardvark-style embedded natives: DirectML on Windows, CoreML on macOS, CPU + system-CUDA discovery on Linux. Pairs with Microsoft.ML.OnnxRuntime.Managed.
| Product | Versions Compatible and additional computed target framework versions. |
|---|---|
| .NET | 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. |
-
net8.0
- Aardvark.Base (>= 5.3.12)
- FSharp.Core (>= 8.0.100)
- Microsoft.ML.OnnxRuntime.Managed (>= 1.24.4)
- Vortice.DXGI (>= 3.6.2)
NuGet packages (1)
Showing the top 1 NuGet packages that depend on Unofficial.OnnxRuntime:
| Package | Downloads |
|---|---|
|
Sam3.Net
SAM3 (Segment Anything 3) text-prompted concept segmentation for .NET via ONNX Runtime. Encode images once, prompt interactively; returns masks, boxes and scores. |
GitHub repositories
This package is not used by any popular GitHub repositories.
- windows: back to the DirectML build (reverts 1.24.8). The E_INVALIDARG that motivated the CUDA swap was never a driver bug — it is `allowzero=1` on dynamo-exported Reshape nodes, which DML rejects on every vendor; fix the model, not the provider.;- drops onnxruntime_providers_cuda.dll (275 MB) and the CUDA 12.x + cuDNN 9.x requirement; works on any DX12 GPU (AMD/Intel/NVIDIA);- restores the DXGI adapter pick (NVIDIA > AMD > Intel) instead of device 0;- linux keeps CUDA-if-found, mac keeps CoreML — unchanged