WACS.WASI.NN
0.3.0
See the version list below for details.
dotnet add package WACS.WASI.NN --version 0.3.0
NuGet\Install-Package WACS.WASI.NN -Version 0.3.0
<PackageReference Include="WACS.WASI.NN" Version="0.3.0" />
<PackageVersion Include="WACS.WASI.NN" Version="0.3.0" />
<PackageReference Include="WACS.WASI.NN" />
paket add WACS.WASI.NN --version 0.3.0
#r "nuget: WACS.WASI.NN, 0.3.0"
#:package WACS.WASI.NN@0.3.0
#addin nuget:?package=WACS.WASI.NN&version=0.3.0
#tool nuget:?package=WACS.WASI.NN&version=0.3.0
WASI-NN host bindings for WACS — wasi:nn@0.3.0-rc-2024-10-28 (component-model WIT) plus the legacy wasi_ephemeral_nn (WITX) ABI. Backend-agnostic core; pluggable backends (ML.NET, ONNX Runtime, LlamaSharp) ship as sibling packages.
| 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 | netcoreapp3.0 was computed. netcoreapp3.1 was computed. |
| .NET Standard | netstandard2.1 is compatible. |
| MonoAndroid | monoandroid was computed. |
| MonoMac | monomac was computed. |
| MonoTouch | monotouch was computed. |
| Tizen | tizen60 was computed. |
| Xamarin.iOS | xamarinios was computed. |
| Xamarin.Mac | xamarinmac was computed. |
| Xamarin.TVOS | xamarintvos was computed. |
| Xamarin.WatchOS | xamarinwatchos was computed. |
-
.NETStandard 2.1
- WACS (>= 0.13.7)
- WACS.ComponentModel (>= 0.3.4)
- WACS.HostBindings.Abstractions (>= 0.3.0)
-
net8.0
- WACS (>= 0.13.7)
- WACS.ComponentModel (>= 0.3.4)
- WACS.HostBindings.Abstractions (>= 0.3.0)
NuGet packages (7)
Showing the top 5 NuGet packages that depend on WACS.WASI.NN:
| Package | Downloads |
|---|---|
|
WACS.WASI.NN.OnnxRuntime
ONNX Runtime backend for WACS.WASI.NN. Implements IBackend for graph-encoding.onnx via Microsoft.ML.OnnxRuntime. Ships as a sibling NuGet so consumers wiring only one backend don't pull the OnnxRuntime native binaries. |
|
|
WACS.WASI.NN.OpenVino
OpenVINO backend for WACS.WASI.NN. Implements IBackend for graph-encoding.openvino via the OpenVINO.CSharp.API NuGet. Loads OpenVINO IR (xml + bin) from the wasi-nn multi-builder shape. Ships as a sibling NuGet so consumers wiring only one backend don't pull the OpenVINO native runtimes. |
|
|
WACS.WASI.NN.MLNet
ML.NET backend for WACS.WASI.NN. Hosts ONNX inference under an MLContext lifecycle so embedders can compose wasi-nn inference with the rest of their ML.NET pipeline (preprocessing transformers, custom predictors, etc.). For raw tensor inference with no pipeline integration, prefer Wacs.WASI.NN.OnnxRuntime — it avoids the Microsoft.ML transitive surface. |
|
|
WACS.WASI.NN.LlamaSharp
LlamaSharp / llama.cpp backend for WACS.WASI.NN. Implements GraphEncoding.ggml on the WasmEdge convention (load-by-name plus U8 tensors carrying UTF-8 prompt and response text). Models are resolved by name through an embedder-supplied registry — model files are GB-scale and not embedded in the wasm. |
|
|
WACS.WASI.NN.TorchSharp
TorchSharp / libtorch backend for WACS.WASI.NN. Implements GraphEncoding.PyTorch — load TorchScript modules from byte buffers (graph.load) or by name (graph.load-by-name), run inference through libtorch's C++ runtime. CPU default; swap LibTorch backend NuGets for CUDA / ROCm / MPS without source change. |
GitHub repositories
This package is not used by any popular GitHub repositories.