Qavren.Edge.Onnx
1.0.0
Prefix Reserved
dotnet add package Qavren.Edge.Onnx --version 1.0.0
NuGet\Install-Package Qavren.Edge.Onnx -Version 1.0.0
<PackageReference Include="Qavren.Edge.Onnx" Version="1.0.0" />
<PackageVersion Include="Qavren.Edge.Onnx" Version="1.0.0" />
<PackageReference Include="Qavren.Edge.Onnx" />
paket add Qavren.Edge.Onnx --version 1.0.0
#r "nuget: Qavren.Edge.Onnx, 1.0.0"
#:package Qavren.Edge.Onnx@1.0.0
#addin nuget:?package=Qavren.Edge.Onnx&version=1.0.0
#tool nuget:?package=Qavren.Edge.Onnx&version=1.0.0
Qavren.Edge.Onnx
ONNX Runtime hosting for the Qavren.Edge suite (sub-project 2): AddOnnx(), the session
factory, the execution-provider policy per platform, consent-gated model provisioning with
pinned SHA-256 digests, UseModelPaths(), and the resource monitor (IEdgeResourceMonitor) the
embedding, ingestion and chat packages pace themselves against.
dotnet add package Qavren.Edge.Onnx
services.AddQavrenEdge(edge => edge
.AddOnnx());
AddOnnxEmbeddings() and AddOnnxChat() call AddOnnx() for you; it is idempotent. Models and
the ORT cache live under the suite's app paths by default; UseModelPaths(IEdgeModelPaths)
overrides both locations. Nothing downloads implicitly: a provisioner's Plan() reports byte
counts and licences before ProvisionAsync moves a byte. Error codes 5000-5299.
Sub-project README: embeddings/README.md. MIT licensed. https://github.com/qavren-oss/qavren-edge
| Product | Versions Compatible and additional computed target framework versions. |
|---|---|
| .NET | net10.0 is compatible. net10.0-android was computed. net10.0-android36.0 is compatible. net10.0-browser was computed. net10.0-ios was computed. net10.0-ios26.0 is compatible. net10.0-maccatalyst was computed. net10.0-maccatalyst26.0 is compatible. net10.0-macos was computed. net10.0-tvos was computed. net10.0-windows was computed. |
-
net10.0
- Microsoft.Extensions.DependencyInjection.Abstractions (>= 10.0.12)
- Microsoft.Extensions.Logging.Abstractions (>= 10.0.12)
- Microsoft.Extensions.Options (>= 10.0.12)
- Microsoft.ML.OnnxRuntime (>= 1.30.0)
- Qavren.Edge.Core (>= 1.0.0)
-
net10.0-android36.0
- Microsoft.Extensions.DependencyInjection.Abstractions (>= 10.0.12)
- Microsoft.Extensions.Logging.Abstractions (>= 10.0.12)
- Microsoft.Extensions.Options (>= 10.0.12)
- Microsoft.ML.OnnxRuntime (>= 1.30.0)
- Qavren.Edge.Core (>= 1.0.0)
-
net10.0-ios26.0
- Microsoft.Extensions.DependencyInjection.Abstractions (>= 10.0.12)
- Microsoft.Extensions.Logging.Abstractions (>= 10.0.12)
- Microsoft.Extensions.Options (>= 10.0.12)
- Microsoft.ML.OnnxRuntime (>= 1.30.0)
- Qavren.Edge.Core (>= 1.0.0)
-
net10.0-maccatalyst26.0
- Microsoft.Extensions.DependencyInjection.Abstractions (>= 10.0.12)
- Microsoft.Extensions.Logging.Abstractions (>= 10.0.12)
- Microsoft.Extensions.Options (>= 10.0.12)
- Microsoft.ML.OnnxRuntime (>= 1.30.0)
- Qavren.Edge.Core (>= 1.0.0)
NuGet packages (2)
Showing the top 2 NuGet packages that depend on Qavren.Edge.Onnx:
| Package | Downloads |
|---|---|
|
Qavren.Edge.Embeddings.Onnx
On-device text embeddings for Qavren.Edge: a Microsoft.Extensions.AI IEmbeddingGenerator over ONNX Runtime, with WordPiece tokenization, masked pooling, L2 normalisation, batching, and pinned model presets. |
|
|
Qavren.Edge.Chat.Onnx
On-device chat for Qavren.Edge: a Microsoft.Extensions.AI IChatClient over ONNX Runtime GenAI, with a KV-cache-aware memory budget, consent-gated model provisioning, thermal-paced streaming and honest per-turn diagnostics. |
GitHub repositories
This package is not used by any popular GitHub repositories.
| Version | Downloads | Last Updated |
|---|---|---|
| 1.0.0 | 566 | 9/25/2026 |
| 1.0.0-rc.1 | 81 | 9/24/2026 |
| 0.1.0-preview.1 | 93 | 9/13/2026 |