Darkspyre.Inference.Tensor.Registry
11.19.3-rc.2
Prefix Reserved
dotnet add package Darkspyre.Inference.Tensor.Registry --version 11.19.3-rc.2
NuGet\Install-Package Darkspyre.Inference.Tensor.Registry -Version 11.19.3-rc.2
<PackageReference Include="Darkspyre.Inference.Tensor.Registry" Version="11.19.3-rc.2" />
<PackageVersion Include="Darkspyre.Inference.Tensor.Registry" Version="11.19.3-rc.2" />
<PackageReference Include="Darkspyre.Inference.Tensor.Registry" />
paket add Darkspyre.Inference.Tensor.Registry --version 11.19.3-rc.2
#r "nuget: Darkspyre.Inference.Tensor.Registry, 11.19.3-rc.2"
#:package Darkspyre.Inference.Tensor.Registry@11.19.3-rc.2
#addin nuget:?package=Darkspyre.Inference.Tensor.Registry&version=11.19.3-rc.2&prerelease
#tool nuget:?package=Darkspyre.Inference.Tensor.Registry&version=11.19.3-rc.2&prerelease
Darkspyre.Inference.Tensor.Registry
Registration and discovery of the shipped Tensor engines: Qwen, Supra, Laya, Whisper, the GGUF embedding engine and
EmbeddingGemma. TensorEngineRegistry lists their definitions and creates their instances and settings managers, so
an application offers every engine without keeping its own engine list.
Install
dotnet add package Darkspyre.Inference.Tensor.Registry
The package references every engine package. An application that uses one engine can reference that engine alone.
Register
services.AddTensorEngines(ggmlRuntimePlan);
AddTensorEngines() registers each shipped engine's ITensorEngineProvider, the shared GgmlRuntimeOwner and the
TensorEngineRegistry as singletons. A repeated call adds nothing. A provider registered separately joins the same
registry.
Example
TensorEngineRegistry registry = serviceProvider.GetRequiredService<TensorEngineRegistry>();
foreach (TensorEngineDefinition definition in registry.Definitions)
{
// Show definition.Setup in the application's provider list.
}
if (registry.TryGetProvider(implementationId, out ITensorEngineProvider? provider))
{
var packs = new TensorModelPackManager(new TensorModelCatalog(provider.BuiltInModels),
Path.Combine(storageRoot, provider.Definition.ModelStoreKey));
ITensorModelInstance instance = provider.CreateInstance(packs, TensorBackendKind.Auto, scratchDirectory);
}
Limits
- Two providers with the same implementation id, or store keys equal ignoring case, fail when the registry is resolved.
TryGetProvidermatches the implementation id exactly and case-sensitively.- Reading a definition or the built-in models constructs no engine, loads no native library and opens no store.
CreateInstancedoes not start, load or download anything. - The registry scans no assemblies and loads no plugins.
The Darkspyre.Inference packages
This package is one library of the Darkspyre.Inference family. The family runs AI inference from .NET applications through typed, provider-neutral contracts.
Darkspyre.Inference.Commonholds the contracts every other package shares: requests, results, capabilities, failures and the provider setup model.Darkspyre.Inference.Connect.Commonholds the conversation and embedding services. Each Connect provider package adds one provider, andAddLlmConnect()discovers every provider package the application references.- The Tensor packages load and run models inside the application's own process.
- The UI.Settings packages provide the setup editors a host places in its own window or page.
Every package of the family carries the same version. Reference all of them at the same version: each package depends on the exact version of the family packages it uses.
The packages are licensed under the MIT license. LICENSE.md in each package holds the license text.
| Package | Holds |
|---|---|
| Darkspyre.Inference.Common | Shared contracts for Connect and Tensor |
| Darkspyre.Inference.Connect | Image, speech and audio connectors |
| Darkspyre.Inference.Connect.Common | Conversation and embedding services and provider discovery |
| Darkspyre.Inference.Connect.Codex | Conversations on a ChatGPT subscription |
| Darkspyre.Inference.Connect.Claude | Conversations on a Claude subscription through the Claude CLI |
| Darkspyre.Inference.Connect.HostTools | The host-tools local service and its client |
| Darkspyre.Inference.Connect.Antigravity | Conversations on a Google subscription through the Antigravity CLI |
| Darkspyre.Inference.Connect.Grok | Conversations on a Grok subscription |
| Darkspyre.Inference.Connect.OpenAiApi | Conversations and embeddings through the OpenAI API |
| Darkspyre.Inference.Connect.SelfHost | Conversations and embeddings on engines the application runs |
| Darkspyre.Inference.Tensor.Common | Model packs, the model lifecycle and the Tensor capability interfaces |
| Darkspyre.Inference.Tensor.Decision.Laya | Laya typed decisions through ONNX Runtime |
| Darkspyre.Inference.Tensor.Embedding | Text embeddings from GGUF sentence encoders |
| Darkspyre.Inference.Tensor.Embedding.Gemma | EmbeddingGemma text and image embeddings |
| Darkspyre.Inference.Tensor.Ggml | The process's GGML and MLX native runtime |
| Darkspyre.Inference.Tensor.Image.Supra | Supra2-IMG image generation |
| Darkspyre.Inference.Tensor.LLM.Qwen | Qwen GGUF text generation |
| Darkspyre.Inference.Tensor.Registry | Registration and discovery of the Tensor engines |
| Darkspyre.Inference.Tensor.STT.Whisper | Whisper speech transcription |
| Darkspyre.Inference.UI.Settings.Core | Editor state and host contracts both setup editors share |
| Darkspyre.Inference.UI.Settings.Avalonia | The Avalonia setup editor |
| Darkspyre.Inference.UI.Settings.Blazor | The Blazor setup editor |
| Product | Versions Compatible and additional computed target framework versions. |
|---|---|
| .NET | net11.0 is compatible. |
-
net11.0
- Darkspyre.Inference.Tensor.Decision.Laya (= 11.19.3-rc.2)
- Darkspyre.Inference.Tensor.Embedding (= 11.19.3-rc.2)
- Darkspyre.Inference.Tensor.Embedding.Gemma (= 11.19.3-rc.2)
- Darkspyre.Inference.Tensor.Image.Supra (= 11.19.3-rc.2)
- Darkspyre.Inference.Tensor.LLM.Qwen (= 11.19.3-rc.2)
- Darkspyre.Inference.Tensor.STT.Whisper (= 11.19.3-rc.2)
- Darkspyre.ML.Tokenizers (>= 2.0.1.1)
- Microsoft.ML.OnnxRuntime (>= 1.30.0)
- Microsoft.ML.OnnxRuntime.EP.WebGpu (>= 0.4.0)
- NAudio.Core (>= 2.2.1)
- StbImageSharp (>= 2.30.15)
- TensorSharp.Backends.Cuda (>= 2026.10.11)
- TensorSharp.Backends.GGML (>= 2026.10.11)
- TensorSharp.Backends.MLX (>= 2026.10.11)
- TensorSharp.Chat (>= 2026.10.11)
- TensorSharp.Models (>= 2026.10.11)
- TensorSharp.Runtime (>= 2026.10.11)
- TensorSharp.Tensors (>= 2026.10.11)
- Whisper.net (>= 1.9.1)
- Whisper.net.Runtime (>= 1.9.1)
- Whisper.net.Runtime.Cuda12.Linux (>= 1.9.1)
NuGet packages
This package is not used by any NuGet packages.
GitHub repositories
This package is not used by any popular GitHub repositories.
| Version | Downloads | Last Updated |
|---|---|---|
| 11.19.3-rc.2 | 0 | 10/31/2026 |
| 11.17.3-rc.2 | 64 | 10/26/2026 |