dvai 

Embeds an OpenAI-compatible HTTP server inside your .NET app process (127.0.0.1:38883, /v1/chat/completions, /v1/embeddings, /v1/models, SSE streaming). Any OpenAI client speaks to it — the OpenAI .NET SDK,... More information

Desktop Llama backend for DVAIBridge — bundles llama.cpp b8946 prebuilt natives per RID (win-x64 / win-arm64 / osx-x64 / osx-arm64 / linux-x64 / linux-arm64). Embeds Kestrel for the OpenAI-compatible HTTP... More information

ML.NET backend for DVAIBridge — integrates LLM inference into existing ML.NET pipelines via Microsoft.ML + OnnxScoringEstimator. Desktop-primary (Windows / macOS / Linux); rejected on mobile (use... More information

iOS native bindings for DVAIBridge — internal slice of the DVAIBridge NuGet family. Pulled in transitively by DVAIBridge when targeting net10.0-ios. Consumers should depend on DVAIBridge directly. Mac Catalyst... More information

Android native bindings for DVAIBridge — internal slice of the DVAIBridge NuGet family. Pulled in transitively by DVAIBridge when targeting net10.0-android. Consumers should depend on DVAIBridge directly. The... More information

ONNX Runtime + OnnxRuntimeGenAI backend for DVAIBridge. Cross-platform LLM inference via Phi-3.5 / Phi-4 / Llama-3.2 ONNX models. Opt-in via `dotnet add package DVAIBridge.OnnxRuntime` — the facade routes... More information