🧩 TensorSharp: Native .NET LLM Inference Engine

In an LLM inference landscape dominated by C/C++ and Python, C# developers often have to rely on external APIs or wrappers. TensorSharp offers a different route as a native .NET LLM inference engine and agent runtime specifically built for GGUF models. The interesting part is its comprehensive cross-platform support and feature set. It runs on Windows, MacOS, Linux, and iOS, with full GPU capability via CUDA. The project includes a console app, a web interface, an iPhone app, and HTTP APIs compatible with Ollama and OpenAI. For developers in the .NET ecosystem, this provides a direct way to embed local model inference into their existing architectures.