zhongkaifu/TensorSharp
A native .NET LLM inference engine and agent runtime for GGUF models with CPU and GPU backends.
Collecting fresh signals — velocity needs a few days of history.
collecting data…
star history
TensorSharp is a .NET-based inference engine that runs GGUF-format language, multimodal, image, and video models on Windows, macOS, iOS, and Linux with CUDA and Metal acceleration. It ships a console application, a browser-based chat UI, and HTTP APIs compatible with Ollama and OpenAI for programmatic access. An optional TensorSharp.AgentHost layer adds agent skills, bounded in-process tool use, and automatic subagent delegation. The project supports a wide range of model families including DeepSeek, GLM, Gemma, Qwen, and others.
Frequently asked
- What is zhongkaifu/TensorSharp?
- A native .NET LLM inference engine and agent runtime for GGUF models with CPU and GPU backends.
- Is TensorSharp open source?
- Yes — zhongkaifu/TensorSharp is open source, released under the BSD-3-Clause license.
- What language is TensorSharp written in?
- zhongkaifu/TensorSharp is primarily written in C#.
- How popular is TensorSharp?
- zhongkaifu/TensorSharp has 504 stars on GitHub.
- Where can I find TensorSharp?
- zhongkaifu/TensorSharp is on GitHub at https://github.com/zhongkaifu/TensorSharp.