SciSharp/LLamaSharp
A C#/.NET library for efficient local execution of Large Language Models (LLMs) like LLaMA and LLAVA, leveraging llama.cpp.
Core Features
Detailed Introduction
LLamaSharp is a powerful C#/.NET library designed to enable efficient local execution of Large Language Models (LLMs) such as LLaMA and LLAVA. Built upon the highly optimized `llama.cpp` project, it offers cross-platform compatibility and supports inference on both CPUs and various GPUs (CUDA, Vulkan). The library provides higher-level APIs and built-in RAG support, simplifying the deployment of LLMs within .NET applications. It also boasts integrations with leading AI development frameworks like Semantic Kernel and Kernel Memory, making it a versatile tool for developers looking to incorporate local LLM capabilities into their projects.