• Documentation
• Examples
• Installation
• • Tips for choosing a version
• Quick Start
• • • Model Inference and Chat Session
    • Web API
• Features
• Console Demo
• FAQ
• Contributing
• Contact us
• Appendix
• • LLamaSharp and llama.cpp versions
• License

The C#/.NET binding of llama.cpp. It provides higher-level APIs to inference the LLaMA Models and deploy it on local device with C#/.NET. It works on Windows, Linux and Mac without need to compile llama.cpp yourself. Even without a GPU or not enough GPU memory, you can still use LLaMA models! 🤗

Furthermore, it provides integrations with other projects such as semantic-kernel, kernel-memory and BotSharp to provide higher-level applications.

Discussions about the roadmap to v1.0.0: #287

Table of Contents

• Documentation
• Examples
• Installation
• Quick Start
  • Model Inference and Chat Session
  • Quantization
  • Web API
• Features
• Console Demo
• FAQ
• Contributing
• Contact us
• Appendix
  • LLamaSharp and llama.cpp versions

Documentation

• Quick start
• Tricks for FAQ
• Full documentation
• API reference

Examples

• Official Console Examples
• Unity Demo
• LLamaStack (with WPF and Web support)
• Blazor Demo (with Model Explorer)

Installation

1. Install LLamaSharp package in NuGet:

PM> Install-Package LLamaSharp

2. Install one of these backends:

   • LLamaSharp.Backend.Cpu: Pure CPU for Windows & Linux. Metal for Mac.
   • LLamaSharp.Backend.Cuda11: CUDA11 for Windows and Linux
   • LLamaSharp.Backend.Cuda12: CUDA 12 for Windows and Linux
   • LLamaSharp.Backend.OpenCL: OpenCL for Windows and Linux
   • If none of these backends is suitable you can compile llama.cpp yourself. In this case, please DO NOT install the backend packages! Instead, add your DLL to your project and ensure it will be copied to the output directory when compiling your project. If you do this you must use exactly the correct llama.cpp commit, refer to the version table further down.

3. (optional) For Microsoft semantic-kernel integration, install the LLamaSharp.semantic-kernel package.

4. (optional) For Microsoft kernel-memory integration, install the LLamaSharp.kernel-memory package (this package currently only supports net6.0).

Tips for choosing a version

Llama.cpp is a fast moving project with frequent breaking changes, therefore breaking changes are expected frequently in LLamaSharp. LLamaSharp follows semantic versioning and will not introduce breaking API changes on patch versions.

It is suggested to update to the latest patch version as soon as it is released, and to update to new major versions as soon as possible.

Quick Start

Model Inference and Chat Session

LLamaSharp provides two ways to run inference: LLamaExecutor and ChatSession. The chat session is a higher-level wrapping of the executor and the model. Here's a simple example to use chat session.

using LLama.Common;
using LLama;

string modelPath = @"<Your Model Path>"; // change it to your own model path.

var parameters = new ModelParams(modelPath)
{
    ContextSize = 1024, // The longest length of chat as memory.
    GpuLayerCount = 5 // How many layers to offload to GPU. Please adjust it according to your GPU memory.
};
using var model = LLamaWeights.LoadFromFile(parameters);
using var context = model.CreateContext(parameters);
var executor = new InteractiveExecutor(context);

// Add chat histories as prompt to tell AI how to act.
var chatHistory = new ChatHistory();
chatHistory.AddMessage(AuthorRole.System, "Transcript of a dialog, where the User interacts with an Assistant named Bob. Bob is helpful, kind, honest, good at writing, and never fails to answer the User's requests immediately and with precision.");
chatHistory.AddMessage(AuthorRole.User, "Hello, Bob.");
chatHistory.AddMessage(AuthorRole.Assistant, "Hello. How may I help you today?");

ChatSession session = new(executor, chatHistory);

InferenceParams inferenceParams = new InferenceParams()
{
    MaxTokens = 256, // No more than 256 tokens should appear in answer. Remove it if antiprompt is enough for control.
    AntiPrompts = new List<string> { "User:" } // Stop generation once antiprompts appear.
};

Console.ForegroundColor = ConsoleColor.Yellow;
Console.Write("The chat session has started.\nUser: ");
Console.ForegroundColor = ConsoleColor.Green;
string userInput = Console.ReadLine() ?? "";

while (userInput != "exit")
{
    await foreach ( // Generate the response streamingly.
        var text
        in session.ChatAsync(
            new ChatHistory.Message(AuthorRole.User, userInput),
            inferenceParams))
    {
        Console.ForegroundColor = ConsoleColor.White;
        Console.Write(text);
    }
    Console.ForegroundColor = ConsoleColor.Green;
    userInput = Console.ReadLine() ?? "";
}

For more usage, please refer to Examples.

Web API

We provide an integration with ASP.NET core and a web app demo. Since we are in short of hands, if you're familiar with ASP.NET core, we'll appreciate it if you would like to help upgrading the Web API integration.

Features

---

✅: completed. ⚠️: outdated for latest release but will be updated. 🔳: not completed

---

✅ LLaMa model inference

✅ Embeddings generation, tokenization and detokenization

✅ Chat session

✅ Quantization

✅ Grammar

✅ State saving and loading

✅ BotSharp Integration Online Demo

✅ ASP.NET core Integration

✅ Semantic-kernel Integration

🔳 Fine-tune

✅ Local document search (enabled by kernel-memory)

🔳 MAUI Integration

Console Demo

FAQ

1. GPU out of memory: Please try setting n_gpu_layers to a smaller number.
2. Unsupported model: llama.cpp is under quick development and often has breaking changes. Please check the release date of the model and find a suitable version of LLamaSharp to install, or generate gguf format weights from original weights yourself.
3. Cannot load native library:
   • Ensure you have installed one of the backend packages.
   • Run NativeLibraryConfig.WithLogs() at the very beginning of your code to print more information.
4. Models in GGUF format are compatible with LLamaSharp. It's a good idea to search for gguf on huggingface to find a model. Another choice is generate a GGUF format file yourself, please refer to convert.py for more information.

Contributing

Any contribution is welcomed! There's a TODO list in LLamaSharp Dev Project and you could pick an interesting one to start. Please read the contributing guide for more information.

You can also do one of the followings to help us make LLamaSharp better:

• Submit a feature request.
• Star and share LLamaSharp to let others know it.
• Write a blog or demo about LLamaSharp.
• Help to develop Web API and UI integration.
• Just open an issue about the problem you met!

Contact us

Join our chat on Discord (please contact Rinne to join the dev channel if you want to be a contributor).

Join QQ group

Appendix

LLamaSharp and llama.cpp versions

If you want to compile llama.cpp yourself you must use the exact commit ID listed for each version.

LLamaSharp	Verified Model Resources	llama.cpp commit id
v0.2.0	This version is not recommended to use.	-
v0.2.1	WizardLM, Vicuna (filenames with "old")	-
v0.2.2, v0.2.3	WizardLM, Vicuna (filenames without "old")	63d2046
v0.3.0, v0.4.0	LLamaSharpSamples v0.3.0, WizardLM	7e4ea5b
v0.4.1-preview	Open llama 3b, Open Buddy	aacdbd4
v0.4.2-preview	Llama2 7B (GGML)	3323112
v0.5.1	Llama2 7B (GGUF)	6b73ef1
v0.6.0		cb33f43
v0.7.0, v0.8.0	Thespis-13B, LLaMA2-7B	207b519
v0.8.1		e937066
v0.9.0, v0.9.1	Mixtral-8x7B	9fb13f9
v0.10.0	Phi2	d71ac90

License

This project is licensed under the terms of the MIT license.