RWKV Runner

This project aims to eliminate the barriers of using large language models by automating everything for you. All you need is a lightweight executable program of just a few megabytes. Additionally, this project provides an interface compatible with the OpenAI API, which means that every ChatGPT client is an RWKV client.

English | 简体中文

FAQs | Preview | Download

Default configs do not enable custom CUDA kernel acceleration, but I strongly recommend that you enable it and run with int8 precision, which is much faster and consumes much less VRAM. Go to the Configs page and turn on Use Custom CUDA kernel to Accelerate.

For different tasks, adjusting API parameters can achieve better results. For example, for translation tasks, you can try setting Temperature to 1 and Top_P to 0.3.

Features

• RWKV model management and one-click startup
• Fully compatible with the OpenAI API, making every ChatGPT client an RWKV client. After starting the model, open http://127.0.0.1:8000/docs to view more details.
• Automatic dependency installation, requiring only a lightweight executable program
• User-friendly chat interaction interface included
• Easy-to-understand and operate parameter configuration
• Built-in model conversion tool
• Built-in download management and remote model inspection
• Multilingual localization
• Theme switching
• Automatic updates

API Concurrency Stress Testing

ab -p body.json -T application/json -c 20 -n 100 -l http://127.0.0.1:8000/chat/completions

body.json:

{
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}

Todo

• Model training functionality
• CUDA operator int8 acceleration
• macOS support
• Linux support

Related Repositories:

• RWKV-4-Raven: https://huggingface.co/BlinkDL/rwkv-4-raven/tree/main
• ChatRWKV: https://github.com/BlinkDL/ChatRWKV
• RWKV-LM: https://github.com/BlinkDL/RWKV-LM

Preview

Homepage

Chat

Completion

Configuration

Model Management

Download Management

Settings