RWKV-Runner
A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is
What is RWKV-Runner?
A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is fully open source and available for commercial use.
Overview of RWKV-Runner
What it is
RWKV-Runner is a management and startup tool for RWKV, which the README describes as a large language model that is fully open source and available for commercial use. The project aims to eliminate the barriers of using large language models by automating everything for you; the README states that all you need is a lightweight executable program of just a few megabytes. It also provides an interface compatible with the OpenAI API, which means that every ChatGPT client is an RWKV client.
Key features
- RWKV model management and one-click startup, with automatic dependency installation that requires only a lightweight executable program.
- Front-end and back-end separation: the front-end service, the back-end inference service, or the back-end inference service with a WebUI can each be deployed separately.
- Compatible with the OpenAI API; after starting the model, open http://127.0.0.1:8000/docs to view more details.
- Pre-set multi-level VRAM configs; switching Strategy to WebGPU on the Configs page allows it to run on AMD, Intel and other graphics cards.
- User-friendly chat, completion and composition interfaces, including chat presets, attachment uploads, MIDI hardware input and track editing.
- Built-in model conversion tool, download management, remote model inspection, and one-click LoRA Finetune (Windows only).
- Can also be used as an OpenAI ChatGPT, GPT-Playground, Ollama or llmman client by filling in the API URL and API Key on the Settings page; includes multilingual localization, theme switching and automatic updates.
Use cases
- Running RWKV models locally with automated setup and one-click startup.
- Serving an OpenAI-compatible endpoint so existing ChatGPT clients can use RWKV.
- Deploying backend-python on a server and using the program as a client by filling in the server address in the Settings
API URL. - Sharing hardware resources through the built-in WebUI option, which starts a Web service with one click.
- Composing with MIDI hardware input, including USB MIDI and Bluetooth MIDI connections.
Getting started
Install via the Windows, MacOS or Linux downloads, or run from source: bash git clone https://github.com/josStorer/RWKV-Runner cd RWKV-Runner python ./backend-python/main.py # request /switch-model API to load the model, docs: http://127.0.0.1:8000/docs # Or start front-end and back-end together: python ./backend-python/main.py --webui
License and pricing
RWKV-Runner is released under the MIT license. The metadata lists it as open source; no pricing is stated.
Based on the project's public README and repository metadata.