RWKV-Runner Docker & Self-Hosted Deployment

GitHub

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...

6,340 stars TypeScript TypeScript 1 file · ~2,246 tokens #api#api-client#chatgpt#llm#rwkv#tool#wails
RAW Compose
1. Pull Image (DOCKERHUB) docker pull library/rwkv-runner
2. Docker Run (1-Click Launch) docker run -d --name rwkv-runner -p 27777:27777 --restart always rwkv-runner:latest
3. Podman Run podman run -d --name rwkv-runner -p 27777:27777 --restart always rwkv-runner:latest
4. Skopeo Inspect (Zero-Pull Manifest) skopeo inspect docker://docker.io/library/rwkv-runner:latest
5. ORAS Pull (OCI Artifact) oras pull rwkv-runner:latest
6. Compose Deployment docker compose up -d
docker-compose.yml
Download .yml 
services:
  rmkv_runner:
    image: rwkv-runner:latest
    build: .
    # Append "--rwkv.cpp" parameter to use rwkv.cpp
    # command: python3.10 ./backend-python/main.py  --port 27777 --host 0.0.0.0 --webui --rwkv.cpp
    volumes:
      - /mnt:/mnt
    ports:
      - "27777:27777"
    # Comment the following lines if use rwkv.cpp
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]