LLM-Server/docker-compose.yml

services:
  llama-server:
    image: ghcr.io/ggml-org/llama.cpp:server-rocm
    container_name: llama-server
    devices:
      - /dev/kfd
      - /dev/dri
    group_add:
      - video
      - render
    security_opt:
      - seccomp=unconfined
    ipc: host
    volumes:
      - models:/models
    command: >
      -m /models/${LLAMA_MODEL_FILE:-Qwen3.8-27B-UD-Q4_K_XL.gguf}
      --host 0.0.0.0
      --port 8080
      --n-gpu-layers ${LLAMA_GPU_LAYERS:-999}
      --ctx-size ${LLAMA_CTX_SIZE:-65536}
      --jinja
    ports:
      # published to the host so Claude Code CLI / Kimi CLI can reach it directly,
      # bypassing Open WebUI.
      - "${LLAMA_PORT:-8080}:8080"
    restart: unless-stopped
    networks: [ai-stack]
    labels:
      # ponytail: idle-timeout tuning lives here, not in a separate lazytainer config file —
      # one place to look. Raise LAZYTAINER_INACTIVE_TIMEOUT if 15 min proves too eager.
      - "lazytainer.group.llamaserver.sleepMethod=stop"
      - "lazytainer.group.llamaserver.ports=8080"
      - "lazytainer.group.llamaserver.inactiveTimeout=${LAZYTAINER_INACTIVE_TIMEOUT:-900}"
      - "lazytainer.group.llamaserver.minPacketThreshold=2"

  # ponytail: one-off downloader, not a standing service — run via
  # `docker compose --profile tools run --rm downloader` (see scripts/download-model.sh).
  # Keeps the model file inside the named `models` volume instead of a host bind-mount.
  downloader:
    image: curlimages/curl:latest
    profiles: ["tools"]
    volumes:
      - models:/models
    entrypoint: ["sh", "-c"]
    command:
      - >
        curl -L --fail --create-dirs -o /models/${LLAMA_MODEL_FILE:-Qwen3.8-27B-UD-Q4_K_XL.gguf}
        https://huggingface.co/unsloth/Qwen3.8-27B-GGUF/resolve/main/${LLAMA_MODEL_FILE:-Qwen3.8-27B-UD-Q4_K_XL.gguf}

  qdrant:
    image: qdrant/qdrant:latest
    container_name: qdrant
    volumes:
      - qdrant-data:/qdrant/storage
    restart: unless-stopped
    networks: [ai-stack]

  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    container_name: open-webui
    depends_on:
      - qdrant
    volumes:
      - openwebui-data:/app/backend/data
    environment:
      - WEBUI_AUTH=True
      - OPENAI_API_BASE_URL=http://llama-server:8080/v1
      - OPENAI_API_KEY=${OPENAI_API_KEY:-local}
      - VECTOR_DB=qdrant
      - QDRANT_URI=http://qdrant:6333
    ports:
      - "${WEBUI_PORT:-3000}:8080"
    restart: unless-stopped
    networks: [ai-stack]

  litellm:
    image: ghcr.io/berriai/litellm:main-stable
    container_name: litellm
    depends_on:
      - litellm-db
      - llama-server
    volumes:
      - ./litellm-config.yaml:/app/config.yaml:ro
    environment:
      - LITELLM_MASTER_KEY=${LITELLM_MASTER_KEY:?set a real master key in .env — see docs/proxy-key-onboarding.md}
      - LITELLM_SALT_KEY=${LITELLM_SALT_KEY:?set a real salt key in .env, do not change after first run}
      - DATABASE_URL=postgresql://litellm:${LITELLM_DB_PASSWORD:-litellm}@litellm-db:5432/litellm
    command: ["--config", "/app/config.yaml", "--port", "4000"]
    ports:
      # published for LAN access (proxy.ai.home) and, via NPM, proxy.ai.haylan.ch —
      # NPM must deny the /ui path on the external host. See docs/network-access.md.
      - "${LITELLM_PORT:-4000}:4000"
    restart: unless-stopped
    networks: [ai-stack]

  litellm-db:
    image: postgres:16-alpine
    container_name: litellm-db
    environment:
      - POSTGRES_USER=litellm
      - POSTGRES_PASSWORD=${LITELLM_DB_PASSWORD:-litellm}
      - POSTGRES_DB=litellm
    volumes:
      - litellm-db-data:/var/lib/postgresql/data
    restart: unless-stopped
    networks: [ai-stack]

  lazytainer:
    image: ghcr.io/vmorganp/lazytainer:master
    container_name: lazytainer
    network_mode: host
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock:ro
    restart: unless-stopped
    depends_on:
      - llama-server

networks:
  ai-stack:

volumes:
  models:
  qdrant-data:
  openwebui-data:
  litellm-db-data: