services:
  ollama:
    image: ollama/ollama:latest
    container_name: ollama
    restart: unless-stopped
    ports:
      - 11434:11434
    environment:
      OLLAMA_KEEP_ALIVE: 24h
      OLLAMA_NUM_PARALLEL: "1"
      OLLAMA_MAX_LOADED_MODELS: "2"
      OLLAMA_FLASH_ATTENTION: "1"
      OLLAMA_KV_CACHE_TYPE: q8_0
      OLLAMA_GPU_OVERHEAD: "1073741824"
      OLLAMA_CONTEXT_LENGTH: "32768"
      OLLAMA_LOAD_TIMEOUT: 10m
      NVIDIA_VISIBLE_DEVICES: all
      NVIDIA_DRIVER_CAPABILITIES: compute,utility
    volumes:
      - /mnt/ssd/apps/ollama-dockge:/root/.ollama
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities:
                - gpu
    healthcheck:
      test:
        - CMD
        - ollama
        - list
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 20s
    logging:
      driver: json-file
      options:
        max-size: 10m
        max-file: "3"
networks: {}