# Docker Compose configuration for llama.cpp
# https://github.com/ggml-org/llama.cpp
# LLM inference in C/C++ with support for various hardware accelerators

x-defaults: &defaults
  restart: unless-stopped
  logging:
    driver: json-file
    options:
      max-size: 100m
      max-file: '3'

services:
  # llama.cpp server - OpenAI-compatible API server
  # Variant: server (CPU), server-cuda (NVIDIA GPU), server-rocm (AMD GPU)
  llama-cpp-server:
    <<: *defaults
    image: ${GHCR_REGISTRY:-ghcr.io/}ggml-org/llama.cpp:${LLAMA_CPP_SERVER_VARIANT:-server}
    ports:
      - '${LLAMA_CPP_SERVER_PORT_OVERRIDE:-8080}:8080'
    volumes:
      - llama_cpp_models:/models
    command:
      - -m
      - '${LLAMA_CPP_MODEL_PATH:-/models/model.gguf}'
      - --port
      - '8080'
      - --host
      - 0.0.0.0
      - -n
      - '${LLAMA_CPP_CONTEXT_SIZE:-512}'
      - --n-gpu-layers
      - '${LLAMA_CPP_GPU_LAYERS:-0}'
    environment:
      - TZ=${TZ:-UTC}
    healthcheck:
      test:
        - CMD
        - wget
        - --quiet
        - --tries=1
        - --spider
        - 'http://localhost:8080/health'

      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s
    deploy:
      resources:
        limits:
          cpus: ${LLAMA_CPP_SERVER_CPU_LIMIT:-4.0}
          memory: ${LLAMA_CPP_SERVER_MEMORY_LIMIT:-8G}
        reservations:
          cpus: ${LLAMA_CPP_SERVER_CPU_RESERVATION:-0.1}
          memory: ${LLAMA_CPP_SERVER_MEMORY_RESERVATION:-4G}
    profiles:
      - server

  # llama.cpp server with NVIDIA GPU support
  llama-cpp-server-cuda:
    <<: *defaults
    image: ${GHCR_REGISTRY:-ghcr.io/}ggml-org/llama.cpp:server-cuda
    ports:
      - '${LLAMA_CPP_SERVER_PORT_OVERRIDE:-8080}:8080'
    volumes:
      - llama_cpp_models:/models
    command:
      - -m
      - '${LLAMA_CPP_MODEL_PATH:-/models/model.gguf}'
      - --port
      - '8080'
      - --host
      - 0.0.0.0
      - -n
      - '${LLAMA_CPP_CONTEXT_SIZE:-512}'
      - --n-gpu-layers
      - '${LLAMA_CPP_GPU_LAYERS:-99}'
    environment:
      - TZ=${TZ:-UTC}
    healthcheck:
      test:
        - CMD
        - wget
        - --quiet
        - --tries=1
        - --spider
        - 'http://localhost:8080/health'

      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s
    deploy:
      resources:
        limits:
          cpus: ${LLAMA_CPP_SERVER_CPU_LIMIT:-4.0}
          memory: ${LLAMA_CPP_SERVER_MEMORY_LIMIT:-8G}
        reservations:
          cpus: ${LLAMA_CPP_SERVER_CPU_RESERVATION:-0.1}
          memory: ${LLAMA_CPP_SERVER_MEMORY_RESERVATION:-4G}
          devices:
            - driver: nvidia
              count: ${LLAMA_CPP_GPU_COUNT:-1}
              capabilities: [gpu]
    profiles:
      - gpu
      - cuda

  # llama.cpp server with AMD ROCm GPU support
  llama-cpp-server-rocm:
    <<: *defaults
    image: ${GHCR_REGISTRY:-ghcr.io/}ggml-org/llama.cpp:server-rocm
    ports:
      - '${LLAMA_CPP_SERVER_PORT_OVERRIDE:-8080}:8080'
    volumes:
      - llama_cpp_models:/models
    devices:
      - /dev/kfd
      - /dev/dri
    command:
      - -m
      - '${LLAMA_CPP_MODEL_PATH:-/models/model.gguf}'
      - --port
      - '8080'
      - --host
      - 0.0.0.0
      - -n
      - '${LLAMA_CPP_CONTEXT_SIZE:-512}'
      - --n-gpu-layers
      - '${LLAMA_CPP_GPU_LAYERS:-99}'
    environment:
      - TZ=${TZ:-UTC}
    healthcheck:
      test:
        - CMD
        - wget
        - --quiet
        - --tries=1
        - --spider
        - 'http://localhost:8080/health'

      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s
    deploy:
      resources:
        limits:
          cpus: ${LLAMA_CPP_SERVER_CPU_LIMIT:-4.0}
          memory: ${LLAMA_CPP_SERVER_MEMORY_LIMIT:-8G}
        reservations:
          cpus: ${LLAMA_CPP_SERVER_CPU_RESERVATION:-0.1}
          memory: ${LLAMA_CPP_SERVER_MEMORY_RESERVATION:-4G}
    profiles:
      - gpu
      - rocm

  # llama.cpp CLI (light) - Interactive command-line interface
  llama-cpp-cli:
    <<: *defaults
    image: ${GHCR_REGISTRY:-ghcr.io/}ggml-org/llama.cpp:${LLAMA_CPP_CLI_VARIANT:-light}
    volumes:
      - llama_cpp_models:/models
    entrypoint: /app/llama-cli
    command:
      - -m
      - '${LLAMA_CPP_MODEL_PATH:-/models/model.gguf}'
      - -p
      - '${LLAMA_CPP_PROMPT:-Hello, how are you?}'
      - -n
      - '${LLAMA_CPP_CONTEXT_SIZE:-512}'
    environment:
      - TZ=${TZ:-UTC}
    deploy:
      resources:
        limits:
          cpus: ${LLAMA_CPP_CLI_CPU_LIMIT:-2.0}
          memory: ${LLAMA_CPP_CLI_MEMORY_LIMIT:-4G}
        reservations:
          cpus: ${LLAMA_CPP_CLI_CPU_RESERVATION:-0.1}
          memory: ${LLAMA_CPP_CLI_MEMORY_RESERVATION:-2G}
    profiles:
      - cli

  # llama.cpp full - Complete toolkit including model conversion tools
  llama-cpp-full:
    <<: *defaults
    image: ${GHCR_REGISTRY:-ghcr.io/}ggml-org/llama.cpp:${LLAMA_CPP_FULL_VARIANT:-full}
    volumes:
      - llama_cpp_models:/models
    command: [sleep, infinity]
    environment:
      - TZ=${TZ:-UTC}
    deploy:
      resources:
        limits:
          cpus: ${LLAMA_CPP_FULL_CPU_LIMIT:-2.0}
          memory: ${LLAMA_CPP_FULL_MEMORY_LIMIT:-4G}
        reservations:
          cpus: ${LLAMA_CPP_FULL_CPU_RESERVATION:-0.1}
          memory: ${LLAMA_CPP_FULL_MEMORY_RESERVATION:-2G}
    profiles:
      - full

volumes:
  llama_cpp_models: