# colibri — OpenAI-compatible server in one command.
#
#   MODEL_DIR=/nvme/glm52_i4 docker compose -f docker/docker-compose.yml up
#
# Then: curl http://localhost:5000/v1/chat/completions -d '{"model":"glm-5.2",
#   "messages":[{"role":"user","content":"Hi"}]}'
#
# The model is bind-mounted read-only from MODEL_DIR on the host — keep it on
# NVMe/ext4, never a network mount (expert streaming is latency-bound).
services:
  colibri:
    build:
      context: ..
      dockerfile: docker/Dockerfile.slim
    image: colibri
    ports:
      - "5000:5000"
    volumes:
      - "${MODEL_DIR:?set MODEL_DIR to the int4 model directory}:/model:ro"
    environment:
      # RAM budget in GB: more cached experts = faster. Size to the host.
      COLI_RAM: "${COLI_RAM:-24}"
    command:
      - serve
      - --host
      - 0.0.0.0
      - --model-id
      - glm-5.2
      - --ram
      - "${COLI_RAM:-24}"
    restart: unless-stopped
    # Streaming a 744B model touches a lot of page cache; give it headroom.
    shm_size: "2gb"