version: "3.8"

services:
  ollama:
    build:
      context: ./
      dockerfile: Dockerfile
    image: ollama/ollama:rocm-gfx906
    container_name: ollama
    privileged: true
    tty: true
    restart: always
    ports:
      - "127.0.0.1:11434:11434"
    networks:
      - ai_backend
    volumes:
      - /mnt/HoardingCow_docker_data/Ollama/ollama:/root/.ollama
    environment:
      - OLLAMA_VULKAN=0
      - OLLAMA_HOST=0.0.0.0
      - OLLAMA_DEBUG=1
      - OLLAMA_FLASH_ATTENTION=0
      - OLLAMA_NUM_PARALLEL=2
      # ROCm / gfx906 configuration
      - HSA_OVERRIDE_GFX_VERSION=9.0.6
      - HCC_AMDGPU_TARGET=gfx906
      - HIP_VISIBLE_DEVICES=0,1
      - ROCR_VISIBLE_DEVICES=0,1
      - HSA_ENABLE_SDMA=0
    devices:
      - /dev/kfd:/dev/kfd
      - /dev/dri:/dev/dri
    group_add:
      - "303"
      - "26"

networks:
  ai_backend:
    external: true
    name: ai_backend