# Qwen3.5-35B-A3B — VKAE Accelerated
# Launch:  docker compose up
services:
  vkae:
    image: vidraft/qwen35-vkae:601
    ports:
      - "8000:8000"          # OpenAI-compatible API -> http://localhost:8000/v1
    ipc: host
    restart: unless-stopped
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]