llama-server-manager config.json

{
  "options": {},
  "llama-server": {
    "options": {
      "host": "0.0.0.0",
      "port": "11235",
      "models-max": 1,
      "parallel": 1,
      "sleep-idle-seconds": 600,
      "fit-target": 512,
      "flash-attn": "on",
      "no-mmap": "",
      "cache-type-k": "f16",
      "cache-type-v": "f16",
      "n-gpu-layers": 999,
      "n-cpu-moe": 30
    }
  },
  "logging": {
    "enabled": true,
    "level": "INFO",
    "file": null
  }
}