{
  "services": {
    "api": {
      "host": "0.0.0.0",
      "port": 8002
    },
    "openai": {
      "host": "0.0.0.0",
      "port": 8001
    }
  },
  "api_key": "",
  "tensor_parallel_size": 2,
  "dtype": "bfloat16",
  "revision": "",
  "default_model": "Qwen3.5-35B-A3B-GPTQ-Int4",
  "selected_model": "Qwen3.5-35B-A3B-GPTQ-Int4",
  "Qwen3-Next-80B-A3B-Instruct-AWQ-4bit": {
    "ctx": "24576",
    "trust_remote": true,
    "valid_tp": [2],
    "max_num_seqs": "32",
    "max_tokens": "16384",
    "gpu_util": "0.98",
    "enforce_eager": false,
    "env": {
      "VLLM_USE_TRITON_AWQ": "1"
    },
    "tool_call_parser": "qwen3_xml",
    "enable_auto_tool_choice": true,
    "served_model_name": "Qwen3-Next-80B-A3B-Instruct-AWQ-4bit",
    "hf_model_id": "cpatonn/Qwen3-Next-80B-A3B-Instruct-AWQ-4bit"
  },
  "GLM-4.7-Flash-AWQ": {
    "ctx": "32768",
    "trust_remote": true,
    "valid_tp": [1, 2],
    "max_num_seqs": "64",
    "max_tokens": "32768",
    "gpu_util": "0.98",
    "tool_call_parser": "qwen3_xml",
    "enable_auto_tool_choice": true,
    "served_model_name": "GLM-4.7-Flash-AWQ",
    "hf_model_id": "THUDM/GLM-4.7-Flash-AWQ"
  },
  "Qwen3.5-27B-FP8": {
    "ctx": "32768",
    "trust_remote": true,
    "valid_tp": [1, 2],
    "max_num_seqs": "64",
    "max_tokens": "32768",
    "gpu_util": "0.98",
    "tool_call_parser": "qwen3_xml",
    "enable_auto_tool_choice": true,
    "served_model_name": "Qwen3.5-27B-FP8",
    "hf_model_id": "RedHatAI/Qwen3.5-27B-FP8-dynamic"
  },
  "Qwen3.5-35B-A3B-GPTQ-Int4": {
    "ctx": "32768",
    "trust_remote": true,
    "valid_tp": [1, 2],
    "max_num_seqs": "64",
    "max_tokens": "32768",
    "gpu_util": "0.98",
    "tool_call_parser": "qwen3_xml",
    "enable_auto_tool_choice": true,
    "served_model_name": "Qwen3.5-35B-A3B-GPTQ-Int4",
    "hf_model_id": "Qwen/Qwen3.5-35B-A3B-GPTQ-Int4"
  }
}