xc-llm-ascend/benchmarks/tests/serving-tests.json

[
  {
    "test_name": "serving_qwen2_5vl_7B_tp1",
    "qps_list": [
      1,
      4,
      16,
      "inf"
    ],
    "server_parameters": {
      "model": "Qwen/Qwen2.5-VL-7B-Instruct",
      "tensor_parallel_size": 1,
      "swap_space": 16,
      "disable_log_stats": "",
      "disable_log_requests": "",
      "trust_remote_code": "",
      "max_model_len": 16384
    },
    "client_parameters": {
      "model": "Qwen/Qwen2.5-VL-7B-Instruct",
      "backend": "openai-chat",
      "dataset_name": "hf",
      "hf_split": "train",
      "endpoint": "/v1/chat/completions",
      "dataset_path": "lmarena-ai/vision-arena-bench-v0.1",
      "num_prompts": 200,
      "no_stream": ""
    }
  },
  {
    "test_name": "serving_qwen3_8B_tp1",
    "qps_list": [
      1,
      4,
      16,
      "inf"
    ],
    "server_parameters": {
      "model": "Qwen/Qwen3-8B",
      "tensor_parallel_size": 1,
      "swap_space": 16,
      "disable_log_stats": "",
      "disable_log_requests": "",
      "load_format": "dummy"
    },
    "client_parameters": {
      "model": "Qwen/Qwen3-8B",
      "backend": "vllm",
      "dataset_name": "sharegpt",
      "dataset_path": "/github/home/.cache/datasets/ShareGPT_V3_unfiltered_cleaned_split.json",
      "num_prompts": 200
    }
  },
  {
    "test_name": "serving_qwen2_5_7B_tp1",
    "qps_list": [
      1,
      4,
      16,
      "inf"
    ],
    "server_parameters": {
      "model": "Qwen/Qwen2.5-7B-Instruct",
      "tensor_parallel_size": 1,
      "swap_space": 16,
      "disable_log_stats": "",
      "disable_log_requests": "",
      "load_format": "dummy"
    },
    "client_parameters": {
      "model": "Qwen/Qwen2.5-7B-Instruct",
      "backend": "vllm",
      "dataset_name": "sharegpt",
      "dataset_path": "/github/home/.cache/datasets/ShareGPT_V3_unfiltered_cleaned_split.json",
      "num_prompts": 200
    }
  }
]