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

[
  {
    "test_name": "throughput_qwen3_8B_tp1",
    "parameters": {
      "model": "Qwen/Qwen3-8B",
      "tensor_parallel_size": 1,
      "load_format": "dummy",
      "dataset_path": "/github/home/.cache/datasets/ShareGPT_V3_unfiltered_cleaned_split.json",
      "num_prompts": 200,
      "backend": "vllm"
    }
  },
  {
    "test_name": "throughput_qwen2_5vl_7B_tp1",
    "parameters": {
      "model": "Qwen/Qwen2.5-VL-7B-Instruct",
      "tensor_parallel_size": 1,
      "backend": "vllm-chat",
      "dataset_name": "hf",
      "hf_split": "train",
      "max_model_len": 16384,
      "dataset_path": "lmarena-ai/vision-arena-bench-v0.1",
      "num_prompts": 200
    }
  },
  {
    "test_name": "throughput_qwen2_5_7B_tp1",
    "parameters": {
      "model": "Qwen/Qwen2.5-7B-Instruct",
      "tensor_parallel_size": 1,
      "load_format": "dummy",
      "dataset_path": "/github/home/.cache/datasets/ShareGPT_V3_unfiltered_cleaned_split.json",
      "num_prompts": 200,
      "backend": "vllm"
    }
  }
]