sskj/bench_results/vllm_dspark_qwen3_20260705_121046/summary.json

{
  "model": "/data/models/Qwen3-4B",
  "draft_model": "deepseek-ai/dspark_qwen3_4b_block7",
  "url": "http://127.0.0.1:30003/v1/completions",
  "max_tokens": 64,
  "num_prompts": 20,
  "dataset": "/data/user1/yy/datasets/ShareGPT_filtered_chat.json",
  "timestamp": "20260705_121046",
  "results": [
    {
      "concurrency": 1,
      "num_prompts": 20,
      "duration_s": 0.07108968612737954,
      "success_count": 0,
      "error": "all requests failed",
      "errors": [
        "404, message='Not Found', url='http://127.0.0.1:30003/v1/completions'",
        "404, message='Not Found', url='http://127.0.0.1:30003/v1/completions'",
        "404, message='Not Found', url='http://127.0.0.1:30003/v1/completions'",
        "404, message='Not Found', url='http://127.0.0.1:30003/v1/completions'",
        "404, message='Not Found', url='http://127.0.0.1:30003/v1/completions'"
      ]
    },
    {
      "concurrency": 4,
      "num_prompts": 20,
      "duration_s": 0.036050053080543876,
      "success_count": 0,
      "error": "all requests failed",
      "errors": [
        "404, message='Not Found', url='http://127.0.0.1:30003/v1/completions'",
        "404, message='Not Found', url='http://127.0.0.1:30003/v1/completions'",
        "404, message='Not Found', url='http://127.0.0.1:30003/v1/completions'",
        "404, message='Not Found', url='http://127.0.0.1:30003/v1/completions'",
        "404, message='Not Found', url='http://127.0.0.1:30003/v1/completions'"
      ]
    }
  ]
}