{
  "run_id": "20260831T132015Z",
  "created_at": "2026-08-31T13:20:15.702115+00:00",
  "host": {
    "platform": "macOS-15.6-arm64-arm-64bit",
    "machine": "arm64",
    "python": "3.12.8"
  },
  "arguments": {
    "output_dir": "/Users/christianmeyer/Documents/git/lai_automatisierung/benchmarks/inference/results",
    "runtime": "vllm",
    "ollama_url": "http://127.0.0.1:11434",
    "ollama_model": "qwen3.8:27b-mlx",
    "vllm_url": "http://127.0.0.1:8001",
    "vllm_model": "qwen3.8-27b-mxfp8",
    "warmups": 2,
    "rounds": 5,
    "concurrency": [
      1,
      4
    ],
    "max_tokens": 128,
    "seed": 42,
    "timeout": 600
  },
  "runtimes": [
    {
      "name": "vllm-metal",
      "kind": "openai",
      "base_url": "http://127.0.0.1:8001",
      "model": "qwen3.8-27b-mxfp8"
    }
  ],
  "versions": {
    "ollama": "ollama version is 0.32.14",
    "vllm": "INFO 08-31 15:20:16 [__init__.py:52] Available plugins for group vllm.platform_plugins:\nINFO 08-31 15:20:16 [__init__.py:54] - metal -> vllm_metal:register\nINFO 08-31 15:20:16 [__init__.py:57] All plugins in this group will be loaded. Set `VLLM_PLUGINS` to control which plugins to load.\nINFO 08-31 15:20:18 [__init__.py:254] Platform plugin metal is activated\nINFO 08-31 15:20:19 [importing.py:88] Triton not installed or not compatible; certain GPU-related functions will not be available.\n0.28.0+cpu"
  },
  "model_metadata": {
    "vllm-metal": {
      "object": "list",
      "data": [
        {
          "id": "qwen3.8-27b-mxfp8",
          "object": "model",
          "created": 1788182421,
          "owned_by": "vllm",
          "root": "mlx-community/Qwen3.8-27B-mxfp8",
          "parent": null,
          "max_model_len": 8192,
          "permission": [
            {
              "id": "modelperm-a3c90f9b6d588379",
              "object": "model_permission",
              "created": 1788182421,
              "allow_create_engine": false,
              "allow_sampling": true,
              "allow_logprobs": true,
              "allow_search_indices": false,
              "allow_view": true,
              "allow_fine_tuning": false,
              "organization": "*",
              "group": null,
              "is_blocking": false
            }
          ]
        }
      ]
    }
  },
  "prompts": {
    "short": "In exactly four concise bullet points, explain why database transactions are useful. Do not use a heading.",
    "medium": "You are reviewing a Laravel service that transfers money between two accounts. Explain the failure modes involving concurrency, partial writes, retries, and audit logs. Then provide a robust implementation plan. Keep the response technical and concise.",
    "code": "Write a Python 3.12 function named merge_intervals that accepts a list of integer pairs, validates each pair, merges overlapping or adjacent intervals, and returns sorted tuples. Include type hints, a short docstring, and five assert-based examples. Output only code."
  },
  "measurement_notes": {
    "ttft": "Client wall time from request start until first non-empty generated text chunk.",
    "total": "Client wall time from request start until stream completion.",
    "decode_tps": "Ollama server eval metric; otherwise output tokens / (total - TTFT).",
    "aggregate_output_tps": "Sum of successful output tokens / concurrent group wall time."
  },
  "completed_at": "2026-08-31T13:22:48.218681+00:00",
  "summary": [
    {
      "runtime": "vllm-metal",
      "model": "qwen3.8-27b-mxfp8",
      "concurrency": 1,
      "requests": 5,
      "successes": 5,
      "failures": 0,
      "ttft_s_mean": 0.37155269999057056,
      "ttft_s_p50": 0.4171057919738814,
      "ttft_s_p95": 0.4531440335791558,
      "total_s_mean": 7.930883799993898,
      "total_s_p50": 8.838838333962485,
      "total_s_p95": 8.998963149765041,
      "prompt_tps_mean": null,
      "prompt_tps_p50": null,
      "prompt_tps_p95": null,
      "decode_tps_mean": 15.079897408512505,
      "decode_tps_p50": 15.126147490283795,
      "decode_tps_p95": 15.196162811046243,
      "request_tps_mean": 14.380896425252896,
      "request_tps_p50": 14.386982882152838,
      "request_tps_p95": 14.53502856074605,
      "aggregate_output_tps_mean": 14.380548747737752,
      "aggregate_output_tps_p50": 14.386712701914696,
      "aggregate_output_tps_p95": 14.534638049200744
    },
    {
      "runtime": "vllm-metal",
      "model": "qwen3.8-27b-mxfp8",
      "concurrency": 4,
      "requests": 20,
      "successes": 20,
      "failures": 0,
      "ttft_s_mean": 1.255672066603438,
      "ttft_s_p50": 1.3144360205042176,
      "ttft_s_p95": 1.419064954231726,
      "total_s_mean": 12.251293779097614,
      "total_s_p50": 12.702340687508695,
      "total_s_p95": 13.641910566360457,
      "prompt_tps_mean": null,
      "prompt_tps_p50": null,
      "prompt_tps_p95": null,
      "decode_tps_mean": 10.500220268362742,
      "decode_tps_p50": 10.485677148644122,
      "decode_tps_p95": 11.071162546140778,
      "request_tps_mean": 9.417789343799708,
      "request_tps_p50": 9.430282582501674,
      "request_tps_p95": 10.077752113288362,
      "aggregate_output_tps_mean": 35.09087333775396,
      "aggregate_output_tps_p50": 34.96408475660248,
      "aggregate_output_tps_p95": 35.52678209465127
    }
  ]
}