{
  "schema_version": 1,
  "run_id": "20260913-210946-683068",
  "maximize": "output_tokens_per_second",
  "execution_mode": "sequential",
  "status": "completed",
  "started_at": "2026-09-13T21:09:46.683089+00:00",
  "completed_at": "2026-09-13T21:11:18.903066+00:00",
  "duration_seconds": 92.219977,
  "trial_counts": {
    "completed": 2,
    "failed": 0,
    "interrupted": 0
  },
  "trials": [
    {
      "trial_id": "baseline",
      "status": "completed",
      "failure": null,
      "benchmark_count": 3,
      "metrics": {
        "requests_per_second": {
          "average": 28.923395356110422
        },
        "throughput_tokens_per_second": {
          "average": 925.5486513955335
        },
        "total_tokens_per_second": {
          "average": 2776.6459541866006
        },
        "ttft_ms": {
          "average": 35.808426041512575,
          "median": 25.93690716579052,
          "p95": 52.2984717511766,
          "p99": 52.47034154648039
        },
        "tpot_ms": {
          "average": 7.744854491946132,
          "median": 7.773433962410632,
          "p95": 10.802795360187476,
          "p99": 11.281436895699708
        },
        "itl_ms": {
          "average": 7.969812262795627,
          "median": 5.149294000148075,
          "p99": 22.789890826752526
        },
        "end_to_end_ms": {
          "average": 275.8989152918427,
          "median": 275.93970116625616,
          "p95": 381.13183524971345,
          "p99": 381.32714145018934
        },
        "total_time_seconds": {
          "average": 0.5532015620022624
        }
      },
      "benchmarks": [
        {
          "name": "short-chat",
          "backend": "vllm",
          "backend_version": "0.28.0",
          "raw_artifact": "/var/tmp/vllm-optimizer-demo/public/baseline-control/20260913-210946-683068/trials/baseline/attempts/001/repeats/001/short-chat/results.json",
          "repeat": 1,
          "elapsed_seconds": 6.6211034309963,
          "successful_requests": 16,
          "failed_requests": 0,
          "errored_requests": 0,
          "incomplete_requests": 0,
          "total_requests": 16,
          "failure_percentage": 0.0,
          "workloads": [
            {
              "index": 0,
              "configuration": {
                "backend": "vllm",
                "model_id": "/var/tmp/vllm-optimizer-demo/models/opt-125m",
                "num_prompts": 16,
                "request_rate": "inf",
                "burstiness": 1.0,
                "max_concurrency": 8
              },
              "metrics": {
                "date": "20260914-001015",
                "endpoint_type": "vllm",
                "backend": "vllm",
                "label": null,
                "model_id": "/var/tmp/vllm-optimizer-demo/models/opt-125m",
                "tokenizer_id": "/var/tmp/vllm-optimizer-demo/models/opt-125m",
                "num_prompts": 16,
                "request_rate": "inf",
                "burstiness": 1.0,
                "max_concurrency": 8,
                "duration": 0.5568704510005773,
                "completed": 16,
                "failed": 0,
                "total_input_tokens": 1024,
                "total_output_tokens": 512,
                "request_throughput": 28.731996770975037,
                "request_goodput": null,
                "output_throughput": 919.4238966712012,
                "total_token_throughput": "<redacted>",
                "ttfts": [
                  0.027390028000809252,
                  0.052197485994838644,
                  0.051786725998681504,
                  0.05180259900225792,
                  0.05179955500352662,
                  0.05132502799824579,
                  0.05124900900409557,
                  0.05118700999446446,
                  0.023685018997639418,
                  0.017565855996508617,
                  0.023381894003250636,
                  0.023378498997772112,
                  0.02286308899783762,
                  0.022546439002326224,
                  0.022504008004034404,
                  0.022462788998382166
                ],
                "max_output_tokens_per_s": 498.0,
                "max_concurrent_requests": 16,
                "rtfx": 0.0,
                "mean_ttft_ms": 35.445314624666935,
                "median_ttft_ms": 25.537523499224335,
                "std_ttft_ms": 14.376934877886665,
                "p50_ttft_ms": 25.537523499224335,
                "p95_ttft_ms": 51.9013207504031,
                "p99_ttft_ms": 52.138252945951535,
                "mean_tpot_ms": 7.816520802422136,
                "median_tpot_ms": 7.843694241948411,
                "std_tpot_ms": 3.0229491101809094,
                "p50_tpot_ms": 7.843694241948411,
                "p95_tpot_ms": 10.935117975790373,
                "p99_tpot_ms": 11.418450975777946,
                "mean_itl_ms": 8.043560060169847,
                "median_itl_ms": 5.212225001741899,
                "std_itl_ms": 5.741247223539477,
                "p50_itl_ms": 5.212225001741899,
                "p95_itl_ms": 20.642403695092042,
                "p99_itl_ms": 21.952506191737484,
                "mean_e2el_ms": 277.75745949975317,
                "median_e2el_ms": 277.83887300029164,
                "std_e2el_ms": 106.66682276035688,
                "p50_e2el_ms": 277.83887300029164,
                "p95_e2el_ms": 384.9628047464648,
                "p99_e2el_ms": 385.07883214915637,
                "requests_per_second": {
                  "average": 28.731996770975037
                },
                "output_tokens_per_second": {
                  "average": 919.4238966712012
                },
                "total_tokens_per_second": {
                  "average": 2758.271690013604
                },
                "time_to_first_token_ms": "<redacted>",
                "time_per_output_token_ms": "<redacted>",
                "inter_token_latency_ms": "<redacted>",
                "end_to_end_latency_ms": {
                  "average": 277.75745949975317,
                  "median": 277.83887300029164,
                  "p99": 385.07883214915637
                },
                "request_totals": {
                  "successful": 16,
                  "errored": 0,
                  "incomplete": 0
                },
                "request_total": 16,
                "requests": {
                  "input": [
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64
                  ],
                  "output": [
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32
                  ],
                  "error_msg": {}
                }
              },
              "successful_requests": 16,
              "failed_requests": 0,
              "errored_requests": 0,
              "incomplete_requests": 0,
              "total_requests": 16,
              "failure_percentage": 0.0
            }
          ]
        },
        {
          "name": "short-chat",
          "backend": "vllm",
          "backend_version": "0.28.0",
          "raw_artifact": "/var/tmp/vllm-optimizer-demo/public/baseline-control/20260913-210946-683068/trials/baseline/attempts/001/repeats/002/short-chat/results.json",
          "repeat": 2,
          "elapsed_seconds": 6.634794607001822,
          "successful_requests": 16,
          "failed_requests": 0,
          "errored_requests": 0,
          "incomplete_requests": 0,
          "total_requests": 16,
          "failure_percentage": 0.0,
          "workloads": [
            {
              "index": 0,
              "configuration": {
                "backend": "vllm",
                "model_id": "/var/tmp/vllm-optimizer-demo/models/opt-125m",
                "num_prompts": 16,
                "request_rate": "inf",
                "burstiness": 1.0,
                "max_concurrency": 8
              },
              "metrics": {
                "date": "20260914-001021",
                "endpoint_type": "vllm",
                "backend": "vllm",
                "label": null,
                "model_id": "/var/tmp/vllm-optimizer-demo/models/opt-125m",
                "tokenizer_id": "/var/tmp/vllm-optimizer-demo/models/opt-125m",
                "num_prompts": 16,
                "request_rate": "inf",
                "burstiness": 1.0,
                "max_concurrency": 8,
                "duration": 0.5495458990044426,
                "completed": 16,
                "failed": 0,
                "total_input_tokens": 1024,
                "total_output_tokens": 512,
                "request_throughput": 29.11494750299402,
                "request_goodput": null,
                "output_throughput": 931.6783200958087,
                "total_token_throughput": "<redacted>",
                "ttfts": [
                  0.028065067999705207,
                  0.05394198099384084,
                  0.05361263800296001,
                  0.05350894799630623,
                  0.053490347003389616,
                  0.052931407997675706,
                  0.05289208600152051,
                  0.05281375200138427,
                  0.02378148699790472,
                  0.017953021000721492,
                  0.02343496599496575,
                  0.02285615599976154,
                  0.02283722500578733,
                  0.02279422900028294,
                  0.022567385996808298,
                  0.022093879997555632
                ],
                "max_output_tokens_per_s": 498.0,
                "max_concurrent_requests": 16,
                "rtfx": 0.0,
                "mean_ttft_ms": 36.22341112441063,
                "median_ttft_ms": 25.923277498804964,
                "std_ttft_ms": 15.183399028614506,
                "p50_ttft_ms": 25.923277498804964,
                "p95_ttft_ms": 53.69497375068022,
                "p99_ttft_ms": 53.89257954520872,
                "mean_tpot_ms": 7.6712394758003715,
                "median_tpot_ms": 7.694385887119889,
                "std_tpot_ms": 3.0112599328328096,
                "p50_tpot_ms": 7.694385887119889,
                "p95_tpot_ms": 10.779751007982169,
                "p99_tpot_ms": 11.274841298337934,
                "mean_itl_ms": 7.894058360980728,
                "median_itl_ms": 4.912910000712145,
                "std_itl_ms": 5.861273226742792,
                "p50_itl_ms": 4.912910000712145,
                "p95_itl_ms": 20.29182394981033,
                "p99_itl_ms": 23.307157570307027,
                "mean_e2el_ms": 274.0318348742221,
                "median_e2el_ms": 274.1764454985969,
                "std_e2el_ms": 107.08313900691736,
                "p50_e2el_ms": 274.1764454985969,
                "p95_e2el_ms": 381.49258849807666,
                "p99_e2el_ms": 381.66176569720847,
                "requests_per_second": {
                  "average": 29.11494750299402
                },
                "output_tokens_per_second": {
                  "average": 931.6783200958087
                },
                "total_tokens_per_second": {
                  "average": 2795.0349602874257
                },
                "time_to_first_token_ms": "<redacted>",
                "time_per_output_token_ms": "<redacted>",
                "inter_token_latency_ms": "<redacted>",
                "end_to_end_latency_ms": {
                  "average": 274.0318348742221,
                  "median": 274.1764454985969,
                  "p99": 381.66176569720847
                },
                "request_totals": {
                  "successful": 16,
                  "errored": 0,
                  "incomplete": 0
                },
                "request_total": 16,
                "requests": {
                  "input": [
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64
                  ],
                  "output": [
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32
                  ],
                  "error_msg": {}
                }
              },
              "successful_requests": 16,
              "failed_requests": 0,
              "errored_requests": 0,
              "incomplete_requests": 0,
              "total_requests": 16,
              "failure_percentage": 0.0
            }
          ]
        },
        {
          "name": "short-chat",
          "backend": "vllm",
          "backend_version": "0.28.0",
          "raw_artifact": "/var/tmp/vllm-optimizer-demo/public/baseline-control/20260913-210946-683068/trials/baseline/attempts/001/repeats/003/short-chat/results.json",
          "repeat": 3,
          "elapsed_seconds": 6.5985015600017505,
          "successful_requests": 16,
          "failed_requests": 0,
          "errored_requests": 0,
          "incomplete_requests": 0,
          "total_requests": 16,
          "failure_percentage": 0.0,
          "workloads": [
            {
              "index": 0,
              "configuration": {
                "backend": "vllm",
                "model_id": "/var/tmp/vllm-optimizer-demo/models/opt-125m",
                "num_prompts": 16,
                "request_rate": "inf",
                "burstiness": 1.0,
                "max_concurrency": 8
              },
              "metrics": {
                "date": "20260914-001028",
                "endpoint_type": "vllm",
                "backend": "vllm",
                "label": null,
                "model_id": "/var/tmp/vllm-optimizer-demo/models/opt-125m",
                "tokenizer_id": "/var/tmp/vllm-optimizer-demo/models/opt-125m",
                "num_prompts": 16,
                "request_rate": "inf",
                "burstiness": 1.0,
                "max_concurrency": 8,
                "duration": 0.5531883360017673,
                "completed": 16,
                "failed": 0,
                "total_input_tokens": 1024,
                "total_output_tokens": 512,
                "request_throughput": 28.92324179436221,
                "request_goodput": null,
                "output_throughput": 925.5437374195907,
                "total_token_throughput": "<redacted>",
                "ttfts": [
                  0.028088799001125153,
                  0.05140045999723952,
                  0.05126534100418212,
                  0.051071800000499934,
                  0.05112475399801042,
                  0.05063521500414936,
                  0.050631443002203014,
                  0.05025333400408272,
                  0.02461104199755937,
                  0.018343661999097094,
                  0.024472422002872918,
                  0.02450507799949264,
                  0.02393332299834583,
                  0.023918619997857604,
                  0.023928807000629604,
                  0.023920738000015263
                ],
                "max_output_tokens_per_s": 498.0,
                "max_concurrent_requests": 16,
                "rtfx": 0.0,
                "mean_ttft_ms": 35.75655237546016,
                "median_ttft_ms": 26.34992049934226,
                "std_ttft_ms": 13.48343145010384,
                "p50_ttft_ms": 26.34992049934226,
                "p95_ttft_ms": 51.29912075244647,
                "p99_ttft_ms": 51.38019214828091,
                "mean_tpot_ms": 7.746803197615889,
                "median_tpot_ms": 7.782221758163595,
                "std_tpot_ms": 2.8557270133423724,
                "p50_tpot_ms": 7.782221758163595,
                "p95_tpot_ms": 10.693517096789888,
                "p99_tpot_ms": 11.151018412983243,
                "mean_itl_ms": 7.971818367236306,
                "median_itl_ms": 5.32274699799018,
                "std_itl_ms": 5.596056037418811,
                "p50_itl_ms": 5.32274699799018,
                "p95_itl_ms": 20.30544309855029,
                "p99_itl_ms": 23.110008718213066,
                "mean_e2el_ms": 275.9074515015527,
                "median_e2el_ms": 275.80378499988,
                "std_e2el_ms": 100.64567682264229,
                "p50_e2el_ms": 275.80378499988,
                "p95_e2el_ms": 376.9401125045988,
                "p99_e2el_ms": 377.24082650420314,
                "requests_per_second": {
                  "average": 28.92324179436221
                },
                "output_tokens_per_second": {
                  "average": 925.5437374195907
                },
                "total_tokens_per_second": {
                  "average": 2776.631212258772
                },
                "time_to_first_token_ms": "<redacted>",
                "time_per_output_token_ms": "<redacted>",
                "inter_token_latency_ms": "<redacted>",
                "end_to_end_latency_ms": {
                  "average": 275.9074515015527,
                  "median": 275.80378499988,
                  "p99": 377.24082650420314
                },
                "request_totals": {
                  "successful": 16,
                  "errored": 0,
                  "incomplete": 0
                },
                "request_total": 16,
                "requests": {
                  "input": [
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64
                  ],
                  "output": [
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32
                  ],
                  "error_msg": {}
                }
              },
              "successful_requests": 16,
              "failed_requests": 0,
              "errored_requests": 0,
              "incomplete_requests": 0,
              "total_requests": 16,
              "failure_percentage": 0.0
            }
          ]
        }
      ],
      "execution": {
        "mode": "sequential"
      }
    },
    {
      "trial_id": "trial-0001",
      "status": "completed",
      "failure": null,
      "benchmark_count": 3,
      "metrics": {
        "requests_per_second": {
          "average": 6.262013313332677
        },
        "throughput_tokens_per_second": {
          "average": 200.38442602664566
        },
        "total_tokens_per_second": {
          "average": 601.153278079937
        },
        "ttft_ms": {
          "average": 868.5719193122168,
          "median": 1039.750525999504,
          "p95": 1118.800431334724,
          "p99": 1195.3448633333512
        },
        "tpot_ms": {
          "average": 4.78174070364427,
          "median": 4.408322854883848,
          "p95": 6.24165098119564,
          "p99": 8.403537155410508
        },
        "itl_ms": {
          "average": 4.9378103127001856,
          "median": 4.512766000213257,
          "p99": 15.2399305535558
        },
        "end_to_end_ms": {
          "average": 1016.8058811251891,
          "median": 1180.861684000168,
          "p95": 1254.1504255010902,
          "p99": 1331.852199501979
        },
        "total_time_seconds": {
          "average": 2.5604960370013337
        }
      },
      "benchmarks": [
        {
          "name": "short-chat",
          "backend": "vllm",
          "backend_version": "0.28.0",
          "raw_artifact": "/var/tmp/vllm-optimizer-demo/public/baseline-control/20260913-210946-683068/trials/trial-0001/attempts/001/repeats/001/short-chat/results.json",
          "repeat": 1,
          "elapsed_seconds": 8.37268743399909,
          "successful_requests": 16,
          "failed_requests": 0,
          "errored_requests": 0,
          "incomplete_requests": 0,
          "total_requests": 16,
          "failure_percentage": 0.0,
          "workloads": [
            {
              "index": 0,
              "configuration": {
                "backend": "vllm",
                "model_id": "/var/tmp/vllm-optimizer-demo/models/opt-125m",
                "num_prompts": 16,
                "request_rate": "inf",
                "burstiness": 1.0,
                "max_concurrency": 8
              },
              "metrics": {
                "date": "20260914-001101",
                "endpoint_type": "vllm",
                "backend": "vllm",
                "label": null,
                "model_id": "/var/tmp/vllm-optimizer-demo/models/opt-125m",
                "tokenizer_id": "/var/tmp/vllm-optimizer-demo/models/opt-125m",
                "num_prompts": 16,
                "request_rate": "inf",
                "burstiness": 1.0,
                "max_concurrency": 8,
                "duration": 2.4869544280008995,
                "completed": 16,
                "failed": 0,
                "total_input_tokens": 1024,
                "total_output_tokens": 512,
                "request_throughput": 6.433571849911764,
                "request_goodput": null,
                "output_throughput": 205.87429919717644,
                "total_token_throughput": "<redacted>",
                "ttfts": [
                  0.025231797000742517,
                  0.2852520300002652,
                  0.43206471799931023,
                  0.5842921779985772,
                  0.7439827830021386,
                  0.8861063029980869,
                  1.0314784820002387,
                  1.1794528050013469,
                  1.054604721000942,
                  1.0508805669960566,
                  1.0448919800037402,
                  1.0369755889987573,
                  1.0383470980013954,
                  1.041974866995588,
                  1.0434260529946187,
                  1.0364189360043383
                ],
                "max_output_tokens_per_s": 211.0,
                "max_concurrent_requests": 13,
                "rtfx": 0.0,
                "mean_ttft_ms": 844.7113066872589,
                "median_ttft_ms": 1036.6972625015478,
                "std_ttft_ms": 325.7372667708726,
                "p50_ttft_ms": 1036.6972625015478,
                "p95_ttft_ms": 1085.8167420010432,
                "p99_ttft_ms": 1160.7255924012861,
                "mean_tpot_ms": 4.64734799395721,
                "median_tpot_ms": 4.4128143549202035,
                "std_tpot_ms": 0.8932748656185375,
                "p50_tpot_ms": 4.4128143549202035,
                "p95_tpot_ms": 5.615733750023685,
                "p99_tpot_ms": 7.575070233912312,
                "mean_itl_ms": 4.792281725544825,
                "median_itl_ms": 4.464744997676462,
                "std_itl_ms": 1.791302287169032,
                "p50_itl_ms": 4.464744997676462,
                "p95_itl_ms": 5.91104799968889,
                "p99_itl_ms": 15.239301000838166,
                "mean_e2el_ms": 988.7790944999324,
                "median_e2el_ms": 1170.17078400022,
                "std_e2el_ms": 307.3709691693757,
                "p50_e2el_ms": 1170.17078400022,
                "p95_e2el_ms": 1220.3382165007497,
                "p99_e2el_ms": 1299.0667041009144,
                "requests_per_second": {
                  "average": 6.433571849911764
                },
                "output_tokens_per_second": {
                  "average": 205.87429919717644
                },
                "total_tokens_per_second": {
                  "average": 617.6228975915293
                },
                "time_to_first_token_ms": "<redacted>",
                "time_per_output_token_ms": "<redacted>",
                "inter_token_latency_ms": "<redacted>",
                "end_to_end_latency_ms": {
                  "average": 988.7790944999324,
                  "median": 1170.17078400022,
                  "p99": 1299.0667041009144
                },
                "request_totals": {
                  "successful": 16,
                  "errored": 0,
                  "incomplete": 0
                },
                "request_total": 16,
                "requests": {
                  "input": [
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64
                  ],
                  "output": [
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32
                  ],
                  "error_msg": {}
                }
              },
              "successful_requests": 16,
              "failed_requests": 0,
              "errored_requests": 0,
              "incomplete_requests": 0,
              "total_requests": 16,
              "failure_percentage": 0.0
            }
          ]
        },
        {
          "name": "short-chat",
          "backend": "vllm",
          "backend_version": "0.28.0",
          "raw_artifact": "/var/tmp/vllm-optimizer-demo/public/baseline-control/20260913-210946-683068/trials/trial-0001/attempts/001/repeats/002/short-chat/results.json",
          "repeat": 2,
          "elapsed_seconds": 8.683645363002142,
          "successful_requests": 16,
          "failed_requests": 0,
          "errored_requests": 0,
          "incomplete_requests": 0,
          "total_requests": 16,
          "failure_percentage": 0.0,
          "workloads": [
            {
              "index": 0,
              "configuration": {
                "backend": "vllm",
                "model_id": "/var/tmp/vllm-optimizer-demo/models/opt-125m",
                "num_prompts": 16,
                "request_rate": "inf",
                "burstiness": 1.0,
                "max_concurrency": 8
              },
              "metrics": {
                "date": "20260914-001109",
                "endpoint_type": "vllm",
                "backend": "vllm",
                "label": null,
                "model_id": "/var/tmp/vllm-optimizer-demo/models/opt-125m",
                "tokenizer_id": "/var/tmp/vllm-optimizer-demo/models/opt-125m",
                "num_prompts": 16,
                "request_rate": "inf",
                "burstiness": 1.0,
                "max_concurrency": 8,
                "duration": 2.7290979890021845,
                "completed": 16,
                "failed": 0,
                "total_input_tokens": 1024,
                "total_output_tokens": 512,
                "request_throughput": 5.862742951875442,
                "request_goodput": null,
                "output_throughput": 187.60777446001416,
                "total_token_throughput": "<redacted>",
                "ttfts": [
                  0.029022063994489145,
                  0.368944341003953,
                  0.5336852059990633,
                  0.6980273760054843,
                  0.8487287270036177,
                  0.9976122059961199,
                  1.1448938110042945,
                  1.2886425090036937,
                  1.0797745699965162,
                  1.0644910979972337,
                  1.055728701998305,
                  1.0519022369990125,
                  1.1245925199982594,
                  1.167566356001771,
                  1.1626358499997878,
                  1.1670223960027215
                ],
                "max_output_tokens_per_s": 201.0,
                "max_concurrent_requests": 13,
                "rtfx": 0.0,
                "mean_ttft_ms": 923.9543730627702,
                "median_ttft_ms": 1060.1098999977694,
                "std_ttft_ms": 335.2804852002237,
                "p50_ttft_ms": 1060.1098999977694,
                "p95_ttft_ms": 1197.8353942522517,
                "p99_ttft_ms": 1270.4810860534053,
                "mean_tpot_ms": 5.1072168528281185,
                "median_tpot_ms": 4.47684332257561,
                "std_tpot_ms": 1.5371002345284,
                "p50_tpot_ms": 4.47684332257561,
                "p95_tpot_ms": 7.653173596824467,
                "p99_tpot_ms": 9.989521145231969,
                "mean_itl_ms": 5.2774638187808405,
                "median_itl_ms": 4.631096999219153,
                "std_itl_ms": 4.900567988974282,
                "p50_itl_ms": 4.631096999219153,
                "p95_itl_ms": 7.124159847808186,
                "p99_itl_ms": 15.161198868227075,
                "mean_e2el_ms": 1082.2780955004419,
                "median_e2el_ms": 1215.7386344988481,
                "std_e2el_ms": 305.81978883766527,
                "p50_e2el_ms": 1215.7386344988481,
                "p95_e2el_ms": 1333.8289702496695,
                "p99_e2el_ms": 1405.9156804545637,
                "requests_per_second": {
                  "average": 5.862742951875442
                },
                "output_tokens_per_second": {
                  "average": 187.60777446001416
                },
                "total_tokens_per_second": {
                  "average": 562.8233233800424
                },
                "time_to_first_token_ms": "<redacted>",
                "time_per_output_token_ms": "<redacted>",
                "inter_token_latency_ms": "<redacted>",
                "end_to_end_latency_ms": {
                  "average": 1082.2780955004419,
                  "median": 1215.7386344988481,
                  "p99": 1405.9156804545637
                },
                "request_totals": {
                  "successful": 16,
                  "errored": 0,
                  "incomplete": 0
                },
                "request_total": 16,
                "requests": {
                  "input": [
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64
                  ],
                  "output": [
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32
                  ],
                  "error_msg": {}
                }
              },
              "successful_requests": 16,
              "failed_requests": 0,
              "errored_requests": 0,
              "incomplete_requests": 0,
              "total_requests": 16,
              "failure_percentage": 0.0
            }
          ]
        },
        {
          "name": "short-chat",
          "backend": "vllm",
          "backend_version": "0.28.0",
          "raw_artifact": "/var/tmp/vllm-optimizer-demo/public/baseline-control/20260913-210946-683068/trials/trial-0001/attempts/001/repeats/003/short-chat/results.json",
          "repeat": 3,
          "elapsed_seconds": 8.408828316001745,
          "successful_requests": 16,
          "failed_requests": 0,
          "errored_requests": 0,
          "incomplete_requests": 0,
          "total_requests": 16,
          "failure_percentage": 0.0,
          "workloads": [
            {
              "index": 0,
              "configuration": {
                "backend": "vllm",
                "model_id": "/var/tmp/vllm-optimizer-demo/models/opt-125m",
                "num_prompts": 16,
                "request_rate": "inf",
                "burstiness": 1.0,
                "max_concurrency": 8
              },
              "metrics": {
                "date": "20260914-001118",
                "endpoint_type": "vllm",
                "backend": "vllm",
                "label": null,
                "model_id": "/var/tmp/vllm-optimizer-demo/models/opt-125m",
                "tokenizer_id": "/var/tmp/vllm-optimizer-demo/models/opt-125m",
                "num_prompts": 16,
                "request_rate": "inf",
                "burstiness": 1.0,
                "max_concurrency": 8,
                "duration": 2.4654356940009166,
                "completed": 16,
                "failed": 0,
                "total_input_tokens": 1024,
                "total_output_tokens": 512,
                "request_throughput": 6.489725138210825,
                "request_goodput": null,
                "output_throughput": 207.6712044227464,
                "total_token_throughput": "<redacted>",
                "ttfts": [
                  0.030523202003678307,
                  0.2954079150003963,
                  0.4415855539991753,
                  0.588207856999361,
                  0.7314118879949092,
                  0.873938390002877,
                  1.0248617409961298,
                  1.1753475999939837,
                  1.038549677003175,
                  1.036741397001606,
                  1.0322472370025935,
                  1.0308321389966295,
                  1.0319554329980747,
                  1.0245435350007028,
                  1.0203452959976858,
                  1.0163023899949621
                ],
                "max_output_tokens_per_s": 214.0,
                "max_concurrent_requests": 13,
                "rtfx": 0.0,
                "mean_ttft_ms": 837.0500781866212,
                "median_ttft_ms": 1022.4444154991943,
                "std_ttft_ms": 318.1408527960537,
                "p50_ttft_ms": 1022.4444154991943,
                "p95_ttft_ms": 1072.7491577508772,
                "p99_ttft_ms": 1154.8279115453624,
                "mean_tpot_ms": 4.590657264147481,
                "median_tpot_ms": 4.335310887155731,
                "std_tpot_ms": 0.9334812561006373,
                "p50_tpot_ms": 4.335310887155731,
                "p95_tpot_ms": 5.456045596738771,
                "p99_tpot_ms": 7.646020087087243,
                "mean_itl_ms": 4.743685393774891,
                "median_itl_ms": 4.442456003744155,
                "std_itl_ms": 1.7213657403808786,
                "p50_itl_ms": 4.442456003744155,
                "p95_itl_ms": 5.589907550165662,
                "p99_itl_ms": 15.319291791602154,
                "mean_e2el_ms": 979.3604533751932,
                "median_e2el_ms": 1156.675633501436,
                "std_e2el_ms": 299.95692985065455,
                "p50_e2el_ms": 1156.675633501436,
                "p95_e2el_ms": 1208.2840897528513,
                "p99_e2el_ms": 1290.5742139504582,
                "requests_per_second": {
                  "average": 6.489725138210825
                },
                "output_tokens_per_second": {
                  "average": 207.6712044227464
                },
                "total_tokens_per_second": {
                  "average": 623.0136132682392
                },
                "time_to_first_token_ms": "<redacted>",
                "time_per_output_token_ms": "<redacted>",
                "inter_token_latency_ms": "<redacted>",
                "end_to_end_latency_ms": {
                  "average": 979.3604533751932,
                  "median": 1156.675633501436,
                  "p99": 1290.5742139504582
                },
                "request_totals": {
                  "successful": 16,
                  "errored": 0,
                  "incomplete": 0
                },
                "request_total": 16,
                "requests": {
                  "input": [
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64,
                    64
                  ],
                  "output": [
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32,
                    32
                  ],
                  "error_msg": {}
                }
              },
              "successful_requests": 16,
              "failed_requests": 0,
              "errored_requests": 0,
              "incomplete_requests": 0,
              "total_requests": 16,
              "failure_percentage": 0.0
            }
          ]
        }
      ],
      "execution": {
        "mode": "sequential"
      }
    }
  ],
  "ranking": [
    {
      "trial_id": "trial-0001",
      "score": 205.87429919717644,
      "successful_requests": 48,
      "errored_requests": 0,
      "incomplete_requests": 0,
      "excluded_workloads": 0,
      "error_rate": 0.0,
      "server_args": {
        "host": "127.0.0.1",
        "port": 8766,
        "dtype": "float16",
        "seed": 42,
        "tensor-parallel-size": 1,
        "gpu-memory-utilization": 0.4,
        "max-model-len": 512,
        "enforce-eager": true,
        "enable-chunked-prefill": true,
        "max-num-seqs": 1,
        "max-num-batched-tokens": 512
      },
      "server_env": {
        "CUDA_VISIBLE_DEVICES": "0",
        "VLLM_USE_V2_MODEL_RUNNER": "0",
        "VLLM_USE_FLASHINFER_SAMPLER": "0"
      }
    }
  ],
  "best": {
    "trial_id": "trial-0001",
    "score": 205.87429919717644,
    "successful_requests": 48,
    "errored_requests": 0,
    "incomplete_requests": 0,
    "excluded_workloads": 0,
    "error_rate": 0.0,
    "server_args": {
      "host": "127.0.0.1",
      "port": 8766,
      "dtype": "float16",
      "seed": 42,
      "tensor-parallel-size": 1,
      "gpu-memory-utilization": 0.4,
      "max-model-len": 512,
      "enforce-eager": true,
      "enable-chunked-prefill": true,
      "max-num-seqs": 1,
      "max-num-batched-tokens": 512
    },
    "server_env": {
      "CUDA_VISIBLE_DEVICES": "0",
      "VLLM_USE_V2_MODEL_RUNNER": "0",
      "VLLM_USE_FLASHINFER_SAMPLER": "0"
    }
  },
  "baseline": {
    "trial_id": "baseline",
    "score": 925.5437374195907,
    "successful_requests": 48,
    "errored_requests": 0,
    "incomplete_requests": 0,
    "excluded_workloads": 0,
    "error_rate": 0.0,
    "server_args": {
      "host": "127.0.0.1",
      "port": 8766,
      "dtype": "float16",
      "seed": 42,
      "tensor-parallel-size": 1,
      "gpu-memory-utilization": 0.4,
      "max-model-len": 512,
      "enforce-eager": true,
      "enable-chunked-prefill": true,
      "max-num-seqs": 16,
      "max-num-batched-tokens": 512
    },
    "server_env": {
      "CUDA_VISIBLE_DEVICES": "0",
      "VLLM_USE_V2_MODEL_RUNNER": "0",
      "VLLM_USE_FLASHINFER_SAMPLER": "0"
    }
  },
  "improvement_percent": -77.75639433624687,
  "best_by_benchmark": {
    "short-chat": {
      "trial_id": "trial-0001",
      "score": 205.87429919717644,
      "successful_requests": 48,
      "errored_requests": 0,
      "incomplete_requests": 0,
      "excluded_workloads": 0,
      "error_rate": 0.0,
      "server_args": {
        "host": "127.0.0.1",
        "port": 8766,
        "dtype": "float16",
        "seed": 42,
        "tensor-parallel-size": 1,
        "gpu-memory-utilization": 0.4,
        "max-model-len": 512,
        "enforce-eager": true,
        "enable-chunked-prefill": true,
        "max-num-seqs": 1,
        "max-num-batched-tokens": 512
      },
      "server_env": {
        "CUDA_VISIBLE_DEVICES": "0",
        "VLLM_USE_V2_MODEL_RUNNER": "0",
        "VLLM_USE_FLASHINFER_SAMPLER": "0"
      }
    }
  },
  "benchmark_order": [
    "short-chat"
  ],
  "benchmark_policy": {
    "repeats": 3,
    "minimum_repeats": 3,
    "warmup_repeats": 1,
    "drift_threshold": 0.05,
    "maximum_failure_percentage": 0.0
  }
}