{ "mode": "gpu", "reps": 8, "by_length": { "1024": { "n": 8, "ttft_p50": 0.04180275100225117, "ttft_mean": 0.05689269150025211, "ttft_min": 0.041313502995762974, "ttft_max": 0.1606091230059974, "tier_observed": "gpu", "verified_frac": 1.0 }, "2048": { "n": 8, "ttft_p50": 0.044922845510882325, "ttft_mean": 0.04646045462868642, "ttft_min": 0.04261300901998766, "ttft_max": 0.06082483098725788, "tier_observed": "gpu", "verified_frac": 1.0 }, "4096": { "n": 8, "ttft_p50": 0.0462174300046172, "ttft_mean": 0.04691218675361597, "ttft_min": 0.044408742018276826, "ttft_max": 0.05101387499598786, "tier_observed": "gpu", "verified_frac": 1.0 }, "8192": { "n": 8, "ttft_p50": 0.052487702007056214, "ttft_mean": 0.05252782000388834, "ttft_min": 0.050384567002765834, "ttft_max": 0.055209266021847725, "tier_observed": "gpu", "verified_frac": 1.0 }, "16384": { "n": 8, "ttft_p50": 0.06340778700541705, "ttft_mean": 0.06307360512437299, "ttft_min": 0.059953891002805904, "ttft_max": 0.06587072199909016, "tier_observed": "gpu", "verified_frac": 1.0 }, "32768": { "n": 8, "ttft_p50": 0.07986902150150854, "ttft_mean": 0.08412684850554797, "ttft_min": 0.07615292401169427, "ttft_max": 0.11761908099288121, "tier_observed": "gpu", "verified_frac": 1.0 }, "65536": { "n": 8, "ttft_p50": 0.11140661900572013, "ttft_mean": 0.10751268000240088, "ttft_min": 0.07390080401091836, "ttft_max": 0.1206158839922864, "tier_observed": "gpu", "verified_frac": 1.0 } }, "raw": { "1024": [ { "ttft_s": 0.1606091230059974, "e2e_s": 0.16078226300305687, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 1008.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.043477901024743915, "e2e_s": 0.0436010490229819, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 1008.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.04137404798530042, "e2e_s": 0.04146770399529487, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 1008.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.04179324599681422, "e2e_s": 0.041887808009050786, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 1008.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.04326947100344114, "e2e_s": 0.04335355598595925, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 1008.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.04149198398226872, "e2e_s": 0.04157822398701683, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 1008.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.04181225600768812, "e2e_s": 0.04190706100780517, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 1008.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.041313502995762974, "e2e_s": 0.041313502995762974, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 1008.0, "d_ext_hits": 0.0 } ], "2048": [ { "ttft_s": 0.04491939002764411, "e2e_s": 0.045019031007541344, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 2032.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.045014784001978114, "e2e_s": 0.04511277299025096, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 2032.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.04492630099412054, "e2e_s": 0.04502850098651834, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 2032.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.04566141500254162, "e2e_s": 0.04576313399593346, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 2032.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.04261300901998766, "e2e_s": 0.04271370900096372, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 2032.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.06082483098725788, "e2e_s": 0.06096197199076414, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 2032.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.04355804901570082, "e2e_s": 0.04355804901570082, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 2032.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.044165857980260625, "e2e_s": 0.044268568977713585, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 2032.0, "d_ext_hits": 0.0 } ], "4096": [ { "ttft_s": 0.05101387499598786, "e2e_s": 0.051123478973750025, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 4080.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.044408742018276826, "e2e_s": 0.044408742018276826, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 4080.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.04538871700060554, "e2e_s": 0.045498208986828104, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 4080.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.04754545699688606, "e2e_s": 0.047664124984294176, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 4080.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.04840670898556709, "e2e_s": 0.04840670898556709, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 4080.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.0462190090038348, "e2e_s": 0.04632823000429198, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 4080.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.04609913402236998, "e2e_s": 0.046204126003431156, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 4080.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.0462158510053996, "e2e_s": 0.0462158510053996, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 4080.0, "d_ext_hits": 0.0 } ], "8192": [ { "ttft_s": 0.05042222701013088, "e2e_s": 0.05053543800022453, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 8176.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.05319672200130299, "e2e_s": 0.053308423986891285, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 8176.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.05063424099353142, "e2e_s": 0.05073276098119095, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 8176.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.050384567002765834, "e2e_s": 0.05048462699051015, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 8176.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.055105848994571716, "e2e_s": 0.055215683998540044, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 8176.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.05349100599414669, "e2e_s": 0.053595816978486255, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 8176.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.05177868201280944, "e2e_s": 0.05188246400211938, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 8176.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.055209266021847725, "e2e_s": 0.05531894601881504, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 8176.0, "d_ext_hits": 0.0 } ], "16384": [ { "ttft_s": 0.0633803239907138, "e2e_s": 0.06349112599855289, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 16368.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.06337857199832797, "e2e_s": 0.06350608498905785, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 16368.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.06098292299429886, "e2e_s": 0.061115075019188225, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 16368.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.06343525002012029, "e2e_s": 0.06355450401315466, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 16368.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.0636955969966948, "e2e_s": 0.0636955969966948, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 16368.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.06389156199293211, "e2e_s": 0.06389156199293211, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 16368.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.06587072199909016, "e2e_s": 0.06587072199909016, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 16368.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.059953891002805904, "e2e_s": 0.060058912000386044, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 16368.0, "d_ext_hits": 0.0 } ], "32768": [ { "ttft_s": 0.07615292401169427, "e2e_s": 0.07625289200223051, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 32752.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.07992992899380624, "e2e_s": 0.0800386439950671, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 32752.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.07980811400921084, "e2e_s": 0.07995001602103002, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 32752.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.11761908099288121, "e2e_s": 0.11776423300034367, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 32752.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.07834753501811065, "e2e_s": 0.07834753501811065, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 32752.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.0814115820103325, "e2e_s": 0.0814115820103325, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 32752.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.08212830501724966, "e2e_s": 0.08224253499065526, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 32752.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.07761731799109839, "e2e_s": 0.07772363899857737, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 32752.0, "d_ext_hits": 0.0 } ], "65536": [ { "ttft_s": 0.1206158839922864, "e2e_s": 0.1206158839922864, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 65520.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.10727833199780434, "e2e_s": 0.10727833199780434, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 65520.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.11010084400186315, "e2e_s": 0.11023741000099108, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 65520.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.11566799599677324, "e2e_s": 0.1157765949901659, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 65520.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.11422122400836088, "e2e_s": 0.11422122400836088, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 65520.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.07390080401091836, "e2e_s": 0.07390080401091836, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 65520.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.11271239400957711, "e2e_s": 0.11271239400957711, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 65520.0, "d_ext_hits": 0.0 }, { "ttft_s": 0.10560396200162359, "e2e_s": 0.10572021701955236, "tier_observed": "gpu", "expect": "gpu", "d_gpu_hits": 65520.0, "d_ext_hits": 0.0 } ] } }