d0rj's picture
Add T5Gemma 2 DSpark Base checkpoint and benchmarks
5405176
Raw
History Blame Contribute Delete
19.7 kB
[
{
"dataset": "math500",
"run": "baseline",
"method": "baseline",
"num_speculative_tokens": null,
"requests": 500,
"output_tokens": 63642,
"request_throughput_rps": 0.9710887696354362,
"output_throughput_tps": 123.60406295427687,
"speedup_vs_baseline": 1.0,
"latency_mean_ms": 1029.6528329752618,
"latency_p50_ms": 1011.0086214990588,
"latency_p95_ms": 1183.8821351528165,
"latency_p99_ms": 1352.1066228914415,
"ttft_mean_ms": 137.17931756953476,
"ttft_p50_ms": 125.86030399688752,
"ttft_p95_ms": 254.1806304405327,
"ttft_p99_ms": 259.12194621312665,
"itl_mean_ms": 7.065699614096616,
"itl_p50_ms": 6.948497625951028,
"itl_p95_ms": 8.149714840967464,
"itl_p99_ms": 9.294363555888458,
"tpot_mean_ms": 7.066986512325109,
"tpot_p50_ms": 6.949724716546406,
"tpot_p95_ms": 8.150898662537166,
"acceptance_rate": null,
"acceptance_pos_1": null,
"acceptance_pos_2": null,
"acceptance_pos_3": null,
"mean_acceptance_length": null
},
{
"dataset": "math500",
"run": "dspark_k3",
"method": "dspark",
"num_speculative_tokens": 3,
"requests": 500,
"output_tokens": 63731,
"request_throughput_rps": 1.1940337177445612,
"output_throughput_tps": 152.19392573115726,
"speedup_vs_baseline": 1.2313019660806477,
"latency_mean_ms": 837.3801779437345,
"latency_p50_ms": 816.9088775030104,
"latency_p95_ms": 1146.009227049944,
"latency_p99_ms": 1370.9137859771727,
"ttft_mean_ms": 119.19492300227284,
"ttft_p50_ms": 106.72050050197868,
"ttft_p95_ms": 213.44604070691275,
"ttft_p99_ms": 258.3343633514596,
"itl_mean_ms": 5.6791052364180485,
"itl_p50_ms": 5.593892366200956,
"itl_p95_ms": 8.0383705036205,
"itl_p99_ms": 9.9072340297603,
"tpot_mean_ms": 5.680338308854861,
"tpot_p50_ms": 5.595103622135508,
"tpot_p95_ms": 8.040039556758208,
"acceptance_rate": 0.4156275683926265,
"acceptance_pos_1": 0.6326171187037689,
"acceptance_pos_2": 0.3862627685804861,
"acceptance_pos_3": 0.2280028178936245,
"mean_acceptance_length": 2.2468827051778795
},
{
"dataset": "math500",
"run": "dspark_k7",
"method": "dspark",
"num_speculative_tokens": 7,
"requests": 500,
"output_tokens": 63668,
"request_throughput_rps": 1.1775733318385104,
"output_throughput_tps": 149.94747778298856,
"speedup_vs_baseline": 1.2131274182989966,
"latency_mean_ms": 849.0922174340812,
"latency_p50_ms": 839.2276294980547,
"latency_p95_ms": 1242.3280104500004,
"latency_p99_ms": 1512.9399566508073,
"ttft_mean_ms": 129.85324780782685,
"ttft_p50_ms": 118.26306749571813,
"ttft_p95_ms": 256.7381934488367,
"ttft_p99_ms": 268.83207743172534,
"itl_mean_ms": 5.692451923082981,
"itl_p50_ms": 5.603080988136545,
"itl_p95_ms": 8.775799772777777,
"itl_p99_ms": 10.470896226674313,
"tpot_mean_ms": 5.693717860424883,
"tpot_p50_ms": 5.604267641709472,
"tpot_p95_ms": 8.777032548852267,
"acceptance_rate": 0.2032188585715368,
"acceptance_pos_1": 0.6206151981210698,
"acceptance_pos_2": 0.36616410334116223,
"acceptance_pos_3": 0.20482612319115084,
"mean_acceptance_length": 2.422532010000758
},
{
"dataset": "gsm8k",
"run": "baseline",
"method": "baseline",
"num_speculative_tokens": null,
"requests": 1319,
"output_tokens": 168500,
"request_throughput_rps": 0.99646643680205,
"output_throughput_tps": 127.29688749139153,
"speedup_vs_baseline": 1.0,
"latency_mean_ms": 1003.4296112389243,
"latency_p50_ms": 979.7711369901663,
"latency_p95_ms": 1147.1265090964152,
"latency_p99_ms": 1165.5087842789362,
"ttft_mean_ms": 121.82556504392818,
"ttft_p50_ms": 98.20042399223894,
"ttft_p95_ms": 253.87967379938343,
"ttft_p99_ms": 259.2248212755658,
"itl_mean_ms": 6.953847864544167,
"itl_p50_ms": 6.954055936964903,
"itl_p95_ms": 7.2364834158344005,
"itl_p99_ms": 7.467789549431415,
"tpot_mean_ms": 6.955123454672103,
"tpot_p50_ms": 6.955686165340699,
"tpot_p95_ms": 7.237693709486319,
"acceptance_rate": null,
"acceptance_pos_1": null,
"acceptance_pos_2": null,
"acceptance_pos_3": null,
"mean_acceptance_length": null
},
{
"dataset": "gsm8k",
"run": "dspark_k3",
"method": "dspark",
"num_speculative_tokens": 3,
"requests": 1319,
"output_tokens": 168418,
"request_throughput_rps": 1.0089794437230273,
"output_throughput_tps": 128.83267623422654,
"speedup_vs_baseline": 1.0120646213202884,
"latency_mean_ms": 990.9843431904721,
"latency_p50_ms": 969.3124250043184,
"latency_p95_ms": 1346.5886881953336,
"latency_p99_ms": 1535.857625339122,
"ttft_mean_ms": 111.30873365058301,
"ttft_p50_ms": 95.77244399406482,
"ttft_p95_ms": 207.4599851010134,
"ttft_p99_ms": 258.9313290748395,
"itl_mean_ms": 6.9409634880545115,
"itl_p50_ms": 6.796889598449274,
"itl_p95_ms": 9.581487464620439,
"itl_p99_ms": 10.733646140910508,
"tpot_mean_ms": 6.942225311685386,
"tpot_p50_ms": 6.797988936978788,
"tpot_p95_ms": 9.582715377937562,
"acceptance_rate": 0.27131373077960613,
"acceptance_pos_1": 0.48776908551389264,
"acceptance_pos_2": 0.22053412462908012,
"acceptance_pos_3": 0.10563798219584569,
"mean_acceptance_length": 1.8139411923388185
},
{
"dataset": "gsm8k",
"run": "dspark_k7",
"method": "dspark",
"num_speculative_tokens": 7,
"requests": 1319,
"output_tokens": 168457,
"request_throughput_rps": 0.9537832973729679,
"output_throughput_tps": 121.81309547047616,
"speedup_vs_baseline": 0.9569212403462244,
"latency_mean_ms": 1048.3418924380537,
"latency_p50_ms": 1024.0400490001775,
"latency_p95_ms": 1480.1234933955127,
"latency_p99_ms": 1657.6216600838231,
"ttft_mean_ms": 127.43488244511649,
"ttft_p50_ms": 108.85212599532679,
"ttft_p95_ms": 265.2473596011987,
"ttft_p99_ms": 272.91192704375135,
"itl_mean_ms": 7.264521106390136,
"itl_p50_ms": 7.101249275637395,
"itl_p95_ms": 10.530224299220105,
"itl_p99_ms": 11.874427473184914,
"tpot_mean_ms": 7.265778957962821,
"tpot_p50_ms": 7.102425023638387,
"tpot_p95_ms": 10.531432203184004,
"acceptance_rate": 0.12425870324814467,
"acceptance_pos_1": 0.4784887142079961,
"acceptance_pos_2": 0.21339195505667877,
"acceptance_pos_3": 0.10025647003963628,
"mean_acceptance_length": 1.8698109227370128
},
{
"dataset": "humaneval",
"run": "baseline",
"method": "baseline",
"num_speculative_tokens": null,
"requests": 164,
"output_tokens": 11593,
"request_throughput_rps": 1.5860477240562036,
"output_throughput_tps": 112.1161662498998,
"speedup_vs_baseline": 1.0,
"latency_mean_ms": 630.4013797863018,
"latency_p50_ms": 523.5549619974336,
"latency_p95_ms": 1166.231724152749,
"latency_p99_ms": 1309.8181371219107,
"ttft_mean_ms": 107.49666936503561,
"ttft_p50_ms": 68.79427550302353,
"ttft_p95_ms": 235.7000987394713,
"ttft_p99_ms": 257.95137990207877,
"itl_mean_ms": 7.297341666050263,
"itl_p50_ms": 7.1785622135738,
"itl_p95_ms": 8.49481829626492,
"itl_p99_ms": 9.019322222237124,
"tpot_mean_ms": 7.301280505914361,
"tpot_p50_ms": 7.182021026551093,
"tpot_p95_ms": 8.49614809654986,
"acceptance_rate": null,
"acceptance_pos_1": null,
"acceptance_pos_2": null,
"acceptance_pos_3": null,
"mean_acceptance_length": null
},
{
"dataset": "humaneval",
"run": "dspark_k3",
"method": "dspark",
"num_speculative_tokens": 3,
"requests": 164,
"output_tokens": 11403,
"request_throughput_rps": 2.3328174923608316,
"output_throughput_tps": 162.20193820360097,
"speedup_vs_baseline": 1.4467310436040344,
"latency_mean_ms": 428.57000031148254,
"latency_p50_ms": 387.70782500796486,
"latency_p95_ms": 818.5407340446543,
"latency_p99_ms": 898.805770642066,
"ttft_mean_ms": 100.60342578719606,
"ttft_p50_ms": 86.00447800563416,
"ttft_p95_ms": 181.3961499959987,
"ttft_p99_ms": 206.1478519160301,
"itl_mean_ms": 5.122034968621708,
"itl_p50_ms": 4.931764990461113,
"itl_p95_ms": 7.476613033529377,
"itl_p99_ms": 8.192469397143373,
"tpot_mean_ms": 5.12586804041208,
"tpot_p50_ms": 4.935711371615048,
"tpot_p95_ms": 7.481607739016129,
"acceptance_rate": 0.5768270082990895,
"acceptance_pos_1": 0.7553782934493595,
"acceptance_pos_2": 0.5569253081943437,
"acceptance_pos_3": 0.4181774232535654,
"mean_acceptance_length": 2.7304810248972684
},
{
"dataset": "humaneval",
"run": "dspark_k7",
"method": "dspark",
"num_speculative_tokens": 7,
"requests": 164,
"output_tokens": 10873,
"request_throughput_rps": 2.251028218808984,
"output_throughput_tps": 149.24042575067125,
"speedup_vs_baseline": 1.3311231621854054,
"latency_mean_ms": 444.1504760051896,
"latency_p50_ms": 404.9552284996025,
"latency_p95_ms": 816.3704766055158,
"latency_p99_ms": 1066.9646934645427,
"ttft_mean_ms": 160.0552513159417,
"ttft_p50_ms": 160.3144644977874,
"ttft_p95_ms": 265.6927762531268,
"ttft_p99_ms": 272.09467787863105,
"itl_mean_ms": 4.944825696685838,
"itl_p50_ms": 4.49954001268619,
"itl_p95_ms": 8.732022160872603,
"itl_p99_ms": 10.318099194431854,
"tpot_mean_ms": 4.949079180467763,
"tpot_p50_ms": 4.503242393642178,
"tpot_p95_ms": 8.749463808814781,
"acceptance_rate": 0.33094945594945596,
"acceptance_pos_1": 0.7306511056511057,
"acceptance_pos_2": 0.538083538083538,
"acceptance_pos_3": 0.382985257985258,
"mean_acceptance_length": 3.316646191646192
},
{
"dataset": "mbpp",
"run": "baseline",
"method": "baseline",
"num_speculative_tokens": null,
"requests": 500,
"output_tokens": 61467,
"request_throughput_rps": 1.060577545227861,
"output_throughput_tps": 130.38103994504186,
"speedup_vs_baseline": 1.0,
"latency_mean_ms": 942.7637862757256,
"latency_p50_ms": 959.554503999243,
"latency_p95_ms": 1136.071662903123,
"latency_p99_ms": 1164.7922664470389,
"ttft_mean_ms": 128.43507730966667,
"ttft_p50_ms": 113.83070349984337,
"ttft_p95_ms": 256.7646375973709,
"ttft_p99_ms": 260.46189150976716,
"itl_mean_ms": 6.666311532516699,
"itl_p50_ms": 6.6432852756234775,
"itl_p95_ms": 7.121261330345493,
"itl_p99_ms": 7.26582164827209,
"tpot_mean_ms": 6.669662882298301,
"tpot_p50_ms": 6.644507716595485,
"tpot_p95_ms": 7.122378109070412,
"acceptance_rate": null,
"acceptance_pos_1": null,
"acceptance_pos_2": null,
"acceptance_pos_3": null,
"mean_acceptance_length": null
},
{
"dataset": "mbpp",
"run": "dspark_k3",
"method": "dspark",
"num_speculative_tokens": 3,
"requests": 500,
"output_tokens": 61643,
"request_throughput_rps": 1.426522036352137,
"output_throughput_tps": 175.87019577370955,
"speedup_vs_baseline": 1.3488939484440547,
"latency_mean_ms": 700.897503109707,
"latency_p50_ms": 703.9270094974199,
"latency_p95_ms": 919.0087530580053,
"latency_p99_ms": 1045.5224799610733,
"ttft_mean_ms": 108.79212251797435,
"ttft_p50_ms": 91.88079299929086,
"ttft_p95_ms": 204.44850095518615,
"ttft_p99_ms": 252.88790728605818,
"itl_mean_ms": 5.011328370238571,
"itl_p50_ms": 4.792381047239568,
"itl_p95_ms": 6.631624132701181,
"itl_p99_ms": 11.0604020699849,
"tpot_mean_ms": 5.013954450995089,
"tpot_p50_ms": 4.79360114569697,
"tpot_p95_ms": 6.632888974820347,
"acceptance_rate": 0.5095989615358338,
"acceptance_pos_1": 0.7010043041606887,
"acceptance_pos_2": 0.49940561590489857,
"acceptance_pos_3": 0.32838696454191435,
"mean_acceptance_length": 2.5287968846075017
},
{
"dataset": "mbpp",
"run": "dspark_k7",
"method": "dspark",
"num_speculative_tokens": 7,
"requests": 500,
"output_tokens": 61199,
"request_throughput_rps": 1.4351988286444157,
"output_throughput_tps": 175.6654662284192,
"speedup_vs_baseline": 1.347323708282014,
"latency_mean_ms": 696.6608542179456,
"latency_p50_ms": 697.1229435002897,
"latency_p95_ms": 978.6413718429683,
"latency_p99_ms": 1134.9274124257497,
"ttft_mean_ms": 144.74703813757515,
"ttft_p50_ms": 139.05306548986118,
"ttft_p95_ms": 269.57134354670416,
"ttft_p99_ms": 274.25451427989174,
"itl_mean_ms": 4.7933126349011435,
"itl_p50_ms": 4.529900153696456,
"itl_p95_ms": 6.829579977194199,
"itl_p99_ms": 12.186756946117372,
"tpot_mean_ms": 4.796161684500074,
"tpot_p50_ms": 4.531059523688732,
"tpot_p95_ms": 6.830801591285134,
"acceptance_rate": 0.27433826068703066,
"acceptance_pos_1": 0.6736976821349007,
"acceptance_pos_2": 0.462388017253638,
"acceptance_pos_3": 0.2917950419490923,
"mean_acceptance_length": 2.9203678248092144
},
{
"dataset": "mt_bench",
"run": "baseline",
"method": "baseline",
"num_speculative_tokens": null,
"requests": 160,
"output_tokens": 20102,
"request_throughput_rps": 1.0145474949999134,
"output_throughput_tps": 127.46521090305163,
"speedup_vs_baseline": 1.0,
"latency_mean_ms": 985.5352811689045,
"latency_p50_ms": 984.0788365036133,
"latency_p95_ms": 1160.0982246920466,
"latency_p99_ms": 1228.7251105705216,
"ttft_mean_ms": 135.88225862440595,
"ttft_p50_ms": 116.72725749667734,
"ttft_p95_ms": 258.65039654891007,
"ttft_p99_ms": 261.56884412805084,
"itl_mean_ms": 6.802873811459109,
"itl_p50_ms": 6.694544555138573,
"itl_p95_ms": 7.932162838574364,
"itl_p99_ms": 8.945381395555675,
"tpot_mean_ms": 6.808100097450948,
"tpot_p50_ms": 6.695755173252367,
"tpot_p95_ms": 7.93327857724984,
"acceptance_rate": null,
"acceptance_pos_1": null,
"acceptance_pos_2": null,
"acceptance_pos_3": null,
"mean_acceptance_length": null
},
{
"dataset": "mt_bench",
"run": "dspark_k3",
"method": "dspark",
"num_speculative_tokens": 3,
"requests": 160,
"output_tokens": 20102,
"request_throughput_rps": 1.146245568010398,
"output_throughput_tps": 144.01142755090638,
"speedup_vs_baseline": 1.1298096675212783,
"latency_mean_ms": 872.2913337876889,
"latency_p50_ms": 843.7197764942539,
"latency_p95_ms": 1313.481805704941,
"latency_p99_ms": 1433.86794267004,
"ttft_mean_ms": 97.44770207444162,
"ttft_p50_ms": 75.82400399405742,
"ttft_p95_ms": 185.91803135059308,
"ttft_p99_ms": 229.50114874707637,
"itl_mean_ms": 6.340698793466556,
"itl_p50_ms": 5.966741342590682,
"itl_p95_ms": 10.206342749464907,
"itl_p99_ms": 12.089351741436634,
"tpot_mean_ms": 6.344304410333824,
"tpot_p50_ms": 5.967888015807757,
"tpot_p95_ms": 10.32622098520203,
"acceptance_rate": 0.3227736367202825,
"acceptance_pos_1": 0.5441349548842683,
"acceptance_pos_2": 0.2823656335817968,
"acceptance_pos_3": 0.14182032169478226,
"mean_acceptance_length": 1.9683209101608474
},
{
"dataset": "mt_bench",
"run": "dspark_k7",
"method": "dspark",
"num_speculative_tokens": 7,
"requests": 160,
"output_tokens": 20102,
"request_throughput_rps": 1.0518269898218957,
"output_throughput_tps": 132.14891343374842,
"speedup_vs_baseline": 1.0367449478764772,
"latency_mean_ms": 950.6035467624315,
"latency_p50_ms": 909.5398534991546,
"latency_p95_ms": 1560.6508335607941,
"latency_p99_ms": 1760.411608337017,
"ttft_mean_ms": 132.69152166194544,
"ttft_p50_ms": 122.75661650346592,
"ttft_p95_ms": 258.31930338608794,
"ttft_p99_ms": 269.76503039040836,
"itl_mean_ms": 6.65775048881359,
"itl_p50_ms": 6.321849094407714,
"itl_p95_ms": 11.558155716175955,
"itl_p99_ms": 13.248131914494198,
"tpot_mean_ms": 6.6624969313339735,
"tpot_p50_ms": 6.32326457077476,
"tpot_p95_ms": 11.559374125591408,
"acceptance_rate": 0.14785346059984694,
"acceptance_pos_1": 0.5276458101688062,
"acceptance_pos_2": 0.257859092287476,
"acceptance_pos_3": 0.1271606186192257,
"mean_acceptance_length": 2.034974224198929
},
{
"dataset": "ultrachat",
"run": "baseline",
"method": "baseline",
"num_speculative_tokens": null,
"requests": 5000,
"output_tokens": 636089,
"request_throughput_rps": 0.5205862124506341,
"output_throughput_tps": 66.22783265830228,
"speedup_vs_baseline": 1.0,
"latency_mean_ms": 1920.7680450268758,
"latency_p50_ms": 1795.524564004154,
"latency_p95_ms": 3165.0052286931896,
"latency_p99_ms": 3293.7335572592565,
"ttft_mean_ms": 134.13350982365372,
"ttft_p50_ms": 127.32078000408364,
"ttft_p95_ms": 226.59587289090268,
"ttft_p99_ms": 258.95474469623883,
"itl_mean_ms": 14.14775085821201,
"itl_p50_ms": 13.20624435037479,
"itl_p95_ms": 23.33603281298938,
"itl_p99_ms": 24.09970887749654,
"tpot_mean_ms": 14.149112711234228,
"tpot_p50_ms": 13.207468862130167,
"tpot_p95_ms": 23.337274902295345,
"acceptance_rate": null,
"acceptance_pos_1": null,
"acceptance_pos_2": null,
"acceptance_pos_3": null,
"mean_acceptance_length": null
},
{
"dataset": "ultrachat",
"run": "dspark_k3",
"method": "dspark",
"num_speculative_tokens": 3,
"requests": 5000,
"output_tokens": 635846,
"request_throughput_rps": 0.6599485226793063,
"output_throughput_tps": 83.92512567030923,
"speedup_vs_baseline": 1.2672183627586737,
"latency_mean_ms": 1515.1526615684213,
"latency_p50_ms": 1470.6976669913274,
"latency_p95_ms": 2205.4712326978915,
"latency_p99_ms": 2478.7801955970654,
"ttft_mean_ms": 154.38469593704212,
"ttft_p50_ms": 149.33674249914475,
"ttft_p95_ms": 250.97870194367718,
"ttft_p99_ms": 286.67091090654156,
"itl_mean_ms": 10.78135369824052,
"itl_p50_ms": 10.431902874002185,
"itl_p95_ms": 15.61618643974625,
"itl_p99_ms": 17.696921136958977,
"tpot_mean_ms": 10.78267526592669,
"tpot_p50_ms": 10.433149968439395,
"tpot_p95_ms": 15.617432073222732,
"acceptance_rate": 0.30246536910398036,
"acceptance_pos_1": 0.5334846321484933,
"acceptance_pos_2": 0.2569174118884798,
"acceptance_pos_3": 0.11699406327496806,
"mean_acceptance_length": 1.907396107311941
},
{
"dataset": "ultrachat",
"run": "dspark_k7",
"method": "dspark",
"num_speculative_tokens": 7,
"requests": 5000,
"output_tokens": 636040,
"request_throughput_rps": 0.6585516278400763,
"output_throughput_tps": 83.77303547428042,
"speedup_vs_baseline": 1.2649218932846762,
"latency_mean_ms": 1518.3681885767612,
"latency_p50_ms": 1479.9964584963163,
"latency_p95_ms": 2203.905933455099,
"latency_p99_ms": 2513.144597544161,
"ttft_mean_ms": 165.56593623632216,
"ttft_p50_ms": 164.75157599779777,
"ttft_p95_ms": 262.971773991012,
"ttft_p99_ms": 305.4997507331428,
"itl_mean_ms": 10.715100522278119,
"itl_p50_ms": 10.43376617324282,
"itl_p95_ms": 15.631104971251936,
"itl_p99_ms": 17.89630725780433,
"tpot_mean_ms": 10.71641033546772,
"tpot_p50_ms": 10.434974913300184,
"tpot_p95_ms": 15.632339404468743,
"acceptance_rate": 0.14185244726020002,
"acceptance_pos_1": 0.5312465705748265,
"acceptance_pos_2": 0.25502381392840456,
"acceptance_pos_3": 0.11516911181415417,
"mean_acceptance_length": 1.9929671308214
}
]