d0rj's picture
Add T5Gemma 2 DSpark Base checkpoint and benchmarks
5405176
Raw
History Blame Contribute Delete
19.8 kB
[
{
"dataset": "math500",
"run": "baseline",
"method": "baseline",
"num_speculative_tokens": null,
"requests": 500,
"output_tokens": 63527,
"request_throughput_rps": 2.575660280906157,
"output_throughput_tps": 327.24794133025085,
"speedup_vs_baseline": 1.0,
"latency_mean_ms": 1549.881507652055,
"latency_p50_ms": 1541.6923305019736,
"latency_p95_ms": 1901.3991399056977,
"latency_p99_ms": 2073.3104983172957,
"ttft_mean_ms": 147.72230004466837,
"ttft_p50_ms": 128.53012699633837,
"ttft_p95_ms": 277.2130677534733,
"ttft_p99_ms": 387.54749131272547,
"itl_mean_ms": 11.11915976237464,
"itl_p50_ms": 11.026409515830519,
"itl_p95_ms": 13.801987814431913,
"itl_p99_ms": 15.665761921923757,
"tpot_mean_ms": 11.12106789862526,
"tpot_p50_ms": 11.028098413518146,
"tpot_p95_ms": 13.803411649602399,
"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": 63539,
"request_throughput_rps": 3.34003084405518,
"output_throughput_tps": 424.44443960084413,
"speedup_vs_baseline": 1.2970117944073019,
"latency_mean_ms": 1195.6849749402609,
"latency_p50_ms": 1169.5264599984512,
"latency_p95_ms": 1773.1451036757787,
"latency_p99_ms": 1944.9941020199901,
"ttft_mean_ms": 143.30231556599028,
"ttft_p50_ms": 116.45177099853754,
"ttft_p95_ms": 297.67805395094905,
"ttft_p99_ms": 373.04166853777133,
"itl_mean_ms": 8.352826905473885,
"itl_p50_ms": 8.158615838546549,
"itl_p95_ms": 12.354124409472469,
"itl_p99_ms": 14.635059152750648,
"tpot_mean_ms": 8.35462870098348,
"tpot_p50_ms": 8.163252110248358,
"tpot_p95_ms": 12.355534362218949,
"acceptance_rate": 0.415486407892723,
"acceptance_pos_1": 0.6332426800409706,
"acceptance_pos_2": 0.38554727510330944,
"acceptance_pos_3": 0.22766926853388902,
"mean_acceptance_length": 2.246459223678169
},
{
"dataset": "math500",
"run": "dspark_k7",
"method": "dspark",
"num_speculative_tokens": 7,
"requests": 500,
"output_tokens": 63493,
"request_throughput_rps": 3.1055917217703812,
"output_throughput_tps": 394.36667038073364,
"speedup_vs_baseline": 1.2051005386852782,
"latency_mean_ms": 1286.8654769104323,
"latency_p50_ms": 1246.8089515023166,
"latency_p95_ms": 1958.8731202602503,
"latency_p99_ms": 2254.721420374407,
"ttft_mean_ms": 169.23283278750023,
"ttft_p50_ms": 150.04799248708878,
"ttft_p95_ms": 310.4628508415771,
"ttft_p99_ms": 383.799409790663,
"itl_mean_ms": 8.871197280140835,
"itl_p50_ms": 8.589971834756103,
"itl_p95_ms": 13.716522226358514,
"itl_p99_ms": 15.951512530517089,
"tpot_mean_ms": 8.87296793212422,
"tpot_p50_ms": 8.60067761416536,
"tpot_p95_ms": 13.71767588804694,
"acceptance_rate": 0.20277687384748888,
"acceptance_pos_1": 0.6178056188306758,
"acceptance_pos_2": 0.36526195899772207,
"acceptance_pos_3": 0.20611237661351556,
"mean_acceptance_length": 2.4194381169324224
},
{
"dataset": "gsm8k",
"run": "baseline",
"method": "baseline",
"num_speculative_tokens": null,
"requests": 1319,
"output_tokens": 168533,
"request_throughput_rps": 2.699786987185922,
"output_throughput_tps": 344.9607280602009,
"speedup_vs_baseline": 1.0,
"latency_mean_ms": 1479.6602965273742,
"latency_p50_ms": 1454.6987209760118,
"latency_p95_ms": 1803.740513609955,
"latency_p99_ms": 1914.7201473527819,
"ttft_mean_ms": 168.7780613106763,
"ttft_p50_ms": 145.47203300753608,
"ttft_p95_ms": 336.32914681511363,
"ttft_p99_ms": 491.5234538837098,
"itl_mean_ms": 10.337075278453744,
"itl_p50_ms": 10.18635707075055,
"itl_p95_ms": 12.4034695235158,
"itl_p99_ms": 13.359812111263784,
"tpot_mean_ms": 10.338842536074479,
"tpot_p50_ms": 10.187574787391716,
"tpot_p95_ms": 12.40562485355891,
"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": 168415,
"request_throughput_rps": 2.95131608515978,
"output_throughput_tps": 376.8354044595787,
"speedup_vs_baseline": 1.0924008845256588,
"latency_mean_ms": 1352.7894092793806,
"latency_p50_ms": 1323.1997079856228,
"latency_p95_ms": 1901.4164583000816,
"latency_p99_ms": 2116.5834879834433,
"ttft_mean_ms": 146.35591101451402,
"ttft_p50_ms": 119.20796197955497,
"ttft_p95_ms": 300.50935930921696,
"ttft_p99_ms": 387.0458965114083,
"itl_mean_ms": 9.517948084655174,
"itl_p50_ms": 9.351653133988322,
"itl_p95_ms": 13.592088056107666,
"itl_p99_ms": 15.135234009802675,
"tpot_mean_ms": 9.519542839852642,
"tpot_p50_ms": 9.352777228419354,
"tpot_p95_ms": 13.593510024599716,
"acceptance_rate": 0.27039498963955716,
"acceptance_pos_1": 0.48590297454239884,
"acceptance_pos_2": 0.220014867325282,
"acceptance_pos_3": 0.10526712705099062,
"mean_acceptance_length": 1.8111849689186714
},
{
"dataset": "gsm8k",
"run": "dspark_k7",
"method": "dspark",
"num_speculative_tokens": 7,
"requests": 1319,
"output_tokens": 168438,
"request_throughput_rps": 2.833061661782182,
"output_throughput_tps": 361.7856256158205,
"speedup_vs_baseline": 1.0487733709579932,
"latency_mean_ms": 1409.892868064269,
"latency_p50_ms": 1389.3212949915323,
"latency_p95_ms": 2024.2955645022444,
"latency_p99_ms": 2287.086103030015,
"ttft_mean_ms": 149.37952628049933,
"ttft_p50_ms": 121.9771110045258,
"ttft_p95_ms": 303.5228224063758,
"ttft_p99_ms": 355.9325602342128,
"itl_mean_ms": 9.94289976587715,
"itl_p50_ms": 9.82163717335926,
"itl_p95_ms": 14.449290831630137,
"itl_p99_ms": 16.439139549680032,
"tpot_mean_ms": 9.944535710893788,
"tpot_p50_ms": 9.823021669386277,
"tpot_p95_ms": 14.453224437911699,
"acceptance_rate": 0.1243881347729851,
"acceptance_pos_1": 0.47593713555839395,
"acceptance_pos_2": 0.21317265507858055,
"acceptance_pos_3": 0.10223801854834232,
"mean_acceptance_length": 1.870716943410896
},
{
"dataset": "humaneval",
"run": "baseline",
"method": "baseline",
"num_speculative_tokens": null,
"requests": 164,
"output_tokens": 11241,
"request_throughput_rps": 3.867290467605202,
"output_throughput_tps": 265.07446430701265,
"speedup_vs_baseline": 1.0,
"latency_mean_ms": 1027.5289629021356,
"latency_p50_ms": 879.5409715094138,
"latency_p95_ms": 2018.1860155600586,
"latency_p99_ms": 2274.2641233184268,
"ttft_mean_ms": 140.52152795707892,
"ttft_p50_ms": 120.44445698847994,
"ttft_p95_ms": 278.58940106234513,
"ttft_p99_ms": 480.18000137846695,
"itl_mean_ms": 13.187347418172193,
"itl_p50_ms": 12.668324928583226,
"itl_p95_ms": 19.83492009233357,
"itl_p99_ms": 28.834143813500756,
"tpot_mean_ms": 13.194289122212655,
"tpot_p50_ms": 12.670714736622909,
"tpot_p95_ms": 19.844658022235045,
"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": 11202,
"request_throughput_rps": 5.440176459827299,
"output_throughput_tps": 371.59058965235,
"speedup_vs_baseline": 1.4018347283047567,
"latency_mean_ms": 731.6780699141573,
"latency_p50_ms": 653.8903180044144,
"latency_p95_ms": 1438.7055883620633,
"latency_p99_ms": 1758.196029517276,
"ttft_mean_ms": 153.84280301219493,
"ttft_p50_ms": 109.24666900245938,
"ttft_p95_ms": 371.5150598072796,
"ttft_p99_ms": 427.1234392697809,
"itl_mean_ms": 9.217930821861229,
"itl_p50_ms": 8.395432637747984,
"itl_p95_ms": 16.543497819817173,
"itl_p99_ms": 21.385043967787766,
"tpot_mean_ms": 9.224179054706173,
"tpot_p50_ms": 8.398416746314833,
"tpot_p95_ms": 16.54860166646416,
"acceptance_rate": 0.5723147241266732,
"acceptance_pos_1": 0.7548971596474046,
"acceptance_pos_2": 0.5506856023506367,
"acceptance_pos_3": 0.41136141038197843,
"mean_acceptance_length": 2.7169441723800194
},
{
"dataset": "humaneval",
"run": "dspark_k7",
"method": "dspark",
"num_speculative_tokens": 7,
"requests": 164,
"output_tokens": 11135,
"request_throughput_rps": 5.728781174033297,
"output_throughput_tps": 388.9632827613461,
"speedup_vs_baseline": 1.467373644527463,
"latency_mean_ms": 695.9294298721943,
"latency_p50_ms": 634.961468007532,
"latency_p95_ms": 1258.2039341956258,
"latency_p99_ms": 1984.7797918543813,
"ttft_mean_ms": 170.66249135340757,
"ttft_p50_ms": 130.76092200935818,
"ttft_p95_ms": 440.41123243077857,
"ttft_p99_ms": 548.8665195452631,
"itl_mean_ms": 9.06925487325878,
"itl_p50_ms": 7.807209323622503,
"itl_p95_ms": 18.29704301704432,
"itl_p99_ms": 30.691704785244347,
"tpot_mean_ms": 9.07486906638103,
"tpot_p50_ms": 7.822465188736613,
"tpot_p95_ms": 18.303107731801564,
"acceptance_rate": 0.33277512988964747,
"acceptance_pos_1": 0.7348963029756538,
"acceptance_pos_2": 0.5404268109407875,
"acceptance_pos_3": 0.38352870453862337,
"mean_acceptance_length": 3.3294259092275325
},
{
"dataset": "mbpp",
"run": "baseline",
"method": "baseline",
"num_speculative_tokens": null,
"requests": 500,
"output_tokens": 61587,
"request_throughput_rps": 2.8009211403112766,
"output_throughput_tps": 345.00066053670116,
"speedup_vs_baseline": 1.0,
"latency_mean_ms": 1426.2509520059102,
"latency_p50_ms": 1449.8898644960718,
"latency_p95_ms": 1792.6750187427385,
"latency_p99_ms": 1927.6900081126948,
"ttft_mean_ms": 146.00965341442497,
"ttft_p50_ms": 129.28127399936784,
"ttft_p95_ms": 278.12606179941207,
"ttft_p99_ms": 302.88602881017135,
"itl_mean_ms": 10.539905415700249,
"itl_p50_ms": 10.33841663381217,
"itl_p95_ms": 12.799749751224665,
"itl_p99_ms": 13.565437609112568,
"tpot_mean_ms": 10.546513464177922,
"tpot_p50_ms": 10.339677704733752,
"tpot_p95_ms": 12.800697692052097,
"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": 61810,
"request_throughput_rps": 3.8673346513351055,
"output_throughput_tps": 478.07990959804573,
"speedup_vs_baseline": 1.385736215270775,
"latency_mean_ms": 1031.8113529087277,
"latency_p50_ms": 1022.938920505112,
"latency_p95_ms": 1450.6354179771733,
"latency_p99_ms": 1667.4116877623596,
"ttft_mean_ms": 149.58043881563935,
"ttft_p50_ms": 120.52947049960494,
"ttft_p95_ms": 290.24569394096017,
"ttft_p99_ms": 465.6294314624392,
"itl_mean_ms": 7.4866564872650105,
"itl_p50_ms": 7.0952005747625035,
"itl_p95_ms": 10.490002014466166,
"itl_p99_ms": 15.616462420633345,
"tpot_mean_ms": 7.490425515753587,
"tpot_p50_ms": 7.09647927951163,
"tpot_p95_ms": 10.49589030935033,
"acceptance_rate": 0.5115081479053122,
"acceptance_pos_1": 0.7031512518952587,
"acceptance_pos_2": 0.5011678891939516,
"acceptance_pos_3": 0.3302053026267262,
"mean_acceptance_length": 2.5345244437159367
},
{
"dataset": "mbpp",
"run": "dspark_k7",
"method": "dspark",
"num_speculative_tokens": 7,
"requests": 500,
"output_tokens": 61424,
"request_throughput_rps": 3.9288605862280823,
"output_throughput_tps": 482.6526652969474,
"speedup_vs_baseline": 1.3989905542386718,
"latency_mean_ms": 1016.7640253802527,
"latency_p50_ms": 1009.4089240010362,
"latency_p95_ms": 1519.8205350112396,
"latency_p99_ms": 1755.0660978292578,
"ttft_mean_ms": 157.01642078207806,
"ttft_p50_ms": 127.09367199568078,
"ttft_p95_ms": 310.5101487963111,
"ttft_p99_ms": 555.6603015074506,
"itl_mean_ms": 7.464304052053599,
"itl_p50_ms": 6.92667360632959,
"itl_p95_ms": 11.035447346997291,
"itl_p99_ms": 15.66697385307634,
"tpot_mean_ms": 7.469533758903007,
"tpot_p50_ms": 6.928639874063014,
"tpot_p95_ms": 11.131861498385357,
"acceptance_rate": 0.27595293416337563,
"acceptance_pos_1": 0.6748067713025748,
"acceptance_pos_2": 0.46773199298212337,
"acceptance_pos_3": 0.29465598179145525,
"mean_acceptance_length": 2.9316705391436293
},
{
"dataset": "mt_bench",
"run": "baseline",
"method": "baseline",
"num_speculative_tokens": null,
"requests": 160,
"output_tokens": 20102,
"request_throughput_rps": 2.865123484091851,
"output_throughput_tps": 359.96695173258996,
"speedup_vs_baseline": 1.0,
"latency_mean_ms": 1379.8839098995813,
"latency_p50_ms": 1349.3874825071543,
"latency_p95_ms": 1778.2662457597326,
"latency_p99_ms": 2064.43852098775,
"ttft_mean_ms": 230.34865414410888,
"ttft_p50_ms": 188.74082650290802,
"ttft_p95_ms": 469.9252384045379,
"ttft_p99_ms": 599.9244086013641,
"itl_mean_ms": 9.196491927825377,
"itl_p50_ms": 8.739159606336653,
"itl_p95_ms": 12.184589993809974,
"itl_p99_ms": 13.513825134104701,
"tpot_mean_ms": 9.201697317973778,
"tpot_p50_ms": 8.741404259885389,
"tpot_p95_ms": 12.185761682743273,
"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": 20228,
"request_throughput_rps": 3.1300295907514477,
"output_throughput_tps": 395.7139910107518,
"speedup_vs_baseline": 1.0993064477338947,
"latency_mean_ms": 1267.3618169241308,
"latency_p50_ms": 1240.8099970052717,
"latency_p95_ms": 1889.9596753937649,
"latency_p99_ms": 2197.152719998557,
"ttft_mean_ms": 149.93388268667331,
"ttft_p50_ms": 120.75363399344496,
"ttft_p95_ms": 296.08547244570207,
"ttft_p99_ms": 370.8032631434613,
"itl_mean_ms": 8.953320217924055,
"itl_p50_ms": 8.487721767728438,
"itl_p95_ms": 13.275213856385248,
"itl_p99_ms": 16.593942496504845,
"tpot_mean_ms": 8.957264486664604,
"tpot_p50_ms": 8.49002677173625,
"tpot_p95_ms": 13.297254559146252,
"acceptance_rate": 0.3200388161086851,
"acceptance_pos_1": 0.5434255215914604,
"acceptance_pos_2": 0.27666181465308104,
"acceptance_pos_3": 0.14002911208151383,
"mean_acceptance_length": 1.9601164483260554
},
{
"dataset": "mt_bench",
"run": "dspark_k7",
"method": "dspark",
"num_speculative_tokens": 7,
"requests": 160,
"output_tokens": 20102,
"request_throughput_rps": 2.8379656094158685,
"output_throughput_tps": 356.5549042529862,
"speedup_vs_baseline": 0.9905212201754052,
"latency_mean_ms": 1404.4557639432242,
"latency_p50_ms": 1343.6405550019117,
"latency_p95_ms": 2271.4736478112154,
"latency_p99_ms": 2877.03235346009,
"ttft_mean_ms": 182.31840012485918,
"ttft_p50_ms": 159.79043499100953,
"ttft_p95_ms": 363.3274522420834,
"ttft_p99_ms": 631.4187010040041,
"itl_mean_ms": 9.922806420825252,
"itl_p50_ms": 9.43615103145515,
"itl_p95_ms": 17.314218461555217,
"itl_p99_ms": 20.890300572353894,
"tpot_mean_ms": 9.927143236485232,
"tpot_p50_ms": 9.4376937125298,
"tpot_p95_ms": 17.32922917495226,
"acceptance_rate": 0.1459540058496301,
"acceptance_pos_1": 0.5190686471296668,
"acceptance_pos_2": 0.258129265355279,
"acceptance_pos_3": 0.12515054195102368,
"mean_acceptance_length": 2.0216780409474104
},
{
"dataset": "ultrachat",
"run": "baseline",
"method": "baseline",
"num_speculative_tokens": null,
"requests": 5000,
"output_tokens": 635560,
"request_throughput_rps": 1.3331967798759812,
"output_throughput_tps": 169.4653090835957,
"speedup_vs_baseline": 1.0,
"latency_mean_ms": 2999.209397312632,
"latency_p50_ms": 3004.6992159914225,
"latency_p95_ms": 3652.681129911798,
"latency_p99_ms": 3792.2580027181543,
"ttft_mean_ms": 191.445676819887,
"ttft_p50_ms": 180.53925450658426,
"ttft_p95_ms": 319.0085294045276,
"ttft_p99_ms": 436.0589518790949,
"itl_mean_ms": 22.255913944838188,
"itl_p50_ms": 22.191040874087605,
"itl_p95_ms": 26.93092076657395,
"itl_p99_ms": 27.96015746255569,
"tpot_mean_ms": 22.257870607914793,
"tpot_p50_ms": 22.192596555178742,
"tpot_p95_ms": 26.93375055238194,
"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": 636234,
"request_throughput_rps": 1.816992286110778,
"output_throughput_tps": 231.20645403228093,
"speedup_vs_baseline": 1.364329108314604,
"latency_mean_ms": 2200.762252031482,
"latency_p50_ms": 2194.020344497403,
"latency_p95_ms": 2860.881272106781,
"latency_p99_ms": 3141.828603268659,
"ttft_mean_ms": 203.0626388980716,
"ttft_p50_ms": 195.85809300770052,
"ttft_p95_ms": 327.66038095142005,
"ttft_p99_ms": 418.8016837404577,
"itl_mean_ms": 15.817088125396433,
"itl_p50_ms": 15.717495220445654,
"itl_p95_ms": 20.662014169011663,
"itl_p99_ms": 22.842756694141052,
"tpot_mean_ms": 15.818637421764908,
"tpot_p50_ms": 15.7196392047615,
"tpot_p95_ms": 20.663277460188848,
"acceptance_rate": 0.3022621517716569,
"acceptance_pos_1": 0.5328723151898772,
"acceptance_pos_2": 0.2570481426653975,
"acceptance_pos_3": 0.11686599745969595,
"mean_acceptance_length": 1.9067864553149707
},
{
"dataset": "ultrachat",
"run": "dspark_k7",
"method": "dspark",
"num_speculative_tokens": 7,
"requests": 5000,
"output_tokens": 636210,
"request_throughput_rps": 1.8127834563773697,
"output_throughput_tps": 230.66219255636926,
"speedup_vs_baseline": 1.361117468841872,
"latency_mean_ms": 2205.888447939884,
"latency_p50_ms": 2192.8646555024898,
"latency_p95_ms": 2923.480463263696,
"latency_p99_ms": 3272.379539081885,
"ttft_mean_ms": 208.6473120003706,
"ttft_p50_ms": 199.3813320004847,
"ttft_p95_ms": 335.6416549038841,
"ttft_p99_ms": 448.6493355646964,
"itl_mean_ms": 15.814628500703911,
"itl_p50_ms": 15.656986732382371,
"itl_p95_ms": 21.199671716881205,
"itl_p99_ms": 23.549442959891635,
"tpot_mean_ms": 15.81632527800587,
"tpot_p50_ms": 15.658670244142634,
"tpot_p95_ms": 21.20066768934127,
"acceptance_rate": 0.14160791914766432,
"acceptance_pos_1": 0.5315988273762544,
"acceptance_pos_2": 0.25404655416494404,
"acceptance_pos_3": 0.11493529271745531,
"mean_acceptance_length": 1.9912554340336501
}
]