Evaluate vLLM 0.20 profiles against Frontier

This commit is contained in:
2026-07-16 23:59:10 +08:00
parent 008324e70c
commit 76107d3e87
33 changed files with 13973 additions and 14 deletions

View File

@@ -0,0 +1,37 @@
time_stats.emb.min,time_stats.emb.max,time_stats.emb.mean,time_stats.emb.median,time_stats.emb.std,time_stats.input_layernorm.min,time_stats.input_layernorm.max,time_stats.input_layernorm.mean,time_stats.input_layernorm.median,time_stats.input_layernorm.std,time_stats.attn_pre_proj.min,time_stats.attn_pre_proj.max,time_stats.attn_pre_proj.mean,time_stats.attn_pre_proj.median,time_stats.attn_pre_proj.std,time_stats.attn_rope.min,time_stats.attn_rope.max,time_stats.attn_rope.mean,time_stats.attn_rope.median,time_stats.attn_rope.std,time_stats.attn_post_proj.min,time_stats.attn_post_proj.max,time_stats.attn_post_proj.mean,time_stats.attn_post_proj.median,time_stats.attn_post_proj.std,time_stats.post_attention_layernorm.min,time_stats.post_attention_layernorm.max,time_stats.post_attention_layernorm.mean,time_stats.post_attention_layernorm.median,time_stats.post_attention_layernorm.std,n_head,n_kv_head,n_embd,n_expanded_embd,vocab_size,use_gated_mlp,use_qk_norm,attn_output_gate,num_tokens,num_tensor_parallel_workers,padded_n_embd,padded_n_expanded_embd,model_arch,is_step2_mini,share_expert_dim,share_q_dim,measurement_type,profiling_precision,quant_signature
0.029184000566601753,0.06780800223350525,0.03157280012965202,0.030736000277101994,0.005874173435341216,0.033215999603271484,0.04825599864125252,0.03443359974771738,0.0337119996547699,0.0031825678429048183,1.438431978225708,1.505568027496338,1.446228802204132,1.4429279565811157,0.014128607642643025,0.538752019405365,0.5440319776535034,0.5416463971138,0.5420799851417542,0.0016099306164432847,1.0073280334472656,1.0163840055465698,1.0098415970802308,1.0081279873847961,0.0032980457197329728,0.04022400081157684,0.041728001087903976,0.04091359991580248,0.04081599973142147,0.0004728505416767937,32,4,2048,768,151936,True,True,False,8192,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.01360000018030405,0.06784000247716904,0.017755200061947106,0.0179840000346303,0.00837681421401443,0.01836800016462803,0.03651199862360954,0.019606399815529585,0.018719999119639397,0.0038821958848767424,0.7512000203132629,0.8208960294723511,0.7566704005002975,0.75382399559021,0.014793092586577971,0.28995200991630554,0.29337599873542786,0.29135999977588656,0.29150401055812836,0.000998381071258815,0.5149760246276855,0.5169600248336792,0.5160208016633987,0.5158880054950714,0.0005038652783291977,0.02051199972629547,0.021503999829292297,0.021067200042307378,0.021104000508785248,0.00023542855306902367,32,4,2048,768,151936,True,True,False,4096,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.0080960001796484,0.04281599819660187,0.011092799971811474,0.011039999779313803,0.005489135752949302,0.012223999947309494,0.026335999369621277,0.013187199970707298,0.01247999956831336,0.0030236510562153375,0.3928639888763428,0.45372799038887024,0.3976895987987518,0.39528000354766846,0.012905176716136006,0.1547199934720993,0.15884800255298615,0.15712319910526276,0.1573439985513687,0.001165121945135037,0.26633599400520325,0.268095999956131,0.26719200164079665,0.2671840041875839,0.0004242740199415328,0.013024000450968742,0.013887999579310417,0.013489600038155913,0.013520000036805868,0.0002382817554057738,32,4,2048,768,151936,True,True,False,2048,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.00825599953532219,0.04755200073122978,0.02398160002194345,0.01961600035429001,0.00874683840888523,0.018880000337958336,0.03868800029158592,0.021590400114655496,0.0208320003002882,0.004057015751746236,0.24316799640655518,0.2710399925708771,0.2521967992186546,0.25065599381923676,0.007998418528894075,0.09644799679517746,0.19120000302791595,0.10407840013504029,0.09963199868798256,0.020043722414992166,0.13600000739097595,0.18892799317836761,0.15760480016469955,0.15760000050067902,0.0112223677907762,0.009664000011980534,0.010015999898314476,0.009836799977347255,0.009824000298976898,9.016971952948177e-05,32,4,2048,768,151936,True,True,False,1024,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.017376000061631203,0.044704001396894455,0.026318399980664254,0.027312000282108784,0.007565344034680866,0.01836800016462803,0.03014400042593479,0.021276800055056812,0.020655999891459942,0.002632977855097951,0.1438719928264618,0.17132799327373505,0.152497598528862,0.15012799948453903,0.007947150319625347,0.1430719941854477,0.19305600225925446,0.16630879789590836,0.1685439944267273,0.014628024163894684,0.08899199962615967,0.10467199981212616,0.0943599995225668,0.09374399855732918,0.003472669494074113,0.007615999784320593,0.007935999892652035,0.007769599952735007,0.0077760000713169575,7.680004540222077e-05,32,4,2048,768,151936,True,True,False,512,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.016992000862956047,0.0544000007212162,0.02573199989274144,0.026016000658273697,0.00803323401720434,0.018432000651955605,0.02348800003528595,0.020648000109940768,0.02062400057911873,0.0013939985047930988,0.10220800340175629,0.1361600011587143,0.11850560046732425,0.11684799939393997,0.010637754898360304,0.16710400581359863,0.21110400557518005,0.19078560024499894,0.19409599900245667,0.013714352646558832,0.06265600025653839,0.0740479975938797,0.06842879951000214,0.0690080001950264,0.0031292240446560557,0.00979200005531311,0.033440001308918,0.01864320016466081,0.017280000261962414,0.006957998188876383,32,4,2048,768,151936,True,True,False,256,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.017152000218629837,0.04396799951791763,0.025907999789342284,0.02598400041460991,0.007714554737915267,0.018400000408291817,0.03667199984192848,0.024132800102233887,0.02112000063061714,0.006120348733354326,0.10678400099277496,0.1363839954137802,0.1193264003843069,0.11583999916911125,0.009838647443214228,0.17017599940299988,0.22748799622058868,0.18853759989142418,0.18433599919080734,0.015728078443174653,0.04569600149989128,0.06652799993753433,0.05192639995366335,0.05151999928057194,0.004516605694976449,0.021856000646948814,0.026335999369621277,0.02384479995816946,0.023599999956786633,0.0011301153013314744,32,4,2048,768,151936,True,True,False,128,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.017343999817967415,1.0683200359344482,0.05748240072280168,0.029504000209271908,0.16366824814254827,0.018688000738620758,0.3317759931087494,0.03685439983382821,0.021151999942958355,0.06767422466731164,0.10255999863147736,0.9434880018234253,0.16412640027701855,0.11956800147891045,0.17964606281728834,0.1714559942483902,2.1306240558624268,0.3011296011507511,0.1926399990916252,0.42310127734378766,0.03574400022625923,0.6859520077705383,0.08389280084520578,0.04279999993741512,0.14321647071615612,0.020479999482631683,0.1831360012292862,0.033024000097066165,0.023856000043451786,0.03470987082429836,32,4,2048,768,151936,True,True,False,64,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.016095999628305435,0.05142400041222572,0.026363200135529043,0.02676799986511469,0.008637725852473854,0.01849599927663803,0.03577600046992302,0.022193600237369538,0.020848000422120094,0.004615266181181815,0.10540799796581268,0.15014399588108063,0.12211520001292228,0.11896000057458878,0.012772013396624768,0.17315199971199036,0.21478399634361267,0.1881632000207901,0.1873439997434616,0.011761164657572015,0.03481600061058998,0.058079998940229416,0.042200000025331974,0.03969600051641464,0.006461281521769989,0.02143999934196472,0.038816001266241074,0.02466559996828437,0.023856000043451786,0.0035418033748569927,32,4,2048,768,151936,True,True,False,32,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.015904000028967857,0.03753599897027016,0.023127999808639287,0.02527999971061945,0.0054230027890305385,0.018400000408291817,0.03001599945127964,0.020488000102341176,0.020096000283956528,0.002585688394137697,0.10355199873447418,0.1438400000333786,0.11536479964852334,0.11124800145626068,0.011136028294919255,0.16502399742603302,0.2072959989309311,0.18646399974822997,0.19075199961662292,0.013296437761247597,0.03142400085926056,0.05215999856591225,0.03888959977775812,0.03750399872660637,0.0057399302067536314,0.020128000527620316,0.04064000025391579,0.023937600292265417,0.023648000322282314,0.004144197400898248,32,4,2048,768,151936,True,True,False,16,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.015200000256299973,0.037151999771595,0.02144480012357235,0.02195199951529503,0.005576364091933697,0.017952000722289085,0.0226879995316267,0.019934400077909233,0.019952000118792057,0.0011812499470458758,0.10063999891281128,0.13468800485134125,0.11595199964940547,0.1207519993185997,0.011974301621092394,0.16332800686359406,0.20748800039291382,0.18162400051951408,0.1767839938402176,0.01474120743720334,0.03222399950027466,0.043455999344587326,0.03829439990222454,0.03859200142323971,0.0031378131240041122,0.020959999412298203,0.03587200120091438,0.023795200139284135,0.023423999547958374,0.0031339489695198443,32,4,2048,768,151936,True,True,False,8,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
0.014944000169634819,0.04022400081157684,0.02162720002233982,0.022463999688625336,0.006017219317026815,0.018464000895619392,0.026528000831604004,0.021264000236988066,0.020896000787615776,0.001934095017586082,0.10156799852848053,0.1703999936580658,0.12565439902245998,0.1244799979031086,0.01641776722785409,0.1653759926557541,0.23865599930286407,0.1969360001385212,0.19223999977111816,0.02058903050274278,0.03254399821162224,0.06752000004053116,0.0443536002188921,0.041519999504089355,0.00984829071098989,0.020096000283956528,0.040031999349594116,0.026934400014579297,0.02478400059044361,0.00562071702648593,32,4,2048,768,151936,True,True,False,1,1,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.7531200051307678,0.8461440205574036,0.7618160009384155,0.7576479911804199,0.019464233617982506,0.2922559976577759,0.2985599935054779,0.2953856036067009,0.29576000571250916,0.001575901077689139,0.510047972202301,0.5140479803085327,0.5121696025133133,0.5123839974403381,0.0012263137313476844,,,,,,32,4,2048,768,151936,True,True,False,8192,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.39529600739479065,0.47279998660087585,0.40216960161924364,0.39825600385665894,0.0162749796240819,0.15625600516796112,0.16211199760437012,0.15959519892930984,0.15988799929618835,0.0011493418942396922,0.2635200023651123,0.2642880082130432,0.2639120012521744,0.26392000913619995,0.0001903593401384135,,,,,,32,4,2048,768,151936,True,True,False,4096,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.2531839907169342,0.32419198751449585,0.26924319565296173,0.26049599051475525,0.01657194262368116,0.10051199793815613,0.2375359982252121,0.12411200068891048,0.10311999917030334,0.039466165428540506,0.15881599485874176,0.19289599359035492,0.16896959990262986,0.1640480011701584,0.009162416086418127,,,,,,32,4,2048,768,151936,True,True,False,2048,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.15302400290966034,0.1780800074338913,0.16284480094909667,0.16113600134849548,0.00740355661356144,0.14521600306034088,0.20233599841594696,0.17807039842009545,0.1796799972653389,0.013908448560094403,0.0907519981265068,0.09750399738550186,0.09460479989647866,0.09478399902582169,0.0017965487667361475,,,,,,32,4,2048,768,151936,True,True,False,1024,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.11740799993276596,0.17958399653434753,0.13262080028653145,0.12878400087356567,0.014146060532423056,0.17468799650669098,0.21161599457263947,0.1910431995987892,0.18966399878263474,0.01270903647700971,0.05926400050520897,0.07577600330114365,0.06530559975653887,0.06404799968004227,0.00479458462514625,,,,,,32,4,2048,768,151936,True,True,False,512,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.11260800063610077,0.17209599912166595,0.13610880002379416,0.13809599727392197,0.017675922458993677,0.18729600310325623,0.26822400093078613,0.20815680101513861,0.2078079953789711,0.01700718593658771,0.04499199986457825,0.06537599861621857,0.0507551996037364,0.04787199944257736,0.005727123232692158,,,,,,32,4,2048,768,151936,True,True,False,256,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.11257600039243698,0.23452800512313843,0.13866880126297473,0.13964799791574478,0.026590047697062115,0.1828799992799759,0.24751999974250793,0.20735519900918006,0.20670399814844131,0.01500438131586336,0.03654399886727333,0.05593600124120712,0.0408239996060729,0.03892800025641918,0.004864409450710354,,,,,,32,4,2048,768,151936,True,True,False,128,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.11734399944543839,0.18726399540901184,0.13890240006148816,0.13308800011873245,0.019086167340006257,0.16991999745368958,0.2443840056657791,0.19185120090842248,0.19257599860429764,0.018017536159219673,0.03033600002527237,0.04956800118088722,0.038387199863791466,0.03750400058925152,0.00500897018702887,,,,,,32,4,2048,768,151936,True,True,False,64,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.11420799791812897,0.18115200102329254,0.13938880078494548,0.1393439993262291,0.018141313962922536,0.1693439930677414,0.221343994140625,0.19187839925289155,0.19438399374485016,0.01430752121272052,0.03017600066959858,0.06019200012087822,0.03866560012102127,0.0364960003644228,0.0074199790031205266,,,,,,32,4,2048,768,151936,True,True,False,32,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.11276800185441971,0.16223999857902527,0.1331360016018152,0.13305599987506866,0.01432493740801146,0.17187200486660004,0.23625600337982178,0.19287680014967917,0.1913280040025711,0.01754628831589704,0.029823999851942062,0.07574400305747986,0.03900959976017475,0.036927999928593636,0.009277465083962879,,,,,,32,4,2048,768,151936,True,True,False,16,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.1130559965968132,0.19814400374889374,0.13379519879817964,0.12531199678778648,0.020074427302248836,0.16841599345207214,0.21139200031757355,0.1893615983426571,0.19092799723148346,0.012418720676762711,0.029503999277949333,0.07558400183916092,0.040144000016152856,0.03728000074625015,0.010223239196498205,,,,,,32,4,2048,768,151936,True,True,False,8,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.115167997777462,0.2640640139579773,0.13805920109152794,0.13118399679660797,0.03132849683515479,0.17103999853134155,0.2977280020713806,0.19899839907884598,0.1976960003376007,0.028928046763067948,0.0297279991209507,0.05990400165319443,0.03834720011800528,0.0363520011305809,0.0070885330713495905,,,,,,32,4,2048,768,151936,True,True,False,1,2,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.3940800130367279,0.46483200788497925,0.39923040121793746,0.3957759886980057,0.015108903906233569,0.16022400557994843,0.1634880006313324,0.16203359961509706,0.16228799521923065,0.0010220720912414007,0.26073598861694336,0.2627840042114258,0.26138080209493636,0.2613760083913803,0.00041640363494172775,,,,,,32,4,2048,768,151936,True,True,False,8192,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.2536959946155548,0.27161601185798645,0.25960480123758317,0.2577280104160309,0.005142017404245015,0.09849599748849869,0.10281600058078766,0.10057279989123344,0.10063999891281128,0.0008836232237268523,0.13913600146770477,0.17606399953365326,0.15875840038061143,0.15988799929618835,0.010058952112389172,,,,,,32,4,2048,768,151936,True,True,False,4096,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.15142400562763214,0.1780479997396469,0.16139679849147798,0.1602879986166954,0.0070656055731385115,0.14601600170135498,0.23343999683856964,0.17913119941949845,0.179967999458313,0.023065274309176566,0.09388799965381622,0.12108799815177917,0.10317599996924401,0.10073599964380264,0.007364345618470178,,,,,,32,4,2048,768,151936,True,True,False,2048,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.12198399752378464,0.18406400084495544,0.13770400024950505,0.13232000172138214,0.01623164885687898,0.1773120015859604,0.20688000321388245,0.1870912007987499,0.18535999953746796,0.00825628058448234,0.05766399949789047,0.06739199906587601,0.06187200043350458,0.061216000467538834,0.003004312467037863,,,,,,32,4,2048,768,151936,True,True,False,1024,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.11737599968910217,0.18614399433135986,0.13109439946711063,0.12771200388669968,0.01372168725934724,0.17587199807167053,0.2699519991874695,0.19926720038056372,0.19075199961662292,0.02327478982490538,0.041728001087903976,0.06224000081419945,0.05000480003654957,0.049375999718904495,0.006185850944273961,,,,,,32,4,2048,768,151936,True,True,False,512,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.1159679964184761,0.1610880047082901,0.12988320142030715,0.12494400516152382,0.011865375783184065,0.1767680048942566,0.27379199862480164,0.21035519987344742,0.21275199949741364,0.023206964017550125,0.037087999284267426,0.062144000083208084,0.04439679980278015,0.04283200018107891,0.006155226392511492,,,,,,32,4,2048,768,151936,True,True,False,256,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.12015999853610992,0.158720001578331,0.13573280088603495,0.1343199983239174,0.010666830836014414,0.1737920045852661,0.22127999365329742,0.20261440128087999,0.20321600139141083,0.011153965849067301,0.03587200120091438,0.04944000020623207,0.038265600241720675,0.037328001111745834,0.0030431580113575636,,,,,,32,4,2048,768,151936,True,True,False,128,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.1212799996137619,0.15139199793338776,0.13183839991688728,0.13014400005340576,0.00851207547022104,0.17257599532604218,0.2250880002975464,0.1872655987739563,0.18193599581718445,0.013638284975248818,0.02969600073993206,0.0525440014898777,0.03840640028938651,0.03444799967110157,0.007598511754254174,,,,,,32,4,2048,768,151936,True,True,False,64,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.11270400136709213,0.1624639928340912,0.13508000001311302,0.13180799782276154,0.014243564451606775,0.17052799463272095,0.23715199530124664,0.1953311987221241,0.1966560035943985,0.01500670718978398,0.030239999294281006,0.05270399898290634,0.03807039987295866,0.03742399998009205,0.004906165602021684,,,,,,32,4,2048,768,151936,True,True,False,32,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.12319999933242798,0.17919999361038208,0.14059039913117885,0.14156799763441086,0.016217662982107223,0.1701119989156723,0.21987199783325195,0.18903039917349815,0.1870879977941513,0.014117854507841239,0.030368000268936157,0.06406400352716446,0.04045119984075427,0.03710399940609932,0.00878942205983628,,,,,,32,4,2048,768,151936,True,True,False,16,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.11296000331640244,0.16761599481105804,0.13843199908733367,0.13814399391412735,0.014925286935582404,0.1711679995059967,0.21561600267887115,0.1906527981162071,0.1876479983329773,0.011803992622137974,0.0306560005992651,0.09216000139713287,0.041129599791020155,0.036847999319434166,0.013739721468154687,,,,,,32,4,2048,768,151936,True,True,False,8,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
,,,,,,,,,,0.11929599940776825,0.2008959949016571,0.14535359852015972,0.13971199840307236,0.024769473061576282,0.16803200542926788,0.25123199820518494,0.19573760256171227,0.19366399943828583,0.023196011081705884,0.03049599938094616,0.08089599758386612,0.04739360017701984,0.0453919991850853,0.01286389846889463,,,,,,32,4,2048,768,151936,True,True,False,1,4,2048,768,generic,False,,,CUDA_EVENT,BF16,none
1 time_stats.emb.min time_stats.emb.max time_stats.emb.mean time_stats.emb.median time_stats.emb.std time_stats.input_layernorm.min time_stats.input_layernorm.max time_stats.input_layernorm.mean time_stats.input_layernorm.median time_stats.input_layernorm.std time_stats.attn_pre_proj.min time_stats.attn_pre_proj.max time_stats.attn_pre_proj.mean time_stats.attn_pre_proj.median time_stats.attn_pre_proj.std time_stats.attn_rope.min time_stats.attn_rope.max time_stats.attn_rope.mean time_stats.attn_rope.median time_stats.attn_rope.std time_stats.attn_post_proj.min time_stats.attn_post_proj.max time_stats.attn_post_proj.mean time_stats.attn_post_proj.median time_stats.attn_post_proj.std time_stats.post_attention_layernorm.min time_stats.post_attention_layernorm.max time_stats.post_attention_layernorm.mean time_stats.post_attention_layernorm.median time_stats.post_attention_layernorm.std n_head n_kv_head n_embd n_expanded_embd vocab_size use_gated_mlp use_qk_norm attn_output_gate num_tokens num_tensor_parallel_workers padded_n_embd padded_n_expanded_embd model_arch is_step2_mini share_expert_dim share_q_dim measurement_type profiling_precision quant_signature
2 0.029184000566601753 0.06780800223350525 0.03157280012965202 0.030736000277101994 0.005874173435341216 0.033215999603271484 0.04825599864125252 0.03443359974771738 0.0337119996547699 0.0031825678429048183 1.438431978225708 1.505568027496338 1.446228802204132 1.4429279565811157 0.014128607642643025 0.538752019405365 0.5440319776535034 0.5416463971138 0.5420799851417542 0.0016099306164432847 1.0073280334472656 1.0163840055465698 1.0098415970802308 1.0081279873847961 0.0032980457197329728 0.04022400081157684 0.041728001087903976 0.04091359991580248 0.04081599973142147 0.0004728505416767937 32 4 2048 768 151936 True True False 8192 1 2048 768 generic False CUDA_EVENT BF16 none
3 0.01360000018030405 0.06784000247716904 0.017755200061947106 0.0179840000346303 0.00837681421401443 0.01836800016462803 0.03651199862360954 0.019606399815529585 0.018719999119639397 0.0038821958848767424 0.7512000203132629 0.8208960294723511 0.7566704005002975 0.75382399559021 0.014793092586577971 0.28995200991630554 0.29337599873542786 0.29135999977588656 0.29150401055812836 0.000998381071258815 0.5149760246276855 0.5169600248336792 0.5160208016633987 0.5158880054950714 0.0005038652783291977 0.02051199972629547 0.021503999829292297 0.021067200042307378 0.021104000508785248 0.00023542855306902367 32 4 2048 768 151936 True True False 4096 1 2048 768 generic False CUDA_EVENT BF16 none
4 0.0080960001796484 0.04281599819660187 0.011092799971811474 0.011039999779313803 0.005489135752949302 0.012223999947309494 0.026335999369621277 0.013187199970707298 0.01247999956831336 0.0030236510562153375 0.3928639888763428 0.45372799038887024 0.3976895987987518 0.39528000354766846 0.012905176716136006 0.1547199934720993 0.15884800255298615 0.15712319910526276 0.1573439985513687 0.001165121945135037 0.26633599400520325 0.268095999956131 0.26719200164079665 0.2671840041875839 0.0004242740199415328 0.013024000450968742 0.013887999579310417 0.013489600038155913 0.013520000036805868 0.0002382817554057738 32 4 2048 768 151936 True True False 2048 1 2048 768 generic False CUDA_EVENT BF16 none
5 0.00825599953532219 0.04755200073122978 0.02398160002194345 0.01961600035429001 0.00874683840888523 0.018880000337958336 0.03868800029158592 0.021590400114655496 0.0208320003002882 0.004057015751746236 0.24316799640655518 0.2710399925708771 0.2521967992186546 0.25065599381923676 0.007998418528894075 0.09644799679517746 0.19120000302791595 0.10407840013504029 0.09963199868798256 0.020043722414992166 0.13600000739097595 0.18892799317836761 0.15760480016469955 0.15760000050067902 0.0112223677907762 0.009664000011980534 0.010015999898314476 0.009836799977347255 0.009824000298976898 9.016971952948177e-05 32 4 2048 768 151936 True True False 1024 1 2048 768 generic False CUDA_EVENT BF16 none
6 0.017376000061631203 0.044704001396894455 0.026318399980664254 0.027312000282108784 0.007565344034680866 0.01836800016462803 0.03014400042593479 0.021276800055056812 0.020655999891459942 0.002632977855097951 0.1438719928264618 0.17132799327373505 0.152497598528862 0.15012799948453903 0.007947150319625347 0.1430719941854477 0.19305600225925446 0.16630879789590836 0.1685439944267273 0.014628024163894684 0.08899199962615967 0.10467199981212616 0.0943599995225668 0.09374399855732918 0.003472669494074113 0.007615999784320593 0.007935999892652035 0.007769599952735007 0.0077760000713169575 7.680004540222077e-05 32 4 2048 768 151936 True True False 512 1 2048 768 generic False CUDA_EVENT BF16 none
7 0.016992000862956047 0.0544000007212162 0.02573199989274144 0.026016000658273697 0.00803323401720434 0.018432000651955605 0.02348800003528595 0.020648000109940768 0.02062400057911873 0.0013939985047930988 0.10220800340175629 0.1361600011587143 0.11850560046732425 0.11684799939393997 0.010637754898360304 0.16710400581359863 0.21110400557518005 0.19078560024499894 0.19409599900245667 0.013714352646558832 0.06265600025653839 0.0740479975938797 0.06842879951000214 0.0690080001950264 0.0031292240446560557 0.00979200005531311 0.033440001308918 0.01864320016466081 0.017280000261962414 0.006957998188876383 32 4 2048 768 151936 True True False 256 1 2048 768 generic False CUDA_EVENT BF16 none
8 0.017152000218629837 0.04396799951791763 0.025907999789342284 0.02598400041460991 0.007714554737915267 0.018400000408291817 0.03667199984192848 0.024132800102233887 0.02112000063061714 0.006120348733354326 0.10678400099277496 0.1363839954137802 0.1193264003843069 0.11583999916911125 0.009838647443214228 0.17017599940299988 0.22748799622058868 0.18853759989142418 0.18433599919080734 0.015728078443174653 0.04569600149989128 0.06652799993753433 0.05192639995366335 0.05151999928057194 0.004516605694976449 0.021856000646948814 0.026335999369621277 0.02384479995816946 0.023599999956786633 0.0011301153013314744 32 4 2048 768 151936 True True False 128 1 2048 768 generic False CUDA_EVENT BF16 none
9 0.017343999817967415 1.0683200359344482 0.05748240072280168 0.029504000209271908 0.16366824814254827 0.018688000738620758 0.3317759931087494 0.03685439983382821 0.021151999942958355 0.06767422466731164 0.10255999863147736 0.9434880018234253 0.16412640027701855 0.11956800147891045 0.17964606281728834 0.1714559942483902 2.1306240558624268 0.3011296011507511 0.1926399990916252 0.42310127734378766 0.03574400022625923 0.6859520077705383 0.08389280084520578 0.04279999993741512 0.14321647071615612 0.020479999482631683 0.1831360012292862 0.033024000097066165 0.023856000043451786 0.03470987082429836 32 4 2048 768 151936 True True False 64 1 2048 768 generic False CUDA_EVENT BF16 none
10 0.016095999628305435 0.05142400041222572 0.026363200135529043 0.02676799986511469 0.008637725852473854 0.01849599927663803 0.03577600046992302 0.022193600237369538 0.020848000422120094 0.004615266181181815 0.10540799796581268 0.15014399588108063 0.12211520001292228 0.11896000057458878 0.012772013396624768 0.17315199971199036 0.21478399634361267 0.1881632000207901 0.1873439997434616 0.011761164657572015 0.03481600061058998 0.058079998940229416 0.042200000025331974 0.03969600051641464 0.006461281521769989 0.02143999934196472 0.038816001266241074 0.02466559996828437 0.023856000043451786 0.0035418033748569927 32 4 2048 768 151936 True True False 32 1 2048 768 generic False CUDA_EVENT BF16 none
11 0.015904000028967857 0.03753599897027016 0.023127999808639287 0.02527999971061945 0.0054230027890305385 0.018400000408291817 0.03001599945127964 0.020488000102341176 0.020096000283956528 0.002585688394137697 0.10355199873447418 0.1438400000333786 0.11536479964852334 0.11124800145626068 0.011136028294919255 0.16502399742603302 0.2072959989309311 0.18646399974822997 0.19075199961662292 0.013296437761247597 0.03142400085926056 0.05215999856591225 0.03888959977775812 0.03750399872660637 0.0057399302067536314 0.020128000527620316 0.04064000025391579 0.023937600292265417 0.023648000322282314 0.004144197400898248 32 4 2048 768 151936 True True False 16 1 2048 768 generic False CUDA_EVENT BF16 none
12 0.015200000256299973 0.037151999771595 0.02144480012357235 0.02195199951529503 0.005576364091933697 0.017952000722289085 0.0226879995316267 0.019934400077909233 0.019952000118792057 0.0011812499470458758 0.10063999891281128 0.13468800485134125 0.11595199964940547 0.1207519993185997 0.011974301621092394 0.16332800686359406 0.20748800039291382 0.18162400051951408 0.1767839938402176 0.01474120743720334 0.03222399950027466 0.043455999344587326 0.03829439990222454 0.03859200142323971 0.0031378131240041122 0.020959999412298203 0.03587200120091438 0.023795200139284135 0.023423999547958374 0.0031339489695198443 32 4 2048 768 151936 True True False 8 1 2048 768 generic False CUDA_EVENT BF16 none
13 0.014944000169634819 0.04022400081157684 0.02162720002233982 0.022463999688625336 0.006017219317026815 0.018464000895619392 0.026528000831604004 0.021264000236988066 0.020896000787615776 0.001934095017586082 0.10156799852848053 0.1703999936580658 0.12565439902245998 0.1244799979031086 0.01641776722785409 0.1653759926557541 0.23865599930286407 0.1969360001385212 0.19223999977111816 0.02058903050274278 0.03254399821162224 0.06752000004053116 0.0443536002188921 0.041519999504089355 0.00984829071098989 0.020096000283956528 0.040031999349594116 0.026934400014579297 0.02478400059044361 0.00562071702648593 32 4 2048 768 151936 True True False 1 1 2048 768 generic False CUDA_EVENT BF16 none
14 0.7531200051307678 0.8461440205574036 0.7618160009384155 0.7576479911804199 0.019464233617982506 0.2922559976577759 0.2985599935054779 0.2953856036067009 0.29576000571250916 0.001575901077689139 0.510047972202301 0.5140479803085327 0.5121696025133133 0.5123839974403381 0.0012263137313476844 32 4 2048 768 151936 True True False 8192 2 2048 768 generic False CUDA_EVENT BF16 none
15 0.39529600739479065 0.47279998660087585 0.40216960161924364 0.39825600385665894 0.0162749796240819 0.15625600516796112 0.16211199760437012 0.15959519892930984 0.15988799929618835 0.0011493418942396922 0.2635200023651123 0.2642880082130432 0.2639120012521744 0.26392000913619995 0.0001903593401384135 32 4 2048 768 151936 True True False 4096 2 2048 768 generic False CUDA_EVENT BF16 none
16 0.2531839907169342 0.32419198751449585 0.26924319565296173 0.26049599051475525 0.01657194262368116 0.10051199793815613 0.2375359982252121 0.12411200068891048 0.10311999917030334 0.039466165428540506 0.15881599485874176 0.19289599359035492 0.16896959990262986 0.1640480011701584 0.009162416086418127 32 4 2048 768 151936 True True False 2048 2 2048 768 generic False CUDA_EVENT BF16 none
17 0.15302400290966034 0.1780800074338913 0.16284480094909667 0.16113600134849548 0.00740355661356144 0.14521600306034088 0.20233599841594696 0.17807039842009545 0.1796799972653389 0.013908448560094403 0.0907519981265068 0.09750399738550186 0.09460479989647866 0.09478399902582169 0.0017965487667361475 32 4 2048 768 151936 True True False 1024 2 2048 768 generic False CUDA_EVENT BF16 none
18 0.11740799993276596 0.17958399653434753 0.13262080028653145 0.12878400087356567 0.014146060532423056 0.17468799650669098 0.21161599457263947 0.1910431995987892 0.18966399878263474 0.01270903647700971 0.05926400050520897 0.07577600330114365 0.06530559975653887 0.06404799968004227 0.00479458462514625 32 4 2048 768 151936 True True False 512 2 2048 768 generic False CUDA_EVENT BF16 none
19 0.11260800063610077 0.17209599912166595 0.13610880002379416 0.13809599727392197 0.017675922458993677 0.18729600310325623 0.26822400093078613 0.20815680101513861 0.2078079953789711 0.01700718593658771 0.04499199986457825 0.06537599861621857 0.0507551996037364 0.04787199944257736 0.005727123232692158 32 4 2048 768 151936 True True False 256 2 2048 768 generic False CUDA_EVENT BF16 none
20 0.11257600039243698 0.23452800512313843 0.13866880126297473 0.13964799791574478 0.026590047697062115 0.1828799992799759 0.24751999974250793 0.20735519900918006 0.20670399814844131 0.01500438131586336 0.03654399886727333 0.05593600124120712 0.0408239996060729 0.03892800025641918 0.004864409450710354 32 4 2048 768 151936 True True False 128 2 2048 768 generic False CUDA_EVENT BF16 none
21 0.11734399944543839 0.18726399540901184 0.13890240006148816 0.13308800011873245 0.019086167340006257 0.16991999745368958 0.2443840056657791 0.19185120090842248 0.19257599860429764 0.018017536159219673 0.03033600002527237 0.04956800118088722 0.038387199863791466 0.03750400058925152 0.00500897018702887 32 4 2048 768 151936 True True False 64 2 2048 768 generic False CUDA_EVENT BF16 none
22 0.11420799791812897 0.18115200102329254 0.13938880078494548 0.1393439993262291 0.018141313962922536 0.1693439930677414 0.221343994140625 0.19187839925289155 0.19438399374485016 0.01430752121272052 0.03017600066959858 0.06019200012087822 0.03866560012102127 0.0364960003644228 0.0074199790031205266 32 4 2048 768 151936 True True False 32 2 2048 768 generic False CUDA_EVENT BF16 none
23 0.11276800185441971 0.16223999857902527 0.1331360016018152 0.13305599987506866 0.01432493740801146 0.17187200486660004 0.23625600337982178 0.19287680014967917 0.1913280040025711 0.01754628831589704 0.029823999851942062 0.07574400305747986 0.03900959976017475 0.036927999928593636 0.009277465083962879 32 4 2048 768 151936 True True False 16 2 2048 768 generic False CUDA_EVENT BF16 none
24 0.1130559965968132 0.19814400374889374 0.13379519879817964 0.12531199678778648 0.020074427302248836 0.16841599345207214 0.21139200031757355 0.1893615983426571 0.19092799723148346 0.012418720676762711 0.029503999277949333 0.07558400183916092 0.040144000016152856 0.03728000074625015 0.010223239196498205 32 4 2048 768 151936 True True False 8 2 2048 768 generic False CUDA_EVENT BF16 none
25 0.115167997777462 0.2640640139579773 0.13805920109152794 0.13118399679660797 0.03132849683515479 0.17103999853134155 0.2977280020713806 0.19899839907884598 0.1976960003376007 0.028928046763067948 0.0297279991209507 0.05990400165319443 0.03834720011800528 0.0363520011305809 0.0070885330713495905 32 4 2048 768 151936 True True False 1 2 2048 768 generic False CUDA_EVENT BF16 none
26 0.3940800130367279 0.46483200788497925 0.39923040121793746 0.3957759886980057 0.015108903906233569 0.16022400557994843 0.1634880006313324 0.16203359961509706 0.16228799521923065 0.0010220720912414007 0.26073598861694336 0.2627840042114258 0.26138080209493636 0.2613760083913803 0.00041640363494172775 32 4 2048 768 151936 True True False 8192 4 2048 768 generic False CUDA_EVENT BF16 none
27 0.2536959946155548 0.27161601185798645 0.25960480123758317 0.2577280104160309 0.005142017404245015 0.09849599748849869 0.10281600058078766 0.10057279989123344 0.10063999891281128 0.0008836232237268523 0.13913600146770477 0.17606399953365326 0.15875840038061143 0.15988799929618835 0.010058952112389172 32 4 2048 768 151936 True True False 4096 4 2048 768 generic False CUDA_EVENT BF16 none
28 0.15142400562763214 0.1780479997396469 0.16139679849147798 0.1602879986166954 0.0070656055731385115 0.14601600170135498 0.23343999683856964 0.17913119941949845 0.179967999458313 0.023065274309176566 0.09388799965381622 0.12108799815177917 0.10317599996924401 0.10073599964380264 0.007364345618470178 32 4 2048 768 151936 True True False 2048 4 2048 768 generic False CUDA_EVENT BF16 none
29 0.12198399752378464 0.18406400084495544 0.13770400024950505 0.13232000172138214 0.01623164885687898 0.1773120015859604 0.20688000321388245 0.1870912007987499 0.18535999953746796 0.00825628058448234 0.05766399949789047 0.06739199906587601 0.06187200043350458 0.061216000467538834 0.003004312467037863 32 4 2048 768 151936 True True False 1024 4 2048 768 generic False CUDA_EVENT BF16 none
30 0.11737599968910217 0.18614399433135986 0.13109439946711063 0.12771200388669968 0.01372168725934724 0.17587199807167053 0.2699519991874695 0.19926720038056372 0.19075199961662292 0.02327478982490538 0.041728001087903976 0.06224000081419945 0.05000480003654957 0.049375999718904495 0.006185850944273961 32 4 2048 768 151936 True True False 512 4 2048 768 generic False CUDA_EVENT BF16 none
31 0.1159679964184761 0.1610880047082901 0.12988320142030715 0.12494400516152382 0.011865375783184065 0.1767680048942566 0.27379199862480164 0.21035519987344742 0.21275199949741364 0.023206964017550125 0.037087999284267426 0.062144000083208084 0.04439679980278015 0.04283200018107891 0.006155226392511492 32 4 2048 768 151936 True True False 256 4 2048 768 generic False CUDA_EVENT BF16 none
32 0.12015999853610992 0.158720001578331 0.13573280088603495 0.1343199983239174 0.010666830836014414 0.1737920045852661 0.22127999365329742 0.20261440128087999 0.20321600139141083 0.011153965849067301 0.03587200120091438 0.04944000020623207 0.038265600241720675 0.037328001111745834 0.0030431580113575636 32 4 2048 768 151936 True True False 128 4 2048 768 generic False CUDA_EVENT BF16 none
33 0.1212799996137619 0.15139199793338776 0.13183839991688728 0.13014400005340576 0.00851207547022104 0.17257599532604218 0.2250880002975464 0.1872655987739563 0.18193599581718445 0.013638284975248818 0.02969600073993206 0.0525440014898777 0.03840640028938651 0.03444799967110157 0.007598511754254174 32 4 2048 768 151936 True True False 64 4 2048 768 generic False CUDA_EVENT BF16 none
34 0.11270400136709213 0.1624639928340912 0.13508000001311302 0.13180799782276154 0.014243564451606775 0.17052799463272095 0.23715199530124664 0.1953311987221241 0.1966560035943985 0.01500670718978398 0.030239999294281006 0.05270399898290634 0.03807039987295866 0.03742399998009205 0.004906165602021684 32 4 2048 768 151936 True True False 32 4 2048 768 generic False CUDA_EVENT BF16 none
35 0.12319999933242798 0.17919999361038208 0.14059039913117885 0.14156799763441086 0.016217662982107223 0.1701119989156723 0.21987199783325195 0.18903039917349815 0.1870879977941513 0.014117854507841239 0.030368000268936157 0.06406400352716446 0.04045119984075427 0.03710399940609932 0.00878942205983628 32 4 2048 768 151936 True True False 16 4 2048 768 generic False CUDA_EVENT BF16 none
36 0.11296000331640244 0.16761599481105804 0.13843199908733367 0.13814399391412735 0.014925286935582404 0.1711679995059967 0.21561600267887115 0.1906527981162071 0.1876479983329773 0.011803992622137974 0.0306560005992651 0.09216000139713287 0.041129599791020155 0.036847999319434166 0.013739721468154687 32 4 2048 768 151936 True True False 8 4 2048 768 generic False CUDA_EVENT BF16 none
37 0.11929599940776825 0.2008959949016571 0.14535359852015972 0.13971199840307236 0.024769473061576282 0.16803200542926788 0.25123199820518494 0.19573760256171227 0.19366399943828583 0.023196011081705884 0.03049599938094616 0.08089599758386612 0.04739360017701984 0.0453919991850853 0.01286389846889463 32 4 2048 768 151936 True True False 1 4 2048 768 generic False CUDA_EVENT BF16 none