Add BF16 NVFP4 DFlash DGX Spark benchmark
Browse files- MANIFEST.md +6 -0
- README.md +22 -7
- benchmark/baseline-elyza100-streaming.csv +101 -0
- benchmark/baseline-elyza100-streaming.json +1120 -0
- benchmark/bf16-elyza100-streaming.csv +101 -0
- benchmark/bf16-elyza100-streaming.json +1120 -0
- benchmark/dflash20k-b4-l1-elyza100-tps-histogram.png +0 -0
- benchmark/elyza100-baseline-vs-dflash-speedup.png +0 -0
- benchmark/elyza100-bf16-nvfp4-dflash-speedup-summary.json +43 -0
- benchmark/elyza100-bf16-nvfp4-dflash-speedup.png +3 -0
MANIFEST.md
CHANGED
|
@@ -18,8 +18,14 @@ e7ffbde19080c85333332bd25f214de07274e172e01fa140aaee806d5c635efc model.safetens
|
|
| 18 |
Primary benchmark artifacts copied from `results/`:
|
| 19 |
|
| 20 |
```text
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
dflash20k-b4-l1-v28k-elyza100-streaming.json
|
| 22 |
dflash20k-b4-l1-v28k-elyza100-streaming.csv
|
|
|
|
|
|
|
| 23 |
elyza100-baseline-vs-dflash-summary.json
|
| 24 |
elyza100-baseline-vs-dflash-speedup.png
|
| 25 |
dflash20k-b4-l1-elyza100-tps-histogram.png
|
|
|
|
| 18 |
Primary benchmark artifacts copied from `results/`:
|
| 19 |
|
| 20 |
```text
|
| 21 |
+
bf16-elyza100-streaming.json
|
| 22 |
+
bf16-elyza100-streaming.csv
|
| 23 |
+
baseline-elyza100-streaming.json
|
| 24 |
+
baseline-elyza100-streaming.csv
|
| 25 |
dflash20k-b4-l1-v28k-elyza100-streaming.json
|
| 26 |
dflash20k-b4-l1-v28k-elyza100-streaming.csv
|
| 27 |
+
elyza100-bf16-nvfp4-dflash-speedup-summary.json
|
| 28 |
+
elyza100-bf16-nvfp4-dflash-speedup.png
|
| 29 |
elyza100-baseline-vs-dflash-summary.json
|
| 30 |
elyza100-baseline-vs-dflash-speedup.png
|
| 31 |
dflash20k-b4-l1-elyza100-tps-histogram.png
|
README.md
CHANGED
|
@@ -50,14 +50,23 @@ If you use an environment wrapper, set the same JSON as `SPECULATIVE_CONFIG`.
|
|
| 50 |
The verifier model still needs the serving requirements documented on the NVFP4
|
| 51 |
model page, including the LLM-jp remote code/plugin setup.
|
| 52 |
|
| 53 |
-
## Benchmark
|
| 54 |
|
| 55 |
-
Representative Japanese streaming decode benchmark on ELYZA-100 prompts
|
|
|
|
|
|
|
|
|
|
| 56 |
|
| 57 |
-
| Setup | Mean decode tok/s | Notes |
|
| 58 |
-
| --- | ---: | --- |
|
| 59 |
-
|
|
| 60 |
-
| NVFP4
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
|
| 62 |
Paired speedup summary:
|
| 63 |
|
|
@@ -71,13 +80,19 @@ Paired speedup summary:
|
|
| 71 |
|
| 72 |
The raw benchmark artifacts are included under [`benchmark/`](benchmark/):
|
| 73 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 74 |
- `dflash20k-b4-l1-v28k-elyza100-streaming.json`
|
| 75 |
- `dflash20k-b4-l1-v28k-elyza100-streaming.csv`
|
|
|
|
|
|
|
| 76 |
- `elyza100-baseline-vs-dflash-summary.json`
|
| 77 |
- `elyza100-baseline-vs-dflash-speedup.png`
|
| 78 |
- `dflash20k-b4-l1-elyza100-tps-histogram.png`
|
| 79 |
|
| 80 |
-
:
|
| 82 |
|
| 83 |
+
- `bf16-elyza100-streaming.json`
|
| 84 |
+
- `bf16-elyza100-streaming.csv`
|
| 85 |
+
- `baseline-elyza100-streaming.json`
|
| 86 |
+
- `baseline-elyza100-streaming.csv`
|
| 87 |
- `dflash20k-b4-l1-v28k-elyza100-streaming.json`
|
| 88 |
- `dflash20k-b4-l1-v28k-elyza100-streaming.csv`
|
| 89 |
+
- `elyza100-bf16-nvfp4-dflash-speedup-summary.json`
|
| 90 |
+
- `elyza100-bf16-nvfp4-dflash-speedup.png`
|
| 91 |
- `elyza100-baseline-vs-dflash-summary.json`
|
| 92 |
- `elyza100-baseline-vs-dflash-speedup.png`
|
| 93 |
- `dflash20k-b4-l1-elyza100-tps-histogram.png`
|
| 94 |
|
| 95 |
+

|
| 96 |
|
| 97 |
## Validation Metrics
|
| 98 |
|
benchmark/baseline-elyza100-streaming.csv
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
prompt_tokens,completion_tokens,ttft_ms,decode_seconds,decode_tokens_per_second,e2e_seconds,e2e_tokens_per_second,index,prompt_characters
|
| 2 |
+
89,128,143.46256002318114,4.237766047997866,29.968619919450532,4.381228608021047,29.215549210479615,0,28
|
| 3 |
+
100,128,149.23513599205762,4.245029520010576,29.91734201171906,4.394264656002633,29.12887821291101,1,50
|
| 4 |
+
86,128,147.96897600172088,4.250384335988201,29.879650864672428,4.398353311989922,29.101800360392076,2,24
|
| 5 |
+
223,128,159.77539197774604,4.268197119992692,29.754951898804862,4.427972511970438,28.907135185227308,3,323
|
| 6 |
+
87,128,147.64036802807823,4.255182991968468,29.845954977661066,4.402823359996546,29.072254218279703,4,15
|
| 7 |
+
138,128,150.07712005171925,4.252459567971528,29.86506937221286,4.402536688023247,29.0741472633752,5,107
|
| 8 |
+
197,128,162.3923999723047,4.261921360041015,29.798766629231707,4.4243137600133196,28.931040369888834,6,286
|
| 9 |
+
129,128,155.38915200158954,4.255304831953254,29.8451004135713,4.410693983954843,29.02037649078274,7,77
|
| 10 |
+
253,128,157.81886398326606,4.268306992016733,29.754185965895992,4.426125855999999,28.91919574010415,8,359
|
| 11 |
+
107,128,149.04068800387904,4.26341652800329,29.788316287144156,4.412457216007169,29.00877985528144,9,76
|
| 12 |
+
115,128,148.95393600454554,4.266124832036439,29.769405490972566,4.415078768040985,28.991555241673503,10,93
|
| 13 |
+
136,128,186.66489596944302,4.235812655999325,29.98244028099911,4.422477551968768,28.943052507528915,11,126
|
| 14 |
+
239,128,159.81835196726024,4.27479575999314,29.70902170077099,4.4346141119604,28.86384176128807,12,301
|
| 15 |
+
113,128,149.9263520236127,4.26866089599207,29.751719120917475,4.418587248015683,28.968535148306227,13,76
|
| 16 |
+
239,128,159.59620795911178,4.279861872026231,29.673854857347045,4.439458079985343,28.832347933877234,14,323
|
| 17 |
+
122,128,182.7699519926682,4.240294800023548,29.950747763880642,4.4230647520162165,28.939210067329963,15,120
|
| 18 |
+
152,128,153.0061599914916,4.274810159986373,29.708921623879746,4.427816319977865,28.90815488946025,16,182
|
| 19 |
+
141,128,151.20801597367972,4.281187455984764,29.66466694245401,4.4323954719584435,28.878289586250187,17,140
|
| 20 |
+
196,128,160.8437920222059,4.278787071991246,29.681308712774342,4.439630864013452,28.831225820492485,18,191
|
| 21 |
+
118,128,149.06441600760445,4.280752464022953,29.667681340454877,4.4298168800305575,28.895099609426076,19,75
|
| 22 |
+
269,128,159.87711999332532,4.284917648008559,29.638842664578164,4.444794768001884,28.797730082269062,20,368
|
| 23 |
+
151,128,188.5674080112949,4.241870319994632,29.93962342539522,4.430437728005927,28.891050469094587,21,137
|
| 24 |
+
83,128,181.51931202737615,4.240379583963659,29.950148915981675,4.421898895991035,28.9468400365388,22,8
|
| 25 |
+
257,128,158.51934399688616,4.284019791986793,29.645054450390717,4.442539135983679,28.81235169392782,23,379
|
| 26 |
+
264,128,157.54560002824292,4.294625615992118,29.57184429000833,4.452171216020361,28.75001741609001,24,480
|
| 27 |
+
115,128,183.9634400093928,4.240709887992125,29.947816133239776,4.424673328001518,28.92868930909606,25,82
|
| 28 |
+
167,128,151.50518395239487,4.277752512018196,29.688487036872267,4.429257695970591,28.898747552314436,26,145
|
| 29 |
+
86,128,145.308943989221,4.2739029280492105,29.715228010096187,4.4192118720384315,28.964440652843823,27,11
|
| 30 |
+
95,128,147.21774403005838,4.27222136000637,29.72692407488236,4.419439104036428,28.962951403288514,28,33
|
| 31 |
+
138,128,152.53638400463387,4.275733312009834,29.702507320388253,4.428269696014468,28.905195208684464,29,155
|
| 32 |
+
89,128,147.56200002739206,4.27770995197352,29.688782415322148,4.425271952000912,28.924776011138494,30,23
|
| 33 |
+
122,128,149.15563201066107,4.275628671981394,29.703234247689284,4.424784303992055,28.927963761876022,31,97
|
| 34 |
+
94,128,145.9132640156895,4.272694383980706,29.723633049008047,4.418607647996396,28.96840140537058,32,61
|
| 35 |
+
132,128,153.64075201796368,4.272159695974551,29.72735315106922,4.425800447992515,28.921322030698228,33,136
|
| 36 |
+
114,128,148.47996801836416,4.275548528006766,29.70379102659995,4.42402849602513,28.93290586057584,34,82
|
| 37 |
+
97,128,147.8521599783562,4.273406176012941,29.71868218679137,4.421258335991297,28.95103390770332,35,49
|
| 38 |
+
116,128,147.574128000997,4.273268640041351,29.719638688283133,4.420842768042348,28.953755362053144,36,101
|
| 39 |
+
127,128,149.55046400427818,4.280436095956247,29.669874085955314,4.4299865599605255,28.893992852461515,37,118
|
| 40 |
+
99,128,146.9279839657247,4.2737699200515635,29.71615280554638,4.420697904017288,28.95470416191086,38,44
|
| 41 |
+
89,128,145.21406398853287,4.270830192021094,29.736607237924275,4.416044256009627,28.985216764032575,39,21
|
| 42 |
+
131,128,153.4373280010186,4.277822831994854,29.68799900971513,4.4312601599958725,28.885688354646103,40,99
|
| 43 |
+
164,128,152.07355201710016,4.281609760015272,29.66174105496878,4.433683312032372,28.86990138709876,41,255
|
| 44 |
+
119,128,147.45664002839476,4.278829519986175,29.6810142602761,4.42628616001457,28.918148391828936,42,98
|
| 45 |
+
109,128,148.86659203330055,4.27835519996006,29.684304847149104,4.427221791993361,28.912036941878142,43,69
|
| 46 |
+
116,128,149.5863359887153,4.2813182240352035,29.66376086856274,4.430904560023919,28.88800656074367,44,63
|
| 47 |
+
99,128,148.91756797442213,4.275036848033778,29.70734627899435,4.4239544160082005,28.93339034797205,45,51
|
| 48 |
+
87,128,181.61635199794546,4.241584288014565,29.94164240914972,4.42320064001251,28.938321007214807,46,16
|
| 49 |
+
121,128,149.99320002971217,4.277360575972125,29.69120740332639,4.427353776001837,28.911175044066976,47,83
|
| 50 |
+
103,128,150.74512001592666,4.27451617596671,29.710964883944584,4.4252612959826365,28.92484566192772,48,52
|
| 51 |
+
128,128,148.76968000316992,4.281864800024778,29.659974317560213,4.430634480027948,28.88976749876072,49,82
|
| 52 |
+
116,128,148.97512004245073,4.279575983993709,29.675837156531415,4.42855110403616,28.90335845584833,50,89
|
| 53 |
+
202,128,159.03887996682897,4.285158192040399,29.637178911131013,4.444197072007228,28.801603062617705,51,202
|
| 54 |
+
133,128,150.73892794316635,4.277238800015766,29.692052732602132,4.4279777279589325,28.9071011337271,52,73
|
| 55 |
+
97,128,148.48937600618228,4.274834448006004,29.708752828835074,4.423323824012186,28.937515111407173,53,42
|
| 56 |
+
208,128,160.55590397445485,4.285696112026926,29.633458994817804,4.446252016001381,28.78829169811958,54,254
|
| 57 |
+
113,128,148.43628800008446,4.276303727994673,29.698545304113676,4.424740015994757,28.92825330692868,55,85
|
| 58 |
+
127,128,182.12604796281084,4.240071760024875,29.952323259560806,4.422197807987686,28.94488341719978,56,107
|
| 59 |
+
144,128,185.98363199271262,4.249349439982325,29.88692782124509,4.4353330719750375,28.859162981192316,57,121
|
| 60 |
+
230,128,162.00067201862112,4.287982367968652,29.617659099695356,4.4499830399872735,28.764154570882603,58,346
|
| 61 |
+
124,128,183.87990404153243,4.242221055959817,29.937148094057964,4.4261009600013494,28.91935840522738,59,93
|
| 62 |
+
170,128,152.916015998926,4.2795338880387135,29.67612906512195,4.4324499040376395,28.8779349504664,60,207
|
| 63 |
+
148,128,153.09798397356644,4.275488400016911,29.70420876349417,4.428586383990478,28.90312819971747,61,122
|
| 64 |
+
123,128,149.6343039907515,4.274956831999589,29.707902322980047,4.42459113599034,28.929226693699963,62,88
|
| 65 |
+
98,128,150.04775999113917,4.279320368019398,29.677609778671357,4.4293681280105375,28.898027055044427,63,43
|
| 66 |
+
196,128,160.95686401240528,4.288259503955487,29.615745008634693,4.449216367967892,28.769111100447994,64,177
|
| 67 |
+
280,128,194.86894400324672,4.253986447991338,29.85434992628322,4.448855391994584,28.771445399265478,65,494
|
| 68 |
+
100,128,146.7246399843134,4.280999056005385,29.665972437402065,4.427723695989698,28.908759622000094,66,56
|
| 69 |
+
111,128,149.47828801814467,4.27679667196935,29.695122247071872,4.426274959987495,28.918221564880284,67,68
|
| 70 |
+
222,128,161.32521600229666,4.284537935978733,29.64146937141984,4.44586315198103,28.790809708788395,68,333
|
| 71 |
+
86,128,149.98059201752767,4.274428736011032,29.71157266702229,4.42440932802856,28.93041545435729,69,20
|
| 72 |
+
116,128,148.25239998754114,4.280142048024572,29.671912421368052,4.428394448012114,28.904380922403746,70,70
|
| 73 |
+
122,128,151.68241603532806,4.279039520013612,29.679557621752465,4.43072193604894,28.88919725667618,71,100
|
| 74 |
+
123,128,182.6112479902804,4.241006672033109,29.94572039640699,4.423617920023389,28.93559125452752,72,100
|
| 75 |
+
304,128,160.21692799404263,4.284923232044093,29.638804039767013,4.445140160038136,28.795492468543863,73,516
|
| 76 |
+
96,128,145.91110398760065,4.27431379200425,29.712371664797445,4.420224895991851,28.957802603226636,74,51
|
| 77 |
+
98,128,182.3572000139393,4.2468398079508916,29.904589234148144,4.429197007964831,28.899143517396766,75,38
|
| 78 |
+
146,128,152.6936799637042,4.277269551996142,29.691839257764542,4.429963231959846,28.894145007016668,76,133
|
| 79 |
+
140,128,152.17240003403276,4.280287823989056,29.67090186978153,4.432460224023089,28.87786771469813,77,158
|
| 80 |
+
89,128,147.72603200981393,4.280198383959942,29.671521879904667,4.4279244159697555,28.90744917378334,78,17
|
| 81 |
+
163,128,186.45403202390298,4.244761504000053,29.919231005162832,4.431215536023956,28.88597924416286,79,193
|
| 82 |
+
154,128,152.16956799849868,4.277686815999914,29.68894298782685,4.429856383998413,28.894841932655726,80,151
|
| 83 |
+
119,128,147.88078400306404,4.278590032015927,29.682675612685866,4.426470816018991,28.916942033545045,81,75
|
| 84 |
+
274,128,158.65448000840843,4.288939487945754,29.611049621226616,4.4475939679541625,28.779605540044024,82,413
|
| 85 |
+
96,128,151.030623994302,4.277100688021164,29.693011519623024,4.428131312015466,28.906098527990746,83,53
|
| 86 |
+
187,128,153.6058560013771,4.2891785760293715,29.609399037325215,4.442784432030749,28.810760899666832,84,243
|
| 87 |
+
175,128,150.53255995735526,4.287062800023705,29.62401203903469,4.43759535998106,28.844450567603424,85,193
|
| 88 |
+
95,128,146.89548802562058,4.2793887840234675,29.677135312906767,4.426284272049088,28.91816072643345,86,54
|
| 89 |
+
135,128,152.44775998871773,4.279913456004579,29.673497210982887,4.432361215993296,28.878512775118008,87,153
|
| 90 |
+
132,128,152.3534239968285,4.280044800019823,29.67258660456353,4.4323982240166515,28.878271655836475,88,83
|
| 91 |
+
151,128,152.58678403915837,4.286318383994512,29.629156918027626,4.438905168033671,28.8359393036326,89,154
|
| 92 |
+
98,128,149.5123039931059,4.2784633280243725,29.68355464639302,4.427975632017478,28.90711481663699,90,47
|
| 93 |
+
120,128,149.92755197454244,4.279246336023789,29.67812320849154,4.429173887998331,28.899294368830212,91,91
|
| 94 |
+
129,128,149.91504000499845,4.284216400003061,29.643694001990486,4.434131440008059,28.86698369946547,92,149
|
| 95 |
+
126,128,148.77603197237477,4.277493072033394,29.690287713225434,4.426269104005769,28.9182598238684,93,129
|
| 96 |
+
176,128,150.4963680054061,4.283495743991807,29.648681261825693,4.433992111997213,28.86789077807914,94,181
|
| 97 |
+
151,128,151.79175999946892,4.284410799969919,29.642348955168274,4.436202559969388,28.853506635387557,95,182
|
| 98 |
+
113,128,147.12048001820222,4.276005279971287,29.700618143496026,4.423125759989489,28.93881091011624,96,72
|
| 99 |
+
159,128,152.09144004620612,4.281069583958015,29.665483708999556,4.433161024004221,28.873302663025065,97,144
|
| 100 |
+
135,128,156.03772801114246,4.28199811198283,29.659050910041422,4.438035839993972,28.84158772367504,98,146
|
| 101 |
+
183,128,154.6247520018369,4.2839804160175845,29.64532693127015,4.438605168019421,28.837888290279196,99,214
|
benchmark/baseline-elyza100-streaming.json
ADDED
|
@@ -0,0 +1,1120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": "training/data/benchmarks/elyza-tasks-100/test.csv",
|
| 3 |
+
"model": "llm-jp-4-8b-instruct-NVFP4",
|
| 4 |
+
"temperature": 0,
|
| 5 |
+
"max_tokens": 128,
|
| 6 |
+
"summary": {
|
| 7 |
+
"count": 100,
|
| 8 |
+
"mean": 29.72816958251134,
|
| 9 |
+
"median": 29.69194599518334,
|
| 10 |
+
"stdev": 0.10065825734656245,
|
| 11 |
+
"min": 29.57184429000833,
|
| 12 |
+
"p05": 29.62401203903469,
|
| 13 |
+
"p25": 29.669874085955314,
|
| 14 |
+
"p75": 29.736607237924275,
|
| 15 |
+
"p95": 29.947816133239776,
|
| 16 |
+
"max": 29.98244028099911
|
| 17 |
+
},
|
| 18 |
+
"records": [
|
| 19 |
+
{
|
| 20 |
+
"prompt_tokens": 89,
|
| 21 |
+
"completion_tokens": 128,
|
| 22 |
+
"ttft_ms": 143.46256002318114,
|
| 23 |
+
"decode_seconds": 4.237766047997866,
|
| 24 |
+
"decode_tokens_per_second": 29.968619919450532,
|
| 25 |
+
"e2e_seconds": 4.381228608021047,
|
| 26 |
+
"e2e_tokens_per_second": 29.215549210479615,
|
| 27 |
+
"index": 0,
|
| 28 |
+
"prompt_characters": 28
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"prompt_tokens": 100,
|
| 32 |
+
"completion_tokens": 128,
|
| 33 |
+
"ttft_ms": 149.23513599205762,
|
| 34 |
+
"decode_seconds": 4.245029520010576,
|
| 35 |
+
"decode_tokens_per_second": 29.91734201171906,
|
| 36 |
+
"e2e_seconds": 4.394264656002633,
|
| 37 |
+
"e2e_tokens_per_second": 29.12887821291101,
|
| 38 |
+
"index": 1,
|
| 39 |
+
"prompt_characters": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"prompt_tokens": 86,
|
| 43 |
+
"completion_tokens": 128,
|
| 44 |
+
"ttft_ms": 147.96897600172088,
|
| 45 |
+
"decode_seconds": 4.250384335988201,
|
| 46 |
+
"decode_tokens_per_second": 29.879650864672428,
|
| 47 |
+
"e2e_seconds": 4.398353311989922,
|
| 48 |
+
"e2e_tokens_per_second": 29.101800360392076,
|
| 49 |
+
"index": 2,
|
| 50 |
+
"prompt_characters": 24
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"prompt_tokens": 223,
|
| 54 |
+
"completion_tokens": 128,
|
| 55 |
+
"ttft_ms": 159.77539197774604,
|
| 56 |
+
"decode_seconds": 4.268197119992692,
|
| 57 |
+
"decode_tokens_per_second": 29.754951898804862,
|
| 58 |
+
"e2e_seconds": 4.427972511970438,
|
| 59 |
+
"e2e_tokens_per_second": 28.907135185227308,
|
| 60 |
+
"index": 3,
|
| 61 |
+
"prompt_characters": 323
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"prompt_tokens": 87,
|
| 65 |
+
"completion_tokens": 128,
|
| 66 |
+
"ttft_ms": 147.64036802807823,
|
| 67 |
+
"decode_seconds": 4.255182991968468,
|
| 68 |
+
"decode_tokens_per_second": 29.845954977661066,
|
| 69 |
+
"e2e_seconds": 4.402823359996546,
|
| 70 |
+
"e2e_tokens_per_second": 29.072254218279703,
|
| 71 |
+
"index": 4,
|
| 72 |
+
"prompt_characters": 15
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"prompt_tokens": 138,
|
| 76 |
+
"completion_tokens": 128,
|
| 77 |
+
"ttft_ms": 150.07712005171925,
|
| 78 |
+
"decode_seconds": 4.252459567971528,
|
| 79 |
+
"decode_tokens_per_second": 29.86506937221286,
|
| 80 |
+
"e2e_seconds": 4.402536688023247,
|
| 81 |
+
"e2e_tokens_per_second": 29.0741472633752,
|
| 82 |
+
"index": 5,
|
| 83 |
+
"prompt_characters": 107
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"prompt_tokens": 197,
|
| 87 |
+
"completion_tokens": 128,
|
| 88 |
+
"ttft_ms": 162.3923999723047,
|
| 89 |
+
"decode_seconds": 4.261921360041015,
|
| 90 |
+
"decode_tokens_per_second": 29.798766629231707,
|
| 91 |
+
"e2e_seconds": 4.4243137600133196,
|
| 92 |
+
"e2e_tokens_per_second": 28.931040369888834,
|
| 93 |
+
"index": 6,
|
| 94 |
+
"prompt_characters": 286
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"prompt_tokens": 129,
|
| 98 |
+
"completion_tokens": 128,
|
| 99 |
+
"ttft_ms": 155.38915200158954,
|
| 100 |
+
"decode_seconds": 4.255304831953254,
|
| 101 |
+
"decode_tokens_per_second": 29.8451004135713,
|
| 102 |
+
"e2e_seconds": 4.410693983954843,
|
| 103 |
+
"e2e_tokens_per_second": 29.02037649078274,
|
| 104 |
+
"index": 7,
|
| 105 |
+
"prompt_characters": 77
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"prompt_tokens": 253,
|
| 109 |
+
"completion_tokens": 128,
|
| 110 |
+
"ttft_ms": 157.81886398326606,
|
| 111 |
+
"decode_seconds": 4.268306992016733,
|
| 112 |
+
"decode_tokens_per_second": 29.754185965895992,
|
| 113 |
+
"e2e_seconds": 4.426125855999999,
|
| 114 |
+
"e2e_tokens_per_second": 28.91919574010415,
|
| 115 |
+
"index": 8,
|
| 116 |
+
"prompt_characters": 359
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"prompt_tokens": 107,
|
| 120 |
+
"completion_tokens": 128,
|
| 121 |
+
"ttft_ms": 149.04068800387904,
|
| 122 |
+
"decode_seconds": 4.26341652800329,
|
| 123 |
+
"decode_tokens_per_second": 29.788316287144156,
|
| 124 |
+
"e2e_seconds": 4.412457216007169,
|
| 125 |
+
"e2e_tokens_per_second": 29.00877985528144,
|
| 126 |
+
"index": 9,
|
| 127 |
+
"prompt_characters": 76
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"prompt_tokens": 115,
|
| 131 |
+
"completion_tokens": 128,
|
| 132 |
+
"ttft_ms": 148.95393600454554,
|
| 133 |
+
"decode_seconds": 4.266124832036439,
|
| 134 |
+
"decode_tokens_per_second": 29.769405490972566,
|
| 135 |
+
"e2e_seconds": 4.415078768040985,
|
| 136 |
+
"e2e_tokens_per_second": 28.991555241673503,
|
| 137 |
+
"index": 10,
|
| 138 |
+
"prompt_characters": 93
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"prompt_tokens": 136,
|
| 142 |
+
"completion_tokens": 128,
|
| 143 |
+
"ttft_ms": 186.66489596944302,
|
| 144 |
+
"decode_seconds": 4.235812655999325,
|
| 145 |
+
"decode_tokens_per_second": 29.98244028099911,
|
| 146 |
+
"e2e_seconds": 4.422477551968768,
|
| 147 |
+
"e2e_tokens_per_second": 28.943052507528915,
|
| 148 |
+
"index": 11,
|
| 149 |
+
"prompt_characters": 126
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"prompt_tokens": 239,
|
| 153 |
+
"completion_tokens": 128,
|
| 154 |
+
"ttft_ms": 159.81835196726024,
|
| 155 |
+
"decode_seconds": 4.27479575999314,
|
| 156 |
+
"decode_tokens_per_second": 29.70902170077099,
|
| 157 |
+
"e2e_seconds": 4.4346141119604,
|
| 158 |
+
"e2e_tokens_per_second": 28.86384176128807,
|
| 159 |
+
"index": 12,
|
| 160 |
+
"prompt_characters": 301
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"prompt_tokens": 113,
|
| 164 |
+
"completion_tokens": 128,
|
| 165 |
+
"ttft_ms": 149.9263520236127,
|
| 166 |
+
"decode_seconds": 4.26866089599207,
|
| 167 |
+
"decode_tokens_per_second": 29.751719120917475,
|
| 168 |
+
"e2e_seconds": 4.418587248015683,
|
| 169 |
+
"e2e_tokens_per_second": 28.968535148306227,
|
| 170 |
+
"index": 13,
|
| 171 |
+
"prompt_characters": 76
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"prompt_tokens": 239,
|
| 175 |
+
"completion_tokens": 128,
|
| 176 |
+
"ttft_ms": 159.59620795911178,
|
| 177 |
+
"decode_seconds": 4.279861872026231,
|
| 178 |
+
"decode_tokens_per_second": 29.673854857347045,
|
| 179 |
+
"e2e_seconds": 4.439458079985343,
|
| 180 |
+
"e2e_tokens_per_second": 28.832347933877234,
|
| 181 |
+
"index": 14,
|
| 182 |
+
"prompt_characters": 323
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"prompt_tokens": 122,
|
| 186 |
+
"completion_tokens": 128,
|
| 187 |
+
"ttft_ms": 182.7699519926682,
|
| 188 |
+
"decode_seconds": 4.240294800023548,
|
| 189 |
+
"decode_tokens_per_second": 29.950747763880642,
|
| 190 |
+
"e2e_seconds": 4.4230647520162165,
|
| 191 |
+
"e2e_tokens_per_second": 28.939210067329963,
|
| 192 |
+
"index": 15,
|
| 193 |
+
"prompt_characters": 120
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"prompt_tokens": 152,
|
| 197 |
+
"completion_tokens": 128,
|
| 198 |
+
"ttft_ms": 153.0061599914916,
|
| 199 |
+
"decode_seconds": 4.274810159986373,
|
| 200 |
+
"decode_tokens_per_second": 29.708921623879746,
|
| 201 |
+
"e2e_seconds": 4.427816319977865,
|
| 202 |
+
"e2e_tokens_per_second": 28.90815488946025,
|
| 203 |
+
"index": 16,
|
| 204 |
+
"prompt_characters": 182
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"prompt_tokens": 141,
|
| 208 |
+
"completion_tokens": 128,
|
| 209 |
+
"ttft_ms": 151.20801597367972,
|
| 210 |
+
"decode_seconds": 4.281187455984764,
|
| 211 |
+
"decode_tokens_per_second": 29.66466694245401,
|
| 212 |
+
"e2e_seconds": 4.4323954719584435,
|
| 213 |
+
"e2e_tokens_per_second": 28.878289586250187,
|
| 214 |
+
"index": 17,
|
| 215 |
+
"prompt_characters": 140
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"prompt_tokens": 196,
|
| 219 |
+
"completion_tokens": 128,
|
| 220 |
+
"ttft_ms": 160.8437920222059,
|
| 221 |
+
"decode_seconds": 4.278787071991246,
|
| 222 |
+
"decode_tokens_per_second": 29.681308712774342,
|
| 223 |
+
"e2e_seconds": 4.439630864013452,
|
| 224 |
+
"e2e_tokens_per_second": 28.831225820492485,
|
| 225 |
+
"index": 18,
|
| 226 |
+
"prompt_characters": 191
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"prompt_tokens": 118,
|
| 230 |
+
"completion_tokens": 128,
|
| 231 |
+
"ttft_ms": 149.06441600760445,
|
| 232 |
+
"decode_seconds": 4.280752464022953,
|
| 233 |
+
"decode_tokens_per_second": 29.667681340454877,
|
| 234 |
+
"e2e_seconds": 4.4298168800305575,
|
| 235 |
+
"e2e_tokens_per_second": 28.895099609426076,
|
| 236 |
+
"index": 19,
|
| 237 |
+
"prompt_characters": 75
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"prompt_tokens": 269,
|
| 241 |
+
"completion_tokens": 128,
|
| 242 |
+
"ttft_ms": 159.87711999332532,
|
| 243 |
+
"decode_seconds": 4.284917648008559,
|
| 244 |
+
"decode_tokens_per_second": 29.638842664578164,
|
| 245 |
+
"e2e_seconds": 4.444794768001884,
|
| 246 |
+
"e2e_tokens_per_second": 28.797730082269062,
|
| 247 |
+
"index": 20,
|
| 248 |
+
"prompt_characters": 368
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"prompt_tokens": 151,
|
| 252 |
+
"completion_tokens": 128,
|
| 253 |
+
"ttft_ms": 188.5674080112949,
|
| 254 |
+
"decode_seconds": 4.241870319994632,
|
| 255 |
+
"decode_tokens_per_second": 29.93962342539522,
|
| 256 |
+
"e2e_seconds": 4.430437728005927,
|
| 257 |
+
"e2e_tokens_per_second": 28.891050469094587,
|
| 258 |
+
"index": 21,
|
| 259 |
+
"prompt_characters": 137
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"prompt_tokens": 83,
|
| 263 |
+
"completion_tokens": 128,
|
| 264 |
+
"ttft_ms": 181.51931202737615,
|
| 265 |
+
"decode_seconds": 4.240379583963659,
|
| 266 |
+
"decode_tokens_per_second": 29.950148915981675,
|
| 267 |
+
"e2e_seconds": 4.421898895991035,
|
| 268 |
+
"e2e_tokens_per_second": 28.9468400365388,
|
| 269 |
+
"index": 22,
|
| 270 |
+
"prompt_characters": 8
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"prompt_tokens": 257,
|
| 274 |
+
"completion_tokens": 128,
|
| 275 |
+
"ttft_ms": 158.51934399688616,
|
| 276 |
+
"decode_seconds": 4.284019791986793,
|
| 277 |
+
"decode_tokens_per_second": 29.645054450390717,
|
| 278 |
+
"e2e_seconds": 4.442539135983679,
|
| 279 |
+
"e2e_tokens_per_second": 28.81235169392782,
|
| 280 |
+
"index": 23,
|
| 281 |
+
"prompt_characters": 379
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"prompt_tokens": 264,
|
| 285 |
+
"completion_tokens": 128,
|
| 286 |
+
"ttft_ms": 157.54560002824292,
|
| 287 |
+
"decode_seconds": 4.294625615992118,
|
| 288 |
+
"decode_tokens_per_second": 29.57184429000833,
|
| 289 |
+
"e2e_seconds": 4.452171216020361,
|
| 290 |
+
"e2e_tokens_per_second": 28.75001741609001,
|
| 291 |
+
"index": 24,
|
| 292 |
+
"prompt_characters": 480
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"prompt_tokens": 115,
|
| 296 |
+
"completion_tokens": 128,
|
| 297 |
+
"ttft_ms": 183.9634400093928,
|
| 298 |
+
"decode_seconds": 4.240709887992125,
|
| 299 |
+
"decode_tokens_per_second": 29.947816133239776,
|
| 300 |
+
"e2e_seconds": 4.424673328001518,
|
| 301 |
+
"e2e_tokens_per_second": 28.92868930909606,
|
| 302 |
+
"index": 25,
|
| 303 |
+
"prompt_characters": 82
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"prompt_tokens": 167,
|
| 307 |
+
"completion_tokens": 128,
|
| 308 |
+
"ttft_ms": 151.50518395239487,
|
| 309 |
+
"decode_seconds": 4.277752512018196,
|
| 310 |
+
"decode_tokens_per_second": 29.688487036872267,
|
| 311 |
+
"e2e_seconds": 4.429257695970591,
|
| 312 |
+
"e2e_tokens_per_second": 28.898747552314436,
|
| 313 |
+
"index": 26,
|
| 314 |
+
"prompt_characters": 145
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"prompt_tokens": 86,
|
| 318 |
+
"completion_tokens": 128,
|
| 319 |
+
"ttft_ms": 145.308943989221,
|
| 320 |
+
"decode_seconds": 4.2739029280492105,
|
| 321 |
+
"decode_tokens_per_second": 29.715228010096187,
|
| 322 |
+
"e2e_seconds": 4.4192118720384315,
|
| 323 |
+
"e2e_tokens_per_second": 28.964440652843823,
|
| 324 |
+
"index": 27,
|
| 325 |
+
"prompt_characters": 11
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"prompt_tokens": 95,
|
| 329 |
+
"completion_tokens": 128,
|
| 330 |
+
"ttft_ms": 147.21774403005838,
|
| 331 |
+
"decode_seconds": 4.27222136000637,
|
| 332 |
+
"decode_tokens_per_second": 29.72692407488236,
|
| 333 |
+
"e2e_seconds": 4.419439104036428,
|
| 334 |
+
"e2e_tokens_per_second": 28.962951403288514,
|
| 335 |
+
"index": 28,
|
| 336 |
+
"prompt_characters": 33
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"prompt_tokens": 138,
|
| 340 |
+
"completion_tokens": 128,
|
| 341 |
+
"ttft_ms": 152.53638400463387,
|
| 342 |
+
"decode_seconds": 4.275733312009834,
|
| 343 |
+
"decode_tokens_per_second": 29.702507320388253,
|
| 344 |
+
"e2e_seconds": 4.428269696014468,
|
| 345 |
+
"e2e_tokens_per_second": 28.905195208684464,
|
| 346 |
+
"index": 29,
|
| 347 |
+
"prompt_characters": 155
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"prompt_tokens": 89,
|
| 351 |
+
"completion_tokens": 128,
|
| 352 |
+
"ttft_ms": 147.56200002739206,
|
| 353 |
+
"decode_seconds": 4.27770995197352,
|
| 354 |
+
"decode_tokens_per_second": 29.688782415322148,
|
| 355 |
+
"e2e_seconds": 4.425271952000912,
|
| 356 |
+
"e2e_tokens_per_second": 28.924776011138494,
|
| 357 |
+
"index": 30,
|
| 358 |
+
"prompt_characters": 23
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"prompt_tokens": 122,
|
| 362 |
+
"completion_tokens": 128,
|
| 363 |
+
"ttft_ms": 149.15563201066107,
|
| 364 |
+
"decode_seconds": 4.275628671981394,
|
| 365 |
+
"decode_tokens_per_second": 29.703234247689284,
|
| 366 |
+
"e2e_seconds": 4.424784303992055,
|
| 367 |
+
"e2e_tokens_per_second": 28.927963761876022,
|
| 368 |
+
"index": 31,
|
| 369 |
+
"prompt_characters": 97
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"prompt_tokens": 94,
|
| 373 |
+
"completion_tokens": 128,
|
| 374 |
+
"ttft_ms": 145.9132640156895,
|
| 375 |
+
"decode_seconds": 4.272694383980706,
|
| 376 |
+
"decode_tokens_per_second": 29.723633049008047,
|
| 377 |
+
"e2e_seconds": 4.418607647996396,
|
| 378 |
+
"e2e_tokens_per_second": 28.96840140537058,
|
| 379 |
+
"index": 32,
|
| 380 |
+
"prompt_characters": 61
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"prompt_tokens": 132,
|
| 384 |
+
"completion_tokens": 128,
|
| 385 |
+
"ttft_ms": 153.64075201796368,
|
| 386 |
+
"decode_seconds": 4.272159695974551,
|
| 387 |
+
"decode_tokens_per_second": 29.72735315106922,
|
| 388 |
+
"e2e_seconds": 4.425800447992515,
|
| 389 |
+
"e2e_tokens_per_second": 28.921322030698228,
|
| 390 |
+
"index": 33,
|
| 391 |
+
"prompt_characters": 136
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"prompt_tokens": 114,
|
| 395 |
+
"completion_tokens": 128,
|
| 396 |
+
"ttft_ms": 148.47996801836416,
|
| 397 |
+
"decode_seconds": 4.275548528006766,
|
| 398 |
+
"decode_tokens_per_second": 29.70379102659995,
|
| 399 |
+
"e2e_seconds": 4.42402849602513,
|
| 400 |
+
"e2e_tokens_per_second": 28.93290586057584,
|
| 401 |
+
"index": 34,
|
| 402 |
+
"prompt_characters": 82
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"prompt_tokens": 97,
|
| 406 |
+
"completion_tokens": 128,
|
| 407 |
+
"ttft_ms": 147.8521599783562,
|
| 408 |
+
"decode_seconds": 4.273406176012941,
|
| 409 |
+
"decode_tokens_per_second": 29.71868218679137,
|
| 410 |
+
"e2e_seconds": 4.421258335991297,
|
| 411 |
+
"e2e_tokens_per_second": 28.95103390770332,
|
| 412 |
+
"index": 35,
|
| 413 |
+
"prompt_characters": 49
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"prompt_tokens": 116,
|
| 417 |
+
"completion_tokens": 128,
|
| 418 |
+
"ttft_ms": 147.574128000997,
|
| 419 |
+
"decode_seconds": 4.273268640041351,
|
| 420 |
+
"decode_tokens_per_second": 29.719638688283133,
|
| 421 |
+
"e2e_seconds": 4.420842768042348,
|
| 422 |
+
"e2e_tokens_per_second": 28.953755362053144,
|
| 423 |
+
"index": 36,
|
| 424 |
+
"prompt_characters": 101
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"prompt_tokens": 127,
|
| 428 |
+
"completion_tokens": 128,
|
| 429 |
+
"ttft_ms": 149.55046400427818,
|
| 430 |
+
"decode_seconds": 4.280436095956247,
|
| 431 |
+
"decode_tokens_per_second": 29.669874085955314,
|
| 432 |
+
"e2e_seconds": 4.4299865599605255,
|
| 433 |
+
"e2e_tokens_per_second": 28.893992852461515,
|
| 434 |
+
"index": 37,
|
| 435 |
+
"prompt_characters": 118
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"prompt_tokens": 99,
|
| 439 |
+
"completion_tokens": 128,
|
| 440 |
+
"ttft_ms": 146.9279839657247,
|
| 441 |
+
"decode_seconds": 4.2737699200515635,
|
| 442 |
+
"decode_tokens_per_second": 29.71615280554638,
|
| 443 |
+
"e2e_seconds": 4.420697904017288,
|
| 444 |
+
"e2e_tokens_per_second": 28.95470416191086,
|
| 445 |
+
"index": 38,
|
| 446 |
+
"prompt_characters": 44
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"prompt_tokens": 89,
|
| 450 |
+
"completion_tokens": 128,
|
| 451 |
+
"ttft_ms": 145.21406398853287,
|
| 452 |
+
"decode_seconds": 4.270830192021094,
|
| 453 |
+
"decode_tokens_per_second": 29.736607237924275,
|
| 454 |
+
"e2e_seconds": 4.416044256009627,
|
| 455 |
+
"e2e_tokens_per_second": 28.985216764032575,
|
| 456 |
+
"index": 39,
|
| 457 |
+
"prompt_characters": 21
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"prompt_tokens": 131,
|
| 461 |
+
"completion_tokens": 128,
|
| 462 |
+
"ttft_ms": 153.4373280010186,
|
| 463 |
+
"decode_seconds": 4.277822831994854,
|
| 464 |
+
"decode_tokens_per_second": 29.68799900971513,
|
| 465 |
+
"e2e_seconds": 4.4312601599958725,
|
| 466 |
+
"e2e_tokens_per_second": 28.885688354646103,
|
| 467 |
+
"index": 40,
|
| 468 |
+
"prompt_characters": 99
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"prompt_tokens": 164,
|
| 472 |
+
"completion_tokens": 128,
|
| 473 |
+
"ttft_ms": 152.07355201710016,
|
| 474 |
+
"decode_seconds": 4.281609760015272,
|
| 475 |
+
"decode_tokens_per_second": 29.66174105496878,
|
| 476 |
+
"e2e_seconds": 4.433683312032372,
|
| 477 |
+
"e2e_tokens_per_second": 28.86990138709876,
|
| 478 |
+
"index": 41,
|
| 479 |
+
"prompt_characters": 255
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"prompt_tokens": 119,
|
| 483 |
+
"completion_tokens": 128,
|
| 484 |
+
"ttft_ms": 147.45664002839476,
|
| 485 |
+
"decode_seconds": 4.278829519986175,
|
| 486 |
+
"decode_tokens_per_second": 29.6810142602761,
|
| 487 |
+
"e2e_seconds": 4.42628616001457,
|
| 488 |
+
"e2e_tokens_per_second": 28.918148391828936,
|
| 489 |
+
"index": 42,
|
| 490 |
+
"prompt_characters": 98
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"prompt_tokens": 109,
|
| 494 |
+
"completion_tokens": 128,
|
| 495 |
+
"ttft_ms": 148.86659203330055,
|
| 496 |
+
"decode_seconds": 4.27835519996006,
|
| 497 |
+
"decode_tokens_per_second": 29.684304847149104,
|
| 498 |
+
"e2e_seconds": 4.427221791993361,
|
| 499 |
+
"e2e_tokens_per_second": 28.912036941878142,
|
| 500 |
+
"index": 43,
|
| 501 |
+
"prompt_characters": 69
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"prompt_tokens": 116,
|
| 505 |
+
"completion_tokens": 128,
|
| 506 |
+
"ttft_ms": 149.5863359887153,
|
| 507 |
+
"decode_seconds": 4.2813182240352035,
|
| 508 |
+
"decode_tokens_per_second": 29.66376086856274,
|
| 509 |
+
"e2e_seconds": 4.430904560023919,
|
| 510 |
+
"e2e_tokens_per_second": 28.88800656074367,
|
| 511 |
+
"index": 44,
|
| 512 |
+
"prompt_characters": 63
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"prompt_tokens": 99,
|
| 516 |
+
"completion_tokens": 128,
|
| 517 |
+
"ttft_ms": 148.91756797442213,
|
| 518 |
+
"decode_seconds": 4.275036848033778,
|
| 519 |
+
"decode_tokens_per_second": 29.70734627899435,
|
| 520 |
+
"e2e_seconds": 4.4239544160082005,
|
| 521 |
+
"e2e_tokens_per_second": 28.93339034797205,
|
| 522 |
+
"index": 45,
|
| 523 |
+
"prompt_characters": 51
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"prompt_tokens": 87,
|
| 527 |
+
"completion_tokens": 128,
|
| 528 |
+
"ttft_ms": 181.61635199794546,
|
| 529 |
+
"decode_seconds": 4.241584288014565,
|
| 530 |
+
"decode_tokens_per_second": 29.94164240914972,
|
| 531 |
+
"e2e_seconds": 4.42320064001251,
|
| 532 |
+
"e2e_tokens_per_second": 28.938321007214807,
|
| 533 |
+
"index": 46,
|
| 534 |
+
"prompt_characters": 16
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"prompt_tokens": 121,
|
| 538 |
+
"completion_tokens": 128,
|
| 539 |
+
"ttft_ms": 149.99320002971217,
|
| 540 |
+
"decode_seconds": 4.277360575972125,
|
| 541 |
+
"decode_tokens_per_second": 29.69120740332639,
|
| 542 |
+
"e2e_seconds": 4.427353776001837,
|
| 543 |
+
"e2e_tokens_per_second": 28.911175044066976,
|
| 544 |
+
"index": 47,
|
| 545 |
+
"prompt_characters": 83
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"prompt_tokens": 103,
|
| 549 |
+
"completion_tokens": 128,
|
| 550 |
+
"ttft_ms": 150.74512001592666,
|
| 551 |
+
"decode_seconds": 4.27451617596671,
|
| 552 |
+
"decode_tokens_per_second": 29.710964883944584,
|
| 553 |
+
"e2e_seconds": 4.4252612959826365,
|
| 554 |
+
"e2e_tokens_per_second": 28.92484566192772,
|
| 555 |
+
"index": 48,
|
| 556 |
+
"prompt_characters": 52
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"prompt_tokens": 128,
|
| 560 |
+
"completion_tokens": 128,
|
| 561 |
+
"ttft_ms": 148.76968000316992,
|
| 562 |
+
"decode_seconds": 4.281864800024778,
|
| 563 |
+
"decode_tokens_per_second": 29.659974317560213,
|
| 564 |
+
"e2e_seconds": 4.430634480027948,
|
| 565 |
+
"e2e_tokens_per_second": 28.88976749876072,
|
| 566 |
+
"index": 49,
|
| 567 |
+
"prompt_characters": 82
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"prompt_tokens": 116,
|
| 571 |
+
"completion_tokens": 128,
|
| 572 |
+
"ttft_ms": 148.97512004245073,
|
| 573 |
+
"decode_seconds": 4.279575983993709,
|
| 574 |
+
"decode_tokens_per_second": 29.675837156531415,
|
| 575 |
+
"e2e_seconds": 4.42855110403616,
|
| 576 |
+
"e2e_tokens_per_second": 28.90335845584833,
|
| 577 |
+
"index": 50,
|
| 578 |
+
"prompt_characters": 89
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"prompt_tokens": 202,
|
| 582 |
+
"completion_tokens": 128,
|
| 583 |
+
"ttft_ms": 159.03887996682897,
|
| 584 |
+
"decode_seconds": 4.285158192040399,
|
| 585 |
+
"decode_tokens_per_second": 29.637178911131013,
|
| 586 |
+
"e2e_seconds": 4.444197072007228,
|
| 587 |
+
"e2e_tokens_per_second": 28.801603062617705,
|
| 588 |
+
"index": 51,
|
| 589 |
+
"prompt_characters": 202
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"prompt_tokens": 133,
|
| 593 |
+
"completion_tokens": 128,
|
| 594 |
+
"ttft_ms": 150.73892794316635,
|
| 595 |
+
"decode_seconds": 4.277238800015766,
|
| 596 |
+
"decode_tokens_per_second": 29.692052732602132,
|
| 597 |
+
"e2e_seconds": 4.4279777279589325,
|
| 598 |
+
"e2e_tokens_per_second": 28.9071011337271,
|
| 599 |
+
"index": 52,
|
| 600 |
+
"prompt_characters": 73
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"prompt_tokens": 97,
|
| 604 |
+
"completion_tokens": 128,
|
| 605 |
+
"ttft_ms": 148.48937600618228,
|
| 606 |
+
"decode_seconds": 4.274834448006004,
|
| 607 |
+
"decode_tokens_per_second": 29.708752828835074,
|
| 608 |
+
"e2e_seconds": 4.423323824012186,
|
| 609 |
+
"e2e_tokens_per_second": 28.937515111407173,
|
| 610 |
+
"index": 53,
|
| 611 |
+
"prompt_characters": 42
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"prompt_tokens": 208,
|
| 615 |
+
"completion_tokens": 128,
|
| 616 |
+
"ttft_ms": 160.55590397445485,
|
| 617 |
+
"decode_seconds": 4.285696112026926,
|
| 618 |
+
"decode_tokens_per_second": 29.633458994817804,
|
| 619 |
+
"e2e_seconds": 4.446252016001381,
|
| 620 |
+
"e2e_tokens_per_second": 28.78829169811958,
|
| 621 |
+
"index": 54,
|
| 622 |
+
"prompt_characters": 254
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"prompt_tokens": 113,
|
| 626 |
+
"completion_tokens": 128,
|
| 627 |
+
"ttft_ms": 148.43628800008446,
|
| 628 |
+
"decode_seconds": 4.276303727994673,
|
| 629 |
+
"decode_tokens_per_second": 29.698545304113676,
|
| 630 |
+
"e2e_seconds": 4.424740015994757,
|
| 631 |
+
"e2e_tokens_per_second": 28.92825330692868,
|
| 632 |
+
"index": 55,
|
| 633 |
+
"prompt_characters": 85
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"prompt_tokens": 127,
|
| 637 |
+
"completion_tokens": 128,
|
| 638 |
+
"ttft_ms": 182.12604796281084,
|
| 639 |
+
"decode_seconds": 4.240071760024875,
|
| 640 |
+
"decode_tokens_per_second": 29.952323259560806,
|
| 641 |
+
"e2e_seconds": 4.422197807987686,
|
| 642 |
+
"e2e_tokens_per_second": 28.94488341719978,
|
| 643 |
+
"index": 56,
|
| 644 |
+
"prompt_characters": 107
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"prompt_tokens": 144,
|
| 648 |
+
"completion_tokens": 128,
|
| 649 |
+
"ttft_ms": 185.98363199271262,
|
| 650 |
+
"decode_seconds": 4.249349439982325,
|
| 651 |
+
"decode_tokens_per_second": 29.88692782124509,
|
| 652 |
+
"e2e_seconds": 4.4353330719750375,
|
| 653 |
+
"e2e_tokens_per_second": 28.859162981192316,
|
| 654 |
+
"index": 57,
|
| 655 |
+
"prompt_characters": 121
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"prompt_tokens": 230,
|
| 659 |
+
"completion_tokens": 128,
|
| 660 |
+
"ttft_ms": 162.00067201862112,
|
| 661 |
+
"decode_seconds": 4.287982367968652,
|
| 662 |
+
"decode_tokens_per_second": 29.617659099695356,
|
| 663 |
+
"e2e_seconds": 4.4499830399872735,
|
| 664 |
+
"e2e_tokens_per_second": 28.764154570882603,
|
| 665 |
+
"index": 58,
|
| 666 |
+
"prompt_characters": 346
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"prompt_tokens": 124,
|
| 670 |
+
"completion_tokens": 128,
|
| 671 |
+
"ttft_ms": 183.87990404153243,
|
| 672 |
+
"decode_seconds": 4.242221055959817,
|
| 673 |
+
"decode_tokens_per_second": 29.937148094057964,
|
| 674 |
+
"e2e_seconds": 4.4261009600013494,
|
| 675 |
+
"e2e_tokens_per_second": 28.91935840522738,
|
| 676 |
+
"index": 59,
|
| 677 |
+
"prompt_characters": 93
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"prompt_tokens": 170,
|
| 681 |
+
"completion_tokens": 128,
|
| 682 |
+
"ttft_ms": 152.916015998926,
|
| 683 |
+
"decode_seconds": 4.2795338880387135,
|
| 684 |
+
"decode_tokens_per_second": 29.67612906512195,
|
| 685 |
+
"e2e_seconds": 4.4324499040376395,
|
| 686 |
+
"e2e_tokens_per_second": 28.8779349504664,
|
| 687 |
+
"index": 60,
|
| 688 |
+
"prompt_characters": 207
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"prompt_tokens": 148,
|
| 692 |
+
"completion_tokens": 128,
|
| 693 |
+
"ttft_ms": 153.09798397356644,
|
| 694 |
+
"decode_seconds": 4.275488400016911,
|
| 695 |
+
"decode_tokens_per_second": 29.70420876349417,
|
| 696 |
+
"e2e_seconds": 4.428586383990478,
|
| 697 |
+
"e2e_tokens_per_second": 28.90312819971747,
|
| 698 |
+
"index": 61,
|
| 699 |
+
"prompt_characters": 122
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"prompt_tokens": 123,
|
| 703 |
+
"completion_tokens": 128,
|
| 704 |
+
"ttft_ms": 149.6343039907515,
|
| 705 |
+
"decode_seconds": 4.274956831999589,
|
| 706 |
+
"decode_tokens_per_second": 29.707902322980047,
|
| 707 |
+
"e2e_seconds": 4.42459113599034,
|
| 708 |
+
"e2e_tokens_per_second": 28.929226693699963,
|
| 709 |
+
"index": 62,
|
| 710 |
+
"prompt_characters": 88
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"prompt_tokens": 98,
|
| 714 |
+
"completion_tokens": 128,
|
| 715 |
+
"ttft_ms": 150.04775999113917,
|
| 716 |
+
"decode_seconds": 4.279320368019398,
|
| 717 |
+
"decode_tokens_per_second": 29.677609778671357,
|
| 718 |
+
"e2e_seconds": 4.4293681280105375,
|
| 719 |
+
"e2e_tokens_per_second": 28.898027055044427,
|
| 720 |
+
"index": 63,
|
| 721 |
+
"prompt_characters": 43
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"prompt_tokens": 196,
|
| 725 |
+
"completion_tokens": 128,
|
| 726 |
+
"ttft_ms": 160.95686401240528,
|
| 727 |
+
"decode_seconds": 4.288259503955487,
|
| 728 |
+
"decode_tokens_per_second": 29.615745008634693,
|
| 729 |
+
"e2e_seconds": 4.449216367967892,
|
| 730 |
+
"e2e_tokens_per_second": 28.769111100447994,
|
| 731 |
+
"index": 64,
|
| 732 |
+
"prompt_characters": 177
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"prompt_tokens": 280,
|
| 736 |
+
"completion_tokens": 128,
|
| 737 |
+
"ttft_ms": 194.86894400324672,
|
| 738 |
+
"decode_seconds": 4.253986447991338,
|
| 739 |
+
"decode_tokens_per_second": 29.85434992628322,
|
| 740 |
+
"e2e_seconds": 4.448855391994584,
|
| 741 |
+
"e2e_tokens_per_second": 28.771445399265478,
|
| 742 |
+
"index": 65,
|
| 743 |
+
"prompt_characters": 494
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"prompt_tokens": 100,
|
| 747 |
+
"completion_tokens": 128,
|
| 748 |
+
"ttft_ms": 146.7246399843134,
|
| 749 |
+
"decode_seconds": 4.280999056005385,
|
| 750 |
+
"decode_tokens_per_second": 29.665972437402065,
|
| 751 |
+
"e2e_seconds": 4.427723695989698,
|
| 752 |
+
"e2e_tokens_per_second": 28.908759622000094,
|
| 753 |
+
"index": 66,
|
| 754 |
+
"prompt_characters": 56
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"prompt_tokens": 111,
|
| 758 |
+
"completion_tokens": 128,
|
| 759 |
+
"ttft_ms": 149.47828801814467,
|
| 760 |
+
"decode_seconds": 4.27679667196935,
|
| 761 |
+
"decode_tokens_per_second": 29.695122247071872,
|
| 762 |
+
"e2e_seconds": 4.426274959987495,
|
| 763 |
+
"e2e_tokens_per_second": 28.918221564880284,
|
| 764 |
+
"index": 67,
|
| 765 |
+
"prompt_characters": 68
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"prompt_tokens": 222,
|
| 769 |
+
"completion_tokens": 128,
|
| 770 |
+
"ttft_ms": 161.32521600229666,
|
| 771 |
+
"decode_seconds": 4.284537935978733,
|
| 772 |
+
"decode_tokens_per_second": 29.64146937141984,
|
| 773 |
+
"e2e_seconds": 4.44586315198103,
|
| 774 |
+
"e2e_tokens_per_second": 28.790809708788395,
|
| 775 |
+
"index": 68,
|
| 776 |
+
"prompt_characters": 333
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"prompt_tokens": 86,
|
| 780 |
+
"completion_tokens": 128,
|
| 781 |
+
"ttft_ms": 149.98059201752767,
|
| 782 |
+
"decode_seconds": 4.274428736011032,
|
| 783 |
+
"decode_tokens_per_second": 29.71157266702229,
|
| 784 |
+
"e2e_seconds": 4.42440932802856,
|
| 785 |
+
"e2e_tokens_per_second": 28.93041545435729,
|
| 786 |
+
"index": 69,
|
| 787 |
+
"prompt_characters": 20
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"prompt_tokens": 116,
|
| 791 |
+
"completion_tokens": 128,
|
| 792 |
+
"ttft_ms": 148.25239998754114,
|
| 793 |
+
"decode_seconds": 4.280142048024572,
|
| 794 |
+
"decode_tokens_per_second": 29.671912421368052,
|
| 795 |
+
"e2e_seconds": 4.428394448012114,
|
| 796 |
+
"e2e_tokens_per_second": 28.904380922403746,
|
| 797 |
+
"index": 70,
|
| 798 |
+
"prompt_characters": 70
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"prompt_tokens": 122,
|
| 802 |
+
"completion_tokens": 128,
|
| 803 |
+
"ttft_ms": 151.68241603532806,
|
| 804 |
+
"decode_seconds": 4.279039520013612,
|
| 805 |
+
"decode_tokens_per_second": 29.679557621752465,
|
| 806 |
+
"e2e_seconds": 4.43072193604894,
|
| 807 |
+
"e2e_tokens_per_second": 28.88919725667618,
|
| 808 |
+
"index": 71,
|
| 809 |
+
"prompt_characters": 100
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"prompt_tokens": 123,
|
| 813 |
+
"completion_tokens": 128,
|
| 814 |
+
"ttft_ms": 182.6112479902804,
|
| 815 |
+
"decode_seconds": 4.241006672033109,
|
| 816 |
+
"decode_tokens_per_second": 29.94572039640699,
|
| 817 |
+
"e2e_seconds": 4.423617920023389,
|
| 818 |
+
"e2e_tokens_per_second": 28.93559125452752,
|
| 819 |
+
"index": 72,
|
| 820 |
+
"prompt_characters": 100
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"prompt_tokens": 304,
|
| 824 |
+
"completion_tokens": 128,
|
| 825 |
+
"ttft_ms": 160.21692799404263,
|
| 826 |
+
"decode_seconds": 4.284923232044093,
|
| 827 |
+
"decode_tokens_per_second": 29.638804039767013,
|
| 828 |
+
"e2e_seconds": 4.445140160038136,
|
| 829 |
+
"e2e_tokens_per_second": 28.795492468543863,
|
| 830 |
+
"index": 73,
|
| 831 |
+
"prompt_characters": 516
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"prompt_tokens": 96,
|
| 835 |
+
"completion_tokens": 128,
|
| 836 |
+
"ttft_ms": 145.91110398760065,
|
| 837 |
+
"decode_seconds": 4.27431379200425,
|
| 838 |
+
"decode_tokens_per_second": 29.712371664797445,
|
| 839 |
+
"e2e_seconds": 4.420224895991851,
|
| 840 |
+
"e2e_tokens_per_second": 28.957802603226636,
|
| 841 |
+
"index": 74,
|
| 842 |
+
"prompt_characters": 51
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"prompt_tokens": 98,
|
| 846 |
+
"completion_tokens": 128,
|
| 847 |
+
"ttft_ms": 182.3572000139393,
|
| 848 |
+
"decode_seconds": 4.2468398079508916,
|
| 849 |
+
"decode_tokens_per_second": 29.904589234148144,
|
| 850 |
+
"e2e_seconds": 4.429197007964831,
|
| 851 |
+
"e2e_tokens_per_second": 28.899143517396766,
|
| 852 |
+
"index": 75,
|
| 853 |
+
"prompt_characters": 38
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"prompt_tokens": 146,
|
| 857 |
+
"completion_tokens": 128,
|
| 858 |
+
"ttft_ms": 152.6936799637042,
|
| 859 |
+
"decode_seconds": 4.277269551996142,
|
| 860 |
+
"decode_tokens_per_second": 29.691839257764542,
|
| 861 |
+
"e2e_seconds": 4.429963231959846,
|
| 862 |
+
"e2e_tokens_per_second": 28.894145007016668,
|
| 863 |
+
"index": 76,
|
| 864 |
+
"prompt_characters": 133
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"prompt_tokens": 140,
|
| 868 |
+
"completion_tokens": 128,
|
| 869 |
+
"ttft_ms": 152.17240003403276,
|
| 870 |
+
"decode_seconds": 4.280287823989056,
|
| 871 |
+
"decode_tokens_per_second": 29.67090186978153,
|
| 872 |
+
"e2e_seconds": 4.432460224023089,
|
| 873 |
+
"e2e_tokens_per_second": 28.87786771469813,
|
| 874 |
+
"index": 77,
|
| 875 |
+
"prompt_characters": 158
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"prompt_tokens": 89,
|
| 879 |
+
"completion_tokens": 128,
|
| 880 |
+
"ttft_ms": 147.72603200981393,
|
| 881 |
+
"decode_seconds": 4.280198383959942,
|
| 882 |
+
"decode_tokens_per_second": 29.671521879904667,
|
| 883 |
+
"e2e_seconds": 4.4279244159697555,
|
| 884 |
+
"e2e_tokens_per_second": 28.90744917378334,
|
| 885 |
+
"index": 78,
|
| 886 |
+
"prompt_characters": 17
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"prompt_tokens": 163,
|
| 890 |
+
"completion_tokens": 128,
|
| 891 |
+
"ttft_ms": 186.45403202390298,
|
| 892 |
+
"decode_seconds": 4.244761504000053,
|
| 893 |
+
"decode_tokens_per_second": 29.919231005162832,
|
| 894 |
+
"e2e_seconds": 4.431215536023956,
|
| 895 |
+
"e2e_tokens_per_second": 28.88597924416286,
|
| 896 |
+
"index": 79,
|
| 897 |
+
"prompt_characters": 193
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"prompt_tokens": 154,
|
| 901 |
+
"completion_tokens": 128,
|
| 902 |
+
"ttft_ms": 152.16956799849868,
|
| 903 |
+
"decode_seconds": 4.277686815999914,
|
| 904 |
+
"decode_tokens_per_second": 29.68894298782685,
|
| 905 |
+
"e2e_seconds": 4.429856383998413,
|
| 906 |
+
"e2e_tokens_per_second": 28.894841932655726,
|
| 907 |
+
"index": 80,
|
| 908 |
+
"prompt_characters": 151
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"prompt_tokens": 119,
|
| 912 |
+
"completion_tokens": 128,
|
| 913 |
+
"ttft_ms": 147.88078400306404,
|
| 914 |
+
"decode_seconds": 4.278590032015927,
|
| 915 |
+
"decode_tokens_per_second": 29.682675612685866,
|
| 916 |
+
"e2e_seconds": 4.426470816018991,
|
| 917 |
+
"e2e_tokens_per_second": 28.916942033545045,
|
| 918 |
+
"index": 81,
|
| 919 |
+
"prompt_characters": 75
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"prompt_tokens": 274,
|
| 923 |
+
"completion_tokens": 128,
|
| 924 |
+
"ttft_ms": 158.65448000840843,
|
| 925 |
+
"decode_seconds": 4.288939487945754,
|
| 926 |
+
"decode_tokens_per_second": 29.611049621226616,
|
| 927 |
+
"e2e_seconds": 4.4475939679541625,
|
| 928 |
+
"e2e_tokens_per_second": 28.779605540044024,
|
| 929 |
+
"index": 82,
|
| 930 |
+
"prompt_characters": 413
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"prompt_tokens": 96,
|
| 934 |
+
"completion_tokens": 128,
|
| 935 |
+
"ttft_ms": 151.030623994302,
|
| 936 |
+
"decode_seconds": 4.277100688021164,
|
| 937 |
+
"decode_tokens_per_second": 29.693011519623024,
|
| 938 |
+
"e2e_seconds": 4.428131312015466,
|
| 939 |
+
"e2e_tokens_per_second": 28.906098527990746,
|
| 940 |
+
"index": 83,
|
| 941 |
+
"prompt_characters": 53
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"prompt_tokens": 187,
|
| 945 |
+
"completion_tokens": 128,
|
| 946 |
+
"ttft_ms": 153.6058560013771,
|
| 947 |
+
"decode_seconds": 4.2891785760293715,
|
| 948 |
+
"decode_tokens_per_second": 29.609399037325215,
|
| 949 |
+
"e2e_seconds": 4.442784432030749,
|
| 950 |
+
"e2e_tokens_per_second": 28.810760899666832,
|
| 951 |
+
"index": 84,
|
| 952 |
+
"prompt_characters": 243
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"prompt_tokens": 175,
|
| 956 |
+
"completion_tokens": 128,
|
| 957 |
+
"ttft_ms": 150.53255995735526,
|
| 958 |
+
"decode_seconds": 4.287062800023705,
|
| 959 |
+
"decode_tokens_per_second": 29.62401203903469,
|
| 960 |
+
"e2e_seconds": 4.43759535998106,
|
| 961 |
+
"e2e_tokens_per_second": 28.844450567603424,
|
| 962 |
+
"index": 85,
|
| 963 |
+
"prompt_characters": 193
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"prompt_tokens": 95,
|
| 967 |
+
"completion_tokens": 128,
|
| 968 |
+
"ttft_ms": 146.89548802562058,
|
| 969 |
+
"decode_seconds": 4.2793887840234675,
|
| 970 |
+
"decode_tokens_per_second": 29.677135312906767,
|
| 971 |
+
"e2e_seconds": 4.426284272049088,
|
| 972 |
+
"e2e_tokens_per_second": 28.91816072643345,
|
| 973 |
+
"index": 86,
|
| 974 |
+
"prompt_characters": 54
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"prompt_tokens": 135,
|
| 978 |
+
"completion_tokens": 128,
|
| 979 |
+
"ttft_ms": 152.44775998871773,
|
| 980 |
+
"decode_seconds": 4.279913456004579,
|
| 981 |
+
"decode_tokens_per_second": 29.673497210982887,
|
| 982 |
+
"e2e_seconds": 4.432361215993296,
|
| 983 |
+
"e2e_tokens_per_second": 28.878512775118008,
|
| 984 |
+
"index": 87,
|
| 985 |
+
"prompt_characters": 153
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"prompt_tokens": 132,
|
| 989 |
+
"completion_tokens": 128,
|
| 990 |
+
"ttft_ms": 152.3534239968285,
|
| 991 |
+
"decode_seconds": 4.280044800019823,
|
| 992 |
+
"decode_tokens_per_second": 29.67258660456353,
|
| 993 |
+
"e2e_seconds": 4.4323982240166515,
|
| 994 |
+
"e2e_tokens_per_second": 28.878271655836475,
|
| 995 |
+
"index": 88,
|
| 996 |
+
"prompt_characters": 83
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"prompt_tokens": 151,
|
| 1000 |
+
"completion_tokens": 128,
|
| 1001 |
+
"ttft_ms": 152.58678403915837,
|
| 1002 |
+
"decode_seconds": 4.286318383994512,
|
| 1003 |
+
"decode_tokens_per_second": 29.629156918027626,
|
| 1004 |
+
"e2e_seconds": 4.438905168033671,
|
| 1005 |
+
"e2e_tokens_per_second": 28.8359393036326,
|
| 1006 |
+
"index": 89,
|
| 1007 |
+
"prompt_characters": 154
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"prompt_tokens": 98,
|
| 1011 |
+
"completion_tokens": 128,
|
| 1012 |
+
"ttft_ms": 149.5123039931059,
|
| 1013 |
+
"decode_seconds": 4.2784633280243725,
|
| 1014 |
+
"decode_tokens_per_second": 29.68355464639302,
|
| 1015 |
+
"e2e_seconds": 4.427975632017478,
|
| 1016 |
+
"e2e_tokens_per_second": 28.90711481663699,
|
| 1017 |
+
"index": 90,
|
| 1018 |
+
"prompt_characters": 47
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"prompt_tokens": 120,
|
| 1022 |
+
"completion_tokens": 128,
|
| 1023 |
+
"ttft_ms": 149.92755197454244,
|
| 1024 |
+
"decode_seconds": 4.279246336023789,
|
| 1025 |
+
"decode_tokens_per_second": 29.67812320849154,
|
| 1026 |
+
"e2e_seconds": 4.429173887998331,
|
| 1027 |
+
"e2e_tokens_per_second": 28.899294368830212,
|
| 1028 |
+
"index": 91,
|
| 1029 |
+
"prompt_characters": 91
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"prompt_tokens": 129,
|
| 1033 |
+
"completion_tokens": 128,
|
| 1034 |
+
"ttft_ms": 149.91504000499845,
|
| 1035 |
+
"decode_seconds": 4.284216400003061,
|
| 1036 |
+
"decode_tokens_per_second": 29.643694001990486,
|
| 1037 |
+
"e2e_seconds": 4.434131440008059,
|
| 1038 |
+
"e2e_tokens_per_second": 28.86698369946547,
|
| 1039 |
+
"index": 92,
|
| 1040 |
+
"prompt_characters": 149
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"prompt_tokens": 126,
|
| 1044 |
+
"completion_tokens": 128,
|
| 1045 |
+
"ttft_ms": 148.77603197237477,
|
| 1046 |
+
"decode_seconds": 4.277493072033394,
|
| 1047 |
+
"decode_tokens_per_second": 29.690287713225434,
|
| 1048 |
+
"e2e_seconds": 4.426269104005769,
|
| 1049 |
+
"e2e_tokens_per_second": 28.9182598238684,
|
| 1050 |
+
"index": 93,
|
| 1051 |
+
"prompt_characters": 129
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"prompt_tokens": 176,
|
| 1055 |
+
"completion_tokens": 128,
|
| 1056 |
+
"ttft_ms": 150.4963680054061,
|
| 1057 |
+
"decode_seconds": 4.283495743991807,
|
| 1058 |
+
"decode_tokens_per_second": 29.648681261825693,
|
| 1059 |
+
"e2e_seconds": 4.433992111997213,
|
| 1060 |
+
"e2e_tokens_per_second": 28.86789077807914,
|
| 1061 |
+
"index": 94,
|
| 1062 |
+
"prompt_characters": 181
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"prompt_tokens": 151,
|
| 1066 |
+
"completion_tokens": 128,
|
| 1067 |
+
"ttft_ms": 151.79175999946892,
|
| 1068 |
+
"decode_seconds": 4.284410799969919,
|
| 1069 |
+
"decode_tokens_per_second": 29.642348955168274,
|
| 1070 |
+
"e2e_seconds": 4.436202559969388,
|
| 1071 |
+
"e2e_tokens_per_second": 28.853506635387557,
|
| 1072 |
+
"index": 95,
|
| 1073 |
+
"prompt_characters": 182
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"prompt_tokens": 113,
|
| 1077 |
+
"completion_tokens": 128,
|
| 1078 |
+
"ttft_ms": 147.12048001820222,
|
| 1079 |
+
"decode_seconds": 4.276005279971287,
|
| 1080 |
+
"decode_tokens_per_second": 29.700618143496026,
|
| 1081 |
+
"e2e_seconds": 4.423125759989489,
|
| 1082 |
+
"e2e_tokens_per_second": 28.93881091011624,
|
| 1083 |
+
"index": 96,
|
| 1084 |
+
"prompt_characters": 72
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"prompt_tokens": 159,
|
| 1088 |
+
"completion_tokens": 128,
|
| 1089 |
+
"ttft_ms": 152.09144004620612,
|
| 1090 |
+
"decode_seconds": 4.281069583958015,
|
| 1091 |
+
"decode_tokens_per_second": 29.665483708999556,
|
| 1092 |
+
"e2e_seconds": 4.433161024004221,
|
| 1093 |
+
"e2e_tokens_per_second": 28.873302663025065,
|
| 1094 |
+
"index": 97,
|
| 1095 |
+
"prompt_characters": 144
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"prompt_tokens": 135,
|
| 1099 |
+
"completion_tokens": 128,
|
| 1100 |
+
"ttft_ms": 156.03772801114246,
|
| 1101 |
+
"decode_seconds": 4.28199811198283,
|
| 1102 |
+
"decode_tokens_per_second": 29.659050910041422,
|
| 1103 |
+
"e2e_seconds": 4.438035839993972,
|
| 1104 |
+
"e2e_tokens_per_second": 28.84158772367504,
|
| 1105 |
+
"index": 98,
|
| 1106 |
+
"prompt_characters": 146
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"prompt_tokens": 183,
|
| 1110 |
+
"completion_tokens": 128,
|
| 1111 |
+
"ttft_ms": 154.6247520018369,
|
| 1112 |
+
"decode_seconds": 4.2839804160175845,
|
| 1113 |
+
"decode_tokens_per_second": 29.64532693127015,
|
| 1114 |
+
"e2e_seconds": 4.438605168019421,
|
| 1115 |
+
"e2e_tokens_per_second": 28.837888290279196,
|
| 1116 |
+
"index": 99,
|
| 1117 |
+
"prompt_characters": 214
|
| 1118 |
+
}
|
| 1119 |
+
]
|
| 1120 |
+
}
|
benchmark/bf16-elyza100-streaming.csv
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
prompt_tokens,completion_tokens,ttft_ms,decode_seconds,decode_tokens_per_second,e2e_seconds,e2e_tokens_per_second,index,prompt_characters
|
| 2 |
+
89,128,287.3321439838037,8.779072656005155,14.466220405765533,9.066404799988959,14.118054821482918,0,28
|
| 3 |
+
100,128,295.72676797397435,8.767456800036598,14.485386457731947,9.063183568010572,14.123072653166709,1,50
|
| 4 |
+
86,128,290.60323198791593,8.77216342400061,14.477614456261545,9.062766655988526,14.123722353087368,2,24
|
| 5 |
+
223,128,304.505567997694,8.789692880003713,14.448741467283934,9.094198448001407,14.074907286428306,3,323
|
| 6 |
+
87,128,289.189808012452,8.793557535973378,14.442391430369154,9.08274734398583,14.092652272746044,4,15
|
| 7 |
+
138,128,298.6349919810891,8.804777184035629,14.42398794943612,9.103412176016718,14.06066181834772,5,107
|
| 8 |
+
197,128,304.21625601593405,8.81909500801703,14.400570566996976,9.123311264032964,14.029993748499768,6,286
|
| 9 |
+
129,128,299.53299200860783,8.820546608010773,14.398200660791169,9.12007960001938,14.034965221107061,7,77
|
| 10 |
+
253,128,309.5190239837393,8.817294720036443,14.403510830981398,9.126813744020183,14.024609638151606,8,359
|
| 11 |
+
107,128,299.14905602345243,8.819510432018433,14.399892259205004,9.118659488041885,14.037150983415694,9,76
|
| 12 |
+
115,128,296.4645279571414,8.813084144028835,14.410392312666938,9.109548671985976,14.051190087345422,10,93
|
| 13 |
+
136,128,370.15520001295954,8.748351391986944,14.517020900226493,9.118506591999903,14.037386353627298,11,126
|
| 14 |
+
239,128,309.37422398710623,8.829718319990207,14.383244787376283,9.139092543977313,14.005766916579956,12,301
|
| 15 |
+
113,128,297.8560159681365,8.81552940804977,14.406395137656943,9.113385424017906,14.045274510464784,13,76
|
| 16 |
+
239,128,309.5741919823922,8.828813120024279,14.384719471743757,9.138387312006671,14.00684777628372,14,323
|
| 17 |
+
122,128,370.8477119798772,8.738631952030119,14.533167284897031,9.109479664009996,14.051296530767418,15,120
|
| 18 |
+
152,128,300.2828800235875,8.817734479962382,14.402792496031452,9.11801735998597,14.038139536970235,16,182
|
| 19 |
+
141,128,298.9331199787557,8.812246479967143,14.411762118627612,9.111179599945899,14.04867488297125,17,140
|
| 20 |
+
196,128,304.14611200103536,8.825933744024951,14.389412348124349,9.130079856025986,14.019592601429233,18,191
|
| 21 |
+
118,128,296.74635198898613,8.812764559988864,14.410914887775066,9.10951091197785,14.05124833120253,19,75
|
| 22 |
+
269,128,309.93571202270687,8.82683105597971,14.38794955908488,9.136766768002417,14.009332102934351,20,368
|
| 23 |
+
151,128,371.7997280182317,8.751005103986245,14.512618663900579,9.122804832004476,14.030772592103743,21,137
|
| 24 |
+
83,128,368.71777597116306,8.740428032004274,14.53018084869209,9.109145807975437,14.051811519794827,22,8
|
| 25 |
+
257,128,310.9340959927067,8.822712880035397,14.394665419452082,9.133646976028103,14.014117289177584,23,379
|
| 26 |
+
264,128,312.00308800907806,8.822620527993422,14.394816097670736,9.1346236160025,14.012618951892343,24,480
|
| 27 |
+
115,128,368.4656799887307,8.752178527996875,14.5106729248891,9.120644207985606,14.034096395069247,25,82
|
| 28 |
+
167,128,300.1571359927766,8.814201600034721,14.408565376982041,9.114358736027498,14.043774631564363,26,145
|
| 29 |
+
86,128,288.03827200317755,8.810084576020017,14.41529861650575,9.098122848023195,14.068836191611915,27,11
|
| 30 |
+
95,128,290.33766401698813,8.809145903971512,14.416834660752226,9.0994835679885,14.066732363834053,28,33
|
| 31 |
+
138,128,300.13843200867996,8.82354910398135,14.393301210586026,9.12368753599003,14.029415134514519,29,155
|
| 32 |
+
89,128,291.2958399974741,8.811235280008987,14.413416049408962,9.10253112000646,14.062022783824236,30,23
|
| 33 |
+
122,128,298.4383839648217,8.810073536005802,14.415316680498178,9.108511919970624,14.05278942648766,31,97
|
| 34 |
+
94,128,287.24841598886997,8.81881228799466,14.401032231164425,9.10606070398353,14.05657222820898,32,61
|
| 35 |
+
132,128,298.8155360217206,8.817851200001314,14.402601849301004,9.116666736023035,14.040219271614777,33,136
|
| 36 |
+
114,128,297.1212000120431,8.809575375984423,14.416131831530919,9.106696575996466,14.055590732800283,34,82
|
| 37 |
+
97,128,297.4157760036178,8.811500575975515,14.412982091411816,9.108916351979133,14.05216548861917,35,49
|
| 38 |
+
116,128,295.1624320121482,8.818597696023062,14.401382666234271,9.11376012803521,14.044697051687148,36,101
|
| 39 |
+
127,128,294.031776022166,8.825343439995777,14.390374818100085,9.119375216017943,14.036049287145392,37,118
|
| 40 |
+
99,128,298.44286397565156,8.810942688025534,14.413894687182415,9.109385552001186,14.051441699257142,38,44
|
| 41 |
+
89,128,290.05577601492405,8.821949823992327,14.395910488473717,9.112005600007251,14.047401375598161,39,21
|
| 42 |
+
131,128,297.30228800326586,8.816554000019096,14.404720937423502,9.113856288022362,14.044548866567112,40,99
|
| 43 |
+
164,128,299.2388000129722,8.815770207962487,14.406001631631959,9.115009007975459,14.04277273758067,41,255
|
| 44 |
+
119,128,297.0329279778525,8.812944128003437,14.410621258388904,9.10997705598129,14.050529349682579,42,98
|
| 45 |
+
109,128,299.9312960309908,8.82349996798439,14.393381363496673,9.12343126401538,14.029809212774731,43,69
|
| 46 |
+
116,128,296.43854399910197,8.814559072023258,14.407981041625595,9.11099761602236,14.048955492525053,44,63
|
| 47 |
+
99,128,296.96737602353096,8.8147550720023,14.407660673792442,9.11172244802583,14.047837906622455,45,51
|
| 48 |
+
87,128,362.1777279768139,8.752297568018548,14.510475565189427,9.114475295995362,14.043595033522063,46,16
|
| 49 |
+
121,128,299.46691199438646,8.81550879997667,14.406428815581934,9.114975711971056,14.04282403428597,47,83
|
| 50 |
+
103,128,297.9078239877708,8.816075871989597,14.405502158109133,9.113983695977367,14.044352532306512,48,52
|
| 51 |
+
128,128,296.2054240051657,8.818844111985527,14.400980263093285,9.115049535990693,14.042710299553846,49,82
|
| 52 |
+
116,128,296.5520319994539,8.82329428801313,14.393716887867562,9.119846320012584,14.03532422680379,50,89
|
| 53 |
+
202,128,303.8067359593697,8.820766672026366,14.397841448721225,9.124573407985736,14.02805306908657,51,202
|
| 54 |
+
133,128,296.68961599236354,8.814125408011023,14.408689929073581,9.110815024003386,14.049237050996068,52,73
|
| 55 |
+
97,128,296.0946400417015,8.822594399971422,14.39485872776962,9.118689040013123,14.037105491626216,53,42
|
| 56 |
+
208,128,304.0414240094833,8.82271115196636,14.394668238877447,9.126752575975843,14.02470363192837,54,254
|
| 57 |
+
113,128,296.58384004142135,8.816141712013632,14.405394576058015,9.112725552055053,14.04629155885575,55,85
|
| 58 |
+
127,128,370.9898079978302,8.744085903977975,14.524102507069776,9.115075711975805,14.04266997276037,56,107
|
| 59 |
+
144,128,370.400496001821,8.756533648003824,14.503455945601425,9.126934144005645,14.024424629388543,57,121
|
| 60 |
+
230,128,309.8742720321752,8.82315703999484,14.393940788350093,9.133031312027015,14.015061990583634,58,346
|
| 61 |
+
124,128,369.675631984137,8.867081984004471,14.322637394026373,9.236757615988608,13.85767661353753,59,93
|
| 62 |
+
170,128,302.19761602347717,8.913596848025918,14.24789590165574,9.215794464049395,13.889198646880102,60,207
|
| 63 |
+
148,128,298.5740000149235,8.821890159975737,14.396007850583949,9.12046415999066,14.034373443569462,61,122
|
| 64 |
+
123,128,297.4766080151312,8.81660511996597,14.404637416775923,9.114081727981102,14.04420146980115,62,88
|
| 65 |
+
98,128,297.258767997846,8.813225760008208,14.410160758196861,9.110484528006054,14.049746707381153,63,43
|
| 66 |
+
196,128,306.2620800337754,8.828527903999202,14.385184187102217,9.134789984032977,14.012363746045144,64,177
|
| 67 |
+
280,128,381.4747359720059,8.757706432021223,14.501513722319327,9.139181167993229,14.005631100549252,65,494
|
| 68 |
+
100,128,296.71494400827214,8.81345068803057,14.40979299657023,9.110165632038843,14.050238510466441,66,56
|
| 69 |
+
111,128,300.6466400111094,8.820130895997863,14.398879279402337,9.120777536008973,14.03389124388288,67,68
|
| 70 |
+
222,128,308.8962400215678,8.82139251200715,14.396819983595018,9.130288752028719,14.019271840834042,68,333
|
| 71 |
+
86,128,288.00887998659164,8.815513295994606,14.406421468129757,9.103522175981198,14.060491920118148,69,20
|
| 72 |
+
116,128,299.3990720133297,8.814984991971869,14.407284880877684,9.114384063985199,14.043735605325471,70,70
|
| 73 |
+
122,128,297.36579197924584,8.820748256053776,14.397871508558078,9.118114048033021,14.03799067720725,71,100
|
| 74 |
+
123,128,366.77401600172743,8.74748774402542,14.518454179800555,9.114261760027148,14.043924057719705,72,100
|
| 75 |
+
304,128,314.2944479477592,8.825065472046845,14.390828079663438,9.139359919994604,14.005357171673307,73,516
|
| 76 |
+
96,128,290.49059201497585,8.813162976002786,14.410263414599976,9.103653568017762,14.060288986575621,74,51
|
| 77 |
+
98,128,368.19483200088143,8.751111984020099,14.51244141680593,9.11930681602098,14.036154565512264,75,38
|
| 78 |
+
146,128,299.2566720349714,8.823440047970507,14.393479109002556,9.122696720005479,14.030938869128944,76,133
|
| 79 |
+
140,128,299.837856029626,8.817254160006996,14.403577088209877,9.117092016036622,14.039564345171993,77,158
|
| 80 |
+
89,128,289.219903992489,8.821538256015629,14.396582128224123,9.110758160008118,14.049324738072727,78,17
|
| 81 |
+
163,128,367.9596959846094,8.744869392015971,14.522801234281493,9.11282908800058,14.046131971085185,79,193
|
| 82 |
+
154,128,301.0328320087865,8.822140367992688,14.395599560030176,9.123173200001474,14.030206069087816,80,151
|
| 83 |
+
119,128,295.11679999995977,8.817949280026369,14.402441652467775,9.113066080026329,14.045766691031192,81,75
|
| 84 |
+
274,128,308.49830398801714,8.834593360021245,14.37530793151238,9.143091664009262,13.999640898697036,82,413
|
| 85 |
+
96,128,289.26540800603107,8.812201760010794,14.411835255102517,9.101467168016825,14.063666619575436,83,53
|
| 86 |
+
187,128,302.0151359960437,8.8206908479915,14.397965214812887,9.122705983987544,14.0309246209041,84,243
|
| 87 |
+
175,128,299.32001599809155,8.830236239999067,14.382401166654791,9.129556255997159,14.020396655742983,85,193
|
| 88 |
+
95,128,288.6429119971581,8.814813839970157,14.407564618566008,9.103456751967315,14.060592968966255,86,54
|
| 89 |
+
135,128,297.78729600366205,8.81484275200637,14.407517362813214,9.112630048010033,14.046438769666937,87,153
|
| 90 |
+
132,128,300.75819202465937,8.814292319992092,14.40841707869679,9.11505051201675,14.042708795881303,88,83
|
| 91 |
+
151,128,300.1510240137577,8.82715395197738,14.38742324999901,9.127304975991137,14.02385483301991,89,154
|
| 92 |
+
98,128,296.32057598792017,8.815685887995642,14.406139421657079,9.112006463983562,14.04740004366078,90,47
|
| 93 |
+
120,128,293.95171196665615,8.818912415998057,14.400868724993128,9.112864127964713,14.046077962163999,91,91
|
| 94 |
+
129,128,301.3722080504522,8.82641545595834,14.388627029137595,9.127787664008792,14.023113235281402,92,149
|
| 95 |
+
126,128,298.66793600376695,8.815982783969957,14.405654265900253,9.114650719973724,14.043324745237083,93,129
|
| 96 |
+
176,128,298.68044797331095,8.825273936032318,14.390488150342547,9.123954384005629,14.029004816637961,94,181
|
| 97 |
+
151,128,300.5360160022974,8.817950623983052,14.40243945737069,9.118486639985349,14.037417068607523,95,182
|
| 98 |
+
113,128,297.2445279592648,8.82403992000036,14.392500617789004,9.121284447959624,14.03311131565827,96,72
|
| 99 |
+
159,128,301.88958399230614,8.817507632018533,14.403163036551492,9.119397216010839,14.03601542602746,97,144
|
| 100 |
+
135,128,299.31110399775207,8.813154784031212,14.410276809175603,9.112465888028964,14.046691814578253,98,146
|
| 101 |
+
183,128,299.85328001203015,8.828092415991705,14.385893805319146,9.127945696003735,14.022870453319975,99,214
|
benchmark/bf16-elyza100-streaming.json
ADDED
|
@@ -0,0 +1,1120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": "training/data/benchmarks/elyza-tasks-100/test.csv",
|
| 3 |
+
"model": "llm-jp-4-8b-instruct",
|
| 4 |
+
"temperature": 0,
|
| 5 |
+
"max_tokens": 128,
|
| 6 |
+
"summary": {
|
| 7 |
+
"count": 100,
|
| 8 |
+
"mean": 14.415907661667651,
|
| 9 |
+
"median": 14.405057756740758,
|
| 10 |
+
"stdev": 0.04455824876122128,
|
| 11 |
+
"min": 14.24789590165574,
|
| 12 |
+
"p05": 14.384719471743757,
|
| 13 |
+
"p25": 14.395599560030176,
|
| 14 |
+
"p75": 14.411835255102517,
|
| 15 |
+
"p95": 14.517020900226493,
|
| 16 |
+
"max": 14.533167284897031
|
| 17 |
+
},
|
| 18 |
+
"records": [
|
| 19 |
+
{
|
| 20 |
+
"prompt_tokens": 89,
|
| 21 |
+
"completion_tokens": 128,
|
| 22 |
+
"ttft_ms": 287.3321439838037,
|
| 23 |
+
"decode_seconds": 8.779072656005155,
|
| 24 |
+
"decode_tokens_per_second": 14.466220405765533,
|
| 25 |
+
"e2e_seconds": 9.066404799988959,
|
| 26 |
+
"e2e_tokens_per_second": 14.118054821482918,
|
| 27 |
+
"index": 0,
|
| 28 |
+
"prompt_characters": 28
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"prompt_tokens": 100,
|
| 32 |
+
"completion_tokens": 128,
|
| 33 |
+
"ttft_ms": 295.72676797397435,
|
| 34 |
+
"decode_seconds": 8.767456800036598,
|
| 35 |
+
"decode_tokens_per_second": 14.485386457731947,
|
| 36 |
+
"e2e_seconds": 9.063183568010572,
|
| 37 |
+
"e2e_tokens_per_second": 14.123072653166709,
|
| 38 |
+
"index": 1,
|
| 39 |
+
"prompt_characters": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"prompt_tokens": 86,
|
| 43 |
+
"completion_tokens": 128,
|
| 44 |
+
"ttft_ms": 290.60323198791593,
|
| 45 |
+
"decode_seconds": 8.77216342400061,
|
| 46 |
+
"decode_tokens_per_second": 14.477614456261545,
|
| 47 |
+
"e2e_seconds": 9.062766655988526,
|
| 48 |
+
"e2e_tokens_per_second": 14.123722353087368,
|
| 49 |
+
"index": 2,
|
| 50 |
+
"prompt_characters": 24
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"prompt_tokens": 223,
|
| 54 |
+
"completion_tokens": 128,
|
| 55 |
+
"ttft_ms": 304.505567997694,
|
| 56 |
+
"decode_seconds": 8.789692880003713,
|
| 57 |
+
"decode_tokens_per_second": 14.448741467283934,
|
| 58 |
+
"e2e_seconds": 9.094198448001407,
|
| 59 |
+
"e2e_tokens_per_second": 14.074907286428306,
|
| 60 |
+
"index": 3,
|
| 61 |
+
"prompt_characters": 323
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"prompt_tokens": 87,
|
| 65 |
+
"completion_tokens": 128,
|
| 66 |
+
"ttft_ms": 289.189808012452,
|
| 67 |
+
"decode_seconds": 8.793557535973378,
|
| 68 |
+
"decode_tokens_per_second": 14.442391430369154,
|
| 69 |
+
"e2e_seconds": 9.08274734398583,
|
| 70 |
+
"e2e_tokens_per_second": 14.092652272746044,
|
| 71 |
+
"index": 4,
|
| 72 |
+
"prompt_characters": 15
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"prompt_tokens": 138,
|
| 76 |
+
"completion_tokens": 128,
|
| 77 |
+
"ttft_ms": 298.6349919810891,
|
| 78 |
+
"decode_seconds": 8.804777184035629,
|
| 79 |
+
"decode_tokens_per_second": 14.42398794943612,
|
| 80 |
+
"e2e_seconds": 9.103412176016718,
|
| 81 |
+
"e2e_tokens_per_second": 14.06066181834772,
|
| 82 |
+
"index": 5,
|
| 83 |
+
"prompt_characters": 107
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"prompt_tokens": 197,
|
| 87 |
+
"completion_tokens": 128,
|
| 88 |
+
"ttft_ms": 304.21625601593405,
|
| 89 |
+
"decode_seconds": 8.81909500801703,
|
| 90 |
+
"decode_tokens_per_second": 14.400570566996976,
|
| 91 |
+
"e2e_seconds": 9.123311264032964,
|
| 92 |
+
"e2e_tokens_per_second": 14.029993748499768,
|
| 93 |
+
"index": 6,
|
| 94 |
+
"prompt_characters": 286
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"prompt_tokens": 129,
|
| 98 |
+
"completion_tokens": 128,
|
| 99 |
+
"ttft_ms": 299.53299200860783,
|
| 100 |
+
"decode_seconds": 8.820546608010773,
|
| 101 |
+
"decode_tokens_per_second": 14.398200660791169,
|
| 102 |
+
"e2e_seconds": 9.12007960001938,
|
| 103 |
+
"e2e_tokens_per_second": 14.034965221107061,
|
| 104 |
+
"index": 7,
|
| 105 |
+
"prompt_characters": 77
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"prompt_tokens": 253,
|
| 109 |
+
"completion_tokens": 128,
|
| 110 |
+
"ttft_ms": 309.5190239837393,
|
| 111 |
+
"decode_seconds": 8.817294720036443,
|
| 112 |
+
"decode_tokens_per_second": 14.403510830981398,
|
| 113 |
+
"e2e_seconds": 9.126813744020183,
|
| 114 |
+
"e2e_tokens_per_second": 14.024609638151606,
|
| 115 |
+
"index": 8,
|
| 116 |
+
"prompt_characters": 359
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"prompt_tokens": 107,
|
| 120 |
+
"completion_tokens": 128,
|
| 121 |
+
"ttft_ms": 299.14905602345243,
|
| 122 |
+
"decode_seconds": 8.819510432018433,
|
| 123 |
+
"decode_tokens_per_second": 14.399892259205004,
|
| 124 |
+
"e2e_seconds": 9.118659488041885,
|
| 125 |
+
"e2e_tokens_per_second": 14.037150983415694,
|
| 126 |
+
"index": 9,
|
| 127 |
+
"prompt_characters": 76
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"prompt_tokens": 115,
|
| 131 |
+
"completion_tokens": 128,
|
| 132 |
+
"ttft_ms": 296.4645279571414,
|
| 133 |
+
"decode_seconds": 8.813084144028835,
|
| 134 |
+
"decode_tokens_per_second": 14.410392312666938,
|
| 135 |
+
"e2e_seconds": 9.109548671985976,
|
| 136 |
+
"e2e_tokens_per_second": 14.051190087345422,
|
| 137 |
+
"index": 10,
|
| 138 |
+
"prompt_characters": 93
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"prompt_tokens": 136,
|
| 142 |
+
"completion_tokens": 128,
|
| 143 |
+
"ttft_ms": 370.15520001295954,
|
| 144 |
+
"decode_seconds": 8.748351391986944,
|
| 145 |
+
"decode_tokens_per_second": 14.517020900226493,
|
| 146 |
+
"e2e_seconds": 9.118506591999903,
|
| 147 |
+
"e2e_tokens_per_second": 14.037386353627298,
|
| 148 |
+
"index": 11,
|
| 149 |
+
"prompt_characters": 126
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"prompt_tokens": 239,
|
| 153 |
+
"completion_tokens": 128,
|
| 154 |
+
"ttft_ms": 309.37422398710623,
|
| 155 |
+
"decode_seconds": 8.829718319990207,
|
| 156 |
+
"decode_tokens_per_second": 14.383244787376283,
|
| 157 |
+
"e2e_seconds": 9.139092543977313,
|
| 158 |
+
"e2e_tokens_per_second": 14.005766916579956,
|
| 159 |
+
"index": 12,
|
| 160 |
+
"prompt_characters": 301
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"prompt_tokens": 113,
|
| 164 |
+
"completion_tokens": 128,
|
| 165 |
+
"ttft_ms": 297.8560159681365,
|
| 166 |
+
"decode_seconds": 8.81552940804977,
|
| 167 |
+
"decode_tokens_per_second": 14.406395137656943,
|
| 168 |
+
"e2e_seconds": 9.113385424017906,
|
| 169 |
+
"e2e_tokens_per_second": 14.045274510464784,
|
| 170 |
+
"index": 13,
|
| 171 |
+
"prompt_characters": 76
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"prompt_tokens": 239,
|
| 175 |
+
"completion_tokens": 128,
|
| 176 |
+
"ttft_ms": 309.5741919823922,
|
| 177 |
+
"decode_seconds": 8.828813120024279,
|
| 178 |
+
"decode_tokens_per_second": 14.384719471743757,
|
| 179 |
+
"e2e_seconds": 9.138387312006671,
|
| 180 |
+
"e2e_tokens_per_second": 14.00684777628372,
|
| 181 |
+
"index": 14,
|
| 182 |
+
"prompt_characters": 323
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"prompt_tokens": 122,
|
| 186 |
+
"completion_tokens": 128,
|
| 187 |
+
"ttft_ms": 370.8477119798772,
|
| 188 |
+
"decode_seconds": 8.738631952030119,
|
| 189 |
+
"decode_tokens_per_second": 14.533167284897031,
|
| 190 |
+
"e2e_seconds": 9.109479664009996,
|
| 191 |
+
"e2e_tokens_per_second": 14.051296530767418,
|
| 192 |
+
"index": 15,
|
| 193 |
+
"prompt_characters": 120
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"prompt_tokens": 152,
|
| 197 |
+
"completion_tokens": 128,
|
| 198 |
+
"ttft_ms": 300.2828800235875,
|
| 199 |
+
"decode_seconds": 8.817734479962382,
|
| 200 |
+
"decode_tokens_per_second": 14.402792496031452,
|
| 201 |
+
"e2e_seconds": 9.11801735998597,
|
| 202 |
+
"e2e_tokens_per_second": 14.038139536970235,
|
| 203 |
+
"index": 16,
|
| 204 |
+
"prompt_characters": 182
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"prompt_tokens": 141,
|
| 208 |
+
"completion_tokens": 128,
|
| 209 |
+
"ttft_ms": 298.9331199787557,
|
| 210 |
+
"decode_seconds": 8.812246479967143,
|
| 211 |
+
"decode_tokens_per_second": 14.411762118627612,
|
| 212 |
+
"e2e_seconds": 9.111179599945899,
|
| 213 |
+
"e2e_tokens_per_second": 14.04867488297125,
|
| 214 |
+
"index": 17,
|
| 215 |
+
"prompt_characters": 140
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"prompt_tokens": 196,
|
| 219 |
+
"completion_tokens": 128,
|
| 220 |
+
"ttft_ms": 304.14611200103536,
|
| 221 |
+
"decode_seconds": 8.825933744024951,
|
| 222 |
+
"decode_tokens_per_second": 14.389412348124349,
|
| 223 |
+
"e2e_seconds": 9.130079856025986,
|
| 224 |
+
"e2e_tokens_per_second": 14.019592601429233,
|
| 225 |
+
"index": 18,
|
| 226 |
+
"prompt_characters": 191
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"prompt_tokens": 118,
|
| 230 |
+
"completion_tokens": 128,
|
| 231 |
+
"ttft_ms": 296.74635198898613,
|
| 232 |
+
"decode_seconds": 8.812764559988864,
|
| 233 |
+
"decode_tokens_per_second": 14.410914887775066,
|
| 234 |
+
"e2e_seconds": 9.10951091197785,
|
| 235 |
+
"e2e_tokens_per_second": 14.05124833120253,
|
| 236 |
+
"index": 19,
|
| 237 |
+
"prompt_characters": 75
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"prompt_tokens": 269,
|
| 241 |
+
"completion_tokens": 128,
|
| 242 |
+
"ttft_ms": 309.93571202270687,
|
| 243 |
+
"decode_seconds": 8.82683105597971,
|
| 244 |
+
"decode_tokens_per_second": 14.38794955908488,
|
| 245 |
+
"e2e_seconds": 9.136766768002417,
|
| 246 |
+
"e2e_tokens_per_second": 14.009332102934351,
|
| 247 |
+
"index": 20,
|
| 248 |
+
"prompt_characters": 368
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"prompt_tokens": 151,
|
| 252 |
+
"completion_tokens": 128,
|
| 253 |
+
"ttft_ms": 371.7997280182317,
|
| 254 |
+
"decode_seconds": 8.751005103986245,
|
| 255 |
+
"decode_tokens_per_second": 14.512618663900579,
|
| 256 |
+
"e2e_seconds": 9.122804832004476,
|
| 257 |
+
"e2e_tokens_per_second": 14.030772592103743,
|
| 258 |
+
"index": 21,
|
| 259 |
+
"prompt_characters": 137
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"prompt_tokens": 83,
|
| 263 |
+
"completion_tokens": 128,
|
| 264 |
+
"ttft_ms": 368.71777597116306,
|
| 265 |
+
"decode_seconds": 8.740428032004274,
|
| 266 |
+
"decode_tokens_per_second": 14.53018084869209,
|
| 267 |
+
"e2e_seconds": 9.109145807975437,
|
| 268 |
+
"e2e_tokens_per_second": 14.051811519794827,
|
| 269 |
+
"index": 22,
|
| 270 |
+
"prompt_characters": 8
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"prompt_tokens": 257,
|
| 274 |
+
"completion_tokens": 128,
|
| 275 |
+
"ttft_ms": 310.9340959927067,
|
| 276 |
+
"decode_seconds": 8.822712880035397,
|
| 277 |
+
"decode_tokens_per_second": 14.394665419452082,
|
| 278 |
+
"e2e_seconds": 9.133646976028103,
|
| 279 |
+
"e2e_tokens_per_second": 14.014117289177584,
|
| 280 |
+
"index": 23,
|
| 281 |
+
"prompt_characters": 379
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"prompt_tokens": 264,
|
| 285 |
+
"completion_tokens": 128,
|
| 286 |
+
"ttft_ms": 312.00308800907806,
|
| 287 |
+
"decode_seconds": 8.822620527993422,
|
| 288 |
+
"decode_tokens_per_second": 14.394816097670736,
|
| 289 |
+
"e2e_seconds": 9.1346236160025,
|
| 290 |
+
"e2e_tokens_per_second": 14.012618951892343,
|
| 291 |
+
"index": 24,
|
| 292 |
+
"prompt_characters": 480
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"prompt_tokens": 115,
|
| 296 |
+
"completion_tokens": 128,
|
| 297 |
+
"ttft_ms": 368.4656799887307,
|
| 298 |
+
"decode_seconds": 8.752178527996875,
|
| 299 |
+
"decode_tokens_per_second": 14.5106729248891,
|
| 300 |
+
"e2e_seconds": 9.120644207985606,
|
| 301 |
+
"e2e_tokens_per_second": 14.034096395069247,
|
| 302 |
+
"index": 25,
|
| 303 |
+
"prompt_characters": 82
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"prompt_tokens": 167,
|
| 307 |
+
"completion_tokens": 128,
|
| 308 |
+
"ttft_ms": 300.1571359927766,
|
| 309 |
+
"decode_seconds": 8.814201600034721,
|
| 310 |
+
"decode_tokens_per_second": 14.408565376982041,
|
| 311 |
+
"e2e_seconds": 9.114358736027498,
|
| 312 |
+
"e2e_tokens_per_second": 14.043774631564363,
|
| 313 |
+
"index": 26,
|
| 314 |
+
"prompt_characters": 145
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"prompt_tokens": 86,
|
| 318 |
+
"completion_tokens": 128,
|
| 319 |
+
"ttft_ms": 288.03827200317755,
|
| 320 |
+
"decode_seconds": 8.810084576020017,
|
| 321 |
+
"decode_tokens_per_second": 14.41529861650575,
|
| 322 |
+
"e2e_seconds": 9.098122848023195,
|
| 323 |
+
"e2e_tokens_per_second": 14.068836191611915,
|
| 324 |
+
"index": 27,
|
| 325 |
+
"prompt_characters": 11
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"prompt_tokens": 95,
|
| 329 |
+
"completion_tokens": 128,
|
| 330 |
+
"ttft_ms": 290.33766401698813,
|
| 331 |
+
"decode_seconds": 8.809145903971512,
|
| 332 |
+
"decode_tokens_per_second": 14.416834660752226,
|
| 333 |
+
"e2e_seconds": 9.0994835679885,
|
| 334 |
+
"e2e_tokens_per_second": 14.066732363834053,
|
| 335 |
+
"index": 28,
|
| 336 |
+
"prompt_characters": 33
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"prompt_tokens": 138,
|
| 340 |
+
"completion_tokens": 128,
|
| 341 |
+
"ttft_ms": 300.13843200867996,
|
| 342 |
+
"decode_seconds": 8.82354910398135,
|
| 343 |
+
"decode_tokens_per_second": 14.393301210586026,
|
| 344 |
+
"e2e_seconds": 9.12368753599003,
|
| 345 |
+
"e2e_tokens_per_second": 14.029415134514519,
|
| 346 |
+
"index": 29,
|
| 347 |
+
"prompt_characters": 155
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"prompt_tokens": 89,
|
| 351 |
+
"completion_tokens": 128,
|
| 352 |
+
"ttft_ms": 291.2958399974741,
|
| 353 |
+
"decode_seconds": 8.811235280008987,
|
| 354 |
+
"decode_tokens_per_second": 14.413416049408962,
|
| 355 |
+
"e2e_seconds": 9.10253112000646,
|
| 356 |
+
"e2e_tokens_per_second": 14.062022783824236,
|
| 357 |
+
"index": 30,
|
| 358 |
+
"prompt_characters": 23
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"prompt_tokens": 122,
|
| 362 |
+
"completion_tokens": 128,
|
| 363 |
+
"ttft_ms": 298.4383839648217,
|
| 364 |
+
"decode_seconds": 8.810073536005802,
|
| 365 |
+
"decode_tokens_per_second": 14.415316680498178,
|
| 366 |
+
"e2e_seconds": 9.108511919970624,
|
| 367 |
+
"e2e_tokens_per_second": 14.05278942648766,
|
| 368 |
+
"index": 31,
|
| 369 |
+
"prompt_characters": 97
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"prompt_tokens": 94,
|
| 373 |
+
"completion_tokens": 128,
|
| 374 |
+
"ttft_ms": 287.24841598886997,
|
| 375 |
+
"decode_seconds": 8.81881228799466,
|
| 376 |
+
"decode_tokens_per_second": 14.401032231164425,
|
| 377 |
+
"e2e_seconds": 9.10606070398353,
|
| 378 |
+
"e2e_tokens_per_second": 14.05657222820898,
|
| 379 |
+
"index": 32,
|
| 380 |
+
"prompt_characters": 61
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"prompt_tokens": 132,
|
| 384 |
+
"completion_tokens": 128,
|
| 385 |
+
"ttft_ms": 298.8155360217206,
|
| 386 |
+
"decode_seconds": 8.817851200001314,
|
| 387 |
+
"decode_tokens_per_second": 14.402601849301004,
|
| 388 |
+
"e2e_seconds": 9.116666736023035,
|
| 389 |
+
"e2e_tokens_per_second": 14.040219271614777,
|
| 390 |
+
"index": 33,
|
| 391 |
+
"prompt_characters": 136
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"prompt_tokens": 114,
|
| 395 |
+
"completion_tokens": 128,
|
| 396 |
+
"ttft_ms": 297.1212000120431,
|
| 397 |
+
"decode_seconds": 8.809575375984423,
|
| 398 |
+
"decode_tokens_per_second": 14.416131831530919,
|
| 399 |
+
"e2e_seconds": 9.106696575996466,
|
| 400 |
+
"e2e_tokens_per_second": 14.055590732800283,
|
| 401 |
+
"index": 34,
|
| 402 |
+
"prompt_characters": 82
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"prompt_tokens": 97,
|
| 406 |
+
"completion_tokens": 128,
|
| 407 |
+
"ttft_ms": 297.4157760036178,
|
| 408 |
+
"decode_seconds": 8.811500575975515,
|
| 409 |
+
"decode_tokens_per_second": 14.412982091411816,
|
| 410 |
+
"e2e_seconds": 9.108916351979133,
|
| 411 |
+
"e2e_tokens_per_second": 14.05216548861917,
|
| 412 |
+
"index": 35,
|
| 413 |
+
"prompt_characters": 49
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"prompt_tokens": 116,
|
| 417 |
+
"completion_tokens": 128,
|
| 418 |
+
"ttft_ms": 295.1624320121482,
|
| 419 |
+
"decode_seconds": 8.818597696023062,
|
| 420 |
+
"decode_tokens_per_second": 14.401382666234271,
|
| 421 |
+
"e2e_seconds": 9.11376012803521,
|
| 422 |
+
"e2e_tokens_per_second": 14.044697051687148,
|
| 423 |
+
"index": 36,
|
| 424 |
+
"prompt_characters": 101
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"prompt_tokens": 127,
|
| 428 |
+
"completion_tokens": 128,
|
| 429 |
+
"ttft_ms": 294.031776022166,
|
| 430 |
+
"decode_seconds": 8.825343439995777,
|
| 431 |
+
"decode_tokens_per_second": 14.390374818100085,
|
| 432 |
+
"e2e_seconds": 9.119375216017943,
|
| 433 |
+
"e2e_tokens_per_second": 14.036049287145392,
|
| 434 |
+
"index": 37,
|
| 435 |
+
"prompt_characters": 118
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"prompt_tokens": 99,
|
| 439 |
+
"completion_tokens": 128,
|
| 440 |
+
"ttft_ms": 298.44286397565156,
|
| 441 |
+
"decode_seconds": 8.810942688025534,
|
| 442 |
+
"decode_tokens_per_second": 14.413894687182415,
|
| 443 |
+
"e2e_seconds": 9.109385552001186,
|
| 444 |
+
"e2e_tokens_per_second": 14.051441699257142,
|
| 445 |
+
"index": 38,
|
| 446 |
+
"prompt_characters": 44
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"prompt_tokens": 89,
|
| 450 |
+
"completion_tokens": 128,
|
| 451 |
+
"ttft_ms": 290.05577601492405,
|
| 452 |
+
"decode_seconds": 8.821949823992327,
|
| 453 |
+
"decode_tokens_per_second": 14.395910488473717,
|
| 454 |
+
"e2e_seconds": 9.112005600007251,
|
| 455 |
+
"e2e_tokens_per_second": 14.047401375598161,
|
| 456 |
+
"index": 39,
|
| 457 |
+
"prompt_characters": 21
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"prompt_tokens": 131,
|
| 461 |
+
"completion_tokens": 128,
|
| 462 |
+
"ttft_ms": 297.30228800326586,
|
| 463 |
+
"decode_seconds": 8.816554000019096,
|
| 464 |
+
"decode_tokens_per_second": 14.404720937423502,
|
| 465 |
+
"e2e_seconds": 9.113856288022362,
|
| 466 |
+
"e2e_tokens_per_second": 14.044548866567112,
|
| 467 |
+
"index": 40,
|
| 468 |
+
"prompt_characters": 99
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"prompt_tokens": 164,
|
| 472 |
+
"completion_tokens": 128,
|
| 473 |
+
"ttft_ms": 299.2388000129722,
|
| 474 |
+
"decode_seconds": 8.815770207962487,
|
| 475 |
+
"decode_tokens_per_second": 14.406001631631959,
|
| 476 |
+
"e2e_seconds": 9.115009007975459,
|
| 477 |
+
"e2e_tokens_per_second": 14.04277273758067,
|
| 478 |
+
"index": 41,
|
| 479 |
+
"prompt_characters": 255
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"prompt_tokens": 119,
|
| 483 |
+
"completion_tokens": 128,
|
| 484 |
+
"ttft_ms": 297.0329279778525,
|
| 485 |
+
"decode_seconds": 8.812944128003437,
|
| 486 |
+
"decode_tokens_per_second": 14.410621258388904,
|
| 487 |
+
"e2e_seconds": 9.10997705598129,
|
| 488 |
+
"e2e_tokens_per_second": 14.050529349682579,
|
| 489 |
+
"index": 42,
|
| 490 |
+
"prompt_characters": 98
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"prompt_tokens": 109,
|
| 494 |
+
"completion_tokens": 128,
|
| 495 |
+
"ttft_ms": 299.9312960309908,
|
| 496 |
+
"decode_seconds": 8.82349996798439,
|
| 497 |
+
"decode_tokens_per_second": 14.393381363496673,
|
| 498 |
+
"e2e_seconds": 9.12343126401538,
|
| 499 |
+
"e2e_tokens_per_second": 14.029809212774731,
|
| 500 |
+
"index": 43,
|
| 501 |
+
"prompt_characters": 69
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"prompt_tokens": 116,
|
| 505 |
+
"completion_tokens": 128,
|
| 506 |
+
"ttft_ms": 296.43854399910197,
|
| 507 |
+
"decode_seconds": 8.814559072023258,
|
| 508 |
+
"decode_tokens_per_second": 14.407981041625595,
|
| 509 |
+
"e2e_seconds": 9.11099761602236,
|
| 510 |
+
"e2e_tokens_per_second": 14.048955492525053,
|
| 511 |
+
"index": 44,
|
| 512 |
+
"prompt_characters": 63
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"prompt_tokens": 99,
|
| 516 |
+
"completion_tokens": 128,
|
| 517 |
+
"ttft_ms": 296.96737602353096,
|
| 518 |
+
"decode_seconds": 8.8147550720023,
|
| 519 |
+
"decode_tokens_per_second": 14.407660673792442,
|
| 520 |
+
"e2e_seconds": 9.11172244802583,
|
| 521 |
+
"e2e_tokens_per_second": 14.047837906622455,
|
| 522 |
+
"index": 45,
|
| 523 |
+
"prompt_characters": 51
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"prompt_tokens": 87,
|
| 527 |
+
"completion_tokens": 128,
|
| 528 |
+
"ttft_ms": 362.1777279768139,
|
| 529 |
+
"decode_seconds": 8.752297568018548,
|
| 530 |
+
"decode_tokens_per_second": 14.510475565189427,
|
| 531 |
+
"e2e_seconds": 9.114475295995362,
|
| 532 |
+
"e2e_tokens_per_second": 14.043595033522063,
|
| 533 |
+
"index": 46,
|
| 534 |
+
"prompt_characters": 16
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"prompt_tokens": 121,
|
| 538 |
+
"completion_tokens": 128,
|
| 539 |
+
"ttft_ms": 299.46691199438646,
|
| 540 |
+
"decode_seconds": 8.81550879997667,
|
| 541 |
+
"decode_tokens_per_second": 14.406428815581934,
|
| 542 |
+
"e2e_seconds": 9.114975711971056,
|
| 543 |
+
"e2e_tokens_per_second": 14.04282403428597,
|
| 544 |
+
"index": 47,
|
| 545 |
+
"prompt_characters": 83
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"prompt_tokens": 103,
|
| 549 |
+
"completion_tokens": 128,
|
| 550 |
+
"ttft_ms": 297.9078239877708,
|
| 551 |
+
"decode_seconds": 8.816075871989597,
|
| 552 |
+
"decode_tokens_per_second": 14.405502158109133,
|
| 553 |
+
"e2e_seconds": 9.113983695977367,
|
| 554 |
+
"e2e_tokens_per_second": 14.044352532306512,
|
| 555 |
+
"index": 48,
|
| 556 |
+
"prompt_characters": 52
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"prompt_tokens": 128,
|
| 560 |
+
"completion_tokens": 128,
|
| 561 |
+
"ttft_ms": 296.2054240051657,
|
| 562 |
+
"decode_seconds": 8.818844111985527,
|
| 563 |
+
"decode_tokens_per_second": 14.400980263093285,
|
| 564 |
+
"e2e_seconds": 9.115049535990693,
|
| 565 |
+
"e2e_tokens_per_second": 14.042710299553846,
|
| 566 |
+
"index": 49,
|
| 567 |
+
"prompt_characters": 82
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"prompt_tokens": 116,
|
| 571 |
+
"completion_tokens": 128,
|
| 572 |
+
"ttft_ms": 296.5520319994539,
|
| 573 |
+
"decode_seconds": 8.82329428801313,
|
| 574 |
+
"decode_tokens_per_second": 14.393716887867562,
|
| 575 |
+
"e2e_seconds": 9.119846320012584,
|
| 576 |
+
"e2e_tokens_per_second": 14.03532422680379,
|
| 577 |
+
"index": 50,
|
| 578 |
+
"prompt_characters": 89
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"prompt_tokens": 202,
|
| 582 |
+
"completion_tokens": 128,
|
| 583 |
+
"ttft_ms": 303.8067359593697,
|
| 584 |
+
"decode_seconds": 8.820766672026366,
|
| 585 |
+
"decode_tokens_per_second": 14.397841448721225,
|
| 586 |
+
"e2e_seconds": 9.124573407985736,
|
| 587 |
+
"e2e_tokens_per_second": 14.02805306908657,
|
| 588 |
+
"index": 51,
|
| 589 |
+
"prompt_characters": 202
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"prompt_tokens": 133,
|
| 593 |
+
"completion_tokens": 128,
|
| 594 |
+
"ttft_ms": 296.68961599236354,
|
| 595 |
+
"decode_seconds": 8.814125408011023,
|
| 596 |
+
"decode_tokens_per_second": 14.408689929073581,
|
| 597 |
+
"e2e_seconds": 9.110815024003386,
|
| 598 |
+
"e2e_tokens_per_second": 14.049237050996068,
|
| 599 |
+
"index": 52,
|
| 600 |
+
"prompt_characters": 73
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"prompt_tokens": 97,
|
| 604 |
+
"completion_tokens": 128,
|
| 605 |
+
"ttft_ms": 296.0946400417015,
|
| 606 |
+
"decode_seconds": 8.822594399971422,
|
| 607 |
+
"decode_tokens_per_second": 14.39485872776962,
|
| 608 |
+
"e2e_seconds": 9.118689040013123,
|
| 609 |
+
"e2e_tokens_per_second": 14.037105491626216,
|
| 610 |
+
"index": 53,
|
| 611 |
+
"prompt_characters": 42
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"prompt_tokens": 208,
|
| 615 |
+
"completion_tokens": 128,
|
| 616 |
+
"ttft_ms": 304.0414240094833,
|
| 617 |
+
"decode_seconds": 8.82271115196636,
|
| 618 |
+
"decode_tokens_per_second": 14.394668238877447,
|
| 619 |
+
"e2e_seconds": 9.126752575975843,
|
| 620 |
+
"e2e_tokens_per_second": 14.02470363192837,
|
| 621 |
+
"index": 54,
|
| 622 |
+
"prompt_characters": 254
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"prompt_tokens": 113,
|
| 626 |
+
"completion_tokens": 128,
|
| 627 |
+
"ttft_ms": 296.58384004142135,
|
| 628 |
+
"decode_seconds": 8.816141712013632,
|
| 629 |
+
"decode_tokens_per_second": 14.405394576058015,
|
| 630 |
+
"e2e_seconds": 9.112725552055053,
|
| 631 |
+
"e2e_tokens_per_second": 14.04629155885575,
|
| 632 |
+
"index": 55,
|
| 633 |
+
"prompt_characters": 85
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"prompt_tokens": 127,
|
| 637 |
+
"completion_tokens": 128,
|
| 638 |
+
"ttft_ms": 370.9898079978302,
|
| 639 |
+
"decode_seconds": 8.744085903977975,
|
| 640 |
+
"decode_tokens_per_second": 14.524102507069776,
|
| 641 |
+
"e2e_seconds": 9.115075711975805,
|
| 642 |
+
"e2e_tokens_per_second": 14.04266997276037,
|
| 643 |
+
"index": 56,
|
| 644 |
+
"prompt_characters": 107
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"prompt_tokens": 144,
|
| 648 |
+
"completion_tokens": 128,
|
| 649 |
+
"ttft_ms": 370.400496001821,
|
| 650 |
+
"decode_seconds": 8.756533648003824,
|
| 651 |
+
"decode_tokens_per_second": 14.503455945601425,
|
| 652 |
+
"e2e_seconds": 9.126934144005645,
|
| 653 |
+
"e2e_tokens_per_second": 14.024424629388543,
|
| 654 |
+
"index": 57,
|
| 655 |
+
"prompt_characters": 121
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"prompt_tokens": 230,
|
| 659 |
+
"completion_tokens": 128,
|
| 660 |
+
"ttft_ms": 309.8742720321752,
|
| 661 |
+
"decode_seconds": 8.82315703999484,
|
| 662 |
+
"decode_tokens_per_second": 14.393940788350093,
|
| 663 |
+
"e2e_seconds": 9.133031312027015,
|
| 664 |
+
"e2e_tokens_per_second": 14.015061990583634,
|
| 665 |
+
"index": 58,
|
| 666 |
+
"prompt_characters": 346
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"prompt_tokens": 124,
|
| 670 |
+
"completion_tokens": 128,
|
| 671 |
+
"ttft_ms": 369.675631984137,
|
| 672 |
+
"decode_seconds": 8.867081984004471,
|
| 673 |
+
"decode_tokens_per_second": 14.322637394026373,
|
| 674 |
+
"e2e_seconds": 9.236757615988608,
|
| 675 |
+
"e2e_tokens_per_second": 13.85767661353753,
|
| 676 |
+
"index": 59,
|
| 677 |
+
"prompt_characters": 93
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"prompt_tokens": 170,
|
| 681 |
+
"completion_tokens": 128,
|
| 682 |
+
"ttft_ms": 302.19761602347717,
|
| 683 |
+
"decode_seconds": 8.913596848025918,
|
| 684 |
+
"decode_tokens_per_second": 14.24789590165574,
|
| 685 |
+
"e2e_seconds": 9.215794464049395,
|
| 686 |
+
"e2e_tokens_per_second": 13.889198646880102,
|
| 687 |
+
"index": 60,
|
| 688 |
+
"prompt_characters": 207
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"prompt_tokens": 148,
|
| 692 |
+
"completion_tokens": 128,
|
| 693 |
+
"ttft_ms": 298.5740000149235,
|
| 694 |
+
"decode_seconds": 8.821890159975737,
|
| 695 |
+
"decode_tokens_per_second": 14.396007850583949,
|
| 696 |
+
"e2e_seconds": 9.12046415999066,
|
| 697 |
+
"e2e_tokens_per_second": 14.034373443569462,
|
| 698 |
+
"index": 61,
|
| 699 |
+
"prompt_characters": 122
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"prompt_tokens": 123,
|
| 703 |
+
"completion_tokens": 128,
|
| 704 |
+
"ttft_ms": 297.4766080151312,
|
| 705 |
+
"decode_seconds": 8.81660511996597,
|
| 706 |
+
"decode_tokens_per_second": 14.404637416775923,
|
| 707 |
+
"e2e_seconds": 9.114081727981102,
|
| 708 |
+
"e2e_tokens_per_second": 14.04420146980115,
|
| 709 |
+
"index": 62,
|
| 710 |
+
"prompt_characters": 88
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"prompt_tokens": 98,
|
| 714 |
+
"completion_tokens": 128,
|
| 715 |
+
"ttft_ms": 297.258767997846,
|
| 716 |
+
"decode_seconds": 8.813225760008208,
|
| 717 |
+
"decode_tokens_per_second": 14.410160758196861,
|
| 718 |
+
"e2e_seconds": 9.110484528006054,
|
| 719 |
+
"e2e_tokens_per_second": 14.049746707381153,
|
| 720 |
+
"index": 63,
|
| 721 |
+
"prompt_characters": 43
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"prompt_tokens": 196,
|
| 725 |
+
"completion_tokens": 128,
|
| 726 |
+
"ttft_ms": 306.2620800337754,
|
| 727 |
+
"decode_seconds": 8.828527903999202,
|
| 728 |
+
"decode_tokens_per_second": 14.385184187102217,
|
| 729 |
+
"e2e_seconds": 9.134789984032977,
|
| 730 |
+
"e2e_tokens_per_second": 14.012363746045144,
|
| 731 |
+
"index": 64,
|
| 732 |
+
"prompt_characters": 177
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"prompt_tokens": 280,
|
| 736 |
+
"completion_tokens": 128,
|
| 737 |
+
"ttft_ms": 381.4747359720059,
|
| 738 |
+
"decode_seconds": 8.757706432021223,
|
| 739 |
+
"decode_tokens_per_second": 14.501513722319327,
|
| 740 |
+
"e2e_seconds": 9.139181167993229,
|
| 741 |
+
"e2e_tokens_per_second": 14.005631100549252,
|
| 742 |
+
"index": 65,
|
| 743 |
+
"prompt_characters": 494
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"prompt_tokens": 100,
|
| 747 |
+
"completion_tokens": 128,
|
| 748 |
+
"ttft_ms": 296.71494400827214,
|
| 749 |
+
"decode_seconds": 8.81345068803057,
|
| 750 |
+
"decode_tokens_per_second": 14.40979299657023,
|
| 751 |
+
"e2e_seconds": 9.110165632038843,
|
| 752 |
+
"e2e_tokens_per_second": 14.050238510466441,
|
| 753 |
+
"index": 66,
|
| 754 |
+
"prompt_characters": 56
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"prompt_tokens": 111,
|
| 758 |
+
"completion_tokens": 128,
|
| 759 |
+
"ttft_ms": 300.6466400111094,
|
| 760 |
+
"decode_seconds": 8.820130895997863,
|
| 761 |
+
"decode_tokens_per_second": 14.398879279402337,
|
| 762 |
+
"e2e_seconds": 9.120777536008973,
|
| 763 |
+
"e2e_tokens_per_second": 14.03389124388288,
|
| 764 |
+
"index": 67,
|
| 765 |
+
"prompt_characters": 68
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"prompt_tokens": 222,
|
| 769 |
+
"completion_tokens": 128,
|
| 770 |
+
"ttft_ms": 308.8962400215678,
|
| 771 |
+
"decode_seconds": 8.82139251200715,
|
| 772 |
+
"decode_tokens_per_second": 14.396819983595018,
|
| 773 |
+
"e2e_seconds": 9.130288752028719,
|
| 774 |
+
"e2e_tokens_per_second": 14.019271840834042,
|
| 775 |
+
"index": 68,
|
| 776 |
+
"prompt_characters": 333
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"prompt_tokens": 86,
|
| 780 |
+
"completion_tokens": 128,
|
| 781 |
+
"ttft_ms": 288.00887998659164,
|
| 782 |
+
"decode_seconds": 8.815513295994606,
|
| 783 |
+
"decode_tokens_per_second": 14.406421468129757,
|
| 784 |
+
"e2e_seconds": 9.103522175981198,
|
| 785 |
+
"e2e_tokens_per_second": 14.060491920118148,
|
| 786 |
+
"index": 69,
|
| 787 |
+
"prompt_characters": 20
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"prompt_tokens": 116,
|
| 791 |
+
"completion_tokens": 128,
|
| 792 |
+
"ttft_ms": 299.3990720133297,
|
| 793 |
+
"decode_seconds": 8.814984991971869,
|
| 794 |
+
"decode_tokens_per_second": 14.407284880877684,
|
| 795 |
+
"e2e_seconds": 9.114384063985199,
|
| 796 |
+
"e2e_tokens_per_second": 14.043735605325471,
|
| 797 |
+
"index": 70,
|
| 798 |
+
"prompt_characters": 70
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"prompt_tokens": 122,
|
| 802 |
+
"completion_tokens": 128,
|
| 803 |
+
"ttft_ms": 297.36579197924584,
|
| 804 |
+
"decode_seconds": 8.820748256053776,
|
| 805 |
+
"decode_tokens_per_second": 14.397871508558078,
|
| 806 |
+
"e2e_seconds": 9.118114048033021,
|
| 807 |
+
"e2e_tokens_per_second": 14.03799067720725,
|
| 808 |
+
"index": 71,
|
| 809 |
+
"prompt_characters": 100
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"prompt_tokens": 123,
|
| 813 |
+
"completion_tokens": 128,
|
| 814 |
+
"ttft_ms": 366.77401600172743,
|
| 815 |
+
"decode_seconds": 8.74748774402542,
|
| 816 |
+
"decode_tokens_per_second": 14.518454179800555,
|
| 817 |
+
"e2e_seconds": 9.114261760027148,
|
| 818 |
+
"e2e_tokens_per_second": 14.043924057719705,
|
| 819 |
+
"index": 72,
|
| 820 |
+
"prompt_characters": 100
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"prompt_tokens": 304,
|
| 824 |
+
"completion_tokens": 128,
|
| 825 |
+
"ttft_ms": 314.2944479477592,
|
| 826 |
+
"decode_seconds": 8.825065472046845,
|
| 827 |
+
"decode_tokens_per_second": 14.390828079663438,
|
| 828 |
+
"e2e_seconds": 9.139359919994604,
|
| 829 |
+
"e2e_tokens_per_second": 14.005357171673307,
|
| 830 |
+
"index": 73,
|
| 831 |
+
"prompt_characters": 516
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"prompt_tokens": 96,
|
| 835 |
+
"completion_tokens": 128,
|
| 836 |
+
"ttft_ms": 290.49059201497585,
|
| 837 |
+
"decode_seconds": 8.813162976002786,
|
| 838 |
+
"decode_tokens_per_second": 14.410263414599976,
|
| 839 |
+
"e2e_seconds": 9.103653568017762,
|
| 840 |
+
"e2e_tokens_per_second": 14.060288986575621,
|
| 841 |
+
"index": 74,
|
| 842 |
+
"prompt_characters": 51
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"prompt_tokens": 98,
|
| 846 |
+
"completion_tokens": 128,
|
| 847 |
+
"ttft_ms": 368.19483200088143,
|
| 848 |
+
"decode_seconds": 8.751111984020099,
|
| 849 |
+
"decode_tokens_per_second": 14.51244141680593,
|
| 850 |
+
"e2e_seconds": 9.11930681602098,
|
| 851 |
+
"e2e_tokens_per_second": 14.036154565512264,
|
| 852 |
+
"index": 75,
|
| 853 |
+
"prompt_characters": 38
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"prompt_tokens": 146,
|
| 857 |
+
"completion_tokens": 128,
|
| 858 |
+
"ttft_ms": 299.2566720349714,
|
| 859 |
+
"decode_seconds": 8.823440047970507,
|
| 860 |
+
"decode_tokens_per_second": 14.393479109002556,
|
| 861 |
+
"e2e_seconds": 9.122696720005479,
|
| 862 |
+
"e2e_tokens_per_second": 14.030938869128944,
|
| 863 |
+
"index": 76,
|
| 864 |
+
"prompt_characters": 133
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"prompt_tokens": 140,
|
| 868 |
+
"completion_tokens": 128,
|
| 869 |
+
"ttft_ms": 299.837856029626,
|
| 870 |
+
"decode_seconds": 8.817254160006996,
|
| 871 |
+
"decode_tokens_per_second": 14.403577088209877,
|
| 872 |
+
"e2e_seconds": 9.117092016036622,
|
| 873 |
+
"e2e_tokens_per_second": 14.039564345171993,
|
| 874 |
+
"index": 77,
|
| 875 |
+
"prompt_characters": 158
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"prompt_tokens": 89,
|
| 879 |
+
"completion_tokens": 128,
|
| 880 |
+
"ttft_ms": 289.219903992489,
|
| 881 |
+
"decode_seconds": 8.821538256015629,
|
| 882 |
+
"decode_tokens_per_second": 14.396582128224123,
|
| 883 |
+
"e2e_seconds": 9.110758160008118,
|
| 884 |
+
"e2e_tokens_per_second": 14.049324738072727,
|
| 885 |
+
"index": 78,
|
| 886 |
+
"prompt_characters": 17
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"prompt_tokens": 163,
|
| 890 |
+
"completion_tokens": 128,
|
| 891 |
+
"ttft_ms": 367.9596959846094,
|
| 892 |
+
"decode_seconds": 8.744869392015971,
|
| 893 |
+
"decode_tokens_per_second": 14.522801234281493,
|
| 894 |
+
"e2e_seconds": 9.11282908800058,
|
| 895 |
+
"e2e_tokens_per_second": 14.046131971085185,
|
| 896 |
+
"index": 79,
|
| 897 |
+
"prompt_characters": 193
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"prompt_tokens": 154,
|
| 901 |
+
"completion_tokens": 128,
|
| 902 |
+
"ttft_ms": 301.0328320087865,
|
| 903 |
+
"decode_seconds": 8.822140367992688,
|
| 904 |
+
"decode_tokens_per_second": 14.395599560030176,
|
| 905 |
+
"e2e_seconds": 9.123173200001474,
|
| 906 |
+
"e2e_tokens_per_second": 14.030206069087816,
|
| 907 |
+
"index": 80,
|
| 908 |
+
"prompt_characters": 151
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"prompt_tokens": 119,
|
| 912 |
+
"completion_tokens": 128,
|
| 913 |
+
"ttft_ms": 295.11679999995977,
|
| 914 |
+
"decode_seconds": 8.817949280026369,
|
| 915 |
+
"decode_tokens_per_second": 14.402441652467775,
|
| 916 |
+
"e2e_seconds": 9.113066080026329,
|
| 917 |
+
"e2e_tokens_per_second": 14.045766691031192,
|
| 918 |
+
"index": 81,
|
| 919 |
+
"prompt_characters": 75
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"prompt_tokens": 274,
|
| 923 |
+
"completion_tokens": 128,
|
| 924 |
+
"ttft_ms": 308.49830398801714,
|
| 925 |
+
"decode_seconds": 8.834593360021245,
|
| 926 |
+
"decode_tokens_per_second": 14.37530793151238,
|
| 927 |
+
"e2e_seconds": 9.143091664009262,
|
| 928 |
+
"e2e_tokens_per_second": 13.999640898697036,
|
| 929 |
+
"index": 82,
|
| 930 |
+
"prompt_characters": 413
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"prompt_tokens": 96,
|
| 934 |
+
"completion_tokens": 128,
|
| 935 |
+
"ttft_ms": 289.26540800603107,
|
| 936 |
+
"decode_seconds": 8.812201760010794,
|
| 937 |
+
"decode_tokens_per_second": 14.411835255102517,
|
| 938 |
+
"e2e_seconds": 9.101467168016825,
|
| 939 |
+
"e2e_tokens_per_second": 14.063666619575436,
|
| 940 |
+
"index": 83,
|
| 941 |
+
"prompt_characters": 53
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"prompt_tokens": 187,
|
| 945 |
+
"completion_tokens": 128,
|
| 946 |
+
"ttft_ms": 302.0151359960437,
|
| 947 |
+
"decode_seconds": 8.8206908479915,
|
| 948 |
+
"decode_tokens_per_second": 14.397965214812887,
|
| 949 |
+
"e2e_seconds": 9.122705983987544,
|
| 950 |
+
"e2e_tokens_per_second": 14.0309246209041,
|
| 951 |
+
"index": 84,
|
| 952 |
+
"prompt_characters": 243
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"prompt_tokens": 175,
|
| 956 |
+
"completion_tokens": 128,
|
| 957 |
+
"ttft_ms": 299.32001599809155,
|
| 958 |
+
"decode_seconds": 8.830236239999067,
|
| 959 |
+
"decode_tokens_per_second": 14.382401166654791,
|
| 960 |
+
"e2e_seconds": 9.129556255997159,
|
| 961 |
+
"e2e_tokens_per_second": 14.020396655742983,
|
| 962 |
+
"index": 85,
|
| 963 |
+
"prompt_characters": 193
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"prompt_tokens": 95,
|
| 967 |
+
"completion_tokens": 128,
|
| 968 |
+
"ttft_ms": 288.6429119971581,
|
| 969 |
+
"decode_seconds": 8.814813839970157,
|
| 970 |
+
"decode_tokens_per_second": 14.407564618566008,
|
| 971 |
+
"e2e_seconds": 9.103456751967315,
|
| 972 |
+
"e2e_tokens_per_second": 14.060592968966255,
|
| 973 |
+
"index": 86,
|
| 974 |
+
"prompt_characters": 54
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"prompt_tokens": 135,
|
| 978 |
+
"completion_tokens": 128,
|
| 979 |
+
"ttft_ms": 297.78729600366205,
|
| 980 |
+
"decode_seconds": 8.81484275200637,
|
| 981 |
+
"decode_tokens_per_second": 14.407517362813214,
|
| 982 |
+
"e2e_seconds": 9.112630048010033,
|
| 983 |
+
"e2e_tokens_per_second": 14.046438769666937,
|
| 984 |
+
"index": 87,
|
| 985 |
+
"prompt_characters": 153
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"prompt_tokens": 132,
|
| 989 |
+
"completion_tokens": 128,
|
| 990 |
+
"ttft_ms": 300.75819202465937,
|
| 991 |
+
"decode_seconds": 8.814292319992092,
|
| 992 |
+
"decode_tokens_per_second": 14.40841707869679,
|
| 993 |
+
"e2e_seconds": 9.11505051201675,
|
| 994 |
+
"e2e_tokens_per_second": 14.042708795881303,
|
| 995 |
+
"index": 88,
|
| 996 |
+
"prompt_characters": 83
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"prompt_tokens": 151,
|
| 1000 |
+
"completion_tokens": 128,
|
| 1001 |
+
"ttft_ms": 300.1510240137577,
|
| 1002 |
+
"decode_seconds": 8.82715395197738,
|
| 1003 |
+
"decode_tokens_per_second": 14.38742324999901,
|
| 1004 |
+
"e2e_seconds": 9.127304975991137,
|
| 1005 |
+
"e2e_tokens_per_second": 14.02385483301991,
|
| 1006 |
+
"index": 89,
|
| 1007 |
+
"prompt_characters": 154
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"prompt_tokens": 98,
|
| 1011 |
+
"completion_tokens": 128,
|
| 1012 |
+
"ttft_ms": 296.32057598792017,
|
| 1013 |
+
"decode_seconds": 8.815685887995642,
|
| 1014 |
+
"decode_tokens_per_second": 14.406139421657079,
|
| 1015 |
+
"e2e_seconds": 9.112006463983562,
|
| 1016 |
+
"e2e_tokens_per_second": 14.04740004366078,
|
| 1017 |
+
"index": 90,
|
| 1018 |
+
"prompt_characters": 47
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"prompt_tokens": 120,
|
| 1022 |
+
"completion_tokens": 128,
|
| 1023 |
+
"ttft_ms": 293.95171196665615,
|
| 1024 |
+
"decode_seconds": 8.818912415998057,
|
| 1025 |
+
"decode_tokens_per_second": 14.400868724993128,
|
| 1026 |
+
"e2e_seconds": 9.112864127964713,
|
| 1027 |
+
"e2e_tokens_per_second": 14.046077962163999,
|
| 1028 |
+
"index": 91,
|
| 1029 |
+
"prompt_characters": 91
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"prompt_tokens": 129,
|
| 1033 |
+
"completion_tokens": 128,
|
| 1034 |
+
"ttft_ms": 301.3722080504522,
|
| 1035 |
+
"decode_seconds": 8.82641545595834,
|
| 1036 |
+
"decode_tokens_per_second": 14.388627029137595,
|
| 1037 |
+
"e2e_seconds": 9.127787664008792,
|
| 1038 |
+
"e2e_tokens_per_second": 14.023113235281402,
|
| 1039 |
+
"index": 92,
|
| 1040 |
+
"prompt_characters": 149
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"prompt_tokens": 126,
|
| 1044 |
+
"completion_tokens": 128,
|
| 1045 |
+
"ttft_ms": 298.66793600376695,
|
| 1046 |
+
"decode_seconds": 8.815982783969957,
|
| 1047 |
+
"decode_tokens_per_second": 14.405654265900253,
|
| 1048 |
+
"e2e_seconds": 9.114650719973724,
|
| 1049 |
+
"e2e_tokens_per_second": 14.043324745237083,
|
| 1050 |
+
"index": 93,
|
| 1051 |
+
"prompt_characters": 129
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"prompt_tokens": 176,
|
| 1055 |
+
"completion_tokens": 128,
|
| 1056 |
+
"ttft_ms": 298.68044797331095,
|
| 1057 |
+
"decode_seconds": 8.825273936032318,
|
| 1058 |
+
"decode_tokens_per_second": 14.390488150342547,
|
| 1059 |
+
"e2e_seconds": 9.123954384005629,
|
| 1060 |
+
"e2e_tokens_per_second": 14.029004816637961,
|
| 1061 |
+
"index": 94,
|
| 1062 |
+
"prompt_characters": 181
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"prompt_tokens": 151,
|
| 1066 |
+
"completion_tokens": 128,
|
| 1067 |
+
"ttft_ms": 300.5360160022974,
|
| 1068 |
+
"decode_seconds": 8.817950623983052,
|
| 1069 |
+
"decode_tokens_per_second": 14.40243945737069,
|
| 1070 |
+
"e2e_seconds": 9.118486639985349,
|
| 1071 |
+
"e2e_tokens_per_second": 14.037417068607523,
|
| 1072 |
+
"index": 95,
|
| 1073 |
+
"prompt_characters": 182
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"prompt_tokens": 113,
|
| 1077 |
+
"completion_tokens": 128,
|
| 1078 |
+
"ttft_ms": 297.2445279592648,
|
| 1079 |
+
"decode_seconds": 8.82403992000036,
|
| 1080 |
+
"decode_tokens_per_second": 14.392500617789004,
|
| 1081 |
+
"e2e_seconds": 9.121284447959624,
|
| 1082 |
+
"e2e_tokens_per_second": 14.03311131565827,
|
| 1083 |
+
"index": 96,
|
| 1084 |
+
"prompt_characters": 72
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"prompt_tokens": 159,
|
| 1088 |
+
"completion_tokens": 128,
|
| 1089 |
+
"ttft_ms": 301.88958399230614,
|
| 1090 |
+
"decode_seconds": 8.817507632018533,
|
| 1091 |
+
"decode_tokens_per_second": 14.403163036551492,
|
| 1092 |
+
"e2e_seconds": 9.119397216010839,
|
| 1093 |
+
"e2e_tokens_per_second": 14.03601542602746,
|
| 1094 |
+
"index": 97,
|
| 1095 |
+
"prompt_characters": 144
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"prompt_tokens": 135,
|
| 1099 |
+
"completion_tokens": 128,
|
| 1100 |
+
"ttft_ms": 299.31110399775207,
|
| 1101 |
+
"decode_seconds": 8.813154784031212,
|
| 1102 |
+
"decode_tokens_per_second": 14.410276809175603,
|
| 1103 |
+
"e2e_seconds": 9.112465888028964,
|
| 1104 |
+
"e2e_tokens_per_second": 14.046691814578253,
|
| 1105 |
+
"index": 98,
|
| 1106 |
+
"prompt_characters": 146
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"prompt_tokens": 183,
|
| 1110 |
+
"completion_tokens": 128,
|
| 1111 |
+
"ttft_ms": 299.85328001203015,
|
| 1112 |
+
"decode_seconds": 8.828092415991705,
|
| 1113 |
+
"decode_tokens_per_second": 14.385893805319146,
|
| 1114 |
+
"e2e_seconds": 9.127945696003735,
|
| 1115 |
+
"e2e_tokens_per_second": 14.022870453319975,
|
| 1116 |
+
"index": 99,
|
| 1117 |
+
"prompt_characters": 214
|
| 1118 |
+
}
|
| 1119 |
+
]
|
| 1120 |
+
}
|
benchmark/dflash20k-b4-l1-elyza100-tps-histogram.png
CHANGED
|
|
Git LFS Details
|
benchmark/elyza100-baseline-vs-dflash-speedup.png
CHANGED
|
|
Git LFS Details
|
benchmark/elyza100-bf16-nvfp4-dflash-speedup-summary.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"count": 100,
|
| 3 |
+
"bf16": {
|
| 4 |
+
"name": "BF16",
|
| 5 |
+
"mean_tps": 14.415907661667651,
|
| 6 |
+
"median_tps": 14.405057756740758,
|
| 7 |
+
"ratio_of_mean_vs_bf16": 1.0,
|
| 8 |
+
"paired_speedup_mean_vs_bf16": 1.0,
|
| 9 |
+
"paired_speedup_median_vs_bf16": 1.0,
|
| 10 |
+
"paired_speedup_p05_vs_bf16": 1.0,
|
| 11 |
+
"paired_speedup_p95_vs_bf16": 1.0,
|
| 12 |
+
"requests_slower_than_bf16": 0
|
| 13 |
+
},
|
| 14 |
+
"nvfp4": {
|
| 15 |
+
"name": "NVFP4",
|
| 16 |
+
"mean_tps": 29.72816958251134,
|
| 17 |
+
"median_tps": 29.69194599518334,
|
| 18 |
+
"ratio_of_mean_vs_bf16": 2.062178135446821,
|
| 19 |
+
"paired_speedup_mean_vs_bf16": 2.062181336331503,
|
| 20 |
+
"paired_speedup_median_vs_bf16": 2.0610139004279286,
|
| 21 |
+
"paired_speedup_p05_vs_bf16": 2.0583650145121104,
|
| 22 |
+
"paired_speedup_p95_vs_bf16": 2.069276803345841,
|
| 23 |
+
"requests_slower_than_bf16": 0
|
| 24 |
+
},
|
| 25 |
+
"nvfp4_dflash": {
|
| 26 |
+
"name": "NVFP4 + DFlash",
|
| 27 |
+
"mean_tps": 49.038942024401024,
|
| 28 |
+
"median_tps": 48.95244489534201,
|
| 29 |
+
"ratio_of_mean_vs_bf16": 3.401724204629661,
|
| 30 |
+
"paired_speedup_mean_vs_bf16": 3.401837646698169,
|
| 31 |
+
"paired_speedup_median_vs_bf16": 3.3984135188496474,
|
| 32 |
+
"paired_speedup_p05_vs_bf16": 2.8543341194603595,
|
| 33 |
+
"paired_speedup_p95_vs_bf16": 4.120080899996654,
|
| 34 |
+
"requests_slower_than_bf16": 0
|
| 35 |
+
},
|
| 36 |
+
"dflash_paired_speedup_vs_nvfp4": {
|
| 37 |
+
"mean": 1.649690142355652,
|
| 38 |
+
"median": 1.6482948864124465,
|
| 39 |
+
"p05": 1.384932896270244,
|
| 40 |
+
"p95": 1.9981834458804657,
|
| 41 |
+
"requests_slower_than_nvfp4": 0
|
| 42 |
+
}
|
| 43 |
+
}
|
benchmark/elyza100-bf16-nvfp4-dflash-speedup.png
ADDED
|
Git LFS Details
|