feat: Add new benchmark results for various models and configurations, and update documentation UI with filtering for attention and tensor parallelism.
此提交包含在:
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 229.17851571500069,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 75285,
|
||||
"requests_per_second": 0.4363410753753066,
|
||||
"tokens_per_second": 328.49937859629955
|
||||
}
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 1302.7062463890015,
|
||||
"num_requests": 200,
|
||||
"total_num_tokens": 146805,
|
||||
"requests_per_second": 0.15352655332265747,
|
||||
"tokens_per_second": 112.69232830266365
|
||||
"elapsed_time": 899.6009820629988,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 75285,
|
||||
"requests_per_second": 0.11116039443473733,
|
||||
"tokens_per_second": 83.68710295019198
|
||||
}
|
||||
+7
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 442.1101265470061,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 75285,
|
||||
"requests_per_second": 0.2261879880043141,
|
||||
"tokens_per_second": 170.28562676904787
|
||||
}
|
||||
+7
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 639.3201232059982,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 75285,
|
||||
"requests_per_second": 0.15641616206061223,
|
||||
"tokens_per_second": 117.75790760733192
|
||||
}
|
||||
+7
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 577.3050836349939,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 75285,
|
||||
"requests_per_second": 0.1732186374842766,
|
||||
"tokens_per_second": 130.40765123003763
|
||||
}
|
||||
+7
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 865.5675225800005,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 75285,
|
||||
"requests_per_second": 0.115531136960788,
|
||||
"tokens_per_second": 86.97761646092924
|
||||
}
|
||||
-7
@@ -1,7 +0,0 @@
|
||||
{
|
||||
"elapsed_time": 540.2676798280002,
|
||||
"num_requests": 200,
|
||||
"total_num_tokens": 146805,
|
||||
"requests_per_second": 0.37018686748700586,
|
||||
"tokens_per_second": 271.7264154071495
|
||||
}
|
||||
+7
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 764.7424081899953,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 75285,
|
||||
"requests_per_second": 0.13076298493329488,
|
||||
"tokens_per_second": 98.44491320703105
|
||||
}
|
||||
+5
-5
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 1303.4944151099999,
|
||||
"num_requests": 200,
|
||||
"total_num_tokens": 146805,
|
||||
"requests_per_second": 0.15343372221746138,
|
||||
"tokens_per_second": 112.62418795067208
|
||||
"elapsed_time": 1052.5878375879984,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 75285,
|
||||
"requests_per_second": 0.09500394782173208,
|
||||
"tokens_per_second": 71.52372211759099
|
||||
}
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 310.4935437940003,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 76062,
|
||||
"requests_per_second": 0.3220678883627477,
|
||||
"tokens_per_second": 244.97127724647316
|
||||
}
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 914.8563823220001,
|
||||
"num_requests": 200,
|
||||
"total_num_tokens": 148857,
|
||||
"requests_per_second": 0.21861354838273012,
|
||||
"tokens_per_second": 162.71078485804028
|
||||
"elapsed_time": 550.0459713920009,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 76062,
|
||||
"requests_per_second": 0.18180298593393945,
|
||||
"tokens_per_second": 138.28298716107304
|
||||
}
|
||||
+7
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 193.03236384499905,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 74504,
|
||||
"requests_per_second": 0.5180478444552329,
|
||||
"tokens_per_second": 385.96636603292677
|
||||
}
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 522.8661062630126,
|
||||
"num_requests": 200,
|
||||
"total_num_tokens": 145877,
|
||||
"requests_per_second": 0.38250710383471637,
|
||||
"tokens_per_second": 278.99494393048457
|
||||
"elapsed_time": 311.826995067001,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 74504,
|
||||
"requests_per_second": 0.3206906444341466,
|
||||
"tokens_per_second": 238.92735772921657
|
||||
}
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 639.9174838529943,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 74946,
|
||||
"requests_per_second": 0.15627014814143225,
|
||||
"tokens_per_second": 117.11822522607781
|
||||
}
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 1339.915984058,
|
||||
"num_requests": 200,
|
||||
"total_num_tokens": 147036,
|
||||
"requests_per_second": 0.14926308990977954,
|
||||
"tokens_per_second": 109.73523843987172
|
||||
"elapsed_time": 1055.754198749999,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 74946,
|
||||
"requests_per_second": 0.09471901709545542,
|
||||
"tokens_per_second": 70.98811455236003
|
||||
}
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 271.0714236530039,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 74946,
|
||||
"requests_per_second": 0.36890646255655896,
|
||||
"tokens_per_second": 276.48063742763867
|
||||
}
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 468.4791132300161,
|
||||
"num_requests": 200,
|
||||
"total_num_tokens": 147036,
|
||||
"requests_per_second": 0.42691337639593563,
|
||||
"tokens_per_second": 313.85817605876395
|
||||
"elapsed_time": 404.31172934999995,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 74946,
|
||||
"requests_per_second": 0.24733390782594175,
|
||||
"tokens_per_second": 185.3668705592303
|
||||
}
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 374.65702054300345,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 75027,
|
||||
"requests_per_second": 0.2669107864442698,
|
||||
"tokens_per_second": 200.2551557455423
|
||||
}
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 560.7857336160014,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 75027,
|
||||
"requests_per_second": 0.17832122681721982,
|
||||
"tokens_per_second": 133.7890668441555
|
||||
}
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 234.33056626700272,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 75285,
|
||||
"requests_per_second": 0.42674757114723666,
|
||||
"tokens_per_second": 321.2769089381971
|
||||
}
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 874.8529941339984,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 75285,
|
||||
"requests_per_second": 0.11430491827828541,
|
||||
"tokens_per_second": 86.05445772580717
|
||||
}
|
||||
+7
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 438.29837328500435,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 75285,
|
||||
"requests_per_second": 0.2281550790401287,
|
||||
"tokens_per_second": 171.7665512553609
|
||||
}
|
||||
+7
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 621.1952276929987,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 75285,
|
||||
"requests_per_second": 0.16097998751758127,
|
||||
"tokens_per_second": 121.19378360261106
|
||||
}
|
||||
+7
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 573.4174093670008,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 75285,
|
||||
"requests_per_second": 0.17439303091685104,
|
||||
"tokens_per_second": 131.2917933257513
|
||||
}
|
||||
+7
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 838.6815635629973,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 75285,
|
||||
"requests_per_second": 0.11923476602390883,
|
||||
"tokens_per_second": 89.76589360109976
|
||||
}
|
||||
+7
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 746.2110970310023,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 75285,
|
||||
"requests_per_second": 0.13401033621434522,
|
||||
"tokens_per_second": 100.8896816189698
|
||||
}
|
||||
+7
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 1064.0833694909998,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 75285,
|
||||
"requests_per_second": 0.09397759881148657,
|
||||
"tokens_per_second": 70.75103526522766
|
||||
}
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 288.17777036500047,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 76062,
|
||||
"requests_per_second": 0.3470080286669645,
|
||||
"tokens_per_second": 263.9412467646666
|
||||
}
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 422.3444380089968,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 76062,
|
||||
"requests_per_second": 0.23677356915463818,
|
||||
"tokens_per_second": 180.0947121704009
|
||||
}
|
||||
+7
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 195.17220506099693,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 74504,
|
||||
"requests_per_second": 0.5123680391311207,
|
||||
"tokens_per_second": 381.7346838742502
|
||||
}
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 308.955628978998,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 74504,
|
||||
"requests_per_second": 0.32367107319089417,
|
||||
"tokens_per_second": 241.1478963701438
|
||||
}
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 619.8506736600029,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 74946,
|
||||
"requests_per_second": 0.16132917854155862,
|
||||
"tokens_per_second": 120.90976614975652
|
||||
}
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 1103.3186353329984,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 74946,
|
||||
"requests_per_second": 0.09063564848591402,
|
||||
"tokens_per_second": 67.92779311425312
|
||||
}
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 260.26568330699956,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 74946,
|
||||
"requests_per_second": 0.38422276317559617,
|
||||
"tokens_per_second": 287.95959208958226
|
||||
}
|
||||
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"elapsed_time": 405.08143226500033,
|
||||
"num_requests": 100,
|
||||
"total_num_tokens": 74946,
|
||||
"requests_per_second": 0.24686394397504988,
|
||||
"tokens_per_second": 185.01465145154089
|
||||
}
|
||||
-7
@@ -1,7 +0,0 @@
|
||||
{
|
||||
"elapsed_time": 1237.550695703001,
|
||||
"num_requests": 200,
|
||||
"total_num_tokens": 146805,
|
||||
"requests_per_second": 0.16160954108339642,
|
||||
"tokens_per_second": 118.62544339374007
|
||||
}
|
||||
-7
@@ -1,7 +0,0 @@
|
||||
{
|
||||
"elapsed_time": 540.6128817510034,
|
||||
"num_requests": 200,
|
||||
"total_num_tokens": 148857,
|
||||
"requests_per_second": 0.36995048906754757,
|
||||
"tokens_per_second": 275.34859975563967
|
||||
}
|
||||
-7
@@ -1,7 +0,0 @@
|
||||
{
|
||||
"elapsed_time": 455.23138687500614,
|
||||
"num_requests": 200,
|
||||
"total_num_tokens": 145877,
|
||||
"requests_per_second": 0.43933701797875907,
|
||||
"tokens_per_second": 320.4458308584372
|
||||
}
|
||||
-7
@@ -1,7 +0,0 @@
|
||||
{
|
||||
"elapsed_time": 1279.5375675789983,
|
||||
"num_requests": 200,
|
||||
"total_num_tokens": 147036,
|
||||
"requests_per_second": 0.15630646967124087,
|
||||
"tokens_per_second": 114.91339037290285
|
||||
}
|
||||
-7
@@ -1,7 +0,0 @@
|
||||
{
|
||||
"elapsed_time": 460.97370730798866,
|
||||
"num_requests": 200,
|
||||
"total_num_tokens": 147036,
|
||||
"requests_per_second": 0.43386422442175154,
|
||||
"tokens_per_second": 318.9683005103833
|
||||
}
|
||||
新增問題並參考
封鎖使用者