feat: Add new benchmark results for various models and configurations, and update documentation UI with filtering for attention and tensor parallelism.

This commit is contained in:
Donato Capitella
2026-02-02 21:30:17 +00:00
vanhempi a412c6bea3
commit 4d3b046870
43 muutettua tiedostoa jossa 859 lisäystä ja 361 poistoa
@@ -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
}
@@ -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
}
@@ -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
}
@@ -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
}
@@ -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
}
@@ -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
}
@@ -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
}
@@ -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
}
@@ -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
}