Files
qwen38-flash-next-dgx-spark/docs/results/profile128k/benchmark-summary.json
T

395 lines
8.4 KiB
JSON

{
"eager": {
"total_requests": 19,
"correct": 19,
"groups": {
"short": {
"n": 3,
"correct": 3,
"ttft_s": {
"median": 0.2627224419993581,
"values": [
0.33354272600263357,
0.2627224419993581,
0.26176839799882146
]
},
"elapsed_s": {
"median": 7.373869219998596,
"values": [
7.68168595500174,
7.373869219998596,
7.35648784199293
]
},
"decode_tps_approx": {
"median": 29.953694756255302,
"values": [
28.987645227728436,
29.953694756255302,
30.02293954286349
]
},
"output_tokens": [
214,
214,
214
],
"reasoning_tokens": [
111,
111,
111
]
},
"prefill-8192": {
"n": 3,
"correct": 3,
"ttft_s": {
"median": 3.7875278329956927,
"values": [
4.006232126004761,
3.7754420729979756,
3.7875278329956927
]
},
"elapsed_s": {
"median": 5.739436170995759,
"values": [
5.835497587999271,
5.626387860997056,
5.739436170995759
]
},
"decode_tps_approx": {
"median": 35.041074313706375,
"values": [
35.584837627199924,
35.041074313706375,
32.64277985613848
]
},
"output_tokens": [
63,
63,
62
],
"reasoning_tokens": [
55,
55,
54
]
},
"reuse-8192": {
"n": 3,
"correct": 3,
"ttft_s": {
"median": 0.8803304789980757,
"values": [
0.8856951920024585,
0.8737719170021592,
0.8803304789980757
]
},
"elapsed_s": {
"median": 2.811309409997193,
"values": [
2.7496982970042154,
2.835690722997242,
2.811309409997193
]
},
"decode_tps_approx": {
"median": 36.047200027797416,
"values": [
34.74998178667343,
36.047200027797416,
36.74879746387076
]
},
"output_tokens": [
63,
69,
69
],
"reasoning_tokens": [
55,
61,
61
]
},
"prefill-32768": {
"n": 3,
"correct": 3,
"ttft_s": {
"median": 15.41581593700539,
"values": [
15.595506220997777,
15.403379977004079,
15.41581593700539
]
},
"elapsed_s": {
"median": 17.35202403000585,
"values": [
17.837196191001567,
17.295454844999767,
17.35202403000585
]
},
"decode_tps_approx": {
"median": 36.438073002765556,
"values": [
33.795316059955795,
36.438073002765556,
36.713832650404036
]
},
"output_tokens": [
74,
67,
69
],
"reasoning_tokens": [
66,
59,
61
]
},
"reuse-32768": {
"n": 3,
"correct": 3,
"ttft_s": {
"median": 1.367758443004277,
"values": [
1.368702627994935,
1.367758443004277,
1.357998088002205
]
},
"elapsed_s": {
"median": 3.5468969909998123,
"values": [
3.579059300995141,
3.5468969909998123,
3.3747847780032316
]
},
"decode_tps_approx": {
"median": 32.877578996597116,
"values": [
32.419700549347965,
32.877578996597116,
33.71865583479496
]
},
"output_tokens": [
70,
70,
69
],
"reasoning_tokens": [
62,
62,
61
]
}
}
},
"graph": {
"total_requests": 19,
"correct": 19,
"groups": {
"short": {
"n": 3,
"correct": 3,
"ttft_s": {
"median": 0.2623967160034226,
"values": [
0.32573997599683935,
0.2600282569983392,
0.2623967160034226
]
},
"elapsed_s": {
"median": 7.0642776130043785,
"values": [
7.360314821999054,
7.060739258995454,
7.0642776130043785
]
},
"decode_tps_approx": {
"median": 31.315723764990278,
"values": [
30.279974628892248,
31.32107217692348,
31.315723764990278
]
},
"output_tokens": [
214,
214,
214
],
"reasoning_tokens": [
111,
111,
111
]
},
"prefill-8192": {
"n": 3,
"correct": 3,
"ttft_s": {
"median": 3.7701075279983343,
"values": [
3.921214998998039,
3.7701075279983343,
3.768740819999948
]
},
"elapsed_s": {
"median": 5.670499198000471,
"values": [
6.191493427999376,
5.596617848997994,
5.670499198000471
]
},
"decode_tps_approx": {
"median": 35.516432222041566,
"values": [
33.338899955373805,
35.516432222041566,
37.32072215199369
]
},
"output_tokens": [
74,
63,
69
],
"reasoning_tokens": [
66,
55,
61
]
},
"reuse-8192": {
"n": 3,
"correct": 3,
"ttft_s": {
"median": 0.8737782960015466,
"values": [
0.8737782960015466,
0.8690901810041396,
0.8816422219970264
]
},
"elapsed_s": {
"median": 2.8319971849996364,
"values": [
2.8319971849996364,
3.0074559670028975,
2.711807350999152
]
},
"decode_tps_approx": {
"median": 35.510793077788634,
"values": [
34.055335354489465,
35.510793077788634,
35.522341967132114
]
},
"output_tokens": [
65,
74,
63
],
"reasoning_tokens": [
57,
66,
55
]
},
"prefill-32768": {
"n": 3,
"correct": 3,
"ttft_s": {
"median": 15.375977513001999,
"values": [
15.511759164000978,
15.357147006005107,
15.375977513001999
]
},
"elapsed_s": {
"median": 17.268514374001825,
"values": [
17.691939716001798,
17.239325528003974,
17.268514374001825
]
},
"decode_tps_approx": {
"median": 37.54862656190945,
"values": [
32.87688689931954,
37.728914829613814,
37.54862656190945
]
},
"output_tokens": [
70,
69,
69
],
"reasoning_tokens": [
62,
61,
61
]
},
"reuse-32768": {
"n": 3,
"correct": 3,
"ttft_s": {
"median": 1.3270910260034725,
"values": [
1.325252010996337,
1.3272808809997514,
1.3270910260034725
]
},
"elapsed_s": {
"median": 3.293290553992847,
"values": [
3.293290553992847,
3.4540864679947845,
3.2060768180017476
]
},
"decode_tps_approx": {
"median": 36.2184980346298,
"values": [
36.2184980346298,
33.71980234098872,
37.82214005937634
]
},
"output_tokens": [
69,
70,
69
],
"reasoning_tokens": [
61,
62,
61
]
}
}
}
}