Files
aituner/runs/frontier-split-rootcause-v0/frozen-inputs/q30-expansion-lo/fixed-pd-real-audit.json
2026-07-20 12:05:20 +08:00

1299 lines
42 KiB
JSON

{
"applicable_metrics": [
"ttft_ms",
"tpot_ms",
"e2e_ms"
],
"case_root": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd",
"configs": {
"tp1_mns16": {
"metrics": {
"e2e_ms": {
"pooled_mean_ms": 767.1236270730016,
"pooled_p90_ms": 766.9662160333246,
"pooled_samples": 387,
"trial_mean_of_means_ms": 767.1236270730016,
"trial_stddev_of_means_ms": 3.640625296359905
},
"tpot_ms": {
"pooled_mean_ms": 4.8488702313524765,
"pooled_p90_ms": 4.838337488362463,
"pooled_samples": 387,
"trial_mean_of_means_ms": 4.8488702313524765,
"trial_stddev_of_means_ms": 0.02240869837530002
},
"ttft_ms": {
"pooled_mean_ms": 151.28173231440826,
"pooled_p90_ms": 152.70179708022624,
"pooled_samples": 387,
"trial_mean_of_means_ms": 151.28173231440823,
"trial_stddev_of_means_ms": 0.9864045576075636
}
},
"trials": [
{
"metrics": {
"e2e_ms": {
"mean_ms": 767.2682947591092,
"p90_ms": 803.2620819285512,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.854438677765834,
"p90_ms": 5.140277842155064,
"samples": 129
},
"ttft_ms": {
"mean_ms": 150.72045104159403,
"p90_ms": 151.41086804214865,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp1_mns16/trial1/results/result.json",
"trial": 1
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 763.412824322022,
"p90_ms": 763.9202950522304,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.824202359768954,
"p90_ms": 4.827735795250793,
"samples": 129
},
"ttft_ms": {
"mean_ms": 150.70405107013187,
"p90_ms": 151.4174829935655,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp1_mns16/trial2/results/result.json",
"trial": 2
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 770.6897621378736,
"p90_ms": 806.9713360164315,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.867969656522642,
"p90_ms": 5.155875693134025,
"samples": 129
},
"ttft_ms": {
"mean_ms": 152.42069483149882,
"p90_ms": 153.3631639322266,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp1_mns16/trial3/results/result.json",
"trial": 3
}
]
},
"tp1_mns32": {
"metrics": {
"e2e_ms": {
"pooled_mean_ms": 767.2448034298387,
"pooled_p90_ms": 768.11003300827,
"pooled_samples": 387,
"trial_mean_of_means_ms": 767.2448034298387,
"trial_stddev_of_means_ms": 2.5069380140145388
},
"tpot_ms": {
"pooled_mean_ms": 4.848521902720499,
"pooled_p90_ms": 4.846741385779923,
"pooled_samples": 387,
"trial_mean_of_means_ms": 4.848521902720499,
"trial_stddev_of_means_ms": 0.016759800320354026
},
"ttft_ms": {
"pooled_mean_ms": 151.4453163664687,
"pooled_p90_ms": 152.51897496636957,
"pooled_samples": 387,
"trial_mean_of_means_ms": 151.4453163664687,
"trial_stddev_of_means_ms": 0.9359392091301725
}
},
"trials": [
{
"metrics": {
"e2e_ms": {
"mean_ms": 766.5741731901834,
"p90_ms": 802.9849890153855,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.851220601996876,
"p90_ms": 5.135506000113123,
"samples": 129
},
"ttft_ms": {
"mean_ms": 150.43522373325544,
"p90_ms": 151.12131391651928,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp1_mns32/trial1/results/result.json",
"trial": 1
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 765.1413833206274,
"p90_ms": 766.2973250262439,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.830576509172996,
"p90_ms": 4.836877464228786,
"samples": 129
},
"ttft_ms": {
"mean_ms": 151.61754613085253,
"p90_ms": 152.396842953749,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp1_mns32/trial2/results/result.json",
"trial": 2
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 770.0188537787054,
"p90_ms": 805.9141940902919,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.863768596991625,
"p90_ms": 5.147916850575253,
"samples": 129
},
"ttft_ms": {
"mean_ms": 152.2831792352981,
"p90_ms": 153.04890798870474,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp1_mns32/trial3/results/result.json",
"trial": 3
}
]
},
"tp1_mns64": {
"metrics": {
"e2e_ms": {
"pooled_mean_ms": 766.7927716823189,
"pooled_p90_ms": 766.5371090406552,
"pooled_samples": 387,
"trial_mean_of_means_ms": 766.7927716823189,
"trial_stddev_of_means_ms": 2.196495670572406
},
"tpot_ms": {
"pooled_mean_ms": 4.84126870357575,
"pooled_p90_ms": 4.839739204919714,
"pooled_samples": 387,
"trial_mean_of_means_ms": 4.84126870357575,
"trial_stddev_of_means_ms": 0.017335823614573528
},
"ttft_ms": {
"pooled_mean_ms": 151.91121668752177,
"pooled_p90_ms": 152.6928918901831,
"pooled_samples": 387,
"trial_mean_of_means_ms": 151.91121668752177,
"trial_stddev_of_means_ms": 0.09417854078816222
}
},
"trials": [
{
"metrics": {
"e2e_ms": {
"mean_ms": 767.9369603139312,
"p90_ms": 773.8644760102034,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.851052223623522,
"p90_ms": 4.915137134499731,
"samples": 129
},
"ttft_ms": {
"mean_ms": 151.8117881212167,
"p90_ms": 152.64031395781785,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp1_mns64/trial1/results/result.json",
"trial": 1
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 764.260392307571,
"p90_ms": 765.39497601334,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.8212526970581795,
"p90_ms": 4.825043646017398,
"samples": 129
},
"ttft_ms": {
"mean_ms": 151.92278562106424,
"p90_ms": 152.61299489066005,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp1_mns64/trial2/results/result.json",
"trial": 2
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 768.1809624254545,
"p90_ms": 804.694763966836,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.85150119004555,
"p90_ms": 5.139402172520874,
"samples": 129
},
"ttft_ms": {
"mean_ms": 151.9990763202844,
"p90_ms": 152.9452829854563,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp1_mns64/trial3/results/result.json",
"trial": 3
}
]
},
"tp1_mns8": {
"metrics": {
"e2e_ms": {
"pooled_mean_ms": 768.6282821211396,
"pooled_p90_ms": 768.3246430242434,
"pooled_samples": 387,
"trial_mean_of_means_ms": 768.6282821211395,
"trial_stddev_of_means_ms": 2.3163990743969975
},
"tpot_ms": {
"pooled_mean_ms": 4.856374974269665,
"pooled_p90_ms": 4.857163118220514,
"pooled_samples": 387,
"trial_mean_of_means_ms": 4.856374974269665,
"trial_stddev_of_means_ms": 0.01888354805682215
},
"ttft_ms": {
"pooled_mean_ms": 151.83002628369175,
"pooled_p90_ms": 152.63689204584807,
"pooled_samples": 387,
"trial_mean_of_means_ms": 151.83002628369175,
"trial_stddev_of_means_ms": 0.2293889652860975
}
},
"trials": [
{
"metrics": {
"e2e_ms": {
"mean_ms": 769.7875488309421,
"p90_ms": 806.7109240218997,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.864016504716275,
"p90_ms": 5.151719298565716,
"samples": 129
},
"ttft_ms": {
"mean_ms": 152.02143533036198,
"p90_ms": 152.73106703534722,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp1_mns8/trial1/results/result.json",
"trial": 1
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 765.9611190793776,
"p90_ms": 765.8235019771382,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.83486823588853,
"p90_ms": 4.831250046570529,
"samples": 129
},
"ttft_ms": {
"mean_ms": 151.89288162297836,
"p90_ms": 152.7155089424923,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp1_mns8/trial2/results/result.json",
"trial": 2
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 770.1361784530991,
"p90_ms": 806.5015620086342,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.8702401822041885,
"p90_ms": 5.154327385853536,
"samples": 129
},
"ttft_ms": {
"mean_ms": 151.5757618977349,
"p90_ms": 152.41257997695357,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp1_mns8/trial3/results/result.json",
"trial": 3
}
]
},
"tp2_mns16": {
"metrics": {
"e2e_ms": {
"pooled_mean_ms": 683.3139202742204,
"pooled_p90_ms": 691.7126830667257,
"pooled_samples": 387,
"trial_mean_of_means_ms": 683.3139202742204,
"trial_stddev_of_means_ms": 13.480078748721647
},
"tpot_ms": {
"pooled_mean_ms": 4.606023389027604,
"pooled_p90_ms": 4.679884338076777,
"pooled_samples": 387,
"trial_mean_of_means_ms": 4.606023389027605,
"trial_stddev_of_means_ms": 0.11860164117227036
},
"ttft_ms": {
"pooled_mean_ms": 98.30897632000838,
"pooled_p90_ms": 100.99728393834084,
"pooled_samples": 387,
"trial_mean_of_means_ms": 98.30897632000837,
"trial_stddev_of_means_ms": 1.6033196848780447
}
},
"trials": [
{
"metrics": {
"e2e_ms": {
"mean_ms": 691.7368602395678,
"p90_ms": 693.4372959658504,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.677960039364579,
"p90_ms": 4.685888802962686,
"samples": 129
},
"ttft_ms": {
"mean_ms": 97.59817232175679,
"p90_ms": 98.27463503461331,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp2_mns16/trial1/results/result.json",
"trial": 1
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 667.7665301777292,
"p90_ms": 672.6519849617034,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.4691333712332115,
"p90_ms": 4.478958197026037,
"samples": 129
},
"ttft_ms": {
"mean_ms": 100.14481820949433,
"p90_ms": 103.45508099999279,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp2_mns16/trial2/results/result.json",
"trial": 2
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 690.4383704053643,
"p90_ms": 691.623940016143,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.670976756485024,
"p90_ms": 4.677882693033284,
"samples": 129
},
"ttft_ms": {
"mean_ms": 97.18393842877401,
"p90_ms": 98.27898698858917,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp2_mns16/trial3/results/result.json",
"trial": 3
}
]
},
"tp2_mns32": {
"metrics": {
"e2e_ms": {
"pooled_mean_ms": 689.548538498116,
"pooled_p90_ms": 691.6915030451491,
"pooled_samples": 387,
"trial_mean_of_means_ms": 689.548538498116,
"trial_stddev_of_means_ms": 0.4691564069544124
},
"tpot_ms": {
"pooled_mean_ms": 4.66880722232803,
"pooled_p90_ms": 4.676126267240331,
"pooled_samples": 387,
"trial_mean_of_means_ms": 4.66880722232803,
"trial_stddev_of_means_ms": 0.006071937772150551
},
"ttft_ms": {
"pooled_mean_ms": 96.57110613066877,
"pooled_p90_ms": 98.41530094854534,
"pooled_samples": 387,
"trial_mean_of_means_ms": 96.57110613066875,
"trial_stddev_of_means_ms": 0.8723383104752306
}
},
"trials": [
{
"metrics": {
"e2e_ms": {
"mean_ms": 689.6087854717995,
"p90_ms": 691.4246910018846,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.661907737752395,
"p90_ms": 4.664850331417571,
"samples": 129
},
"ttft_ms": {
"mean_ms": 97.50512631721939,
"p90_ms": 99.51729699969292,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp2_mns32/trial1/results/result.json",
"trial": 1
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 689.9846611488538,
"p90_ms": 692.5024109659716,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.673336901073146,
"p90_ms": 4.679785157722517,
"samples": 129
},
"ttft_ms": {
"mean_ms": 96.43071331534996,
"p90_ms": 98.4487070236355,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp2_mns32/trial2/results/result.json",
"trial": 2
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 689.0521688736947,
"p90_ms": 691.1603320622817,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.671177028158549,
"p90_ms": 4.681181668589904,
"samples": 129
},
"ttft_ms": {
"mean_ms": 95.77747875943693,
"p90_ms": 97.0232019899413,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp2_mns32/trial3/results/result.json",
"trial": 3
}
]
},
"tp2_mns64": {
"metrics": {
"e2e_ms": {
"pooled_mean_ms": 689.733952092541,
"pooled_p90_ms": 691.8661230010912,
"pooled_samples": 387,
"trial_mean_of_means_ms": 689.733952092541,
"trial_stddev_of_means_ms": 1.30873077294457
},
"tpot_ms": {
"pooled_mean_ms": 4.680890721121927,
"pooled_p90_ms": 4.687803739674506,
"pooled_samples": 387,
"trial_mean_of_means_ms": 4.680890721121927,
"trial_stddev_of_means_ms": 0.0021247475013520785
},
"ttft_ms": {
"pooled_mean_ms": 95.22211026624134,
"pooled_p90_ms": 97.45279501657933,
"pooled_samples": 387,
"trial_mean_of_means_ms": 95.22211026624133,
"trial_stddev_of_means_ms": 1.485311605474211
}
},
"trials": [
{
"metrics": {
"e2e_ms": {
"mean_ms": 688.8176469527575,
"p90_ms": 690.4401639476418,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.680177864121985,
"p90_ms": 4.685609865434996,
"samples": 129
},
"ttft_ms": {
"mean_ms": 94.3946194773641,
"p90_ms": 95.91560496482998,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp2_mns64/trial1/results/result.json",
"trial": 1
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 691.2328087049717,
"p90_ms": 693.3015899267048,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.679214066220331,
"p90_ms": 4.690911558522719,
"samples": 129
},
"ttft_ms": {
"mean_ms": 96.93685328216083,
"p90_ms": 98.8241919549182,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp2_mns64/trial2/results/result.json",
"trial": 2
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 689.1514006198939,
"p90_ms": 690.7796860905364,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.683280233023465,
"p90_ms": 4.687803739674506,
"samples": 129
},
"ttft_ms": {
"mean_ms": 94.33485803919909,
"p90_ms": 95.42244195472449,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp2_mns64/trial3/results/result.json",
"trial": 3
}
]
},
"tp2_mns8": {
"metrics": {
"e2e_ms": {
"pooled_mean_ms": 688.7246717025648,
"pooled_p90_ms": 691.0650019999593,
"pooled_samples": 387,
"trial_mean_of_means_ms": 688.7246717025649,
"trial_stddev_of_means_ms": 1.440994479221059
},
"tpot_ms": {
"pooled_mean_ms": 4.67674757633165,
"pooled_p90_ms": 4.68690808693783,
"pooled_samples": 387,
"trial_mean_of_means_ms": 4.67674757633165,
"trial_stddev_of_means_ms": 0.014951986782554206
},
"ttft_ms": {
"pooled_mean_ms": 94.74037260235858,
"pooled_p90_ms": 96.15806792862713,
"pooled_samples": 387,
"trial_mean_of_means_ms": 94.74037260235859,
"trial_stddev_of_means_ms": 0.5067099323623165
}
},
"trials": [
{
"metrics": {
"e2e_ms": {
"mean_ms": 687.0613511852097,
"p90_ms": 689.566144021228,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.659691155888254,
"p90_ms": 4.6653019678668946,
"samples": 129
},
"ttft_ms": {
"mean_ms": 95.2438001354882,
"p90_ms": 96.90531203523278,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp2_mns8/trial1/results/result.json",
"trial": 1
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 689.5177478770285,
"p90_ms": 691.6546910069883,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.682958287904102,
"p90_ms": 4.686032913214579,
"samples": 129
},
"ttft_ms": {
"mean_ms": 94.74687482042657,
"p90_ms": 96.44627594389021,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp2_mns8/trial2/results/result.json",
"trial": 2
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 689.5949160454563,
"p90_ms": 691.671111038886,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.687593285202594,
"p90_ms": 4.695545803154196,
"samples": 129
},
"ttft_ms": {
"mean_ms": 94.23044285116096,
"p90_ms": 95.47765098977834,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp2_mns8/trial3/results/result.json",
"trial": 3
}
]
},
"tp4_mns16": {
"metrics": {
"e2e_ms": {
"pooled_mean_ms": 607.6659436830384,
"pooled_p90_ms": 614.7840449120849,
"pooled_samples": 387,
"trial_mean_of_means_ms": 607.6659436830384,
"trial_stddev_of_means_ms": 5.83329156754365
},
"tpot_ms": {
"pooled_mean_ms": 4.288118025279364,
"pooled_p90_ms": 4.3549379049690335,
"pooled_samples": 387,
"trial_mean_of_means_ms": 4.288118025279364,
"trial_stddev_of_means_ms": 0.05739660569371236
},
"ttft_ms": {
"pooled_mean_ms": 63.03574686938565,
"pooled_p90_ms": 66.4233659626916,
"pooled_samples": 387,
"trial_mean_of_means_ms": 63.035746869385655,
"trial_stddev_of_means_ms": 1.4920342964335762
}
},
"trials": [
{
"metrics": {
"e2e_ms": {
"mean_ms": 604.923196775882,
"p90_ms": 609.2176410602406,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.258012776043345,
"p90_ms": 4.267158401088686,
"samples": 129
},
"ttft_ms": {
"mean_ms": 64.11492886642615,
"p90_ms": 68.74241400510073,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp4_mns16/trial1/results/result.json",
"trial": 1
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 614.3651023297751,
"p90_ms": 616.209093015641,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.354304061884912,
"p90_ms": 4.365195747552894,
"samples": 129
},
"ttft_ms": {
"mean_ms": 61.33310341947647,
"p90_ms": 62.62887897901237,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp4_mns16/trial2/results/result.json",
"trial": 2
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 603.7095319434582,
"p90_ms": 607.3436400620267,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.252037237909835,
"p90_ms": 4.25958238619079,
"samples": 129
},
"ttft_ms": {
"mean_ms": 63.65920832225432,
"p90_ms": 66.49800203740597,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp4_mns16/trial3/results/result.json",
"trial": 3
}
]
},
"tp4_mns32": {
"metrics": {
"e2e_ms": {
"pooled_mean_ms": 604.4058500071964,
"pooled_p90_ms": 611.0399010358378,
"pooled_samples": 387,
"trial_mean_of_means_ms": 604.4058500071964,
"trial_stddev_of_means_ms": 4.461581159639322
},
"tpot_ms": {
"pooled_mean_ms": 4.254808547439789,
"pooled_p90_ms": 4.27782233056473,
"pooled_samples": 387,
"trial_mean_of_means_ms": 4.254808547439789,
"trial_stddev_of_means_ms": 0.018762002450543058
},
"ttft_ms": {
"pooled_mean_ms": 64.01019376246572,
"pooled_p90_ms": 68.59070702921599,
"pooled_samples": 387,
"trial_mean_of_means_ms": 64.0101937624657,
"trial_stddev_of_means_ms": 2.2209645174649575
}
},
"trials": [
{
"metrics": {
"e2e_ms": {
"mean_ms": 609.0962116628192,
"p90_ms": 614.4514320185408,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.276095369246001,
"p90_ms": 4.289275638421807,
"samples": 129
},
"ttft_ms": {
"mean_ms": 65.99773169953608,
"p90_ms": 71.24563900288194,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp4_mns32/trial1/results/result.json",
"trial": 1
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 603.9062279290989,
"p90_ms": 610.2306098910049,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.247653137253014,
"p90_ms": 4.260518551459462,
"samples": 129
},
"ttft_ms": {
"mean_ms": 64.41997497093452,
"p90_ms": 68.43586196191609,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp4_mns32/trial2/results/result.json",
"trial": 2
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 600.215110429671,
"p90_ms": 602.216740953736,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.240677135820352,
"p90_ms": 4.246149299204291,
"samples": 129
},
"ttft_ms": {
"mean_ms": 61.61287461692655,
"p90_ms": 63.24575201142579,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp4_mns32/trial3/results/result.json",
"trial": 3
}
]
},
"tp4_mns64": {
"metrics": {
"e2e_ms": {
"pooled_mean_ms": 605.5669432571543,
"pooled_p90_ms": 610.7392100384459,
"pooled_samples": 387,
"trial_mean_of_means_ms": 605.5669432571543,
"trial_stddev_of_means_ms": 2.5583322144334986
},
"tpot_ms": {
"pooled_mean_ms": 4.264903840417586,
"pooled_p90_ms": 4.27982993753935,
"pooled_samples": 387,
"trial_mean_of_means_ms": 4.264903840417586,
"trial_stddev_of_means_ms": 0.008241890125268254
},
"ttft_ms": {
"pooled_mean_ms": 63.8859268507706,
"pooled_p90_ms": 67.59266997687519,
"pooled_samples": 387,
"trial_mean_of_means_ms": 63.8859268507706,
"trial_stddev_of_means_ms": 1.5158748686612207
}
},
"trials": [
{
"metrics": {
"e2e_ms": {
"mean_ms": 605.7536339084077,
"p90_ms": 610.4160649701953,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.264924569000695,
"p90_ms": 4.281197173161593,
"samples": 129
},
"ttft_ms": {
"mean_ms": 64.06844277909502,
"p90_ms": 67.37245502881706,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp4_mns64/trial1/results/result.json",
"trial": 1
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 602.9203796349539,
"p90_ms": 606.4624059945345,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.256651605550648,
"p90_ms": 4.271073574860265,
"samples": 129
},
"ttft_ms": {
"mean_ms": 62.287057342022194,
"p90_ms": 64.74815693218261,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp4_mns64/trial2/results/result.json",
"trial": 2
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 608.0268162281014,
"p90_ms": 613.2307189982384,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.273135346701415,
"p90_ms": 4.29227040974262,
"samples": 129
},
"ttft_ms": {
"mean_ms": 65.30228043119459,
"p90_ms": 69.0081981010735,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp4_mns64/trial3/results/result.json",
"trial": 3
}
]
},
"tp4_mns8": {
"metrics": {
"e2e_ms": {
"pooled_mean_ms": 605.0888788116282,
"pooled_p90_ms": 610.0081680342555,
"pooled_samples": 387,
"trial_mean_of_means_ms": 605.0888788116282,
"trial_stddev_of_means_ms": 0.8901667424570828
},
"tpot_ms": {
"pooled_mean_ms": 4.256483071855015,
"pooled_p90_ms": 4.268226101921182,
"pooled_samples": 387,
"trial_mean_of_means_ms": 4.256483071855015,
"trial_stddev_of_means_ms": 0.0026292150472670742
},
"ttft_ms": {
"pooled_mean_ms": 64.47646671392322,
"pooled_p90_ms": 68.37363401427865,
"pooled_samples": 387,
"trial_mean_of_means_ms": 64.47646671392322,
"trial_stddev_of_means_ms": 1.0383603866006366
}
},
"trials": [
{
"metrics": {
"e2e_ms": {
"mean_ms": 606.0357820910452,
"p90_ms": 611.1916180234402,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.2545578456668816,
"p90_ms": 4.264190204544213,
"samples": 129
},
"ttft_ms": {
"mean_ms": 65.67109757204099,
"p90_ms": 71.20707002468407,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp4_mns8/trial1/results/result.json",
"trial": 1
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 604.2691217230041,
"p90_ms": 608.334549004212,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.2554127314675245,
"p90_ms": 4.26826358307153,
"samples": 129
},
"ttft_ms": {
"mean_ms": 63.79063503163354,
"p90_ms": 67.93791998643428,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp4_mns8/trial2/results/result.json",
"trial": 2
},
{
"metrics": {
"e2e_ms": {
"mean_ms": 604.9617326208354,
"p90_ms": 610.0081680342555,
"samples": 129
},
"tpot_ms": {
"mean_ms": 4.259478638430637,
"p90_ms": 4.271154976669904,
"samples": 129
},
"ttft_ms": {
"mean_ms": 63.96766753809512,
"p90_ms": 67.67752906307578,
"samples": 129
}
},
"requests": 129,
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-pd/real/tp4_mns8/trial3/results/result.json",
"trial": 3
}
]
}
},
"prefill_only": false,
"schema": "qwen30-latency-case-real-audit-v1",
"trace_manifests": {
"tp1": {
"description": "fixed-shape: deterministic token IDs, uniform TP-normalized QPS, no prefix reuse",
"first_arrival_s": 0.0,
"global_offered_request_rate": 0.215,
"last_arrival_s": 595.3488372093024,
"output_tokens": [
128
],
"per_gpu_offered_request_rate": 0.215,
"prefix_caching": false,
"private_jsonl": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/fixed-pd/tp1/private/real_requests.jsonl",
"private_jsonl_sha256": "fa903f38c522a1ab5fa6325697f7aebd8ce17c0809ecee5cba7f28ec7eb6a030",
"public_csv": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/fixed-pd/tp1/public/frontier.csv",
"public_csv_sha256": "d33dd9fcd1aea6c6a6fb6730d8bfe30392ad6827f4132682ad151cccabe4bf2d",
"requests": 129,
"row_vector_sha256": "6cb1cdd992eca886c8f1611ee83ec1373ff162bd1b608a8ce23974885b393aea",
"schema": "qwen30-latency-case-v1",
"tensor_parallel_size": 1
},
"tp2": {
"description": "fixed-shape: deterministic token IDs, uniform TP-normalized QPS, no prefix reuse",
"first_arrival_s": 0.0,
"global_offered_request_rate": 0.43,
"last_arrival_s": 297.6744186046512,
"output_tokens": [
128
],
"per_gpu_offered_request_rate": 0.215,
"prefix_caching": false,
"private_jsonl": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/fixed-pd/tp2/private/real_requests.jsonl",
"private_jsonl_sha256": "51d9e597d5efec87f9a6a7ea425ee1fa95eb4d80db8cadaaef8acbab0f024919",
"public_csv": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/fixed-pd/tp2/public/frontier.csv",
"public_csv_sha256": "c3d7ce76385f348e8082d9aae1449384e9710a2d4c9a0b8b5d36bac28a5f2434",
"requests": 129,
"row_vector_sha256": "51947bb92449fc5be3ecaafb5b0ba08acd848ff5c6cff9a04a66bd3fda74d45e",
"schema": "qwen30-latency-case-v1",
"tensor_parallel_size": 2
},
"tp4": {
"description": "fixed-shape: deterministic token IDs, uniform TP-normalized QPS, no prefix reuse",
"first_arrival_s": 0.0,
"global_offered_request_rate": 0.86,
"last_arrival_s": 148.8372093023256,
"output_tokens": [
128
],
"per_gpu_offered_request_rate": 0.215,
"prefix_caching": false,
"private_jsonl": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/fixed-pd/tp4/private/real_requests.jsonl",
"private_jsonl_sha256": "90450c8ca24055ed18d3edeb43255380decb7de285ff982b48cb4211775f0326",
"public_csv": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/fixed-pd/tp4/public/frontier.csv",
"public_csv_sha256": "c78ced228c0df8a20874f14cc620a4e259a828d9fc876a8dc022fb0280af1591",
"requests": 129,
"row_vector_sha256": "ce55943d20be72c04040e4bbeb0621d529590594dd11e968eefcf788895564a1",
"schema": "qwen30-latency-case-v1",
"tensor_parallel_size": 4
}
},
"traces_root": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/fixed-pd",
"winners": {
"e2e_ms:pooled_mean_ms": {
"ranking": [
"tp4_mns32",
"tp4_mns8",
"tp4_mns64",
"tp4_mns16",
"tp2_mns16",
"tp2_mns8",
"tp2_mns32",
"tp2_mns64",
"tp1_mns64",
"tp1_mns16",
"tp1_mns32",
"tp1_mns8"
],
"winner": "tp4_mns32",
"winner_value_ms": 604.4058500071964
},
"e2e_ms:pooled_p90_ms": {
"ranking": [
"tp4_mns8",
"tp4_mns64",
"tp4_mns32",
"tp4_mns16",
"tp2_mns8",
"tp2_mns32",
"tp2_mns16",
"tp2_mns64",
"tp1_mns64",
"tp1_mns16",
"tp1_mns32",
"tp1_mns8"
],
"winner": "tp4_mns8",
"winner_value_ms": 610.0081680342555
},
"tpot_ms:pooled_mean_ms": {
"ranking": [
"tp4_mns32",
"tp4_mns8",
"tp4_mns64",
"tp4_mns16",
"tp2_mns16",
"tp2_mns32",
"tp2_mns8",
"tp2_mns64",
"tp1_mns64",
"tp1_mns32",
"tp1_mns16",
"tp1_mns8"
],
"winner": "tp4_mns32",
"winner_value_ms": 4.254808547439789
},
"tpot_ms:pooled_p90_ms": {
"ranking": [
"tp4_mns8",
"tp4_mns32",
"tp4_mns64",
"tp4_mns16",
"tp2_mns32",
"tp2_mns16",
"tp2_mns8",
"tp2_mns64",
"tp1_mns16",
"tp1_mns64",
"tp1_mns32",
"tp1_mns8"
],
"winner": "tp4_mns8",
"winner_value_ms": 4.268226101921182
},
"ttft_ms:pooled_mean_ms": {
"ranking": [
"tp4_mns16",
"tp4_mns64",
"tp4_mns32",
"tp4_mns8",
"tp2_mns8",
"tp2_mns64",
"tp2_mns32",
"tp2_mns16",
"tp1_mns16",
"tp1_mns32",
"tp1_mns8",
"tp1_mns64"
],
"winner": "tp4_mns16",
"winner_value_ms": 63.03574686938565
},
"ttft_ms:pooled_p90_ms": {
"ranking": [
"tp4_mns16",
"tp4_mns64",
"tp4_mns8",
"tp4_mns32",
"tp2_mns8",
"tp2_mns64",
"tp2_mns32",
"tp2_mns16",
"tp1_mns32",
"tp1_mns8",
"tp1_mns64",
"tp1_mns16"
],
"winner": "tp4_mns16",
"winner_value_ms": 66.4233659626916
}
}
}