998 lines
32 KiB
JSON
998 lines
32 KiB
JSON
{
|
|
"applicable_metrics": [
|
|
"ttft_ms",
|
|
"e2e_ms"
|
|
],
|
|
"case_root": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po",
|
|
"configs": {
|
|
"tp1_mns16": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 552.8720716136033,
|
|
"pooled_p90_ms": 1849.5772210881114,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 552.8720716136035,
|
|
"trial_stddev_of_means_ms": 2.521785864921604
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 552.8045099093855,
|
|
"pooled_p90_ms": 1849.544870085083,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 552.8045099093856,
|
|
"trial_stddev_of_means_ms": 2.520195001336989
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 551.4591356410912,
|
|
"p90_ms": 1849.5772210881114,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 551.3877547012152,
|
|
"p90_ms": 1849.544870085083,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp1_mns16/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 551.3735196675904,
|
|
"p90_ms": 1854.1427809977904,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 551.311527398711,
|
|
"p90_ms": 1854.09467399586,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp1_mns16/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 555.7835595321286,
|
|
"p90_ms": 1865.3576440410689,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 555.7142476282306,
|
|
"p90_ms": 1865.324669983238,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp1_mns16/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp1_mns32": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 553.9655365312751,
|
|
"pooled_p90_ms": 1858.5613030008972,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 553.9655365312751,
|
|
"trial_stddev_of_means_ms": 0.562579474030608
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 553.8995644734638,
|
|
"pooled_p90_ms": 1858.5308340843767,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 553.8995644734638,
|
|
"trial_stddev_of_means_ms": 0.5595598051891147
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 554.533127208002,
|
|
"p90_ms": 1863.7738740071654,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 554.4650907711263,
|
|
"p90_ms": 1863.7414400000125,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp1_mns32/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 553.4081058838412,
|
|
"p90_ms": 1860.4962331010029,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 553.3461683987488,
|
|
"p90_ms": 1860.462275100872,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp1_mns32/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 553.9553765019821,
|
|
"p90_ms": 1858.5613030008972,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 553.8874342505163,
|
|
"p90_ms": 1858.5308340843767,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp1_mns32/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp1_mns64": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 553.5116215725009,
|
|
"pooled_p90_ms": 1862.3707490041852,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 553.5116215725008,
|
|
"trial_stddev_of_means_ms": 2.551946974085908
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 553.4431933351968,
|
|
"pooled_p90_ms": 1862.3419440118596,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 553.4431933351968,
|
|
"trial_stddev_of_means_ms": 2.558476651513527
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 551.9927626163446,
|
|
"p90_ms": 1863.004481070675,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 551.9189011646695,
|
|
"p90_ms": 1862.9671899834648,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp1_mns64/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 556.4578829970312,
|
|
"p90_ms": 1876.7878300277516,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 556.3969604667392,
|
|
"p90_ms": 1876.7514559440315,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp1_mns64/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 552.0842191041266,
|
|
"p90_ms": 1862.3707490041852,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 552.0137183741818,
|
|
"p90_ms": 1862.3419440118596,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp1_mns64/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp1_mns8": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 554.3623829256859,
|
|
"pooled_p90_ms": 1849.5380710810423,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 554.3623829256859,
|
|
"trial_stddev_of_means_ms": 1.2895027720806873
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 554.2973810096947,
|
|
"pooled_p90_ms": 1849.499023053795,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 554.2973810096947,
|
|
"trial_stddev_of_means_ms": 1.2879745625238963
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 552.8872783905863,
|
|
"p90_ms": 1849.5380710810423,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 552.8246594192243,
|
|
"p90_ms": 1849.499023053795,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp1_mns8/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 555.2756262775293,
|
|
"p90_ms": 1865.9542039968073,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 555.2131765045572,
|
|
"p90_ms": 1865.9242549911141,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp1_mns8/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 554.9242441089419,
|
|
"p90_ms": 1863.5734919225797,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 554.8543071053027,
|
|
"p90_ms": 1863.5354900034145,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp1_mns8/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp2_mns16": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 354.36655512622264,
|
|
"pooled_p90_ms": 1137.23775499966,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 354.36655512622264,
|
|
"trial_stddev_of_means_ms": 1.8755237488897505
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 354.2987044818834,
|
|
"pooled_p90_ms": 1137.2028539190069,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 354.29870448188336,
|
|
"trial_stddev_of_means_ms": 1.8738441773930947
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 352.474492817554,
|
|
"p90_ms": 1146.7004970181733,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 352.4049650534785,
|
|
"p90_ms": 1146.5505469823256,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp2_mns16/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 356.2250907998532,
|
|
"p90_ms": 1142.300286097452,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 356.1519986188198,
|
|
"p90_ms": 1142.2789900097996,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp2_mns16/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 354.40008176126076,
|
|
"p90_ms": 1137.23775499966,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 354.3391497733519,
|
|
"p90_ms": 1137.2028539190069,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp2_mns16/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp2_mns32": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 353.6182792498718,
|
|
"pooled_p90_ms": 1133.6436610436067,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 353.6182792498718,
|
|
"trial_stddev_of_means_ms": 1.6113304304047518
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 353.5506138878872,
|
|
"pooled_p90_ms": 1133.6100719636306,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 353.5506138878872,
|
|
"trial_stddev_of_means_ms": 1.6067873099412449
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 355.363455723769,
|
|
"p90_ms": 1137.4261770397425,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 355.2912532689425,
|
|
"p90_ms": 1137.4054140178487,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp2_mns32/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 353.3043994003358,
|
|
"p90_ms": 1133.6436610436067,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 353.2365282921684,
|
|
"p90_ms": 1133.6100719636306,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp2_mns32/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 352.1869826255106,
|
|
"p90_ms": 1137.214289046824,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 352.12406010255074,
|
|
"p90_ms": 1137.1923619881272,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp2_mns32/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp2_mns64": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 344.2724434967521,
|
|
"pooled_p90_ms": 1112.3684010235593,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 344.27244349675215,
|
|
"trial_stddev_of_means_ms": 1.2293359433030469
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 344.2076703236325,
|
|
"pooled_p90_ms": 1112.340173101984,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 344.20767032363256,
|
|
"trial_stddev_of_means_ms": 1.2250537007477627
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 342.85445375793955,
|
|
"p90_ms": 1112.3684010235593,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 342.79442101431823,
|
|
"p90_ms": 1112.340173101984,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp2_mns64/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 345.03840929702244,
|
|
"p90_ms": 1119.2332479404286,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 344.96722287271,
|
|
"p90_ms": 1119.2107619717717,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp2_mns64/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 344.92446743529433,
|
|
"p90_ms": 1121.5684060007334,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 344.86136708386937,
|
|
"p90_ms": 1121.5376510517672,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp2_mns64/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp2_mns8": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 347.7476487716525,
|
|
"pooled_p90_ms": 1112.5693990616128,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 347.74764877165256,
|
|
"trial_stddev_of_means_ms": 0.717530137997859
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 347.67954972228495,
|
|
"pooled_p90_ms": 1112.5206090509892,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 347.67954972228495,
|
|
"trial_stddev_of_means_ms": 0.7137879732940912
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 347.8964949396706,
|
|
"p90_ms": 1126.5470329672098,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 347.825654325718,
|
|
"p90_ms": 1126.4982499415055,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp2_mns8/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 348.37908198508296,
|
|
"p90_ms": 1108.5135659668595,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 348.3089811246221,
|
|
"p90_ms": 1108.4930589422584,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp2_mns8/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 346.967369390204,
|
|
"p90_ms": 1112.5693990616128,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 346.90401371651467,
|
|
"p90_ms": 1112.5206090509892,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp2_mns8/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp4_mns16": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 230.30740981957652,
|
|
"pooled_p90_ms": 669.3113599903882,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 230.30740981957652,
|
|
"trial_stddev_of_means_ms": 2.164263687280578
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 230.23591205587212,
|
|
"pooled_p90_ms": 669.2857249872759,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 230.2359120558721,
|
|
"trial_stddev_of_means_ms": 2.1675472527430966
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 230.70611610156737,
|
|
"p90_ms": 682.0242760004476,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 230.64041384333356,
|
|
"p90_ms": 681.8402550416067,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp4_mns16/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 232.2445988110014,
|
|
"p90_ms": 669.8487129760906,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 232.17271348053603,
|
|
"p90_ms": 669.6453359909356,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp4_mns16/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 227.9715145461608,
|
|
"p90_ms": 668.2263769907877,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 227.89460884374674,
|
|
"p90_ms": 667.8900560364127,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp4_mns16/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp4_mns32": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 227.01489424738475,
|
|
"pooled_p90_ms": 668.1078639812768,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 227.01489424738475,
|
|
"trial_stddev_of_means_ms": 1.0302265785061928
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 226.9508410934046,
|
|
"pooled_p90_ms": 668.0838000029325,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 226.9508410934046,
|
|
"trial_stddev_of_means_ms": 1.0309199236641802
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 227.36105044253256,
|
|
"p90_ms": 668.9074879977852,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 227.29304120623212,
|
|
"p90_ms": 668.8842560397461,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp4_mns32/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 227.82746249586054,
|
|
"p90_ms": 668.1078639812768,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 227.7671468305192,
|
|
"p90_ms": 668.0838000029325,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp4_mns32/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 225.8561698037611,
|
|
"p90_ms": 668.5177159961313,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 225.79233524346247,
|
|
"p90_ms": 668.1753649609163,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp4_mns32/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp4_mns64": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 223.1923911500318,
|
|
"pooled_p90_ms": 668.0814319988713,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 223.1923911500318,
|
|
"trial_stddev_of_means_ms": 1.0834054130133073
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 223.12445959072676,
|
|
"pooled_p90_ms": 668.0591680342332,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 223.1244595907268,
|
|
"trial_stddev_of_means_ms": 1.078830920161661
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 224.0322316110553,
|
|
"p90_ms": 668.6453759903088,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 223.96008559961103,
|
|
"p90_ms": 668.1041569681838,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp4_mns64/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 223.57544556978453,
|
|
"p90_ms": 697.0440980512649,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 223.50675472538455,
|
|
"p90_ms": 697.0191639848053,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp4_mns64/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 221.96949626925553,
|
|
"p90_ms": 668.0814319988713,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 221.9065384471847,
|
|
"p90_ms": 668.0591680342332,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp4_mns64/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp4_mns8": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 229.07142115104702,
|
|
"pooled_p90_ms": 667.0993800507858,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 229.07142115104702,
|
|
"trial_stddev_of_means_ms": 1.6982436653662605
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 229.00724306236953,
|
|
"pooled_p90_ms": 666.7667380534112,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 229.00724306236953,
|
|
"trial_stddev_of_means_ms": 1.6999412520227009
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 227.73505919955872,
|
|
"p90_ms": 667.3817320261151,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 227.67112628275225,
|
|
"p90_ms": 667.0240580569953,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp4_mns8/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 230.98243522013775,
|
|
"p90_ms": 667.0993800507858,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 230.92065048909407,
|
|
"p90_ms": 666.7667380534112,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp4_mns8/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 228.4967690334446,
|
|
"p90_ms": 667.9027479840443,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 228.42995241526225,
|
|
"p90_ms": 667.7060039946809,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/trace-po/real/tp4_mns8/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"prefill_only": true,
|
|
"schema": "qwen30-latency-case-real-audit-v1",
|
|
"trace_manifests": {
|
|
"tp1": {
|
|
"description": "trace-derived: exact input/arrival/session/prefix; output override only",
|
|
"first_arrival_s": 6.698,
|
|
"global_offered_request_rate": 0.215,
|
|
"last_arrival_s": 597.037,
|
|
"output_tokens": [
|
|
1
|
|
],
|
|
"per_gpu_offered_request_rate": 0.215,
|
|
"prefix_caching": true,
|
|
"private_jsonl": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/trace-po/tp1/private/real_requests.jsonl",
|
|
"private_jsonl_sha256": "525bf779bbd111bc3c42ac65af5cfed36ce59806acc521ee16d1c5ce7b3a6152",
|
|
"public_csv": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/trace-po/tp1/public/frontier.csv",
|
|
"public_csv_sha256": "eccab2e2f50f566eb4ec78291d126fce5fe9cb426eb89993c1b63b18f83dfc29",
|
|
"requests": 129,
|
|
"row_vector_sha256": "3df3a57e6a796e76d42f846fbfef59049f2bd804f4d3eda8ecbc9d96b43dc6ce",
|
|
"schema": "qwen30-latency-case-v1",
|
|
"tensor_parallel_size": 1
|
|
},
|
|
"tp2": {
|
|
"description": "trace-derived: exact input/arrival/session/prefix; output override only",
|
|
"first_arrival_s": 3.349,
|
|
"global_offered_request_rate": 0.43,
|
|
"last_arrival_s": 298.5185,
|
|
"output_tokens": [
|
|
1
|
|
],
|
|
"per_gpu_offered_request_rate": 0.215,
|
|
"prefix_caching": true,
|
|
"private_jsonl": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/trace-po/tp2/private/real_requests.jsonl",
|
|
"private_jsonl_sha256": "61bdb8a7245426a7c283d0f2944657d3eda46b1c04998c88b025a2411fe15340",
|
|
"public_csv": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/trace-po/tp2/public/frontier.csv",
|
|
"public_csv_sha256": "26701486cfb655a301b129acd14ab8d78b94ec843b4ceca8e222cee466e40535",
|
|
"requests": 129,
|
|
"row_vector_sha256": "f20dd473240fd243d38cb727f7896457e86da9e965b4f23f565aef5f3fc70351",
|
|
"schema": "qwen30-latency-case-v1",
|
|
"tensor_parallel_size": 2
|
|
},
|
|
"tp4": {
|
|
"description": "trace-derived: exact input/arrival/session/prefix; output override only",
|
|
"first_arrival_s": 1.6745,
|
|
"global_offered_request_rate": 0.86,
|
|
"last_arrival_s": 149.25925,
|
|
"output_tokens": [
|
|
1
|
|
],
|
|
"per_gpu_offered_request_rate": 0.215,
|
|
"prefix_caching": true,
|
|
"private_jsonl": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/trace-po/tp4/private/real_requests.jsonl",
|
|
"private_jsonl_sha256": "c38514fa524fc215cd9097d990a2985532f83ac6314bc46ad89ebfc1bd89b4f8",
|
|
"public_csv": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/trace-po/tp4/public/frontier.csv",
|
|
"public_csv_sha256": "f4112a2b0366b559bfced6a0986a01e2b7b39899a650d030c3e680b3dc63c92e",
|
|
"requests": 129,
|
|
"row_vector_sha256": "851e796f6d3e87444b58da87e0ef4b7482a13bb6502cb6873fa80523877ab74e",
|
|
"schema": "qwen30-latency-case-v1",
|
|
"tensor_parallel_size": 4
|
|
}
|
|
},
|
|
"traces_root": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/trace-po",
|
|
"winners": {
|
|
"e2e_ms:pooled_mean_ms": {
|
|
"ranking": [
|
|
"tp4_mns64",
|
|
"tp4_mns32",
|
|
"tp4_mns8",
|
|
"tp4_mns16",
|
|
"tp2_mns64",
|
|
"tp2_mns8",
|
|
"tp2_mns32",
|
|
"tp2_mns16",
|
|
"tp1_mns16",
|
|
"tp1_mns64",
|
|
"tp1_mns32",
|
|
"tp1_mns8"
|
|
],
|
|
"winner": "tp4_mns64",
|
|
"winner_value_ms": 223.1923911500318
|
|
},
|
|
"e2e_ms:pooled_p90_ms": {
|
|
"ranking": [
|
|
"tp4_mns8",
|
|
"tp4_mns64",
|
|
"tp4_mns32",
|
|
"tp4_mns16",
|
|
"tp2_mns64",
|
|
"tp2_mns8",
|
|
"tp2_mns32",
|
|
"tp2_mns16",
|
|
"tp1_mns8",
|
|
"tp1_mns16",
|
|
"tp1_mns32",
|
|
"tp1_mns64"
|
|
],
|
|
"winner": "tp4_mns8",
|
|
"winner_value_ms": 667.0993800507858
|
|
},
|
|
"ttft_ms:pooled_mean_ms": {
|
|
"ranking": [
|
|
"tp4_mns64",
|
|
"tp4_mns32",
|
|
"tp4_mns8",
|
|
"tp4_mns16",
|
|
"tp2_mns64",
|
|
"tp2_mns8",
|
|
"tp2_mns32",
|
|
"tp2_mns16",
|
|
"tp1_mns16",
|
|
"tp1_mns64",
|
|
"tp1_mns32",
|
|
"tp1_mns8"
|
|
],
|
|
"winner": "tp4_mns64",
|
|
"winner_value_ms": 223.12445959072676
|
|
},
|
|
"ttft_ms:pooled_p90_ms": {
|
|
"ranking": [
|
|
"tp4_mns8",
|
|
"tp4_mns64",
|
|
"tp4_mns32",
|
|
"tp4_mns16",
|
|
"tp2_mns64",
|
|
"tp2_mns8",
|
|
"tp2_mns32",
|
|
"tp2_mns16",
|
|
"tp1_mns8",
|
|
"tp1_mns16",
|
|
"tp1_mns32",
|
|
"tp1_mns64"
|
|
],
|
|
"winner": "tp4_mns8",
|
|
"winner_value_ms": 666.7667380534112
|
|
}
|
|
}
|
|
}
|