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/fixed-po",
|
|
"configs": {
|
|
"tp1_mns16": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 151.54830888467202,
|
|
"pooled_p90_ms": 152.33826905023307,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 151.54830888467202,
|
|
"trial_stddev_of_means_ms": 0.33839071804993504
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 151.50490087229585,
|
|
"pooled_p90_ms": 152.29528304189444,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 151.50490087229585,
|
|
"trial_stddev_of_means_ms": 0.3392777547312034
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 151.25221894176806,
|
|
"p90_ms": 152.03110210131854,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 151.20715750724278,
|
|
"p90_ms": 151.9814640050754,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp1_mns16/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 151.4755454836702,
|
|
"p90_ms": 152.21454401034862,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 151.4332707151915,
|
|
"p90_ms": 152.16313605196774,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp1_mns16/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 151.9171622285778,
|
|
"p90_ms": 152.64088998083025,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 151.87427439445327,
|
|
"p90_ms": 152.5908849434927,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp1_mns16/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp1_mns32": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 151.4782552960514,
|
|
"pooled_p90_ms": 152.49883604701608,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 151.4782552960514,
|
|
"trial_stddev_of_means_ms": 0.5555788512092701
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 151.43368434935846,
|
|
"pooled_p90_ms": 152.45853806845844,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 151.43368434935846,
|
|
"trial_stddev_of_means_ms": 0.5560791927635007
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 151.00544339222762,
|
|
"p90_ms": 151.96295792702585,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 150.96285229624618,
|
|
"p90_ms": 151.92402398679405,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp1_mns32/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 151.33915553880178,
|
|
"p90_ms": 152.3007940268144,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 151.29099727893436,
|
|
"p90_ms": 152.25290204398334,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp1_mns32/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 152.09016695712484,
|
|
"p90_ms": 152.93943404685706,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 152.04720347289486,
|
|
"p90_ms": 152.89701998699456,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp1_mns32/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp1_mns64": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 152.62579285143815,
|
|
"pooled_p90_ms": 153.7184970220551,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 152.62579285143815,
|
|
"trial_stddev_of_means_ms": 0.5522776932799126
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 152.58183204256076,
|
|
"pooled_p90_ms": 153.6727879429236,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 152.58183204256076,
|
|
"trial_stddev_of_means_ms": 0.552880728503269
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 152.98813100463835,
|
|
"p90_ms": 153.7133390083909,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 152.9461515773189,
|
|
"p90_ms": 153.67183403577656,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp1_mns64/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 152.89909483832415,
|
|
"p90_ms": 154.20521004125476,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 152.85368830727253,
|
|
"p90_ms": 154.1550400434062,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp1_mns64/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 151.99015271135195,
|
|
"p90_ms": 152.67854696139693,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 151.94565624309084,
|
|
"p90_ms": 152.6353599037975,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp1_mns64/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp1_mns8": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 152.22744446955332,
|
|
"pooled_p90_ms": 152.97825809102505,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 152.22744446955332,
|
|
"trial_stddev_of_means_ms": 0.15844676271042335
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 152.18195707226792,
|
|
"pooled_p90_ms": 152.93638303410262,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 152.18195707226792,
|
|
"trial_stddev_of_means_ms": 0.1592296957231754
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 152.08507488055747,
|
|
"p90_ms": 152.94339996762574,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 152.04033442473315,
|
|
"p90_ms": 152.89624000433832,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp1_mns8/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 152.3981458541771,
|
|
"p90_ms": 153.33553205709904,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 152.3543132889597,
|
|
"p90_ms": 153.2915000570938,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp1_mns8/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 152.19911267392538,
|
|
"p90_ms": 152.6885419152677,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 152.15122350311094,
|
|
"p90_ms": 152.64206391293555,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp1_mns8/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp2_mns16": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 97.51495216234325,
|
|
"pooled_p90_ms": 98.90919097233564,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 97.51495216234325,
|
|
"trial_stddev_of_means_ms": 0.41813696851903276
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 97.46812211917545,
|
|
"pooled_p90_ms": 98.85558602400124,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 97.46812211917545,
|
|
"trial_stddev_of_means_ms": 0.41503784318372017
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 97.09843800785814,
|
|
"p90_ms": 98.22496003471315,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 97.05583205674017,
|
|
"p90_ms": 98.16953900735825,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp2_mns16/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 97.93469326682533,
|
|
"p90_ms": 99.07599200960249,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 97.88585422369255,
|
|
"p90_ms": 99.02978304307908,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp2_mns16/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 97.51172521234628,
|
|
"p90_ms": 99.18248606845737,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 97.46268007709364,
|
|
"p90_ms": 99.13825406692922,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp2_mns16/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp2_mns32": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 97.09498990484747,
|
|
"pooled_p90_ms": 98.50096399895847,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 97.09498990484747,
|
|
"trial_stddev_of_means_ms": 0.27051136106210416
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 97.04873380816761,
|
|
"pooled_p90_ms": 98.45811000559479,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 97.0487338081676,
|
|
"trial_stddev_of_means_ms": 0.27130252759105145
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 96.8018446240372,
|
|
"p90_ms": 97.90838800836354,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 96.75326022814035,
|
|
"p90_ms": 97.85841300617903,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp2_mns32/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 97.33497442735373,
|
|
"p90_ms": 98.68263697717339,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 97.28661816668256,
|
|
"p90_ms": 98.63975096959621,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp2_mns32/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 97.14815066315147,
|
|
"p90_ms": 98.70580595452338,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 97.1063230296799,
|
|
"p90_ms": 98.66256301756948,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp2_mns32/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp2_mns64": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 94.78371690426897,
|
|
"pooled_p90_ms": 95.95681494101882,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 94.78371690426899,
|
|
"trial_stddev_of_means_ms": 0.09464944657839716
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 94.73932527026128,
|
|
"pooled_p90_ms": 95.90691793709993,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 94.73932527026129,
|
|
"trial_stddev_of_means_ms": 0.09810418936504331
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 94.80111797740899,
|
|
"p90_ms": 95.66861705388874,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 94.75897805848297,
|
|
"p90_ms": 95.61934601515532,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp2_mns64/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 94.68157430154149,
|
|
"p90_ms": 95.95681494101882,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 94.63288232525305,
|
|
"p90_ms": 95.90691793709993,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp2_mns64/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 94.86845843385645,
|
|
"p90_ms": 96.28609393257648,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 94.82611542704782,
|
|
"p90_ms": 96.24539199285209,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp2_mns64/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp2_mns8": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 95.65880776170006,
|
|
"pooled_p90_ms": 97.55863400641829,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 95.65880776170006,
|
|
"trial_stddev_of_means_ms": 1.2232525642643362
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 95.61450884031319,
|
|
"pooled_p90_ms": 97.50729007646441,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 95.61450884031319,
|
|
"trial_stddev_of_means_ms": 1.2245345925842415
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 97.06745062893357,
|
|
"p90_ms": 99.17883900925517,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 97.02484949686846,
|
|
"p90_ms": 99.13210896775126,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp2_mns8/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 94.86425999920209,
|
|
"p90_ms": 96.06455289758742,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 94.82164932920259,
|
|
"p90_ms": 96.02120891213417,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp2_mns8/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 95.0447126569645,
|
|
"p90_ms": 97.03064302448183,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 94.99702769486855,
|
|
"p90_ms": 96.98293695691973,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp2_mns8/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp4_mns16": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 65.28745120113297,
|
|
"pooled_p90_ms": 70.42863499373198,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 65.28745120113297,
|
|
"trial_stddev_of_means_ms": 3.4421132551731515
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 65.24474184372936,
|
|
"pooled_p90_ms": 70.38743107113987,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 65.24474184372936,
|
|
"trial_stddev_of_means_ms": 3.440733102883723
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 64.19509824892405,
|
|
"p90_ms": 67.92093603871763,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 64.15208354917203,
|
|
"p90_ms": 67.87848006933928,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp4_mns16/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 69.1431922154039,
|
|
"p90_ms": 78.7114379927516,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 69.09912444791908,
|
|
"p90_ms": 78.66681204177439,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp4_mns16/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 62.524063139070954,
|
|
"p90_ms": 63.537837006151676,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 62.48301753409698,
|
|
"p90_ms": 63.49677708931267,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp4_mns16/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp4_mns32": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 64.54067908164875,
|
|
"pooled_p90_ms": 69.61812602821738,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 64.54067908164875,
|
|
"trial_stddev_of_means_ms": 0.8919869576553885
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 64.4944863910101,
|
|
"pooled_p90_ms": 69.50995896477252,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 64.49448639101008,
|
|
"trial_stddev_of_means_ms": 0.8942503909647054
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 65.55543364614046,
|
|
"p90_ms": 71.84744393453002,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 65.51214804161744,
|
|
"p90_ms": 71.80331903509796,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp4_mns32/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 63.88050908684846,
|
|
"p90_ms": 66.97378400713205,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 63.83413878312811,
|
|
"p90_ms": 66.91711395978928,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp4_mns32/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 64.18609451195731,
|
|
"p90_ms": 69.55521402414888,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 64.13717234828474,
|
|
"p90_ms": 69.50995896477252,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp4_mns32/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp4_mns64": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 65.03269931623949,
|
|
"pooled_p90_ms": 68.43663903418928,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 65.03269931623947,
|
|
"trial_stddev_of_means_ms": 1.1339679108088652
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 64.98623655348516,
|
|
"pooled_p90_ms": 68.38861701544374,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 64.98623655348516,
|
|
"trial_stddev_of_means_ms": 1.1341449568113504
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 66.32654335125991,
|
|
"p90_ms": 70.97568700555712,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 66.28015979965643,
|
|
"p90_ms": 70.93840499874204,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp4_mns64/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 64.56001544761104,
|
|
"p90_ms": 67.99875595606863,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 64.51422280213225,
|
|
"p90_ms": 67.94618198182434,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp4_mns64/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 64.21153914984748,
|
|
"p90_ms": 67.55471904762089,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 64.16432705866679,
|
|
"p90_ms": 67.51206307671964,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp4_mns64/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
},
|
|
"tp4_mns8": {
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"pooled_mean_ms": 64.32922621852013,
|
|
"pooled_p90_ms": 67.98768497537822,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 64.32922621852013,
|
|
"trial_stddev_of_means_ms": 1.8052761808674234
|
|
},
|
|
"ttft_ms": {
|
|
"pooled_mean_ms": 64.2842707174255,
|
|
"pooled_p90_ms": 67.94753996655345,
|
|
"pooled_samples": 387,
|
|
"trial_mean_of_means_ms": 64.2842707174255,
|
|
"trial_stddev_of_means_ms": 1.80289690665978
|
|
}
|
|
},
|
|
"trials": [
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 62.84650166739183,
|
|
"p90_ms": 63.89774801209569,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 62.80200301792271,
|
|
"p90_ms": 63.856702065095305,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp4_mns8/trial1/results/result.json",
|
|
"trial": 1
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 66.3395124548945,
|
|
"p90_ms": 70.76063798740506,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 66.29134260132447,
|
|
"p90_ms": 70.7101090811193,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp4_mns8/trial2/results/result.json",
|
|
"trial": 2
|
|
},
|
|
{
|
|
"metrics": {
|
|
"e2e_ms": {
|
|
"mean_ms": 63.801664533274064,
|
|
"p90_ms": 67.48319591861218,
|
|
"samples": 129
|
|
},
|
|
"ttft_ms": {
|
|
"mean_ms": 63.759466533029325,
|
|
"p90_ms": 67.4400629941374,
|
|
"samples": 129
|
|
}
|
|
},
|
|
"requests": 129,
|
|
"result_path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/real-r6/fixed-po/real/tp4_mns8/trial3/results/result.json",
|
|
"trial": 3
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"prefill_only": true,
|
|
"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": [
|
|
1
|
|
],
|
|
"per_gpu_offered_request_rate": 0.215,
|
|
"prefix_caching": false,
|
|
"private_jsonl": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/fixed-po/tp1/private/real_requests.jsonl",
|
|
"private_jsonl_sha256": "ce7582fc13050078a243d7f6adfc2b2e071dbe87b5f760c7bf111af57718ccfb",
|
|
"public_csv": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/fixed-po/tp1/public/frontier.csv",
|
|
"public_csv_sha256": "e6f1ca0354e9d93c60ff18261ae6e08e2e54dbc888e30e244776f9cc8695a8cf",
|
|
"requests": 129,
|
|
"row_vector_sha256": "7c8dc7cccd2bd874768c1b06ca40d2327452390577b9907bacb76270b46998fa",
|
|
"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": [
|
|
1
|
|
],
|
|
"per_gpu_offered_request_rate": 0.215,
|
|
"prefix_caching": false,
|
|
"private_jsonl": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/fixed-po/tp2/private/real_requests.jsonl",
|
|
"private_jsonl_sha256": "3fe3c01ac31cd776b2458cafb818d889b20c5e14948154bbd716cce7200c8d5b",
|
|
"public_csv": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/fixed-po/tp2/public/frontier.csv",
|
|
"public_csv_sha256": "78b900d8f47fec3a1c83b748f82cb9623ce3f0cf08265aa20c3ef1511a4a97e0",
|
|
"requests": 129,
|
|
"row_vector_sha256": "c9382d9007ea1dc572898836f2d0efb8e2244c4febc1ed59d5aeacfcc5475c0a",
|
|
"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": [
|
|
1
|
|
],
|
|
"per_gpu_offered_request_rate": 0.215,
|
|
"prefix_caching": false,
|
|
"private_jsonl": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/fixed-po/tp4/private/real_requests.jsonl",
|
|
"private_jsonl_sha256": "af3ba5a7888ea5f283bb360dd36f1f455906f69f5ad82cef84e82018545710db",
|
|
"public_csv": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/fixed-po/tp4/public/frontier.csv",
|
|
"public_csv_sha256": "8b1100ccab34d9dac62b7ff1508d36bdf75aa3c3135e6f6642a0d3ac77af2505",
|
|
"requests": 129,
|
|
"row_vector_sha256": "a5e4959f28790eaa99a59a1b86c449a4e484967f1e35e47900d1a27fa061607f",
|
|
"schema": "qwen30-latency-case-v1",
|
|
"tensor_parallel_size": 4
|
|
}
|
|
},
|
|
"traces_root": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/traces/fixed-po",
|
|
"winners": {
|
|
"e2e_ms:pooled_mean_ms": {
|
|
"ranking": [
|
|
"tp4_mns8",
|
|
"tp4_mns32",
|
|
"tp4_mns64",
|
|
"tp4_mns16",
|
|
"tp2_mns64",
|
|
"tp2_mns8",
|
|
"tp2_mns32",
|
|
"tp2_mns16",
|
|
"tp1_mns32",
|
|
"tp1_mns16",
|
|
"tp1_mns8",
|
|
"tp1_mns64"
|
|
],
|
|
"winner": "tp4_mns8",
|
|
"winner_value_ms": 64.32922621852013
|
|
},
|
|
"e2e_ms:pooled_p90_ms": {
|
|
"ranking": [
|
|
"tp4_mns8",
|
|
"tp4_mns64",
|
|
"tp4_mns32",
|
|
"tp4_mns16",
|
|
"tp2_mns64",
|
|
"tp2_mns8",
|
|
"tp2_mns32",
|
|
"tp2_mns16",
|
|
"tp1_mns16",
|
|
"tp1_mns32",
|
|
"tp1_mns8",
|
|
"tp1_mns64"
|
|
],
|
|
"winner": "tp4_mns8",
|
|
"winner_value_ms": 67.98768497537822
|
|
},
|
|
"ttft_ms:pooled_mean_ms": {
|
|
"ranking": [
|
|
"tp4_mns8",
|
|
"tp4_mns32",
|
|
"tp4_mns64",
|
|
"tp4_mns16",
|
|
"tp2_mns64",
|
|
"tp2_mns8",
|
|
"tp2_mns32",
|
|
"tp2_mns16",
|
|
"tp1_mns32",
|
|
"tp1_mns16",
|
|
"tp1_mns8",
|
|
"tp1_mns64"
|
|
],
|
|
"winner": "tp4_mns8",
|
|
"winner_value_ms": 64.2842707174255
|
|
},
|
|
"ttft_ms:pooled_p90_ms": {
|
|
"ranking": [
|
|
"tp4_mns8",
|
|
"tp4_mns64",
|
|
"tp4_mns32",
|
|
"tp4_mns16",
|
|
"tp2_mns64",
|
|
"tp2_mns8",
|
|
"tp2_mns32",
|
|
"tp2_mns16",
|
|
"tp1_mns16",
|
|
"tp1_mns32",
|
|
"tp1_mns8",
|
|
"tp1_mns64"
|
|
],
|
|
"winner": "tp4_mns8",
|
|
"winner_value_ms": 67.94753996655345
|
|
}
|
|
}
|
|
}
|