Gahow Wang
847f52f03b
gen_synthetic_trace.py --mode regular: maximally-regular multi-turn trace (fixed prefix/delta/turns, constant arrivals, zero session skew) to isolate the structural PD cost (per-turn full-context transfer + P/D capacity split) from the skew/hot-pin artifact. analysis/crossover/: SLO-goodput PD_advantage sweeps bracketing the prefill<->decode bottleneck axis (D1 grow input -> prefill-bound; D2 grow output -> decode-bound). figs/crossover_pd_advantage.png shows the crossover (y=1) with the agentic operating region annotated. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
121 lines
3.1 KiB
JSON
121 lines
3.1 KiB
JSON
{
|
|
"baseline": "8C-proxy",
|
|
"arms": {
|
|
"8C-proxy": {
|
|
"name": "8C-proxy",
|
|
"n_offered": 3552,
|
|
"n_success": 1050,
|
|
"completion_rate": 0.2956081081081081,
|
|
"offered_window_s": 299.74141899999995,
|
|
"offered_qps": 11.850214134070008,
|
|
"wall_clock_s": 414.92026689198974,
|
|
"amplification": 1.3842607013613617,
|
|
"ttft": {
|
|
"count": 1050,
|
|
"mean": 0.8393797435154972,
|
|
"p50": 0.8442945880015031,
|
|
"p90": 1.4299255040969001,
|
|
"p99": 2.1686189359705894
|
|
},
|
|
"tpot": {
|
|
"count": 1050,
|
|
"mean": 0.08418485046407832,
|
|
"p50": 0.08937374470713316,
|
|
"p90": 0.09085719287396188,
|
|
"p99": 0.09190563933350096
|
|
},
|
|
"e2e": {
|
|
"count": 1050,
|
|
"mean": 173.22149556513375,
|
|
"p50": 183.9983977669981,
|
|
"p90": 187.03014375649946,
|
|
"p99": 189.36978534828302
|
|
}
|
|
},
|
|
"4P+4D": {
|
|
"name": "4P+4D",
|
|
"n_offered": 3552,
|
|
"n_success": 1320,
|
|
"completion_rate": 0.3716216216216216,
|
|
"offered_window_s": 299.74141899999995,
|
|
"offered_qps": 11.850214134070008,
|
|
"wall_clock_s": 802.1317602040072,
|
|
"amplification": 2.6760791447511205,
|
|
"ttft": {
|
|
"count": 1320,
|
|
"mean": 19.92388417242484,
|
|
"p50": 8.059029546493548,
|
|
"p90": 64.71132232169766,
|
|
"p99": 87.07121913193099
|
|
},
|
|
"tpot": {
|
|
"count": 1320,
|
|
"mean": 0.05007250707090057,
|
|
"p50": 0.0492711045202749,
|
|
"p90": 0.07142825628519621,
|
|
"p99": 0.08267229383702501
|
|
},
|
|
"e2e": {
|
|
"count": 1320,
|
|
"mean": 122.44309290737698,
|
|
"p50": 118.35192646600626,
|
|
"p90": 167.89536100080443,
|
|
"p99": 187.19021692074878
|
|
}
|
|
},
|
|
"6P+2D": {
|
|
"name": "6P+2D",
|
|
"n_offered": 3552,
|
|
"n_success": 1041,
|
|
"completion_rate": 0.29307432432432434,
|
|
"offered_window_s": 299.74141899999995,
|
|
"offered_qps": 11.850214134070008,
|
|
"wall_clock_s": 879.8981197069952,
|
|
"amplification": 2.935523968100636,
|
|
"ttft": {
|
|
"count": 1041,
|
|
"mean": 86.06142147925078,
|
|
"p50": 92.45557322700915,
|
|
"p90": 153.47880471601093,
|
|
"p99": 159.16995789420034
|
|
},
|
|
"tpot": {
|
|
"count": 1041,
|
|
"mean": 0.04275836784091199,
|
|
"p50": 0.038143618996089604,
|
|
"p90": 0.06297858072350163,
|
|
"p99": 0.07100282797010407
|
|
},
|
|
"e2e": {
|
|
"count": 1041,
|
|
"mean": 173.5925440399473,
|
|
"p50": 199.81516771799943,
|
|
"p90": 230.71809448600106,
|
|
"p99": 234.9438766648003
|
|
}
|
|
}
|
|
},
|
|
"slo_grid": [
|
|
{
|
|
"ttft_slo_s": 2.0,
|
|
"tpot_slo_s": 0.05,
|
|
"arms": {
|
|
"8C-proxy": {
|
|
"attainment": 0.009009009009009009,
|
|
"pd_advantage": 1.0,
|
|
"n_slo": 32
|
|
},
|
|
"4P+4D": {
|
|
"attainment": 0.11486486486486487,
|
|
"pd_advantage": 12.75,
|
|
"n_slo": 408
|
|
},
|
|
"6P+2D": {
|
|
"attainment": 0.04954954954954955,
|
|
"pd_advantage": 5.5,
|
|
"n_slo": 176
|
|
}
|
|
}
|
|
}
|
|
]
|
|
} |