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": 3552,
|
|
"completion_rate": 1.0,
|
|
"offered_window_s": 299.74141899999995,
|
|
"offered_qps": 11.850214134070008,
|
|
"wall_clock_s": 301.78380814404227,
|
|
"amplification": 1.0068138369093473,
|
|
"ttft": {
|
|
"count": 3552,
|
|
"mean": 0.14506312318632342,
|
|
"p50": 0.14291562204016373,
|
|
"p90": 0.1491016250802204,
|
|
"p99": 0.1832571337954128
|
|
},
|
|
"tpot": {
|
|
"count": 3552,
|
|
"mean": 0.0089611879488046,
|
|
"p50": 0.008925844482420122,
|
|
"p90": 0.010698060123752072,
|
|
"p99": 0.011754058378410762
|
|
},
|
|
"e2e": {
|
|
"count": 3552,
|
|
"mean": 2.430673889741114,
|
|
"p50": 2.419925262918696,
|
|
"p90": 2.874893436266575,
|
|
"p99": 3.1480205075151746
|
|
}
|
|
},
|
|
"4P+4D": {
|
|
"name": "4P+4D",
|
|
"n_offered": 3552,
|
|
"n_success": 3551,
|
|
"completion_rate": 0.9997184684684685,
|
|
"offered_window_s": 299.74141899999995,
|
|
"offered_qps": 11.850214134070008,
|
|
"wall_clock_s": 744.8868488909211,
|
|
"amplification": 2.4850981601942745,
|
|
"ttft": {
|
|
"count": 3551,
|
|
"mean": 0.20500909556101396,
|
|
"p50": 0.20017725799698383,
|
|
"p90": 0.21613375598099083,
|
|
"p99": 0.29023518750909716
|
|
},
|
|
"tpot": {
|
|
"count": 3551,
|
|
"mean": 0.010307210080394247,
|
|
"p50": 0.010299421709450874,
|
|
"p90": 0.011793581666607482,
|
|
"p99": 0.012639003840969035
|
|
},
|
|
"e2e": {
|
|
"count": 3551,
|
|
"mean": 2.8339171693501317,
|
|
"p50": 2.8360355379991233,
|
|
"p90": 3.2198793930001557,
|
|
"p99": 3.438588996999897
|
|
}
|
|
},
|
|
"6P+2D": {
|
|
"name": "6P+2D",
|
|
"n_offered": 3552,
|
|
"n_success": 3552,
|
|
"completion_rate": 1.0,
|
|
"offered_window_s": 299.74141899999995,
|
|
"offered_qps": 11.850214134070008,
|
|
"wall_clock_s": 303.4300506779691,
|
|
"amplification": 1.0123060459587976,
|
|
"ttft": {
|
|
"count": 3552,
|
|
"mean": 0.2333820717117756,
|
|
"p50": 0.23283391550648957,
|
|
"p90": 0.24394672318594532,
|
|
"p99": 0.2734717815916518
|
|
},
|
|
"tpot": {
|
|
"count": 3552,
|
|
"mean": 0.016453822599812207,
|
|
"p50": 0.016576926972415737,
|
|
"p90": 0.017214638463623238,
|
|
"p99": 0.01769411424845092
|
|
},
|
|
"e2e": {
|
|
"count": 3552,
|
|
"mean": 4.430368151474328,
|
|
"p50": 4.463736370031256,
|
|
"p90": 4.628522685484495,
|
|
"p99": 4.75812664218829
|
|
}
|
|
}
|
|
},
|
|
"slo_grid": [
|
|
{
|
|
"ttft_slo_s": 2.0,
|
|
"tpot_slo_s": 0.05,
|
|
"arms": {
|
|
"8C-proxy": {
|
|
"attainment": 1.0,
|
|
"pd_advantage": 1.0,
|
|
"n_slo": 3552
|
|
},
|
|
"4P+4D": {
|
|
"attainment": 0.9997184684684685,
|
|
"pd_advantage": 0.9997184684684685,
|
|
"n_slo": 3551
|
|
},
|
|
"6P+2D": {
|
|
"attainment": 1.0,
|
|
"pd_advantage": 1.0,
|
|
"n_slo": 3552
|
|
}
|
|
}
|
|
}
|
|
]
|
|
} |