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>
142 lines
3.4 KiB
JSON
142 lines
3.4 KiB
JSON
{
|
|
"baseline": "8C-proxy",
|
|
"arms": {
|
|
"8C-proxy": {
|
|
"name": "8C-proxy",
|
|
"n_offered": 1167,
|
|
"n_success": 1167,
|
|
"completion_rate": 1.0,
|
|
"offered_window_s": 299.736197,
|
|
"offered_qps": 3.8934236561358655,
|
|
"wall_clock_s": 300.1927249849541,
|
|
"amplification": 1.0015230992770423,
|
|
"ttft": {
|
|
"count": 1167,
|
|
"mean": 0.1367582682356152,
|
|
"p50": 0.1337889520218596,
|
|
"p90": 0.13568343156948687,
|
|
"p99": 0.1417779766954481
|
|
},
|
|
"tpot": {
|
|
"count": 1167,
|
|
"mean": 0.005039774583944486,
|
|
"p50": 0.005025791809968059,
|
|
"p90": 0.005088228446667984,
|
|
"p99": 0.0051380019550329985
|
|
},
|
|
"e2e": {
|
|
"count": 1167,
|
|
"mean": 0.45452996390628697,
|
|
"p50": 0.45110413199290633,
|
|
"p90": 0.4555703255813569,
|
|
"p99": 0.4688122991356063
|
|
}
|
|
},
|
|
"4P+4D": {
|
|
"name": "4P+4D",
|
|
"n_offered": 1167,
|
|
"n_success": 1167,
|
|
"completion_rate": 1.0,
|
|
"offered_window_s": 299.736197,
|
|
"offered_qps": 3.8934236561358655,
|
|
"wall_clock_s": 300.2166367470054,
|
|
"amplification": 1.0016028753010615,
|
|
"ttft": {
|
|
"count": 1167,
|
|
"mean": 0.1660798433322169,
|
|
"p50": 0.16653224604669958,
|
|
"p90": 0.17306958099361508,
|
|
"p99": 0.1832630861806683
|
|
},
|
|
"tpot": {
|
|
"count": 1167,
|
|
"mean": 0.005046875948133808,
|
|
"p50": 0.0050270736812510425,
|
|
"p90": 0.0050664691831029595,
|
|
"p99": 0.005532995437730161
|
|
},
|
|
"e2e": {
|
|
"count": 1167,
|
|
"mean": 0.48433690918382055,
|
|
"p50": 0.4845748710213229,
|
|
"p90": 0.4916891472181305,
|
|
"p99": 0.5235905526624989
|
|
}
|
|
},
|
|
"6P+2D": {
|
|
"name": "6P+2D",
|
|
"n_offered": 1167,
|
|
"n_success": 1167,
|
|
"completion_rate": 1.0,
|
|
"offered_window_s": 299.736197,
|
|
"offered_qps": 3.8934236561358655,
|
|
"wall_clock_s": 300.2855537990108,
|
|
"amplification": 1.001832800991369,
|
|
"ttft": {
|
|
"count": 1167,
|
|
"mean": 0.17076528707394278,
|
|
"p50": 0.16959826194215566,
|
|
"p90": 0.17923957279417663,
|
|
"p99": 0.18792458378709853
|
|
},
|
|
"tpot": {
|
|
"count": 1167,
|
|
"mean": 0.005377765550956012,
|
|
"p50": 0.005177637602808693,
|
|
"p90": 0.006078562941697855,
|
|
"p99": 0.007001848420689976
|
|
},
|
|
"e2e": {
|
|
"count": 1167,
|
|
"mean": 0.5098518045703324,
|
|
"p50": 0.4961305959150195,
|
|
"p90": 0.5569328068522736,
|
|
"p99": 0.6314893902023319
|
|
}
|
|
}
|
|
},
|
|
"slo_grid": [
|
|
{
|
|
"ttft_slo_s": 2.0,
|
|
"tpot_slo_s": 0.05,
|
|
"arms": {
|
|
"8C-proxy": {
|
|
"attainment": 1.0,
|
|
"pd_advantage": 1.0,
|
|
"n_slo": 1167
|
|
},
|
|
"4P+4D": {
|
|
"attainment": 1.0,
|
|
"pd_advantage": 1.0,
|
|
"n_slo": 1167
|
|
},
|
|
"6P+2D": {
|
|
"attainment": 1.0,
|
|
"pd_advantage": 1.0,
|
|
"n_slo": 1167
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"ttft_slo_s": 5.0,
|
|
"tpot_slo_s": 0.05,
|
|
"arms": {
|
|
"8C-proxy": {
|
|
"attainment": 1.0,
|
|
"pd_advantage": 1.0,
|
|
"n_slo": 1167
|
|
},
|
|
"4P+4D": {
|
|
"attainment": 1.0,
|
|
"pd_advantage": 1.0,
|
|
"n_slo": 1167
|
|
},
|
|
"6P+2D": {
|
|
"attainment": 1.0,
|
|
"pd_advantage": 1.0,
|
|
"n_slo": 1167
|
|
}
|
|
}
|
|
}
|
|
]
|
|
} |