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": 1950,
|
|
"completion_rate": 0.5489864864864865,
|
|
"offered_window_s": 299.74141899999995,
|
|
"offered_qps": 11.850214134070008,
|
|
"wall_clock_s": 348.4953830049999,
|
|
"amplification": 1.1626534102882857,
|
|
"ttft": {
|
|
"count": 1950,
|
|
"mean": 0.8245253885559363,
|
|
"p50": 0.7988759850013594,
|
|
"p90": 1.5384256363991882,
|
|
"p99": 2.125257717882705
|
|
},
|
|
"tpot": {
|
|
"count": 1950,
|
|
"mean": 0.07444567704430907,
|
|
"p50": 0.08914986800879843,
|
|
"p90": 0.09127071481447005,
|
|
"p99": 0.09233926755616054
|
|
},
|
|
"e2e": {
|
|
"count": 1950,
|
|
"mean": 77.04034660455785,
|
|
"p50": 92.29079191399796,
|
|
"p90": 94.47993849659906,
|
|
"p99": 95.72745552870882
|
|
}
|
|
},
|
|
"4P+4D": {
|
|
"name": "4P+4D",
|
|
"n_offered": 3552,
|
|
"n_success": 2754,
|
|
"completion_rate": 0.7753378378378378,
|
|
"offered_window_s": 299.74141899999995,
|
|
"offered_qps": 11.850214134070008,
|
|
"wall_clock_s": 744.3694221920014,
|
|
"amplification": 2.4833719166185753,
|
|
"ttft": {
|
|
"count": 2754,
|
|
"mean": 4.5006646864741695,
|
|
"p50": 2.329877773499902,
|
|
"p90": 10.863291689799375,
|
|
"p99": 21.572781211729307
|
|
},
|
|
"tpot": {
|
|
"count": 2754,
|
|
"mean": 0.046089308743682535,
|
|
"p50": 0.04704797274047173,
|
|
"p90": 0.04792202048768524,
|
|
"p99": 0.059544689888886115
|
|
},
|
|
"e2e": {
|
|
"count": 2754,
|
|
"mean": 51.68415100813728,
|
|
"p50": 50.91020956099965,
|
|
"p90": 59.22212425199977,
|
|
"p99": 68.42946432940865
|
|
}
|
|
},
|
|
"6P+2D": {
|
|
"name": "6P+2D",
|
|
"n_offered": 3552,
|
|
"n_success": 1928,
|
|
"completion_rate": 0.5427927927927928,
|
|
"offered_window_s": 299.74141899999995,
|
|
"offered_qps": 11.850214134070008,
|
|
"wall_clock_s": 821.7403777359868,
|
|
"amplification": 2.7414975897474716,
|
|
"ttft": {
|
|
"count": 1928,
|
|
"mean": 39.07585104131927,
|
|
"p50": 42.6814165695032,
|
|
"p90": 63.28579387369681,
|
|
"p99": 73.84470144698193
|
|
},
|
|
"tpot": {
|
|
"count": 1928,
|
|
"mean": 0.04064862157373329,
|
|
"p50": 0.0398688508558163,
|
|
"p90": 0.04277554483881431,
|
|
"p99": 0.0695667276081441
|
|
},
|
|
"e2e": {
|
|
"count": 1928,
|
|
"mean": 80.66499786808757,
|
|
"p50": 84.05398454950046,
|
|
"p90": 105.42814423799427,
|
|
"p99": 113.52591980495636
|
|
}
|
|
}
|
|
},
|
|
"slo_grid": [
|
|
{
|
|
"ttft_slo_s": 2.0,
|
|
"tpot_slo_s": 0.05,
|
|
"arms": {
|
|
"8C-proxy": {
|
|
"attainment": 0.10191441441441441,
|
|
"pd_advantage": 1.0,
|
|
"n_slo": 362
|
|
},
|
|
"4P+4D": {
|
|
"attainment": 0.3502252252252252,
|
|
"pd_advantage": 3.43646408839779,
|
|
"n_slo": 1244
|
|
},
|
|
"6P+2D": {
|
|
"attainment": 0.06447072072072071,
|
|
"pd_advantage": 0.6325966850828729,
|
|
"n_slo": 229
|
|
}
|
|
}
|
|
}
|
|
]
|
|
} |