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": 304.97662343096454,
|
|
"amplification": 1.0174657357946404,
|
|
"ttft": {
|
|
"count": 3552,
|
|
"mean": 0.16242270423816507,
|
|
"p50": 0.15836620499612764,
|
|
"p90": 0.17363918052287775,
|
|
"p99": 0.24847999344696287
|
|
},
|
|
"tpot": {
|
|
"count": 3552,
|
|
"mean": 0.013691483182659388,
|
|
"p50": 0.013865661168213087,
|
|
"p90": 0.015242900696529327,
|
|
"p99": 0.01626683903372128
|
|
},
|
|
"e2e": {
|
|
"count": 3552,
|
|
"mean": 7.160272567887971,
|
|
"p50": 7.247483663493767,
|
|
"p90": 7.962273431208451,
|
|
"p99": 8.480892732607899
|
|
}
|
|
},
|
|
"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": 744.9637431279989,
|
|
"amplification": 2.4853546954349977,
|
|
"ttft": {
|
|
"count": 3551,
|
|
"mean": 0.2446379999283825,
|
|
"p50": 0.24067969399038702,
|
|
"p90": 0.2630795220611617,
|
|
"p99": 0.3426029055262916
|
|
},
|
|
"tpot": {
|
|
"count": 3551,
|
|
"mean": 0.016916919575073883,
|
|
"p50": 0.016998299133030737,
|
|
"p90": 0.01775875886689886,
|
|
"p99": 0.018166751548973206
|
|
},
|
|
"e2e": {
|
|
"count": 3551,
|
|
"mean": 8.89104466149889,
|
|
"p50": 8.933106195996515,
|
|
"p90": 9.333998591057025,
|
|
"p99": 9.536390463996213
|
|
}
|
|
},
|
|
"6P+2D": {
|
|
"name": "6P+2D",
|
|
"n_offered": 3552,
|
|
"n_success": 3551,
|
|
"completion_rate": 0.9997184684684685,
|
|
"offered_window_s": 299.74141899999995,
|
|
"offered_qps": 11.850214134070008,
|
|
"wall_clock_s": 312.45468625507783,
|
|
"amplification": 1.0424141157985172,
|
|
"ttft": {
|
|
"count": 3551,
|
|
"mean": 0.36231219612768273,
|
|
"p50": 0.3462264990666881,
|
|
"p90": 0.4059687410481274,
|
|
"p99": 0.9837204645154998
|
|
},
|
|
"tpot": {
|
|
"count": 3551,
|
|
"mean": 0.03268022218101953,
|
|
"p50": 0.03333031399418835,
|
|
"p90": 0.03557429400772957,
|
|
"p99": 0.038558618127279086
|
|
},
|
|
"e2e": {
|
|
"count": 3551,
|
|
"mean": 17.068018403084057,
|
|
"p50": 17.392655145958997,
|
|
"p90": 18.56302695896011,
|
|
"p99": 20.159411454980727
|
|
}
|
|
}
|
|
},
|
|
"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": 0.9997184684684685,
|
|
"pd_advantage": 0.9997184684684685,
|
|
"n_slo": 3551
|
|
}
|
|
}
|
|
}
|
|
]
|
|
} |