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
3.0 KiB
JSON
121 lines
3.0 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": 300.61600343801547,
|
|
"amplification": 1.0029177964157683,
|
|
"ttft": {
|
|
"count": 3552,
|
|
"mean": 0.139721406387908,
|
|
"p50": 0.13759525847854093,
|
|
"p90": 0.14188919204752892,
|
|
"p99": 0.17052793529117438
|
|
},
|
|
"tpot": {
|
|
"count": 3552,
|
|
"mean": 0.006496044329480822,
|
|
"p50": 0.006430442302898453,
|
|
"p90": 0.007889476366154117,
|
|
"p99": 0.009282101713493095
|
|
},
|
|
"e2e": {
|
|
"count": 3552,
|
|
"mean": 0.9651016481538636,
|
|
"p50": 0.9548319909954444,
|
|
"p90": 1.1440699087572284,
|
|
"p99": 1.3324073514551853
|
|
}
|
|
},
|
|
"4P+4D": {
|
|
"name": "4P+4D",
|
|
"n_offered": 3552,
|
|
"n_success": 3552,
|
|
"completion_rate": 1.0,
|
|
"offered_window_s": 299.74141899999995,
|
|
"offered_qps": 11.850214134070008,
|
|
"wall_clock_s": 300.7410873459885,
|
|
"amplification": 1.0033351024670651,
|
|
"ttft": {
|
|
"count": 3552,
|
|
"mean": 0.18467717330343286,
|
|
"p50": 0.1806962049449794,
|
|
"p90": 0.1929074571467936,
|
|
"p99": 0.2592483600333798
|
|
},
|
|
"tpot": {
|
|
"count": 3552,
|
|
"mean": 0.006980159784640828,
|
|
"p50": 0.006945047342387123,
|
|
"p90": 0.008164690015837552,
|
|
"p99": 0.009163911323187739
|
|
},
|
|
"e2e": {
|
|
"count": 3552,
|
|
"mean": 1.0715517728354285,
|
|
"p50": 1.063076548918616,
|
|
"p90": 1.2275727374362762,
|
|
"p99": 1.4021264237130526
|
|
}
|
|
},
|
|
"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": 301.1243950970238,
|
|
"amplification": 1.004613897210595,
|
|
"ttft": {
|
|
"count": 3552,
|
|
"mean": 0.20078434001432569,
|
|
"p50": 0.19958186394069344,
|
|
"p90": 0.213167638995219,
|
|
"p99": 0.23225504373782313
|
|
},
|
|
"tpot": {
|
|
"count": 3552,
|
|
"mean": 0.010393430778126047,
|
|
"p50": 0.010396533917478015,
|
|
"p90": 0.012065167099743436,
|
|
"p99": 0.01323438493101344
|
|
},
|
|
"e2e": {
|
|
"count": 3552,
|
|
"mean": 1.5212831554822883,
|
|
"p50": 1.5218885459471494,
|
|
"p90": 1.7440477049094625,
|
|
"p99": 1.9191367691196497
|
|
}
|
|
}
|
|
},
|
|
"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": 1.0,
|
|
"pd_advantage": 1.0,
|
|
"n_slo": 3552
|
|
},
|
|
"6P+2D": {
|
|
"attainment": 1.0,
|
|
"pd_advantage": 1.0,
|
|
"n_slo": 3552
|
|
}
|
|
}
|
|
}
|
|
]
|
|
} |