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": 300.21845804993063,
|
|
"amplification": 1.001591501940313,
|
|
"ttft": {
|
|
"count": 3552,
|
|
"mean": 0.1369056966029782,
|
|
"p50": 0.13516780693316832,
|
|
"p90": 0.13835511771030723,
|
|
"p99": 0.15317223175661632
|
|
},
|
|
"tpot": {
|
|
"count": 3552,
|
|
"mean": 0.005430781936309906,
|
|
"p50": 0.005039893150780468,
|
|
"p90": 0.007063257358303028,
|
|
"p99": 0.0077793481296283135
|
|
},
|
|
"e2e": {
|
|
"count": 3552,
|
|
"mean": 0.4793568905444592,
|
|
"p50": 0.45412574551301077,
|
|
"p90": 0.5810393166844734,
|
|
"p99": 0.6301419002050533
|
|
}
|
|
},
|
|
"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": 735.1059510430787,
|
|
"amplification": 2.452467041410379,
|
|
"ttft": {
|
|
"count": 3551,
|
|
"mean": 0.17374673821534295,
|
|
"p50": 0.17102365801110864,
|
|
"p90": 0.18273873499128968,
|
|
"p99": 0.24688138795318082
|
|
},
|
|
"tpot": {
|
|
"count": 3551,
|
|
"mean": 0.005485491774206834,
|
|
"p50": 0.0053864502226046865,
|
|
"p90": 0.006091995366168992,
|
|
"p99": 0.007109403222178419
|
|
},
|
|
"e2e": {
|
|
"count": 3551,
|
|
"mean": 0.5196563635758822,
|
|
"p50": 0.5100997349945828,
|
|
"p90": 0.5655082209268585,
|
|
"p99": 0.6639982180204242
|
|
}
|
|
},
|
|
"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": 300.38101644301787,
|
|
"amplification": 1.0021338307036503,
|
|
"ttft": {
|
|
"count": 3552,
|
|
"mean": 0.18293367427152893,
|
|
"p50": 0.1822461549891159,
|
|
"p90": 0.1938482352765277,
|
|
"p99": 0.21272844232735222
|
|
},
|
|
"tpot": {
|
|
"count": 3552,
|
|
"mean": 0.007192309629699456,
|
|
"p50": 0.007143509595484902,
|
|
"p90": 0.008732455453672816,
|
|
"p99": 0.009842920153335268
|
|
},
|
|
"e2e": {
|
|
"count": 3552,
|
|
"mean": 0.636424056327808,
|
|
"p50": 0.6324848984950222,
|
|
"p90": 0.7393875011475757,
|
|
"p99": 0.8261980937235056
|
|
}
|
|
}
|
|
},
|
|
"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
|
|
}
|
|
}
|
|
}
|
|
]
|
|
} |