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": 300.66455180699995,
|
|
"amplification": 1.0030972395602922,
|
|
"ttft": {
|
|
"count": 1167,
|
|
"mean": 0.584800394000121,
|
|
"p50": 0.5817365200055065,
|
|
"p90": 0.5870239008043427,
|
|
"p99": 0.6088061455392736
|
|
},
|
|
"tpot": {
|
|
"count": 1167,
|
|
"mean": 0.005585180932058873,
|
|
"p50": 0.005308644777941813,
|
|
"p90": 0.005355837698406836,
|
|
"p99": 0.014590345752427337
|
|
},
|
|
"e2e": {
|
|
"count": 1167,
|
|
"mean": 0.9369382756572071,
|
|
"p50": 0.9158835929993074,
|
|
"p90": 0.9229304600012256,
|
|
"p99": 1.5052119748995754
|
|
}
|
|
},
|
|
"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": 300.7607197400066,
|
|
"amplification": 1.003418081467173,
|
|
"ttft": {
|
|
"count": 1167,
|
|
"mean": 0.7293765576349805,
|
|
"p50": 0.6887177099997643,
|
|
"p90": 0.8911576298065484,
|
|
"p99": 1.1879012519156076
|
|
},
|
|
"tpot": {
|
|
"count": 1167,
|
|
"mean": 0.005308951736224922,
|
|
"p50": 0.0053098901269203495,
|
|
"p90": 0.005347346425488857,
|
|
"p99": 0.005420954272433716
|
|
},
|
|
"e2e": {
|
|
"count": 1167,
|
|
"mean": 1.064155324243521,
|
|
"p50": 1.0238807429996086,
|
|
"p90": 1.22566919879755,
|
|
"p99": 1.521622942700049
|
|
}
|
|
},
|
|
"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": 300.8507765819959,
|
|
"amplification": 1.003718535142407,
|
|
"ttft": {
|
|
"count": 1167,
|
|
"mean": 0.7028102769056583,
|
|
"p50": 0.6950660040020011,
|
|
"p90": 0.7394948218076024,
|
|
"p99": 0.8658222487580485
|
|
},
|
|
"tpot": {
|
|
"count": 1167,
|
|
"mean": 0.005782890183689697,
|
|
"p50": 0.00558671395230617,
|
|
"p90": 0.006629064533303286,
|
|
"p99": 0.007366264003757681
|
|
},
|
|
"e2e": {
|
|
"count": 1167,
|
|
"mean": 1.0674261210719522,
|
|
"p50": 1.0612060459970962,
|
|
"p90": 1.1425091800017981,
|
|
"p99": 1.3045775910036173
|
|
}
|
|
}
|
|
},
|
|
"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
|
|
}
|
|
}
|
|
}
|
|
]
|
|
} |