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
3.5 KiB
JSON
142 lines
3.5 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": 303.05708941399644,
|
|
"amplification": 1.0110793839624128,
|
|
"ttft": {
|
|
"count": 1167,
|
|
"mean": 1.674437926279444,
|
|
"p50": 1.5353219069947954,
|
|
"p90": 2.0787689138029237,
|
|
"p99": 3.039117059087727
|
|
},
|
|
"tpot": {
|
|
"count": 1167,
|
|
"mean": 0.035498316425319934,
|
|
"p50": 0.02951206674587743,
|
|
"p90": 0.085249871320677,
|
|
"p99": 0.15422643764865662
|
|
},
|
|
"e2e": {
|
|
"count": 1167,
|
|
"mean": 3.9111985703531236,
|
|
"p50": 3.392241114997887,
|
|
"p90": 7.760864628604043,
|
|
"p99": 11.30427318874542
|
|
}
|
|
},
|
|
"4P+4D": {
|
|
"name": "4P+4D",
|
|
"n_offered": 1167,
|
|
"n_success": 1136,
|
|
"completion_rate": 0.9734361610968295,
|
|
"offered_window_s": 299.736197,
|
|
"offered_qps": 3.8934236561358655,
|
|
"wall_clock_s": 866.9596620649972,
|
|
"amplification": 2.8924089607535697,
|
|
"ttft": {
|
|
"count": 1136,
|
|
"mean": 65.09021699308856,
|
|
"p50": 66.22900710900285,
|
|
"p90": 112.5535424454938,
|
|
"p99": 124.55262411334482
|
|
},
|
|
"tpot": {
|
|
"count": 1136,
|
|
"mean": 0.005710658520121912,
|
|
"p50": 0.005725543936557461,
|
|
"p90": 0.005750613698356098,
|
|
"p99": 0.0058447879207267845
|
|
},
|
|
"e2e": {
|
|
"count": 1136,
|
|
"mean": 65.4504681098121,
|
|
"p50": 66.59053339700768,
|
|
"p90": 112.9150809329949,
|
|
"p99": 124.91415351489852
|
|
}
|
|
},
|
|
"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": 307.42712411200046,
|
|
"amplification": 1.0256589867656205,
|
|
"ttft": {
|
|
"count": 1167,
|
|
"mean": 3.6233640342625417,
|
|
"p50": 3.255483777000336,
|
|
"p90": 6.0935156565916255,
|
|
"p99": 7.349482456580735
|
|
},
|
|
"tpot": {
|
|
"count": 1167,
|
|
"mean": 0.006360297526341433,
|
|
"p50": 0.006324973206372104,
|
|
"p90": 0.007198417158741947,
|
|
"p99": 0.007942749238420567
|
|
},
|
|
"e2e": {
|
|
"count": 1167,
|
|
"mean": 4.024414356593621,
|
|
"p50": 3.6796783979953034,
|
|
"p90": 6.510242249601289,
|
|
"p99": 7.7530036393977895
|
|
}
|
|
}
|
|
},
|
|
"slo_grid": [
|
|
{
|
|
"ttft_slo_s": 2.0,
|
|
"tpot_slo_s": 0.05,
|
|
"arms": {
|
|
"8C-proxy": {
|
|
"attainment": 0.6563838903170522,
|
|
"pd_advantage": 1.0,
|
|
"n_slo": 766
|
|
},
|
|
"4P+4D": {
|
|
"attainment": 0.0,
|
|
"pd_advantage": 0.0,
|
|
"n_slo": 0
|
|
},
|
|
"6P+2D": {
|
|
"attainment": 0.20565552699228792,
|
|
"pd_advantage": 0.3133159268929504,
|
|
"n_slo": 240
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"ttft_slo_s": 5.0,
|
|
"tpot_slo_s": 0.05,
|
|
"arms": {
|
|
"8C-proxy": {
|
|
"attainment": 0.7095115681233933,
|
|
"pd_advantage": 1.0,
|
|
"n_slo": 828
|
|
},
|
|
"4P+4D": {
|
|
"attainment": 0.012853470437017995,
|
|
"pd_advantage": 0.018115942028985508,
|
|
"n_slo": 15
|
|
},
|
|
"6P+2D": {
|
|
"attainment": 0.7746358183376179,
|
|
"pd_advantage": 1.0917874396135265,
|
|
"n_slo": 904
|
|
}
|
|
}
|
|
}
|
|
]
|
|
} |