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": 545,
|
|
"completion_rate": 0.15343468468468469,
|
|
"offered_window_s": 299.74141899999995,
|
|
"offered_qps": 11.850214134070008,
|
|
"wall_clock_s": 505.4139580530027,
|
|
"amplification": 1.6861665622961597,
|
|
"ttft": {
|
|
"count": 545,
|
|
"mean": 4.137136383750316,
|
|
"p50": 0.5702517530007754,
|
|
"p90": 1.6976309113961179,
|
|
"p99": 56.1814190310361
|
|
},
|
|
"tpot": {
|
|
"count": 545,
|
|
"mean": 0.08390926873267023,
|
|
"p50": 0.08933810225128375,
|
|
"p90": 0.09449654152820693,
|
|
"p99": 0.10591519025133134
|
|
},
|
|
"e2e": {
|
|
"count": 545,
|
|
"mean": 347.7765141811284,
|
|
"p50": 366.3568219640001,
|
|
"p90": 388.1241692415934,
|
|
"p99": 435.2848098113155
|
|
}
|
|
},
|
|
"4P+4D": {
|
|
"name": "4P+4D",
|
|
"n_offered": 3552,
|
|
"n_success": 771,
|
|
"completion_rate": 0.2170608108108108,
|
|
"offered_window_s": 299.74141899999995,
|
|
"offered_qps": 11.850214134070008,
|
|
"wall_clock_s": 850.1328976760124,
|
|
"amplification": 2.8362209684341706,
|
|
"ttft": {
|
|
"count": 771,
|
|
"mean": 63.210636654403324,
|
|
"p50": 1.1097561890055658,
|
|
"p90": 179.64081536799495,
|
|
"p99": 186.67013871119852
|
|
},
|
|
"tpot": {
|
|
"count": 771,
|
|
"mean": 0.05484690890217986,
|
|
"p50": 0.04795774376874187,
|
|
"p90": 0.08067800507863548,
|
|
"p99": 0.09099416300415113
|
|
},
|
|
"e2e": {
|
|
"count": 771,
|
|
"mean": 287.81779562259663,
|
|
"p50": 312.2160719559906,
|
|
"p90": 372.0004520520015,
|
|
"p99": 379.3279856524052
|
|
}
|
|
},
|
|
"6P+2D": {
|
|
"name": "6P+2D",
|
|
"n_offered": 3552,
|
|
"n_success": 627,
|
|
"completion_rate": 0.17652027027027026,
|
|
"offered_window_s": 299.74141899999995,
|
|
"offered_qps": 11.850214134070008,
|
|
"wall_clock_s": 867.8833550199925,
|
|
"amplification": 2.8954402028102515,
|
|
"ttft": {
|
|
"count": 627,
|
|
"mean": 179.58769048342904,
|
|
"p50": 238.1998468660022,
|
|
"p90": 378.29023678940143,
|
|
"p99": 385.40577973942356
|
|
},
|
|
"tpot": {
|
|
"count": 627,
|
|
"mean": 0.04188420961205498,
|
|
"p50": 0.03654626756630041,
|
|
"p90": 0.06031132874202571,
|
|
"p99": 0.06738955674930582
|
|
},
|
|
"e2e": {
|
|
"count": 627,
|
|
"mean": 351.1066520824709,
|
|
"p50": 387.2650127700035,
|
|
"p90": 507.9008203571953,
|
|
"p99": 570.6463984230224
|
|
}
|
|
}
|
|
},
|
|
"slo_grid": [
|
|
{
|
|
"ttft_slo_s": 2.0,
|
|
"tpot_slo_s": 0.05,
|
|
"arms": {
|
|
"8C-proxy": {
|
|
"attainment": 0.0,
|
|
"pd_advantage": NaN,
|
|
"n_slo": 0
|
|
},
|
|
"4P+4D": {
|
|
"attainment": 0.05855855855855856,
|
|
"pd_advantage": NaN,
|
|
"n_slo": 208
|
|
},
|
|
"6P+2D": {
|
|
"attainment": 0.036036036036036036,
|
|
"pd_advantage": NaN,
|
|
"n_slo": 128
|
|
}
|
|
}
|
|
}
|
|
]
|
|
} |