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": 300.32634208898526,
|
|
"amplification": 1.0019688816195438,
|
|
"ttft": {
|
|
"count": 1167,
|
|
"mean": 0.2628433253752162,
|
|
"p50": 0.2604120689211413,
|
|
"p90": 0.2637787788407877,
|
|
"p99": 0.2976114549371393
|
|
},
|
|
"tpot": {
|
|
"count": 1167,
|
|
"mean": 0.005143964614959416,
|
|
"p50": 0.005124552334318795,
|
|
"p90": 0.005180289564166395,
|
|
"p99": 0.0052467077378080115
|
|
},
|
|
"e2e": {
|
|
"count": 1167,
|
|
"mean": 0.5871811069348818,
|
|
"p50": 0.5839827890740708,
|
|
"p90": 0.5883447280153632,
|
|
"p99": 0.6408826243295329
|
|
}
|
|
},
|
|
"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": 300.3759389320621,
|
|
"amplification": 1.0021343499332585,
|
|
"ttft": {
|
|
"count": 1167,
|
|
"mean": 0.30861241175426407,
|
|
"p50": 0.3091614870354533,
|
|
"p90": 0.3227507559815422,
|
|
"p99": 0.3547600568598136
|
|
},
|
|
"tpot": {
|
|
"count": 1167,
|
|
"mean": 0.005148936446188915,
|
|
"p50": 0.0051316127147791645,
|
|
"p90": 0.005184003428393413,
|
|
"p99": 0.00547781713853871
|
|
},
|
|
"e2e": {
|
|
"count": 1167,
|
|
"mean": 0.6332931331915089,
|
|
"p50": 0.6365591660141945,
|
|
"p90": 0.6472898541716858,
|
|
"p99": 0.7053035433730102
|
|
}
|
|
},
|
|
"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": 300.4041277950164,
|
|
"amplification": 1.0022283955081221,
|
|
"ttft": {
|
|
"count": 1167,
|
|
"mean": 0.31527804771431056,
|
|
"p50": 0.31678270106203854,
|
|
"p90": 0.3284846659982577,
|
|
"p99": 0.3402980738645419
|
|
},
|
|
"tpot": {
|
|
"count": 1167,
|
|
"mean": 0.0055213440500518985,
|
|
"p50": 0.005325577683776381,
|
|
"p90": 0.006278165857056304,
|
|
"p99": 0.0070092806818761975
|
|
},
|
|
"e2e": {
|
|
"count": 1167,
|
|
"mean": 0.6634175265073216,
|
|
"p50": 0.6494167000055313,
|
|
"p90": 0.7135140666039661,
|
|
"p99": 0.7741130576422437
|
|
}
|
|
}
|
|
},
|
|
"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
|
|
}
|
|
}
|
|
}
|
|
]
|
|
} |