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": 300.1385939740576,
|
|
"amplification": 1.0013425037685975,
|
|
"ttft": {
|
|
"count": 1167,
|
|
"mean": 0.08144469193556772,
|
|
"p50": 0.07862715201918036,
|
|
"p90": 0.08015060934703797,
|
|
"p99": 0.0875979653932154
|
|
},
|
|
"tpot": {
|
|
"count": 1167,
|
|
"mean": 0.005001699398049616,
|
|
"p50": 0.004988961030788246,
|
|
"p90": 0.005045765990923557,
|
|
"p99": 0.005062779263327164
|
|
},
|
|
"e2e": {
|
|
"count": 1167,
|
|
"mean": 0.3968209869372152,
|
|
"p50": 0.393534954986535,
|
|
"p90": 0.39730903680901974,
|
|
"p99": 0.40925762055674536
|
|
}
|
|
},
|
|
"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": 300.1604231200181,
|
|
"amplification": 1.0014153316291596,
|
|
"ttft": {
|
|
"count": 1167,
|
|
"mean": 0.09946277569807849,
|
|
"p50": 0.09600010397844017,
|
|
"p90": 0.10452785079833121,
|
|
"p99": 0.11205230774357905
|
|
},
|
|
"tpot": {
|
|
"count": 1167,
|
|
"mean": 0.005007447102661814,
|
|
"p50": 0.004987124730611131,
|
|
"p90": 0.005003212126977151,
|
|
"p99": 0.005478902989961502
|
|
},
|
|
"e2e": {
|
|
"count": 1167,
|
|
"mean": 0.415208436744531,
|
|
"p50": 0.41056320699863136,
|
|
"p90": 0.4200975856045261,
|
|
"p99": 0.44871115096379066
|
|
}
|
|
},
|
|
"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": 300.2032543020323,
|
|
"amplification": 1.0015582278907484,
|
|
"ttft": {
|
|
"count": 1167,
|
|
"mean": 0.10561635944505095,
|
|
"p50": 0.10468761203810573,
|
|
"p90": 0.11257308297790587,
|
|
"p99": 0.12065987563692024
|
|
},
|
|
"tpot": {
|
|
"count": 1167,
|
|
"mean": 0.005328901365752947,
|
|
"p50": 0.005144592110318915,
|
|
"p90": 0.005990574603515958,
|
|
"p99": 0.006688486758013448
|
|
},
|
|
"e2e": {
|
|
"count": 1167,
|
|
"mean": 0.4416300980896939,
|
|
"p50": 0.42991435900330544,
|
|
"p90": 0.4854830394731835,
|
|
"p99": 0.5404117306252005
|
|
}
|
|
}
|
|
},
|
|
"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
|
|
}
|
|
}
|
|
}
|
|
]
|
|
} |