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": 951,
|
|
"completion_rate": 0.8149100257069408,
|
|
"offered_window_s": 299.736197,
|
|
"offered_qps": 3.8934236561358655,
|
|
"wall_clock_s": 567.1572082909988,
|
|
"amplification": 1.8921879104611408,
|
|
"ttft": {
|
|
"count": 951,
|
|
"mean": 156.08624654169503,
|
|
"p50": 159.80228465000982,
|
|
"p90": 263.44082942500245,
|
|
"p99": 267.3189407904938
|
|
},
|
|
"tpot": {
|
|
"count": 951,
|
|
"mean": 0.5120599246480225,
|
|
"p50": 0.5265210192539223,
|
|
"p90": 0.5403215261268621,
|
|
"p99": 0.5436686666190138
|
|
},
|
|
"e2e": {
|
|
"count": 951,
|
|
"mean": 188.3470215559188,
|
|
"p50": 192.9057134770119,
|
|
"p90": 294.68771972299146,
|
|
"p99": 300.2205298934932
|
|
}
|
|
},
|
|
"4P+4D": {
|
|
"name": "4P+4D",
|
|
"n_offered": 1167,
|
|
"n_success": 596,
|
|
"completion_rate": 0.5107112253641817,
|
|
"offered_window_s": 299.736197,
|
|
"offered_qps": 3.8934236561358655,
|
|
"wall_clock_s": 789.8321366070013,
|
|
"amplification": 2.63509093833936,
|
|
"ttft": {
|
|
"count": 596,
|
|
"mean": 240.99040966441748,
|
|
"p50": 259.1066791820049,
|
|
"p90": 379.7789027979961,
|
|
"p99": 381.22047349565617
|
|
},
|
|
"tpot": {
|
|
"count": 596,
|
|
"mean": 0.006412497327210905,
|
|
"p50": 0.006444117785865692,
|
|
"p90": 0.0064974606745333095,
|
|
"p99": 0.006660929446938789
|
|
},
|
|
"e2e": {
|
|
"count": 596,
|
|
"mean": 241.39516468475196,
|
|
"p50": 259.5132920899996,
|
|
"p90": 380.1822811405,
|
|
"p99": 381.620277955458
|
|
}
|
|
},
|
|
"6P+2D": {
|
|
"name": "6P+2D",
|
|
"n_offered": 1167,
|
|
"n_success": 712,
|
|
"completion_rate": 0.6101113967437874,
|
|
"offered_window_s": 299.736197,
|
|
"offered_qps": 3.8934236561358655,
|
|
"wall_clock_s": 880.7267912379903,
|
|
"amplification": 2.938339780290167,
|
|
"ttft": {
|
|
"count": 712,
|
|
"mean": 175.69983718378106,
|
|
"p50": 172.43730882649834,
|
|
"p90": 250.6456608123961,
|
|
"p99": 594.014642834873
|
|
},
|
|
"tpot": {
|
|
"count": 712,
|
|
"mean": 0.007946936024875445,
|
|
"p50": 0.007568808706382119,
|
|
"p90": 0.010293392149296345,
|
|
"p99": 0.011275891952114068
|
|
},
|
|
"e2e": {
|
|
"count": 712,
|
|
"mean": 176.20114515147316,
|
|
"p50": 172.91078094949626,
|
|
"p90": 251.09661155799986,
|
|
"p99": 594.4257701966026
|
|
}
|
|
}
|
|
},
|
|
"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": 0.0,
|
|
"pd_advantage": NaN,
|
|
"n_slo": 0
|
|
},
|
|
"6P+2D": {
|
|
"attainment": 0.0,
|
|
"pd_advantage": NaN,
|
|
"n_slo": 0
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"ttft_slo_s": 5.0,
|
|
"tpot_slo_s": 0.05,
|
|
"arms": {
|
|
"8C-proxy": {
|
|
"attainment": 0.0,
|
|
"pd_advantage": NaN,
|
|
"n_slo": 0
|
|
},
|
|
"4P+4D": {
|
|
"attainment": 0.0,
|
|
"pd_advantage": NaN,
|
|
"n_slo": 0
|
|
},
|
|
"6P+2D": {
|
|
"attainment": 0.0,
|
|
"pd_advantage": NaN,
|
|
"n_slo": 0
|
|
}
|
|
}
|
|
}
|
|
]
|
|
} |