174 lines
5.5 KiB
JSON
174 lines
5.5 KiB
JSON
{
|
|
"boundary": "This identifies where the selection error is created, but the frozen real logs do not attribute service-time overprediction to one operator.",
|
|
"cells": {
|
|
"tp2_mns64": {
|
|
"arrival_rate_requests_per_s": 2.25,
|
|
"mns": 64,
|
|
"real": {
|
|
"e2e_ms": 3354.8816545874283,
|
|
"periodic_queue": {
|
|
"running_max": 10,
|
|
"running_mean": 7.257142857142857,
|
|
"samples": 35,
|
|
"waiting_max": 0,
|
|
"waiting_mean": 0.0
|
|
},
|
|
"required_slots_upper_bound": 7.548483722821714,
|
|
"slot_margin_lower_bound": 56.451516277178285,
|
|
"tpot_ms": 12.393283087182931,
|
|
"ttft_ms": 194.56193759030603
|
|
},
|
|
"simulator": {
|
|
"first_scheduling_delay_ms": 38.22329108338011,
|
|
"queue_free_ttft_ms": 191.02937373774816,
|
|
"request_execution_ms": 25761.91467886552,
|
|
"required_slots": 57.96430802744742,
|
|
"slot_margin": 6.035691972552577,
|
|
"tpot_ms": 100.27798158873513,
|
|
"ttft_ms": 229.2526648211283,
|
|
"ttft_queue_fraction": 0.16672997503956338
|
|
},
|
|
"tp": 2,
|
|
"tpot_overprediction_ratio": 8.091316956395687
|
|
},
|
|
"tp4_mns16": {
|
|
"arrival_rate_requests_per_s": 4.5,
|
|
"mns": 16,
|
|
"real": {
|
|
"e2e_ms": 3252.7993474094965,
|
|
"periodic_queue": {
|
|
"running_max": 16,
|
|
"running_mean": 15.166666666666666,
|
|
"samples": 18,
|
|
"waiting_max": 0,
|
|
"waiting_mean": 0.0
|
|
},
|
|
"required_slots_upper_bound": 14.637597063342735,
|
|
"slot_margin_lower_bound": 1.362402936657265,
|
|
"tpot_ms": 12.267737219892378,
|
|
"ttft_ms": 124.49453797538061
|
|
},
|
|
"simulator": {
|
|
"first_scheduling_delay_ms": 64906.25631809643,
|
|
"queue_free_ttft_ms": 134.74066995065758,
|
|
"request_execution_ms": 12108.627705569606,
|
|
"required_slots": 54.488824675063235,
|
|
"slot_margin": -38.488824675063235,
|
|
"tpot_ms": 46.95641974752248,
|
|
"ttft_ms": 65040.99698804708,
|
|
"ttft_queue_fraction": 0.9979283732385681
|
|
},
|
|
"tp": 4,
|
|
"tpot_overprediction_ratio": 3.8276349505907024
|
|
},
|
|
"tp4_mns32": {
|
|
"arrival_rate_requests_per_s": 4.5,
|
|
"mns": 32,
|
|
"real": {
|
|
"e2e_ms": 3227.015463910283,
|
|
"periodic_queue": {
|
|
"running_max": 16,
|
|
"running_mean": 14.944444444444445,
|
|
"samples": 18,
|
|
"waiting_max": 0,
|
|
"waiting_mean": 0.0
|
|
},
|
|
"required_slots_upper_bound": 14.521569587596273,
|
|
"slot_margin_lower_bound": 17.478430412403725,
|
|
"tpot_ms": 12.171863019540417,
|
|
"ttft_ms": 123.15859724408143
|
|
},
|
|
"simulator": {
|
|
"first_scheduling_delay_ms": 27180.676177927482,
|
|
"queue_free_ttft_ms": 135.62147333612225,
|
|
"request_execution_ms": 14643.080360640608,
|
|
"required_slots": 65.89386162288272,
|
|
"slot_margin": -33.893861622882724,
|
|
"tpot_ms": 56.89199563649036,
|
|
"ttft_ms": 27316.2976512636,
|
|
"ttft_queue_fraction": 0.9950351444010626
|
|
},
|
|
"tp": 4,
|
|
"tpot_overprediction_ratio": 4.6740581573385525
|
|
},
|
|
"tp4_mns64": {
|
|
"arrival_rate_requests_per_s": 4.5,
|
|
"mns": 64,
|
|
"real": {
|
|
"e2e_ms": 3258.202659738964,
|
|
"periodic_queue": {
|
|
"running_max": 17,
|
|
"running_mean": 14.833333333333334,
|
|
"samples": 18,
|
|
"waiting_max": 0,
|
|
"waiting_mean": 0.0
|
|
},
|
|
"required_slots_upper_bound": 14.661911968825338,
|
|
"slot_margin_lower_bound": 49.338088031174664,
|
|
"tpot_ms": 12.29409478300949,
|
|
"ttft_ms": 123.17715882596677
|
|
},
|
|
"simulator": {
|
|
"first_scheduling_delay_ms": 6367.273779218055,
|
|
"queue_free_ttft_ms": 136.7304324624105,
|
|
"request_execution_ms": 17736.957363112386,
|
|
"required_slots": 79.81630813400574,
|
|
"slot_margin": -15.816308134005737,
|
|
"tpot_ms": 69.02049776725552,
|
|
"ttft_ms": 6504.004211680465,
|
|
"ttft_queue_fraction": 0.9789774993969319
|
|
},
|
|
"tp": 4,
|
|
"tpot_overprediction_ratio": 5.614117914776633
|
|
}
|
|
},
|
|
"contrasts": {
|
|
"observed_sim_ttft_tp4_minus_tp2_ms": 27087.044986442474,
|
|
"queue_free_sim_ttft_tp4_minus_tp2_ms": -55.40790040162591,
|
|
"real_ttft_tp4_minus_tp2_ms": -71.4033403462246
|
|
},
|
|
"schema": "qwen30-fixed-pd-ttft-admission-diagnosis-v1",
|
|
"selection": {
|
|
"agreement": 0.5909090909090909,
|
|
"concordant_pairs": 39,
|
|
"discordant_pairs": 27,
|
|
"informative_pairs": 66,
|
|
"real_ranking": [
|
|
"tp4_mns32",
|
|
"tp4_mns64",
|
|
"tp4_mns16",
|
|
"tp2_mns64",
|
|
"tp2_mns8",
|
|
"tp2_mns32",
|
|
"tp2_mns16",
|
|
"tp1_mns8",
|
|
"tp1_mns32",
|
|
"tp1_mns16",
|
|
"tp1_mns64",
|
|
"tp4_mns8"
|
|
],
|
|
"real_winner": "tp4_mns32",
|
|
"selected_config_real_regret": 0.5797674051508896,
|
|
"sim_ranking": [
|
|
"tp2_mns64",
|
|
"tp1_mns64",
|
|
"tp4_mns64",
|
|
"tp1_mns32",
|
|
"tp2_mns32",
|
|
"tp4_mns32",
|
|
"tp4_mns16",
|
|
"tp2_mns16",
|
|
"tp1_mns16",
|
|
"tp4_mns8",
|
|
"tp2_mns8",
|
|
"tp1_mns8"
|
|
],
|
|
"sim_winner": "tp2_mns64",
|
|
"tied_pairs": 0,
|
|
"winner_match": false
|
|
},
|
|
"status": "PASS",
|
|
"verdict": "Frontier overpredicts decode service time, so TP4's higher global arrival rate crosses the MNS admission cap only in simulation. The resulting first-scheduling queue reverses the TP topology ranking; without that queue Frontier itself predicts TP4 faster than TP2, matching real hardware.",
|
|
"workload": "Qwen3-30B Fixed-PD 4096->256 at 1.125 req/s/GPU"
|
|
}
|