gahow/aituner
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Decompose good/bad selection split across frozen surfaces

Browse Source 
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Gahow Wang
2026-07-20 12:05:20 +08:00
parent 18c0b25ae7
commit 39766141fb
54 changed files with 24465 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

453
runs/frontier-split-rootcause-v0/frozen-inputs/q30-fixed-hi/fixed-pd/comparison.json Normal file
View File

@@ -0,0 +1,453 @@
{
"applicable_metrics": [
"ttft_ms",
"tpot_ms",
"e2e_ms"
],
"cells": {
"tp1_mns16": {
"metrics": {
"e2e_ms": {
"mean": 128201.44370110576,
"p90": 216221.8716312423
},
"tpot_ms": {
"mean": 106.74127671151493,
"p90": 107.53204073371177
},
"ttft_ms": {
"mean": 100982.41813966946,
"p90": 188801.20124415262
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-fixed-pressure-surface-20260719-r1/sim/fixed-pd/runs/tp1_mns16/tp1/result.json"
},
"tp1_mns32": {
"metrics": {
"e2e_ms": {
"mean": 54134.6392206195,
"p90": 70757.16788718625
},
"tpot_ms": {
"mean": 131.73148052557949,
"p90": 134.09269340154515
},
"ttft_ms": {
"mean": 20543.111686596734,
"p90": 40978.20939546926
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-fixed-pressure-surface-20260719-r1/sim/fixed-pd/runs/tp1_mns32/tp1/result.json"
},
"tp1_mns64": {
"metrics": {
"e2e_ms": {
"mean": 36992.839178769755,
"p90": 38253.17393690583
},
"tpot_ms": {
"mean": 143.73592141724885,
"p90": 148.50084455017992
},
"ttft_ms": {
"mean": 340.1792173712992,
"p90": 390.1667904730175
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-fixed-pressure-surface-20260719-r1/sim/fixed-pd/runs/tp1_mns64/tp1/result.json"
},
"tp1_mns8": {
"metrics": {
"e2e_ms": {
"mean": 231355.5665072295,
"p90": 401099.3133242681
},
"tpot_ms": {
"mean": 79.72075104221494,
"p90": 80.05841803805441
},
"ttft_ms": {
"mean": 211026.77499146466,
"p90": 380684.4167245642
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-fixed-pressure-surface-20260719-r1/sim/fixed-pd/runs/tp1_mns8/tp1/result.json"
},
"tp2_mns16": {
"metrics": {
"e2e_ms": {
"mean": 99415.72204671855,
"p90": 170023.18522015438
},
"tpot_ms": {
"mean": 69.3294093088488,
"p90": 69.78173796567563
},
"ttft_ms": {
"mean": 81736.72267296212,
"p90": 152228.84203890432
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-fixed-pressure-surface-20260719-r1/sim/fixed-pd/runs/tp2_mns16/tp2/result.json"
},
"tp2_mns32": {
"metrics": {
"e2e_ms": {
"mean": 47656.99443299207,
"p90": 71358.22494490076
},
"tpot_ms": {
"mean": 83.38213205445625,
"p90": 84.68169232450846
},
"ttft_ms": {
"mean": 26394.55075910572,
"p90": 52520.58767404907
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-fixed-pressure-surface-20260719-r1/sim/fixed-pd/runs/tp2_mns32/tp2/result.json"
},
"tp2_mns64": {
"metrics": {
"e2e_ms": {
"mean": 25800.137969948584,
"p90": 26994.699921135867
},
"tpot_ms": {
"mean": 100.27798158873513,
"p90": 104.85288258852235
},
"ttft_ms": {
"mean": 229.2526648211283,
"p90": 261.37367146904467
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-fixed-pressure-surface-20260719-r1/sim/fixed-pd/runs/tp2_mns64/tp2/result.json"
},
"tp2_mns8": {
"metrics": {
"e2e_ms": {
"mean": 173225.23923299377,
"p90": 301133.20586389
},
"tpot_ms": {
"mean": 53.275061700270285,
"p90": 53.466591976089035
},
"ttft_ms": {
"mean": 159640.09849942484,
"p90": 287499.22490998777
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-fixed-pressure-surface-20260719-r1/sim/fixed-pd/runs/tp2_mns8/tp2/result.json"
},
"tp4_mns16": {
"metrics": {
"e2e_ms": {
"mean": 77014.8840236653,
"p90": 132893.6304418779
},
"tpot_ms": {
"mean": 46.95641974752248,
"p90": 47.23194326182317
},
"ttft_ms": {
"mean": 65040.99698804708,
"p90": 120849.48491011641
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-fixed-pressure-surface-20260719-r1/sim/fixed-pd/runs/tp4_mns16/tp4/result.json"
},
"tp4_mns32": {
"metrics": {
"e2e_ms": {
"mean": 41823.75653856865,
"p90": 66900.19803040712
},
"tpot_ms": {
"mean": 56.89199563649036,
"p90": 57.75799749592927
},
"ttft_ms": {
"mean": 27316.2976512636,
"p90": 54230.649753904916
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-fixed-pressure-surface-20260719-r1/sim/fixed-pd/runs/tp4_mns32/tp4/result.json"
},
"tp4_mns64": {
"metrics": {
"e2e_ms": {
"mean": 24104.231142330624,
"p90": 29174.179941975835
},
"tpot_ms": {
"mean": 69.02049776725552,
"p90": 72.06184134879742
},
"ttft_ms": {
"mean": 6504.004211680465,
"p90": 13004.945097644395
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-fixed-pressure-surface-20260719-r1/sim/fixed-pd/runs/tp4_mns64/tp4/result.json"
},
"tp4_mns8": {
"metrics": {
"e2e_ms": {
"mean": 133968.39678804282,
"p90": 233355.7233519645
},
"tpot_ms": {
"mean": 37.645089303294014,
"p90": 37.75522144488961
},
"ttft_ms": {
"mean": 124368.89901570287,
"p90": 223728.14188352478
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-fixed-pressure-surface-20260719-r1/sim/fixed-pd/runs/tp4_mns8/tp4/result.json"
}
},
"prefill_only": false,
"real_audit": "/home/admin/cpfs/wjh/aituner/qwen30-fixed-pressure-surface-20260719-r1/analysis/fixed-pd/real-audit.json",
"schema": "qwen30-latency-case-frontier-real-comparison-v1",
"selection": {
"e2e_ms:mean": {
"agreement": 0.5151515151515151,
"concordant_pairs": 34,
"discordant_pairs": 32,
"informative_pairs": 66,
"real_ranking": [
"tp1_mns32",
"tp4_mns32",
"tp1_mns16",
"tp1_mns8",
"tp4_mns16",
"tp4_mns64",
"tp1_mns64",
"tp2_mns8",
"tp2_mns64",
"tp2_mns16",
"tp2_mns32",
"tp4_mns8"
],
"real_winner": "tp1_mns32",
"selected_config_real_regret": 0.017005214686575575,
"sim_ranking": [
"tp4_mns64",
"tp2_mns64",
"tp1_mns64",
"tp4_mns32",
"tp2_mns32",
"tp1_mns32",
"tp4_mns16",
"tp2_mns16",
"tp1_mns16",
"tp4_mns8",
"tp2_mns8",
"tp1_mns8"
],
"sim_winner": "tp4_mns64",
"tied_pairs": 0,
"winner_match": false
},
"e2e_ms:p90": {
"agreement": 0.5151515151515151,
"concordant_pairs": 34,
"discordant_pairs": 32,
"informative_pairs": 66,
"real_ranking": [
"tp1_mns32",
"tp1_mns8",
"tp1_mns16",
"tp1_mns64",
"tp4_mns32",
"tp4_mns64",
"tp4_mns16",
"tp2_mns8",
"tp2_mns64",
"tp2_mns32",
"tp2_mns16",
"tp4_mns8"
],
"real_winner": "tp1_mns32",
"selected_config_real_regret": 0.054933980018932745,
"sim_ranking": [
"tp2_mns64",
"tp4_mns64",
"tp1_mns64",
"tp4_mns32",
"tp1_mns32",
"tp2_mns32",
"tp4_mns16",
"tp2_mns16",
"tp1_mns16",
"tp4_mns8",
"tp2_mns8",
"tp1_mns8"
],
"sim_winner": "tp2_mns64",
"tied_pairs": 0,
"winner_match": false
},
"tpot_ms:mean": {
"agreement": 0.48484848484848486,
"concordant_pairs": 32,
"discordant_pairs": 34,
"informative_pairs": 66,
"real_ranking": [
"tp4_mns8",
"tp1_mns32",
"tp1_mns16",
"tp1_mns8",
"tp1_mns64",
"tp4_mns32",
"tp2_mns8",
"tp4_mns16",
"tp4_mns64",
"tp2_mns64",
"tp2_mns16",
"tp2_mns32"
],
"real_winner": "tp4_mns8",
"selected_config_real_regret": 0.0,
"sim_ranking": [
"tp4_mns8",
"tp4_mns16",
"tp2_mns8",
"tp4_mns32",
"tp4_mns64",
"tp2_mns16",
"tp1_mns8",
"tp2_mns32",
"tp2_mns64",
"tp1_mns16",
"tp1_mns32",
"tp1_mns64"
],
"sim_winner": "tp4_mns8",
"tied_pairs": 0,
"winner_match": true
},
"tpot_ms:p90": {
"agreement": 0.42424242424242425,
"concordant_pairs": 28,
"discordant_pairs": 38,
"informative_pairs": 66,
"real_ranking": [
"tp4_mns8",
"tp1_mns32",
"tp1_mns16",
"tp1_mns8",
"tp1_mns64",
"tp2_mns8",
"tp4_mns32",
"tp2_mns64",
"tp4_mns64",
"tp4_mns16",
"tp2_mns32",
"tp2_mns16"
],
"real_winner": "tp4_mns8",
"selected_config_real_regret": 0.0,
"sim_ranking": [
"tp4_mns8",
"tp4_mns16",
"tp2_mns8",
"tp4_mns32",
"tp2_mns16",
"tp4_mns64",
"tp1_mns8",
"tp2_mns32",
"tp2_mns64",
"tp1_mns16",
"tp1_mns32",
"tp1_mns64"
],
"sim_winner": "tp4_mns8",
"tied_pairs": 0,
"winner_match": true
},
"ttft_ms:mean": {
"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
},
"ttft_ms:p90": {
"agreement": 0.5909090909090909,
"concordant_pairs": 39,
"discordant_pairs": 27,
"informative_pairs": 66,
"real_ranking": [
"tp4_mns64",
"tp4_mns32",
"tp4_mns16",
"tp2_mns64",
"tp2_mns8",
"tp2_mns16",
"tp2_mns32",
"tp1_mns8",
"tp1_mns32",
"tp1_mns16",
"tp1_mns64",
"tp4_mns8"
],
"real_winner": "tp4_mns64",
"selected_config_real_regret": 0.5620663582204116,
"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
}
},
"sim_root": "/home/admin/cpfs/wjh/aituner/qwen30-fixed-pressure-surface-20260719-r1/sim/fixed-pd"
}