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

326
runs/frontier-split-rootcause-v0/frozen-inputs/q30-expansion-lo/fixed-po-comparison.json Normal file
View File

@@ -0,0 +1,326 @@
{
"applicable_metrics": [
"ttft_ms",
"e2e_ms"
],
"cells": {
"tp1_mns16": {
"metrics": {
"e2e_ms": {
"mean": 166.66991554923203,
"p90": 166.6699155492779
},
"ttft_ms": {
"mean": 166.66991554923203,
"p90": 166.6699155492779
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/fixed-po/runs/tp1_mns16/tp1/result.json"
},
"tp1_mns32": {
"metrics": {
"e2e_ms": {
"mean": 166.66991554923203,
"p90": 166.6699155492779
},
"ttft_ms": {
"mean": 166.66991554923203,
"p90": 166.6699155492779
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/fixed-po/runs/tp1_mns32/tp1/result.json"
},
"tp1_mns64": {
"metrics": {
"e2e_ms": {
"mean": 166.66991554923203,
"p90": 166.6699155492779
},
"ttft_ms": {
"mean": 166.66991554923203,
"p90": 166.6699155492779
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/fixed-po/runs/tp1_mns64/tp1/result.json"
},
"tp1_mns8": {
"metrics": {
"e2e_ms": {
"mean": 166.66991554923203,
"p90": 166.6699155492779
},
"ttft_ms": {
"mean": 166.66991554923203,
"p90": 166.6699155492779
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/fixed-po/runs/tp1_mns8/tp1/result.json"
},
"tp2_mns16": {
"metrics": {
"e2e_ms": {
"mean": 118.55592059231998,
"p90": 118.55592059232833
},
"ttft_ms": {
"mean": 118.55592059231998,
"p90": 118.55592059232833
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/fixed-po/runs/tp2_mns16/tp2/result.json"
},
"tp2_mns32": {
"metrics": {
"e2e_ms": {
"mean": 118.55592059231998,
"p90": 118.55592059232833
},
"ttft_ms": {
"mean": 118.55592059231998,
"p90": 118.55592059232833
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/fixed-po/runs/tp2_mns32/tp2/result.json"
},
"tp2_mns64": {
"metrics": {
"e2e_ms": {
"mean": 118.55592059231998,
"p90": 118.55592059232833
},
"ttft_ms": {
"mean": 118.55592059231998,
"p90": 118.55592059232833
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/fixed-po/runs/tp2_mns64/tp2/result.json"
},
"tp2_mns8": {
"metrics": {
"e2e_ms": {
"mean": 118.55592059231998,
"p90": 118.55592059232833
},
"ttft_ms": {
"mean": 118.55592059231998,
"p90": 118.55592059232833
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/fixed-po/runs/tp2_mns8/tp2/result.json"
},
"tp4_mns16": {
"metrics": {
"e2e_ms": {
"mean": 86.52545838364681,
"p90": 86.52545838364745
},
"ttft_ms": {
"mean": 86.52545838364681,
"p90": 86.52545838364745
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/fixed-po/runs/tp4_mns16/tp4/result.json"
},
"tp4_mns32": {
"metrics": {
"e2e_ms": {
"mean": 86.52545838364681,
"p90": 86.52545838364745
},
"ttft_ms": {
"mean": 86.52545838364681,
"p90": 86.52545838364745
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/fixed-po/runs/tp4_mns32/tp4/result.json"
},
"tp4_mns64": {
"metrics": {
"e2e_ms": {
"mean": 86.52545838364681,
"p90": 86.52545838364745
},
"ttft_ms": {
"mean": 86.52545838364681,
"p90": 86.52545838364745
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/fixed-po/runs/tp4_mns64/tp4/result.json"
},
"tp4_mns8": {
"metrics": {
"e2e_ms": {
"mean": 86.52545838364681,
"p90": 86.52545838364745
},
"ttft_ms": {
"mean": 86.52545838364681,
"p90": 86.52545838364745
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/fixed-po/runs/tp4_mns8/tp4/result.json"
}
},
"prefill_only": true,
"real_audit": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/analysis-r6/fixed-po-real-audit.json",
"schema": "qwen30-latency-case-frontier-real-comparison-v1",
"selection": {
"e2e_ms:mean": {
"agreement": 1.0,
"concordant_pairs": 48,
"discordant_pairs": 0,
"informative_pairs": 48,
"real_ranking": [
"tp4_mns8",
"tp4_mns32",
"tp4_mns64",
"tp4_mns16",
"tp2_mns64",
"tp2_mns8",
"tp2_mns32",
"tp2_mns16",
"tp1_mns32",
"tp1_mns16",
"tp1_mns8",
"tp1_mns64"
],
"real_winner": "tp4_mns8",
"selected_config_real_regret": 0.014895639803871355,
"sim_ranking": [
"tp4_mns16",
"tp4_mns32",
"tp4_mns64",
"tp4_mns8",
"tp2_mns16",
"tp2_mns32",
"tp2_mns64",
"tp2_mns8",
"tp1_mns16",
"tp1_mns32",
"tp1_mns64",
"tp1_mns8"
],
"sim_winner": "tp4_mns16",
"tied_pairs": 18,
"winner_match": false
},
"e2e_ms:p90": {
"agreement": 1.0,
"concordant_pairs": 48,
"discordant_pairs": 0,
"informative_pairs": 48,
"real_ranking": [
"tp4_mns8",
"tp4_mns64",
"tp4_mns32",
"tp4_mns16",
"tp2_mns64",
"tp2_mns8",
"tp2_mns32",
"tp2_mns16",
"tp1_mns16",
"tp1_mns32",
"tp1_mns8",
"tp1_mns64"
],
"real_winner": "tp4_mns8",
"selected_config_real_regret": 0.03590282591969048,
"sim_ranking": [
"tp4_mns16",
"tp4_mns32",
"tp4_mns64",
"tp4_mns8",
"tp2_mns16",
"tp2_mns32",
"tp2_mns64",
"tp2_mns8",
"tp1_mns16",
"tp1_mns32",
"tp1_mns64",
"tp1_mns8"
],
"sim_winner": "tp4_mns16",
"tied_pairs": 18,
"winner_match": false
},
"ttft_ms:mean": {
"agreement": 1.0,
"concordant_pairs": 48,
"discordant_pairs": 0,
"informative_pairs": 48,
"real_ranking": [
"tp4_mns8",
"tp4_mns32",
"tp4_mns64",
"tp4_mns16",
"tp2_mns64",
"tp2_mns8",
"tp2_mns32",
"tp2_mns16",
"tp1_mns32",
"tp1_mns16",
"tp1_mns8",
"tp1_mns64"
],
"real_winner": "tp4_mns8",
"selected_config_real_regret": 0.014940997472395743,
"sim_ranking": [
"tp4_mns16",
"tp4_mns32",
"tp4_mns64",
"tp4_mns8",
"tp2_mns16",
"tp2_mns32",
"tp2_mns64",
"tp2_mns8",
"tp1_mns16",
"tp1_mns32",
"tp1_mns64",
"tp1_mns8"
],
"sim_winner": "tp4_mns16",
"tied_pairs": 18,
"winner_match": false
},
"ttft_ms:p90": {
"agreement": 1.0,
"concordant_pairs": 48,
"discordant_pairs": 0,
"informative_pairs": 48,
"real_ranking": [
"tp4_mns8",
"tp4_mns64",
"tp4_mns32",
"tp4_mns16",
"tp2_mns64",
"tp2_mns8",
"tp2_mns32",
"tp2_mns16",
"tp1_mns16",
"tp1_mns32",
"tp1_mns8",
"tp1_mns64"
],
"real_winner": "tp4_mns8",
"selected_config_real_regret": 0.035908453871728634,
"sim_ranking": [
"tp4_mns16",
"tp4_mns32",
"tp4_mns64",
"tp4_mns8",
"tp2_mns16",
"tp2_mns32",
"tp2_mns64",
"tp2_mns8",
"tp1_mns16",
"tp1_mns32",
"tp1_mns64",
"tp1_mns8"
],
"sim_winner": "tp4_mns16",
"tied_pairs": 18,
"winner_match": false
}
},
"sim_root": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/fixed-po"
}