Decompose good/bad selection split across frozen surfaces

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
2026-07-20 12:05:20 +08:00
parent 18c0b25ae7
commit 39766141fb
54 changed files with 24465 additions and 5 deletions

View File

@@ -0,0 +1,326 @@
{
"applicable_metrics": [
"ttft_ms",
"e2e_ms"
],
"cells": {
"tp1_mns16": {
"metrics": {
"e2e_ms": {
"mean": 340.75522510609915,
"p90": 832.752247743656
},
"ttft_ms": {
"mean": 340.75522510609915,
"p90": 832.752247743656
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/trace-po/runs/tp1_mns16/tp1/result.json"
},
"tp1_mns32": {
"metrics": {
"e2e_ms": {
"mean": 340.75598360435777,
"p90": 832.752247743656
},
"ttft_ms": {
"mean": 340.75598360435777,
"p90": 832.752247743656
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/trace-po/runs/tp1_mns32/tp1/result.json"
},
"tp1_mns64": {
"metrics": {
"e2e_ms": {
"mean": 340.7569941487134,
"p90": 832.752247743656
},
"ttft_ms": {
"mean": 340.7569941487134,
"p90": 832.752247743656
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/trace-po/runs/tp1_mns64/tp1/result.json"
},
"tp1_mns8": {
"metrics": {
"e2e_ms": {
"mean": 340.75522510609915,
"p90": 832.752247743656
},
"ttft_ms": {
"mean": 340.75522510609915,
"p90": 832.752247743656
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/trace-po/runs/tp1_mns8/tp1/result.json"
},
"tp2_mns16": {
"metrics": {
"e2e_ms": {
"mean": 222.73961839402438,
"p90": 513.3421414172687
},
"ttft_ms": {
"mean": 222.73961839402438,
"p90": 513.3421414172687
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/trace-po/runs/tp2_mns16/tp2/result.json"
},
"tp2_mns32": {
"metrics": {
"e2e_ms": {
"mean": 222.7393083124536,
"p90": 513.3421414172687
},
"ttft_ms": {
"mean": 222.7393083124536,
"p90": 513.3421414172687
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/trace-po/runs/tp2_mns32/tp2/result.json"
},
"tp2_mns64": {
"metrics": {
"e2e_ms": {
"mean": 222.73932355314494,
"p90": 513.3421414172687
},
"ttft_ms": {
"mean": 222.73932355314494,
"p90": 513.3421414172687
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/trace-po/runs/tp2_mns64/tp2/result.json"
},
"tp2_mns8": {
"metrics": {
"e2e_ms": {
"mean": 222.73961839402438,
"p90": 513.3421414172687
},
"ttft_ms": {
"mean": 222.73961839402438,
"p90": 513.3421414172687
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/trace-po/runs/tp2_mns8/tp2/result.json"
},
"tp4_mns16": {
"metrics": {
"e2e_ms": {
"mean": 164.583607484367,
"p90": 355.93888195481327
},
"ttft_ms": {
"mean": 164.583607484367,
"p90": 355.93888195481327
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/trace-po/runs/tp4_mns16/tp4/result.json"
},
"tp4_mns32": {
"metrics": {
"e2e_ms": {
"mean": 164.58396574139448,
"p90": 355.93888195481327
},
"ttft_ms": {
"mean": 164.58396574139448,
"p90": 355.93888195481327
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/trace-po/runs/tp4_mns32/tp4/result.json"
},
"tp4_mns64": {
"metrics": {
"e2e_ms": {
"mean": 164.58471606968033,
"p90": 355.93888195481327
},
"ttft_ms": {
"mean": 164.58471606968033,
"p90": 355.93888195481327
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/trace-po/runs/tp4_mns64/tp4/result.json"
},
"tp4_mns8": {
"metrics": {
"e2e_ms": {
"mean": 164.583607484367,
"p90": 355.93888195481327
},
"ttft_ms": {
"mean": 164.583607484367,
"p90": 355.93888195481327
}
},
"path": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/sim/trace-po/runs/tp4_mns8/tp4/result.json"
}
},
"prefill_only": true,
"real_audit": "/home/admin/cpfs/wjh/aituner/qwen30-latency-expansion-20260718-r2/analysis-r6/trace-po-real-audit.json",
"schema": "qwen30-latency-case-frontier-real-comparison-v1",
"selection": {
"e2e_ms:mean": {
"agreement": 0.8412698412698413,
"concordant_pairs": 53,
"discordant_pairs": 10,
"informative_pairs": 63,
"real_ranking": [
"tp4_mns64",
"tp4_mns32",
"tp4_mns8",
"tp4_mns16",
"tp2_mns64",
"tp2_mns8",
"tp2_mns32",
"tp2_mns16",
"tp1_mns16",
"tp1_mns64",
"tp1_mns32",
"tp1_mns8"
],
"real_winner": "tp4_mns64",
"selected_config_real_regret": 0.0318784105178655,
"sim_ranking": [
"tp4_mns16",
"tp4_mns8",
"tp4_mns32",
"tp4_mns64",
"tp2_mns32",
"tp2_mns64",
"tp2_mns16",
"tp2_mns8",
"tp1_mns16",
"tp1_mns8",
"tp1_mns32",
"tp1_mns64"
],
"sim_winner": "tp4_mns16",
"tied_pairs": 3,
"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_mns8",
"tp1_mns16",
"tp1_mns32",
"tp1_mns64"
],
"real_winner": "tp4_mns8",
"selected_config_real_regret": 0.0033158177113489728,
"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": 0.8412698412698413,
"concordant_pairs": 53,
"discordant_pairs": 10,
"informative_pairs": 63,
"real_ranking": [
"tp4_mns64",
"tp4_mns32",
"tp4_mns8",
"tp4_mns16",
"tp2_mns64",
"tp2_mns8",
"tp2_mns32",
"tp2_mns16",
"tp1_mns16",
"tp1_mns64",
"tp1_mns32",
"tp1_mns8"
],
"real_winner": "tp4_mns64",
"selected_config_real_regret": 0.03187213306057872,
"sim_ranking": [
"tp4_mns16",
"tp4_mns8",
"tp4_mns32",
"tp4_mns64",
"tp2_mns32",
"tp2_mns64",
"tp2_mns16",
"tp2_mns8",
"tp1_mns16",
"tp1_mns8",
"tp1_mns32",
"tp1_mns64"
],
"sim_winner": "tp4_mns16",
"tied_pairs": 3,
"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_mns8",
"tp1_mns16",
"tp1_mns32",
"tp1_mns64"
],
"real_winner": "tp4_mns8",
"selected_config_real_regret": 0.0037779133092611917,
"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/trace-po"
}