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

Record code-trace canary fidelity gates

Browse Source
This commit is contained in:
Gahow Wang
2026-07-24 02:42:29 +08:00
parent e1f2557a0c
commit e0811e95b4
8 changed files with 1526 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

484
runs/frontier-code-trace-v0/results/canary-analysis-tp4-v2.json Normal file
View File

@@ -0,0 +1,484 @@
{
"drain": {
"interpretation": "Report the max-completion request explicitly; a response that arrived well before the cutoff can create a long drain tail without implying queue accumulation.",
"real_per_trial": [
{
"last_arrival_s": 597.0069999999832,
"last_completion_s": 689.6167901020963,
"tail_after_last_arrival_s": 92.60979010211304,
"tail_driver": {
"admission_lag_ms": 11.249033967033029,
"arrival_before_cutoff_s": 62.03099999995902,
"arrival_s": 534.9760000000242,
"e2e_ms": 154629.54106810503,
"input_tokens": 61976,
"output_tokens": 21361,
"request_index": 40
}
},
{
"last_arrival_s": 597.0069999999832,
"last_completion_s": 689.344073610846,
"tail_after_last_arrival_s": 92.33707361086272,
"tail_driver": {
"admission_lag_ms": 12.91605201549828,
"arrival_before_cutoff_s": 62.03099999995902,
"arrival_s": 534.9760000000242,
"e2e_ms": 154355.15755880624,
"input_tokens": 61976,
"output_tokens": 21361,
"request_index": 40
}
}
],
"sim": {
"last_arrival_s": 597.007,
"last_completion_s": 688.377327361797,
"tail_after_last_arrival_s": 91.37032736179708,
"tail_driver": {
"arrival_before_cutoff_s": 62.03099999999995,
"arrival_s": 534.976,
"e2e_ms": 153401.32736179704,
"input_tokens": 61976,
"output_tokens": 21361,
"request_index": 40,
"waiting_ms": 0.0
}
}
},
"input": {
"frontier_csv_sha256": "624bc983d3c9fba58cbfa3bb5126304b99b19883da4c78f63cd8622b856dbc1f",
"manifest": "runs/frontier-code-trace-v0/results/canary-input-r0p0004-v1/manifest.json",
"paired_row_vector_sha256": "72b09903851f5684838da23498a068efc409e6481d1e84efeeefddd8e431c3e7"
},
"latency_ms": {
"e2e": {
"real": {
"count": 106,
"max": 154629.54106810503,
"mean": 10734.692601765997,
"p50": 1698.6070264829323,
"p90": 16955.372447962873,
"p95": 40098.011117079295,
"p99": 152916.82229990847
},
"real_per_trial": [
{
"count": 53,
"max": 154629.54106810503,
"mean": 10752.865282098219,
"p50": 1699.7638561297208,
"p90": 16719.75081679412,
"p95": 32787.88763261397,
"p99": 139528.17495073183
},
{
"count": 53,
"max": 154355.15755880624,
"mean": 10716.519921433777,
"p50": 1697.8129579219967,
"p90": 16614.017988741405,
"p95": 32681.116299051762,
"p99": 139096.4567810855
}
],
"real_trial_statistic_mean": {
"mean": 10734.692601765997,
"p50": 1698.7884070258588,
"p90": 16666.884402767762,
"p95": 32734.501965832867,
"p99": 139312.31586590866
},
"relative_bias_percent": {
"mean": 2.2014558826783013,
"p50": 6.0982380145415895,
"p90": 11.04630840126803,
"p95": 1.3549410756255433,
"p99": -1.3257901787372948
},
"sim": {
"count": 53,
"max": 153401.32736179704,
"mean": 10971.012123535007,
"p50": 1802.3845674497352,
"p90": 18507.95985478033,
"p95": 33178.03517886939,
"p99": 137465.32686438697
}
},
"tpot": {
"real": {
"count": 106,
"max": 212.7724236343056,
"mean": 10.903347021010111,
"p50": 6.172303046257078,
"p90": 8.493485802941574,
"p95": 9.056036081054664,
"p99": 203.35920991970733
},
"real_per_trial": [
{
"count": 53,
"max": 212.7724236343056,
"mean": 10.931995250979348,
"p50": 6.17668606558597,
"p90": 8.407062460850472,
"p95": 8.930405185071265,
"p99": 137.66455429146993
},
{
"count": 53,
"max": 210.46578868602714,
"mean": 10.874698791040872,
"p50": 6.167920026928186,
"p90": 8.391951717689471,
"p95": 8.880314963829257,
"p99": 136.53404073389595
}
],
"real_trial_statistic_mean": {
"mean": 10.90334702101011,
"p50": 6.172303046257078,
"p90": 8.39950708926997,
"p95": 8.905360074450261,
"p99": 137.09929751268294
},
"relative_bias_percent": {
"mean": -29.893478835305263,
"p50": 8.372972857395876,
"p90": -4.849833918394976,
"p95": 9.343177342624926,
"p99": -71.54426929141353
},
"sim": {
"count": 53,
"max": 68.73522813087318,
"mean": 7.643957286944565,
"p50": 6.6891083049964015,
"p90": 7.992144945476565,
"p95": 9.737403659205464,
"p99": 39.01260690357286
}
},
"ttft": {
"real": {
"count": 106,
"max": 12213.839336996898,
"mean": 1499.2377276352238,
"p50": 523.7399585312232,
"p90": 3843.0782224750146,
"p95": 7372.6646098075435,
"p99": 12137.850578338843
},
"real_per_trial": [
{
"count": 53,
"max": 12213.839336996898,
"mean": 1501.9183055506492,
"p50": 524.1345730610192,
"p90": 3807.3078704066584,
"p95": 6591.913985600691,
"p99": 11615.677419919517
},
{
"count": 53,
"max": 12194.393874146044,
"mean": 1496.5571497197984,
"p50": 523.3453440014273,
"p90": 3795.468537742273,
"p95": 6574.768227571618,
"p99": 11596.839222898703
}
],
"real_trial_statistic_mean": {
"mean": 1499.2377276352238,
"p50": 523.7399585312232,
"p90": 3801.3882040744656,
"p95": 6583.341106586155,
"p99": 11606.25832140911
},
"relative_bias_percent": {
"mean": -8.33138601964073,
"p50": -4.13255547614917,
"p90": -8.820129670118508,
"p95": -13.08726396978494,
"p99": -6.311340671626045
},
"sim": {
"count": 53,
"max": 11454.943556960472,
"mean": 1374.3304451938434,
"p50": 502.0961141941598,
"p90": 3466.1008352105086,
"p95": 5721.761877935864,
"p99": 10873.747819516035
}
}
},
"prefix_cache": {
"real_hit_ratio_mean": 0.2399084848137731,
"real_per_trial": [
{
"hit_ratio": 0.2399084848137731,
"hit_tokens": 309968.0,
"query_tokens": 1292026.0
},
{
"hit_ratio": 0.2399084848137731,
"hit_tokens": 309968.0,
"query_tokens": 1292026.0
}
],
"sim": {
"block_size_tokens": 16,
"hit_ratio": 0.23997274866840085,
"mean_cached_prefill_tokens": 5848.452830188679,
"requests": 53,
"requests_with_hits": 9,
"total_cached_prefill_tokens": 309968,
"total_hit_blocks": 19373,
"total_query_blocks": 80730
}
},
"real_artifacts": [
{
"result_sha256": "c1105d6ba182be86fcd85f4eaf6889d1e788d48f923779b742ab95b4d3bd46ca",
"root": "runs/frontier-code-trace-v0/results/real-canary/r0p0004-tp4-t1-v2"
},
{
"result_sha256": "8e9092ac94b9d84d13aca41bd41d33db67d9917c8cedc8b61854aa2963a124ce",
"root": "runs/frontier-code-trace-v0/results/real-canary/r0p0004-tp4-t2-v3"
}
],
"real_decode_batch_per_trial": [
{
"histogram": {
"1": 54699,
"2": 9377,
"3": 867,
"4": 77
},
"max": 4,
"mixed_steps_excluded": 155,
"share_gt_1": 0.15873577360812058,
"steps": 65020
},
{
"histogram": {
"1": 54893,
"2": 9265,
"3": 877,
"4": 77
},
"max": 4,
"mixed_steps_excluded": 155,
"share_gt_1": 0.15694495638284803,
"steps": 65112
}
],
"requests_per_trial": 53,
"schema": "frontier-code-trace-canary-analysis-v1",
"sim_decode_batch": {
"histogram": {
"1": 54192,
"2": 9673,
"3": 840,
"4": 77
},
"max": 4,
"share_gt_1": 0.1634713346299898,
"share_gt_4": 0.0,
"stages": 64782
},
"slo": {
"definition": {
"target_pass_rate": 0.95,
"tpot_ms": 150,
"ttft_ms": "1000 + 1000 * input_tokens / 8000"
},
"feasibility_flip": true,
"real_per_trial": [
{
"feasible": false,
"pass_rate": 0.9433962264150944,
"passed": 50
},
{
"feasible": false,
"pass_rate": 0.9433962264150944,
"passed": 50
}
],
"sim": {
"feasible": true,
"pass_rate": 0.9811320754716981,
"passed": 52
}
},
"topology": "tp4_mns16",
"tpot_by_min_output_tokens": {
"2": {
"real": {
"count": 106,
"max": 212.7724236343056,
"mean": 10.903347021010111,
"p50": 6.172303046257078,
"p90": 8.493485802941574,
"p95": 9.056036081054664,
"p99": 203.35920991970733
},
"real_per_trial": [
{
"count": 53,
"max": 212.7724236343056,
"mean": 10.931995250979348,
"p50": 6.17668606558597,
"p90": 8.407062460850472,
"p95": 8.930405185071265,
"p99": 137.66455429146993
},
{
"count": 53,
"max": 210.46578868602714,
"mean": 10.874698791040872,
"p50": 6.167920026928186,
"p90": 8.391951717689471,
"p95": 8.880314963829257,
"p99": 136.53404073389595
}
],
"real_trial_statistic_mean": {
"mean": 10.90334702101011,
"p50": 6.172303046257078,
"p90": 8.39950708926997,
"p95": 8.905360074450261,
"p99": 137.09929751268294
},
"relative_bias_percent": {
"mean": -29.893478835305263,
"p50": 8.372972857395876,
"p90": -4.849833918394976,
"p95": 9.343177342624926,
"p99": -71.54426929141353
},
"sim": {
"count": 53,
"max": 68.73522813087318,
"mean": 7.643957286944565,
"p50": 6.6891083049964015,
"p90": 7.992144945476565,
"p95": 9.737403659205464,
"p99": 39.01260690357286
}
},
"32": {
"real": {
"count": 90,
"max": 68.33421335962247,
"mean": 7.270237487352443,
"p50": 6.167292870073156,
"p90": 8.490015433923487,
"p95": 8.695471711641535,
"p99": 68.2942852512835
},
"real_per_trial": [
{
"count": 45,
"max": 68.33421335962247,
"mean": 7.2794157345844095,
"p50": 6.17668606558597,
"p90": 8.316301157486755,
"p95": 8.667796532745909,
"p99": 42.34591449575732
},
{
"count": 45,
"max": 68.28935031654497,
"mean": 7.261059240120478,
"p50": 6.157899674560342,
"p90": 8.294755593709974,
"p95": 8.647785231561759,
"p99": 42.27831274721521
}
],
"real_trial_statistic_mean": {
"mean": 7.270237487352444,
"p50": 6.167292870073156,
"p90": 8.305528375598364,
"p95": 8.657790882153833,
"p99": 42.31211362148626
},
"relative_bias_percent": {
"mean": 8.827198903080898,
"p50": 10.602910786790718,
"p90": 3.6523081450671953,
"p95": 13.443742144167812,
"p99": 3.009077380352242
},
"sim": {
"count": 45,
"max": 68.73522813087318,
"mean": 7.911995811087395,
"p50": 6.821205431047118,
"p90": 8.60887186495121,
"p95": 9.821721963731866,
"p99": 43.585317861619345
}
},
"8": {
"real": {
"count": 104,
"max": 68.33421335962247,
"mean": 7.043428576026337,
"p50": 6.162909850744264,
"p90": 8.031762239708375,
"p95": 8.660612540767117,
"p99": 66.51876673984641
},
"real_per_trial": [
{
"count": 52,
"max": 68.33421335962247,
"mean": 7.050448551299998,
"p50": 6.167180339419747,
"p90": 8.00607090381441,
"p95": 8.604306061843479,
"p99": 38.21141240377873
},
{
"count": 52,
"max": 68.28935031654497,
"mean": 7.036408600752676,
"p50": 6.162909850744264,
"p90": 7.971146045984491,
"p95": 8.582739223220587,
"p99": 38.14019313391272
}
],
"real_trial_statistic_mean": {
"mean": 7.043428576026336,
"p50": 6.1650450950820055,
"p90": 7.988608474899451,
"p95": 8.593522642532033,
"p99": 38.17580276884573
},
"relative_bias_percent": {
"mean": 8.736391650572934,
"p50": 8.20225561474644,
"p90": 0.591743534737434,
"p95": 13.433615674969445,
"p99": 3.6892295703930555
},
"sim": {
"count": 52,
"max": 68.73522813087318,
"mean": 7.658770082056369,
"p50": 6.670717852545019,
"p90": 8.035880549065155,
"p95": 9.747943447271265,
"p99": 39.584195773328915
}
}
},
"trials": 2
}