state: generation 16697 (cycle)
This commit is contained in:
@@ -3261,7 +3261,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-26T17:08:27.253986+00:00",
|
||||
"generatedAt": "2026-09-26T17:14:27.691343+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 164,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -396,99 +396,99 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-26T17:13:15.743520+00:00",
|
||||
"generatedAt": "2026-09-26T17:15:15.865495+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1408.426229508197,
|
||||
"backlogHours": 1385.7096774193546,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 2.0453295752952694,
|
||||
"queueFactor": 0.9096905989670387,
|
||||
"queueWeight": 0.9096905989670387,
|
||||
"qualityFactor": 2.0794298537708658,
|
||||
"queueFactor": 0.9156390571456166,
|
||||
"queueWeight": 0.9156390571456166,
|
||||
"recentSuccess": 50,
|
||||
"recentSuccessRate": 0.4098360655737705,
|
||||
"recentTerminal": 122,
|
||||
"recentWilsonLowerBound": 0.32661631886466974,
|
||||
"recentSuccessRate": 0.4032258064516129,
|
||||
"recentTerminal": 124,
|
||||
"recentWilsonLowerBound": 0.32104885004590483,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.8606170864353526,
|
||||
"selectionWeight": 1.904007190707203,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 20.333333333333332,
|
||||
"throughputPerHour": 20.666666666666668,
|
||||
"waiting": 28638
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 127.79057591623037,
|
||||
"backlogHours": 128.49473684210525,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.31406556063459556,
|
||||
"qualityFactor": 0.3355588725249378,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 36,
|
||||
"recentSuccessRate": 0.18848167539267016,
|
||||
"recentTerminal": 191,
|
||||
"recentWilsonLowerBound": 0.1393653166559651,
|
||||
"recentSuccessRate": 0.18947368421052632,
|
||||
"recentTerminal": 190,
|
||||
"recentWilsonLowerBound": 0.14011715932170268,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.40828522882497426,
|
||||
"selectionWeight": 0.4362265342824192,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 31.833333333333332,
|
||||
"waiting": 4068
|
||||
"throughputPerHour": 31.666666666666668,
|
||||
"waiting": 4069
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1244.2191780821918,
|
||||
"backlogHours": 1210.88,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.4375913302792414,
|
||||
"queueFactor": 0.9267642843380729,
|
||||
"queueWeight": 0.9267642843380729,
|
||||
"qualityFactor": 0.43430324261784414,
|
||||
"queueFactor": 0.9343508415361031,
|
||||
"queueWeight": 0.9343508415361031,
|
||||
"recentSuccess": 18,
|
||||
"recentSuccessRate": 0.2465753424657534,
|
||||
"recentTerminal": 73,
|
||||
"recentWilsonLowerBound": 0.16204336317654708,
|
||||
"recentSuccessRate": 0.24,
|
||||
"recentTerminal": 75,
|
||||
"recentWilsonLowerBound": 0.1575474872875825,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.4055440160387864,
|
||||
"selectionWeight": 0.4057916002218411,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.166666666666666,
|
||||
"waiting": 15138
|
||||
"throughputPerHour": 12.5,
|
||||
"waiting": 15136
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 459.1304347826087,
|
||||
"backlogHours": 432.78688524590166,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.339798532636921,
|
||||
"queueFactor": 1.076250608328948,
|
||||
"queueWeight": 1.076250608328948,
|
||||
"qualityFactor": 0.31379312228475176,
|
||||
"queueFactor": 1.090269927349764,
|
||||
"queueWeight": 1.090269927349764,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.20869565217391303,
|
||||
"recentTerminal": 115,
|
||||
"recentWilsonLowerBound": 0.14444439637630882,
|
||||
"recentSuccessRate": 0.19672131147540983,
|
||||
"recentTerminal": 122,
|
||||
"recentWilsonLowerBound": 0.13591035553474007,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.36570837745977014,
|
||||
"selectionWeight": 0.3421192046362519,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 19.166666666666668,
|
||||
"throughputPerHour": 20.333333333333332,
|
||||
"waiting": 8800
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 35.487804878048784,
|
||||
"backlogHours": 35.97029702970297,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -497,197 +497,197 @@
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 20,
|
||||
"recentSuccessRate": 0.04878048780487805,
|
||||
"recentTerminal": 410,
|
||||
"recentWilsonLowerBound": 0.031796579045881034,
|
||||
"recentSuccess": 18,
|
||||
"recentSuccessRate": 0.04455445544554455,
|
||||
"recentTerminal": 404,
|
||||
"recentWilsonLowerBound": 0.02836569714434178,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 68.33333333333333,
|
||||
"waiting": 2425
|
||||
"throughputPerHour": 67.33333333333333,
|
||||
"waiting": 2422
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 102.31468531468532,
|
||||
"backlogHours": 102.37894736842105,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.11803096366330204,
|
||||
"qualityFactor": 0.12560372894056832,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 35,
|
||||
"recentSuccessRate": 0.12237762237762238,
|
||||
"recentTerminal": 286,
|
||||
"recentWilsonLowerBound": 0.08932269413693737,
|
||||
"running": 11,
|
||||
"selectionWeight": 0.15344025276229264,
|
||||
"recentSuccessRate": 0.12280701754385964,
|
||||
"recentTerminal": 285,
|
||||
"recentWilsonLowerBound": 0.08964099956646664,
|
||||
"running": 15,
|
||||
"selectionWeight": 0.16328484762273882,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 47.666666666666664,
|
||||
"waiting": 4877
|
||||
"throughputPerHour": 47.5,
|
||||
"waiting": 4863
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 2458.4615384615386,
|
||||
"backlogHours": 2397.2999999999997,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.7445714231214313,
|
||||
"queueFactor": 0.8367665474951181,
|
||||
"queueWeight": 0.8367665474951181,
|
||||
"recentSuccess": 13,
|
||||
"recentSuccessRate": 0.3333333333333333,
|
||||
"recentTerminal": 39,
|
||||
"recentWilsonLowerBound": 0.2063276610691516,
|
||||
"qualityFactor": 0.9175589752952811,
|
||||
"queueFactor": 0.84336736046996,
|
||||
"queueWeight": 0.84336736046996,
|
||||
"recentSuccess": 14,
|
||||
"recentSuccessRate": 0.35,
|
||||
"recentTerminal": 40,
|
||||
"recentWilsonLowerBound": 0.22134333171049148,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.6230324590888469,
|
||||
"selectionWeight": 0.7738392910703024,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 6.5,
|
||||
"waiting": 15980
|
||||
"throughputPerHour": 6.666666666666667,
|
||||
"waiting": 15982
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 387.66442953020135,
|
||||
"backlogHours": 387.74496644295306,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.5119333092476935,
|
||||
"queueFactor": 1.1039144779511998,
|
||||
"queueWeight": 1.1039144779511998,
|
||||
"recentSuccess": 35,
|
||||
"recentSuccessRate": 0.2348993288590604,
|
||||
"qualityFactor": 0.4634860689660759,
|
||||
"queueFactor": 1.1083915895069607,
|
||||
"queueWeight": 1.1083915895069607,
|
||||
"recentSuccess": 33,
|
||||
"recentSuccessRate": 0.2214765100671141,
|
||||
"recentTerminal": 149,
|
||||
"recentWilsonLowerBound": 0.17402278009427918,
|
||||
"recentWilsonLowerBound": 0.1622742038249329,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.5651305918239977,
|
||||
"selectionWeight": 0.5137240606956417,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 24.833333333333332,
|
||||
"waiting": 9627
|
||||
"waiting": 9629
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 522.0983606557377,
|
||||
"backlogHours": 530.5,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.6919673469307108,
|
||||
"queueFactor": 1.0557010969783553,
|
||||
"queueWeight": 1.0557010969783553,
|
||||
"recentSuccess": 33,
|
||||
"recentSuccessRate": 0.27049180327868855,
|
||||
"recentTerminal": 122,
|
||||
"recentWilsonLowerBound": 0.1995691795923129,
|
||||
"qualityFactor": 0.5900559274138781,
|
||||
"queueFactor": 1.0574804295061313,
|
||||
"queueWeight": 1.0574804295061313,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.25,
|
||||
"recentTerminal": 120,
|
||||
"recentWilsonLowerBound": 0.1810971138452223,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.7305106872279536,
|
||||
"selectionWeight": 0.6239725955542665,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 20.333333333333332,
|
||||
"waiting": 10616
|
||||
"throughputPerHour": 20.0,
|
||||
"waiting": 10610
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 2013.6190476190477,
|
||||
"backlogHours": 2046.2903225806451,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.8621984259426925,
|
||||
"queueWeight": 0.8621984259426925,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.47619047619047616,
|
||||
"recentTerminal": 63,
|
||||
"recentWilsonLowerBound": 0.35781921387369653,
|
||||
"queueFactor": 0.8636346520631482,
|
||||
"queueWeight": 0.8636346520631482,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.46774193548387094,
|
||||
"recentTerminal": 62,
|
||||
"recentWilsonLowerBound": 0.3490863086762221,
|
||||
"running": 4,
|
||||
"selectionWeight": 2.155496064856731,
|
||||
"selectionWeight": 2.15908663015787,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 10.5,
|
||||
"waiting": 21143
|
||||
"throughputPerHour": 10.333333333333334,
|
||||
"waiting": 21145
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 3393.1034482758623,
|
||||
"backlogHours": 3394.137931034483,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.5037594005454711,
|
||||
"queueFactor": 0.7972862185534568,
|
||||
"queueWeight": 0.7972862185534568,
|
||||
"recentSuccess": 9,
|
||||
"recentSuccessRate": 0.3103448275862069,
|
||||
"qualityFactor": 0.7293022096209673,
|
||||
"queueFactor": 0.8005080874505882,
|
||||
"queueWeight": 0.8005080874505882,
|
||||
"recentSuccess": 10,
|
||||
"recentSuccessRate": 0.3448275862068966,
|
||||
"recentTerminal": 29,
|
||||
"recentWilsonLowerBound": 0.17275424489768068,
|
||||
"recentWilsonLowerBound": 0.19940508749190483,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.40164042752165485,
|
||||
"selectionWeight": 0.5838123169971685,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 4.833333333333333,
|
||||
"waiting": 16400
|
||||
"waiting": 16405
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 749.3628318584072,
|
||||
"backlogHours": 770.0181818181819,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 1.2792029647883543,
|
||||
"qualityFactor": 1.4373760643804303,
|
||||
"queueFactor": 1.0,
|
||||
"queueWeight": 1.0,
|
||||
"recentSuccess": 39,
|
||||
"recentSuccessRate": 0.34513274336283184,
|
||||
"recentTerminal": 113,
|
||||
"recentWilsonLowerBound": 0.2638704023847232,
|
||||
"recentSuccessRate": 0.35454545454545455,
|
||||
"recentTerminal": 110,
|
||||
"recentWilsonLowerBound": 0.2714400375949107,
|
||||
"running": 16,
|
||||
"selectionWeight": 1.2792029647883543,
|
||||
"selectionWeight": 1.4373760643804303,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.833333333333332,
|
||||
"waiting": 14113
|
||||
"throughputPerHour": 18.333333333333332,
|
||||
"waiting": 14117
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 945.8181818181819,
|
||||
"backlogHours": 963.2222222222222,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.5675887769409739,
|
||||
"queueFactor": 0.9656787472368935,
|
||||
"queueWeight": 0.9656787472368935,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.2545454545454545,
|
||||
"recentTerminal": 110,
|
||||
"recentWilsonLowerBound": 0.18238075813593077,
|
||||
"qualityFactor": 0.6861113285304788,
|
||||
"queueFactor": 0.9669770638026711,
|
||||
"queueWeight": 0.9669770638026711,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.26851851851851855,
|
||||
"recentTerminal": 108,
|
||||
"recentWilsonLowerBound": 0.19394781819614243,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.5481084190620802,
|
||||
"selectionWeight": 0.6634539179041523,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.333333333333332,
|
||||
"waiting": 17340
|
||||
"throughputPerHour": 18.0,
|
||||
"waiting": 17338
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-26T17:04:36.663690+00:00",
|
||||
"queueAttemptedAt": "2026-09-26T17:15:15.865495+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-26T17:04:36.663690+00:00",
|
||||
"queueUpdatedAt": "2026-09-26T17:15:15.865495+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Cambricon_mlu-370-x4",
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-26T17:13:15.743520+00:00",
|
||||
"catalogUpdatedAt": "2026-09-26T17:15:15.865495+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-26T17:13:15.743520+00:00",
|
||||
"generatedAt": "2026-09-26T17:15:15.865495+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6265,6 +6265,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-26T17:13:15.743520+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-26T17:15:15.865495+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-26T16:27:11.287145+00:00",
|
||||
"lastSyncTime": "2026-09-26T16:27:10.959007+00:00",
|
||||
"generatedAt": "2026-09-26T17:14:27.607568+00:00",
|
||||
"lastSyncTime": "2026-09-26T17:14:27.552028+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -5378,9 +5378,9 @@
|
||||
},
|
||||
"Sunrise_pt-200-x1|unknown|text-generation": {
|
||||
"attributableFailureCount": 13,
|
||||
"decisionFailureRate": 0.1238,
|
||||
"decisionSuccessRate": 0.8762,
|
||||
"decisionTotal": 105,
|
||||
"decisionFailureRate": 0.1226,
|
||||
"decisionSuccessRate": 0.8774,
|
||||
"decisionTotal": 106,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 52,
|
||||
"context_length": 5,
|
||||
@@ -5389,16 +5389,16 @@
|
||||
"验证失败": 32
|
||||
},
|
||||
"failureCount": 309,
|
||||
"failureRate": 0.7706,
|
||||
"failureRate": 0.7687,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 92,
|
||||
"successRate": 0.2294,
|
||||
"successCount": 93,
|
||||
"successRate": 0.2313,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 401,
|
||||
"total": 402,
|
||||
"unresolvedFailureCount": 296
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
@@ -5926,9 +5926,9 @@
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 1860,
|
||||
"decisionFailureRate": 0.6958,
|
||||
"decisionSuccessRate": 0.3042,
|
||||
"decisionTotal": 2673,
|
||||
"decisionFailureRate": 0.6956,
|
||||
"decisionSuccessRate": 0.3044,
|
||||
"decisionTotal": 2674,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1967,
|
||||
"architecture_compatibility": 100,
|
||||
@@ -5946,13 +5946,13 @@
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 8375,
|
||||
"failureRate": 0.9115,
|
||||
"failureRate": 0.9114,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 42,
|
||||
"successCount": 813,
|
||||
"successRate": 0.0885,
|
||||
"total": 9188,
|
||||
"successCount": 814,
|
||||
"successRate": 0.0886,
|
||||
"total": 9189,
|
||||
"unresolvedFailureCount": 6473
|
||||
},
|
||||
"vllm": {
|
||||
@@ -6133,7 +6133,7 @@
|
||||
"unresolvedFailureCount": 196
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-26T16:27:11.273389+00:00",
|
||||
"generatedAt": "2026-09-26T17:14:27.595531+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 102,
|
||||
@@ -6469,9 +6469,9 @@
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"attributableFailureCount": 743,
|
||||
"decisionFailureRate": 0.8898,
|
||||
"decisionSuccessRate": 0.1102,
|
||||
"decisionTotal": 835,
|
||||
"decisionFailureRate": 0.8888,
|
||||
"decisionSuccessRate": 0.1112,
|
||||
"decisionTotal": 836,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 162,
|
||||
"architecture_compatibility": 44,
|
||||
@@ -6487,13 +6487,13 @@
|
||||
"验证失败": 32
|
||||
},
|
||||
"failureCount": 1389,
|
||||
"failureRate": 0.9379,
|
||||
"failureRate": 0.9372,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 224,
|
||||
"successCount": 92,
|
||||
"successRate": 0.0621,
|
||||
"total": 1481,
|
||||
"successCount": 93,
|
||||
"successRate": 0.0628,
|
||||
"total": 1482,
|
||||
"unresolvedFailureCount": 422
|
||||
},
|
||||
"Vastai_va16": {
|
||||
@@ -23146,21 +23146,21 @@
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 6,
|
||||
"decisionTotal": 7,
|
||||
"failureBreakdown": {},
|
||||
"failureCount": 0,
|
||||
"failureRate": 0.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-24T03:51:15.462039+00:00",
|
||||
"lastTerminalAt": "2026-09-26T17:14:27.552028+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 6,
|
||||
"successCount": 7,
|
||||
"successRate": 1.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 6,
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
@@ -23241,18 +23241,18 @@
|
||||
"unresolvedFailureCount": 9
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
|
||||
"attributableFailureCount": 6,
|
||||
"consecutiveFailures": 6,
|
||||
"attributableFailureCount": 5,
|
||||
"consecutiveFailures": 5,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 6,
|
||||
"decisionTotal": 5,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 6,
|
||||
"repository_structure": 1,
|
||||
"runtime_memory": 5
|
||||
"runtime_memory": 4
|
||||
},
|
||||
"failureCount": 12,
|
||||
"failureCount": 11,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -23264,7 +23264,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 12,
|
||||
"total": 11,
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"hygon_k100-ai|vllm|text-generation": {
|
||||
@@ -26172,16 +26172,16 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|starcoder2|compressed-tensors": {
|
||||
"attributableFailureCount": 3,
|
||||
"consecutiveFailures": 3,
|
||||
"attributableFailureCount": 2,
|
||||
"consecutiveFailures": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 3,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"runtime_memory": 3
|
||||
"runtime_memory": 2
|
||||
},
|
||||
"failureCount": 4,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"lastTerminalAt": "2026-09-23T23:59:25.752490+00:00",
|
||||
@@ -26194,7 +26194,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 4,
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"hygon_k100-ai|vllm|text-generation|qwen3_vl|none": {
|
||||
@@ -50813,13 +50813,13 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17039,
|
||||
"totalRecords": 17260,
|
||||
"terminalRecords": 17040,
|
||||
"totalRecords": 17261,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6110,
|
||||
"decisionFailureRate": 0.8636,
|
||||
"decisionSuccessRate": 0.1364,
|
||||
"decisionTotal": 7075,
|
||||
"decisionFailureRate": 0.8635,
|
||||
"decisionSuccessRate": 0.1365,
|
||||
"decisionTotal": 7076,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4407,
|
||||
"architecture_compatibility": 212,
|
||||
@@ -50838,29 +50838,29 @@
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16074,
|
||||
"failureRate": 0.9434,
|
||||
"failureRate": 0.9433,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 935,
|
||||
"successCount": 965,
|
||||
"successRate": 0.0566,
|
||||
"total": 17039,
|
||||
"successCount": 966,
|
||||
"successRate": 0.0567,
|
||||
"total": 17040,
|
||||
"unresolvedFailureCount": 9029
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"组合 Iluvatar_bi-150|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Sunrise_pt-200-x1|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -50873,7 +50873,6 @@
|
||||
"组合 Iluvatar_bi-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x4|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Ascend_910-b4|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|vllm-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -50899,10 +50898,11 @@
|
||||
"组合 Cambricon_mlu-370-x4|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 MetaX_c-500|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17260,
|
||||
"summarizedRecords": 17261,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-26T17:14:27.552028+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-26T17:12:10+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458906", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-24T03:51:15.462039+00:00", "modelId": "BAAI/CareBot_Medical_multi-llama3-8b-rl", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-24T03:50:10+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457984", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-24T02:15:32.962539+00:00", "modelId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-24T02:14:08+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457989", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-24T02:06:26.859275+00:00", "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-24T02:02:08+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457987", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-25T09:35:33.057165+00:00", "modelId": "neuralmagic/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7855165704, "estimatedRequiredGiB": 8.783, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7858541078, "modelscopeLicense": "other", "modelscopeParams": 7400416256, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7858541078}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:09:37.383882+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991862", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-26T14:37:53.556324+00:00", "modelId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7686303632, "estimatedRequiredGiB": 8.592, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 7688299919, "modelscopeLicense": "llama2", "modelscopeParams": 13960238080, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7688299919}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:09:36.977617+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991858", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-26T01:14:46.157767+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014810120, "estimatedRequiredGiB": 2.256, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018195521, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2018195521}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:09:20.980304+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991857", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "runtime_memory", "failureAction": "lower_memory_risk_or_reject_combination", "failureCategory": "runtime_memory", "failureClassificationReason": "structured_device_oom", "failureCode": "DEVICE_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-24T04:50:24.455191+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663867, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788663867}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:09:20.778237+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4991855", "taskType": "text-generation", "verifyResult": -1}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user