state: generation 6485 (cycle)

This commit is contained in:
2026-09-13 02:57:24 +00:00
parent 8116e93661
commit 94db3da49e
9 changed files with 2243 additions and 2212 deletions

View File

@@ -205,17 +205,19 @@
"architectures": [
"spark2_5forcausallm"
],
"evidenceCount": 1,
"expiresAt": "2026-10-12T16:39:21+00:00",
"evidenceCount": 2,
"expiresAt": "2026-10-13T02:47:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-12T16:39:21+00:00",
"latestFailureAt": "2026-09-13T02:47:21+00:00",
"latestSuccessfulAt": null,
"matchType": "architectures",
"modelType": null,
"sourceModelIds": [
"XHToken/Spark-X2.5-1.7B",
"XHToken/Spark-X2.5-4B"
],
"sourceTaskIds": [
"4557197",
"4548919"
],
"targetGpu": "Ascend_910-b4",
@@ -1450,7 +1452,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-13T02:54:29.108060+00:00",
"generatedAt": "2026-09-13T02:57:22.674477+00:00",
"summary": {
"activeBlockCount": 73,
"byGpuFramework": {

View File

@@ -59,7 +59,7 @@
"5": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 469,
"listingErrors": 470,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0,
"mode": "incremental_decision_only",
"nextAccountIndex": 5,
"nextAccountIndex": 6,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-13T02:54:29.081592+00:00",
"updatedAt": "2026-09-13T02:57:22.647228+00:00",
"version": 1
}

View File

@@ -416,121 +416,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-13T02:52:38.363860+00:00",
"generatedAt": "2026-09-13T02:55:36.877864+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 826.5798816568047,
"backlogHours": 821.5058823529412,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.010685702335496,
"queueFactor": 1.0007063083335355,
"queueWeight": 1.0007063083335355,
"recentSuccess": 54,
"recentSuccessRate": 0.31952662721893493,
"recentTerminal": 169,
"recentWilsonLowerBound": 0.253905220669305,
"qualityFactor": 2.3458179879923686,
"queueFactor": 0.9999064089327836,
"queueWeight": 0.9999064089327836,
"recentSuccess": 55,
"recentSuccessRate": 0.3235294117647059,
"recentTerminal": 170,
"recentWilsonLowerBound": 0.25777571272728994,
"running": 8,
"selectionWeight": 2.0121058664031763,
"selectionWeight": 2.345598440383377,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 28.166666666666668,
"waiting": 23282
"throughputPerHour": 28.333333333333332,
"waiting": 23276
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 999.5853658536586,
"backlogHours": 1011.8518518518518,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.1538911207807443,
"queueFactor": 0.9725823383930163,
"queueWeight": 0.9725823383930163,
"qualityFactor": 2.5,
"queueFactor": 0.9691330714270063,
"queueWeight": 0.9691330714270063,
"recentSuccess": 54,
"recentSuccessRate": 0.32926829268292684,
"recentTerminal": 164,
"recentWilsonLowerBound": 0.26197101765012754,
"recentSuccessRate": 0.3333333333333333,
"recentTerminal": 162,
"recentWilsonLowerBound": 0.2653433586296137,
"running": 8,
"selectionWeight": 2.094836462892891,
"selectionWeight": 2.4228326785675156,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 27.333333333333332,
"waiting": 27322
"throughputPerHour": 27.0,
"waiting": 27320
},
"Biren_166m": {
"available": true,
"backlogHours": 153.25714285714284,
"backlogHours": 154.95953757225433,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.33923793506424016,
"queueFactor": 1.2885054309552753,
"queueWeight": 1.2885054309552753,
"recentSuccess": 28,
"recentSuccessRate": 0.16,
"recentTerminal": 175,
"recentWilsonLowerBound": 0.11307870395124361,
"qualityFactor": 0.35689754970756826,
"queueFactor": 1.2841572466505198,
"queueWeight": 1.2841572466505198,
"recentSuccess": 27,
"recentSuccessRate": 0.15606936416184972,
"recentTerminal": 173,
"recentWilsonLowerBound": 0.10953101490588989,
"running": 8,
"selectionWeight": 0.43710992171632645,
"selectionWeight": 0.4583125747687879,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 29.166666666666668,
"waiting": 4470
"throughputPerHour": 28.833333333333332,
"waiting": 4468
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1844.6808510638298,
"backlogHours": 1667.5384615384617,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 1.4915336860558837,
"queueFactor": 0.8871788425456589,
"queueWeight": 0.8871788425456589,
"recentSuccess": 16,
"recentSuccessRate": 0.3404255319148936,
"recentTerminal": 47,
"recentWilsonLowerBound": 0.2216726071376219,
"qualityFactor": 1.577245646172782,
"queueFactor": 0.8991653748589896,
"queueWeight": 0.8991653748589896,
"recentSuccess": 17,
"recentSuccessRate": 0.3269230769230769,
"recentTerminal": 52,
"recentWilsonLowerBound": 0.2152190173110406,
"running": 7,
"selectionWeight": 1.3232571292129192,
"selectionWeight": 1.4182046726856588,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 7.833333333333333,
"waiting": 14450
"throughputPerHour": 8.666666666666666,
"waiting": 14452
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 428.2439024390244,
"backlogHours": 479.0727272727273,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.3053385610317276,
"queueFactor": 1.1044490448325075,
"queueWeight": 1.1044490448325075,
"recentSuccess": 20,
"recentSuccessRate": 0.16260162601626016,
"recentTerminal": 123,
"recentWilsonLowerBound": 0.1077947851092691,
"qualityFactor": 0.3326754093524709,
"queueFactor": 1.0841534007833338,
"queueWeight": 1.0841534007833338,
"recentSuccess": 18,
"recentSuccessRate": 0.16363636363636364,
"recentTerminal": 110,
"recentWilsonLowerBound": 0.10608722310923731,
"running": 7,
"selectionWeight": 0.3372308820820238,
"selectionWeight": 0.360671176406469,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 20.5,
"waiting": 8779
"throughputPerHour": 18.333333333333332,
"waiting": 8783
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 45.928338762214985,
"backlogHours": 46.03921568627451,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -539,197 +539,197 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 16,
"recentSuccessRate": 0.05211726384364821,
"recentTerminal": 307,
"recentWilsonLowerBound": 0.03233113815783921,
"recentSuccess": 15,
"recentSuccessRate": 0.049019607843137254,
"recentTerminal": 306,
"recentWilsonLowerBound": 0.029928212044126865,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 51.166666666666664,
"waiting": 2350
"throughputPerHour": 51.0,
"waiting": 2348
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 210.375,
"backlogHours": 199.6779661016949,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.24196719162057637,
"queueFactor": 1.2287124046665756,
"queueWeight": 1.2287124046665756,
"recentSuccess": 17,
"recentSuccessRate": 0.15178571428571427,
"recentTerminal": 112,
"recentWilsonLowerBound": 0.09697889223230617,
"running": 4,
"selectionWeight": 0.29730808986653645,
"qualityFactor": 0.4318796790116173,
"queueFactor": 1.2362361298351625,
"queueWeight": 1.2362361298351625,
"recentSuccess": 21,
"recentSuccessRate": 0.17796610169491525,
"recentTerminal": 118,
"recentWilsonLowerBound": 0.119448913662713,
"running": 2,
"selectionWeight": 0.533905262935774,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.666666666666668,
"throughputPerHour": 19.666666666666668,
"waiting": 3927
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 1859.28,
"backlogHours": 1897.2244897959185,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.0752501926477225,
"queueFactor": 0.8861304133899259,
"queueWeight": 0.8861304133899259,
"qualityFactor": 1.2717114473640647,
"queueFactor": 0.8819280289802969,
"queueWeight": 0.8819280289802969,
"recentSuccess": 15,
"recentSuccessRate": 0.3,
"recentTerminal": 50,
"recentWilsonLowerBound": 0.1910338908960936,
"recentSuccessRate": 0.30612244897959184,
"recentTerminal": 49,
"recentWilsonLowerBound": 0.1951532349314748,
"running": 2,
"selectionWeight": 0.9528118977085238,
"selectionWeight": 1.12155797020547,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 8.333333333333334,
"throughputPerHour": 8.166666666666666,
"waiting": 15494
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 834.379746835443,
"backlogHours": 867.3947368421053,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.8348564426146853,
"queueFactor": 0.9992974957543633,
"queueWeight": 0.9992974957543633,
"recentSuccess": 20,
"recentSuccessRate": 0.25316455696202533,
"recentTerminal": 79,
"recentWilsonLowerBound": 0.1702773604894678,
"qualityFactor": 0.8942436948084186,
"queueFactor": 0.9917870567242505,
"queueWeight": 0.9917870567242505,
"recentSuccess": 19,
"recentSuccessRate": 0.25,
"recentTerminal": 76,
"recentWilsonLowerBound": 0.16628799382577897,
"running": 7,
"selectionWeight": 0.8342699524192513,
"selectionWeight": 0.8868993220682604,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 13.166666666666666,
"waiting": 10986
"throughputPerHour": 12.666666666666666,
"waiting": 10987
},
"MetaX_c-500": {
"available": true,
"backlogHours": 764.2247191011236,
"backlogHours": 755.2,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.8241486456574143,
"queueFactor": 1.0125493518232962,
"queueWeight": 1.0125493518232962,
"qualityFactor": 0.9065778092522563,
"queueFactor": 1.0126087048205619,
"queueWeight": 1.0126087048205619,
"recentSuccess": 22,
"recentSuccessRate": 0.24719101123595505,
"recentTerminal": 89,
"recentWilsonLowerBound": 0.16928115452187478,
"recentSuccessRate": 0.24444444444444444,
"recentTerminal": 90,
"recentWilsonLowerBound": 0.16732663395366265,
"running": 4,
"selectionWeight": 0.8344911769664622,
"selectionWeight": 0.9180085812459896,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 14.833333333333334,
"waiting": 11336
"throughputPerHour": 15.0,
"waiting": 11328
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1518.4941176470588,
"backlogHours": 1483.655172413793,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 1.7564958690133834,
"queueFactor": 0.9134554999709532,
"queueWeight": 0.9134554999709532,
"qualityFactor": 1.8783158288242943,
"queueFactor": 0.9150630255258815,
"queueWeight": 0.9150630255258815,
"recentSuccess": 28,
"recentSuccessRate": 0.32941176470588235,
"recentTerminal": 85,
"recentWilsonLowerBound": 0.23877626262769044,
"recentSuccessRate": 0.3218390804597701,
"recentTerminal": 87,
"recentWilsonLowerBound": 0.23300577279734025,
"running": 4,
"selectionWeight": 1.6044808122265342,
"selectionWeight": 1.7187773652171123,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 14.166666666666666,
"waiting": 21512
"throughputPerHour": 14.5,
"waiting": 21513
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 4328.099999999999,
"backlogHours": 3935.1818181818185,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.9571048412396761,
"queueFactor": 0.7806471331725917,
"queueWeight": 0.7806471331725917,
"qualityFactor": 0.8627953595497807,
"queueFactor": 0.790507934133047,
"queueWeight": 0.790507934133047,
"recentSuccess": 7,
"recentSuccessRate": 0.35,
"recentTerminal": 20,
"recentWilsonLowerBound": 0.1811895478679446,
"recentSuccessRate": 0.3181818181818182,
"recentTerminal": 22,
"recentWilsonLowerBound": 0.16360387354692477,
"running": 2,
"selectionWeight": 0.7471611504593617,
"selectionWeight": 0.6820465772572767,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 3.3333333333333335,
"waiting": 14427
"throughputPerHour": 3.6666666666666665,
"waiting": 14429
},
"Vastai_va16": {
"available": true,
"backlogHours": 841.7142857142857,
"backlogHours": 820.4810126582279,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.8854278644000197,
"queueFactor": 0.9979864790616062,
"queueWeight": 0.9979864790616062,
"recentSuccess": 20,
"recentSuccessRate": 0.2597402597402597,
"recentTerminal": 77,
"recentWilsonLowerBound": 0.17489066479540774,
"qualityFactor": 1.0767033679840505,
"queueFactor": 1.0000936582699786,
"queueWeight": 1.0000936582699786,
"recentSuccess": 21,
"recentSuccessRate": 0.26582278481012656,
"recentTerminal": 79,
"recentWilsonLowerBound": 0.18093205809599439,
"running": 16,
"selectionWeight": 0.883645036855613,
"selectionWeight": 1.076804210158776,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.833333333333334,
"waiting": 10802
"throughputPerHour": 13.166666666666666,
"waiting": 10803
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 491.01724137931035,
"backlogHours": 499.7368421052632,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 2.5,
"queueFactor": 1.0820189100167024,
"queueWeight": 1.0820189100167024,
"recentSuccess": 42,
"recentSuccessRate": 0.3620689655172414,
"recentTerminal": 116,
"recentWilsonLowerBound": 0.2803300988879438,
"qualityFactor": 2.4198189103431282,
"queueFactor": 1.077307661478909,
"queueWeight": 1.077307661478909,
"recentSuccess": 39,
"recentSuccessRate": 0.34210526315789475,
"recentTerminal": 114,
"recentWilsonLowerBound": 0.26144067569416146,
"running": 6,
"selectionWeight": 2.705047275041756,
"selectionWeight": 2.6068894515041974,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 19.333333333333332,
"waiting": 9493
"throughputPerHour": 19.0,
"waiting": 9495
}
},
"queueAttemptedAt": "2026-09-13T02:43:58.542913+00:00",
"queueAttemptedAt": "2026-09-13T02:55:36.877864+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-13T02:43:58.542913+00:00",
"queueUpdatedAt": "2026-09-13T02:55:36.877864+00:00",
"supportedGpus": [
"Vastai_va16",
"Iluvatar_mrv-100",

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-13T02:47:04.270444+00:00",
"lastSyncTime": "2026-09-13T02:47:03.906686+00:00",
"generatedAt": "2026-09-13T02:55:30.151645+00:00",
"lastSyncTime": "2026-09-13T02:55:29.910747+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -209,17 +209,19 @@
"architectures": [
"spark2_5forcausallm"
],
"evidenceCount": 1,
"expiresAt": "2026-10-12T16:39:21+00:00",
"evidenceCount": 2,
"expiresAt": "2026-10-13T02:47:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-12T16:39:21+00:00",
"latestFailureAt": "2026-09-13T02:47:21+00:00",
"latestSuccessfulAt": null,
"matchType": "architectures",
"modelType": null,
"sourceModelIds": [
"XHToken/Spark-X2.5-1.7B",
"XHToken/Spark-X2.5-4B"
],
"sourceTaskIds": [
"4557197",
"4548919"
],
"targetGpu": "Ascend_910-b4",
@@ -1606,18 +1608,18 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 44,
"attributableFailureCount": 45,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 44,
"decisionTotal": 45,
"failureBreakdown": {
"ambiguous_runtime": 35,
"framework_architecture_unsupported": 40,
"framework_architecture_unsupported": 41,
"memory_capacity": 1,
"repository_structure": 1,
"tokenizer_compatibility": 2
},
"failureCount": 79,
"failureCount": 80,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1627,7 +1629,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 79,
"total": 80,
"unresolvedFailureCount": 35
},
"Biren_166m|unknown|text-generation": {
@@ -2052,21 +2054,21 @@
"decisionSuccessRate": 1.0,
"decisionTotal": 9,
"failureBreakdown": {
"参数/模板问题": 8,
"参数/模板问题": 9,
"验证失败": 48
},
"failureCount": 56,
"failureRate": 0.8615,
"failureCount": 57,
"failureRate": 0.8636,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.1385,
"successRate": 0.1364,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 65,
"unresolvedFailureCount": 56
"total": 66,
"unresolvedFailureCount": 57
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 53,
@@ -2193,21 +2195,21 @@
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {
"参数/模板问题": 1,
"参数/模板问题": 2,
"验证失败": 32
},
"failureCount": 33,
"failureRate": 0.9706,
"failureCount": 34,
"failureRate": 0.9714,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0294,
"successRate": 0.0286,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 34,
"unresolvedFailureCount": 33
"total": 35,
"unresolvedFailureCount": 34
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 44,
@@ -2471,28 +2473,28 @@
"model_load": 43,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 59,
"参数/模板问题": 61,
"验证失败": 673
},
"failureCount": 1021,
"failureCount": 1023,
"failureRate": 0.9507,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 53,
"successRate": 0.0493,
"total": 1074,
"unresolvedFailureCount": 871
"total": 1076,
"unresolvedFailureCount": 873
},
"vllm": {
"attributableFailureCount": 290,
"attributableFailureCount": 291,
"decisionFailureRate": 0.9898,
"decisionSuccessRate": 0.0102,
"decisionTotal": 293,
"decisionTotal": 294,
"failureBreakdown": {
"ambiguous_runtime": 201,
"backend_operator": 34,
"framework_architecture_unsupported": 204,
"framework_architecture_unsupported": 205,
"memory_capacity": 6,
"model_load": 26,
"platform_infrastructure": 1,
@@ -2501,14 +2503,14 @@
"tokenizer_compatibility": 6,
"参数/模板问题": 24
},
"failureCount": 516,
"failureCount": 517,
"failureRate": 0.9942,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0058,
"total": 519,
"total": 520,
"unresolvedFailureCount": 225
},
"vllm-mlu": {
@@ -2613,7 +2615,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-13T02:47:04.265926+00:00",
"generatedAt": "2026-09-13T02:55:30.147369+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 30,
@@ -2639,13 +2641,13 @@
"unresolvedFailureCount": 63
},
"Ascend_910-b4": {
"attributableFailureCount": 45,
"decisionFailureRate": 0.9574,
"decisionSuccessRate": 0.0426,
"decisionTotal": 47,
"attributableFailureCount": 46,
"decisionFailureRate": 0.9583,
"decisionSuccessRate": 0.0417,
"decisionTotal": 48,
"failureBreakdown": {
"ambiguous_runtime": 36,
"framework_architecture_unsupported": 40,
"framework_architecture_unsupported": 41,
"memory_capacity": 1,
"model_load": 1,
"repository_structure": 1,
@@ -2653,14 +2655,14 @@
"参数/模板问题": 12,
"验证失败": 175
},
"failureCount": 268,
"failureCount": 269,
"failureRate": 0.9926,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0074,
"total": 270,
"total": 271,
"unresolvedFailureCount": 223
},
"Biren_166m": {
@@ -2833,18 +2835,18 @@
"memory_capacity": 1,
"model_load": 7,
"repository_structure": 1,
"参数/模板问题": 17,
"参数/模板问题": 18,
"验证失败": 48
},
"failureCount": 127,
"failureRate": 0.9137,
"failureCount": 128,
"failureRate": 0.9143,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 12,
"successRate": 0.0863,
"total": 139,
"unresolvedFailureCount": 74
"successRate": 0.0857,
"total": 140,
"unresolvedFailureCount": 75
},
"Mthreads_s4000": {
"attributableFailureCount": 36,
@@ -2883,18 +2885,18 @@
"framework_architecture_unsupported": 5,
"platform_infrastructure": 3,
"tokenizer_compatibility": 42,
"参数/模板问题": 9,
"参数/模板问题": 10,
"验证失败": 32
},
"failureCount": 93,
"failureRate": 0.9894,
"failureCount": 94,
"failureRate": 0.9895,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 1,
"successRate": 0.0106,
"total": 94,
"unresolvedFailureCount": 42
"successRate": 0.0105,
"total": 95,
"unresolvedFailureCount": 43
},
"Vastai_va16": {
"attributableFailureCount": 50,
@@ -4485,21 +4487,21 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"attributableFailureCount": 8,
"consecutiveFailures": 8,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 13,
"framework_architecture_unsupported": 7
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 8
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T23:26:15.638604+00:00",
"lastTerminalAt": "2026-09-13T02:55:29.910747+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4508,7 +4510,7 @@
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 13
"unresolvedFailureCount": 12
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 8,
@@ -4746,6 +4748,31 @@
"total": 2,
"unresolvedFailureCount": 2
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-13T02:55:29.910734+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 6,
"consecutiveFailures": 6,
@@ -4833,21 +4860,23 @@
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"failureBreakdown": {
"参数/模板问题": 1
},
"failureCount": 1,
"failureRate": 0.5,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-09T17:24:58.529030+00:00",
"lastTerminalAt": "2026-09-13T02:55:29.910704+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 1.0,
"successRate": 0.5,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
"total": 2,
"unresolvedFailureCount": 1
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 14,
@@ -7362,41 +7391,40 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1753,
"totalRecords": 1840,
"terminalRecords": 1756,
"totalRecords": 1843,
"totals": {
"attributableFailureCount": 505,
"decisionFailureRate": 0.897,
"decisionSuccessRate": 0.103,
"decisionTotal": 563,
"attributableFailureCount": 506,
"decisionFailureRate": 0.8972,
"decisionSuccessRate": 0.1028,
"decisionTotal": 564,
"failureBreakdown": {
"ambiguous_runtime": 412,
"backend_operator": 42,
"framework_architecture_unsupported": 317,
"framework_architecture_unsupported": 318,
"memory_capacity": 11,
"model_load": 73,
"platform_infrastructure": 4,
"repository_structure": 8,
"runtime_memory": 6,
"tokenizer_compatibility": 48,
"参数/模板问题": 101,
"参数/模板问题": 103,
"验证失败": 673
},
"failureCount": 1695,
"failureRate": 0.9669,
"failureCount": 1698,
"failureRate": 0.967,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 58,
"successRate": 0.0331,
"total": 1753,
"unresolvedFailureCount": 1186
"successRate": 0.033,
"total": 1756,
"unresolvedFailureCount": 1188
},
"warnings": [
"GPU Ascend_910-b3 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 Mthreads_s4000 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。",
"GPU hygon_k100-ai 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 Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
@@ -7405,6 +7433,7 @@
"GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Biren_166m 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 hygon_k100-ai|vllm-patch-tokenizer|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|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7427,6 +7456,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1840,
"summarizedRecords": 1843,
"version": 1
}

View File

@@ -1,3 +1,6 @@
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-13T02:55:29.910704+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-13T02:51:53+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4133475", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-13T02:55:29.910734+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-13T02:51:53+00:00", "targetGpu": "MetaX_c-500", "taskId": "4133144", "taskType": "text-generation", "verifyResult": null}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-13T02:55:29.910747+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T02:47:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4557197", "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": "", "lastSyncTime": "2026-09-13T02:47:03.906686+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T02:41:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4549639", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-13T02:20:50.802489+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T02:13:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4549809", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-13T02:12:14.114155+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T02:09:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4543931", "taskType": "text-generation", "verifyResult": -1}
@@ -295,6 +298,3 @@
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-09T05:53:14.296748+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T05:51:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4083446", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T05:15:37.097487+00:00", "modelId": "RedHatAI/Qwen2.5-3B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T05:15:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4591599", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-09T05:12:14.918874+00:00", "modelId": "nm-testing/tinyllama-marlin24-w4a16-group128", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T05:11:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523219", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-09T04:51:59.603427+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T04:51:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332977", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T04:15:14.005422+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T04:13:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471924", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T03:27:28.006277+00:00", "modelId": "RedHatAI/Qwen2.5-3B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T03:27:22+00:00", "targetGpu": "Vastai_va16", "taskId": "4081077", "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

View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "8a201d7a3ba7186f695c2d374f243823e586cfe9a5501531c18588d9fdaf409c",
".modelhub_state/architecture_history_backfill.json": "32ad5919a9059ae7a02abcac2fac0f9926017a503ce9ce6875e420105c32cf44",
".modelhub_state/market_intelligence.json": "d822844a97792314c86a1ebc46aa512a889d33b403a71829c3a48f30129d1966",
".modelhub_state/official_capabilities.json": "acf75aa5c74fae1f353dce755c93ae894706da7f8641847ab9222ecee4ff0bf8",
".modelhub_state/outcome_checkpoint.json": "b72732f0ba976efffd7c1d11c3ae02bb150af878baba79ce9847ee1e68784997",
".modelhub_state/architecture_compatibility_blacklist.json": "2ef2d88cf4625c568bde13ac40d79bc3e1ee69cdf9327c76e40c54c9fa7765d6",
".modelhub_state/architecture_history_backfill.json": "04d6d9af0572591b31e1014797405e272cbec4b3d3e62c9f283be0647cde4a0a",
".modelhub_state/market_intelligence.json": "99ebdaad9f6249d2f1fba8ad241a4ba785c0691b12fafd1d5e7693cb67dc79d4",
".modelhub_state/official_capabilities.json": "38e59db9666567b9d9540b8042550bf53ec3d07b094288d16382a966eb08811e",
".modelhub_state/outcome_checkpoint.json": "0af93a790447468ccf3d601802ae53e9c465048a8832d883794e238d23f28a56",
".modelhub_state/queue_cleanup_latest.json": "51e7d1585319177976584ac9d97c18e02335e06fbd17bfdd6be748f1310ef4da",
".modelhub_state/recent_outcomes.jsonl": "f6110868dc9ff3ea89356845e2011b3787dbac3c2f9340cfe3adb25faf9e6d15",
".modelhub_state/recovery_active_tasks.jsonl": "3dc245bf2faae753aca0a3222b0388cb8e1892d99a2852bb013ab1afaa607cd2",
".modelhub_state/recovery_intents.jsonl": "45c7d7e4669b841c597dee07ecb2b4048d25fbc9defac84a09ee377bd33d9f14",
".modelhub_state/recent_outcomes.jsonl": "78cda521f02b151a7c7ed63db5df59f02953d6fae88ad8e53c2dfe94b809a0fc",
".modelhub_state/recovery_active_tasks.jsonl": "b9b677ed96557738e32a7949d5bd456dbb1699d6ef00e81e8c56491ae9964519",
".modelhub_state/recovery_intents.jsonl": "5acf7bb9a2b7af11c3543a643f906e39c9c01865c9b0cba43ccb3c426ec14ccc",
".modelhub_state/routing_intelligence.json": "cdd3341d66484775862c4a1f5c766a7fc0200b1a3a204a76975162502e1d3457",
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
"ledger/submissions.jsonl": "b7a4c9900ee212be7c7f8578a0a71942885eb83e97c5583098a169266bedf55c",
"outcomes/submissions.jsonl": "52eb59d3f79d7002ef2c21ead04124871025575876c40b3c89e753c66cc8d521"
},
"generation": 6484,
"generation": 6485,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-13T02:54:29.192083+00:00",
"updatedAt": "2026-09-13T02:57:24.273108+00:00",
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
}