state: generation 4987 (cycle)

This commit is contained in:
2026-09-10 05:51:31 +00:00
parent 15a2633657
commit a153f9f452
9 changed files with 2148 additions and 2151 deletions

View File

@@ -1323,7 +1323,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T05:48:47.668064+00:00",
"generatedAt": "2026-09-10T05:51:30.408685+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -11,7 +11,7 @@
"1": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 355,
"listingErrors": 356,
"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": 1,
"nextAccountIndex": 2,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-10T05:48:47.643306+00:00",
"updatedAt": "2026-09-10T05:51:30.383284+00:00",
"version": 1
}

View File

@@ -416,320 +416,320 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T05:47:23.445226+00:00",
"generatedAt": "2026-09-10T05:49:55.585375+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 934.24,
"backlogHours": 987.1267605633802,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.3309316472174901,
"queueFactor": 0.9545130220383132,
"queueWeight": 0.9545130220383132,
"recentSuccess": 53,
"recentSuccessRate": 0.35333333333333333,
"recentTerminal": 150,
"recentWilsonLowerBound": 0.28137142404545956,
"qualityFactor": 1.265837675010713,
"queueFactor": 0.9464972579415434,
"queueWeight": 0.9464972579415434,
"recentSuccess": 51,
"recentSuccessRate": 0.3591549295774648,
"recentTerminal": 142,
"recentWilsonLowerBound": 0.28491328176623315,
"running": 8,
"selectionWeight": 1.2703915887119968,
"selectionWeight": 1.1981118883967383,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 25.0,
"waiting": 23356
"throughputPerHour": 23.666666666666668,
"waiting": 23362
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1096.4,
"backlogHours": 1096.6,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.0881504527288801,
"queueFactor": 0.931869875032184,
"queueWeight": 0.931869875032184,
"recentSuccess": 49,
"recentSuccessRate": 0.32666666666666666,
"qualityFactor": 0.855775685209701,
"queueFactor": 0.9316827673374161,
"queueWeight": 0.9316827673374161,
"recentSuccess": 46,
"recentSuccessRate": 0.30666666666666664,
"recentTerminal": 150,
"recentWilsonLowerBound": 0.2567570339087464,
"recentWilsonLowerBound": 0.2384689020846879,
"running": 8,
"selectionWeight": 1.014014626400676,
"selectionWeight": 0.7973114586162477,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 25.0,
"waiting": 27410
"waiting": 27415
},
"Biren_166m": {
"available": true,
"backlogHours": 150.65895953757226,
"backlogHours": 148.4318181818182,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.2610061088396657,
"queueFactor": 1.2550221239883155,
"queueWeight": 1.2550221239883155,
"qualityFactor": 0.2323181743272944,
"queueFactor": 1.2576107697845085,
"queueWeight": 1.2576107697845085,
"recentSuccess": 32,
"recentSuccessRate": 0.18497109826589594,
"recentTerminal": 173,
"recentWilsonLowerBound": 0.13417968576824785,
"recentSuccessRate": 0.18181818181818182,
"recentTerminal": 176,
"recentWilsonLowerBound": 0.1318357597784602,
"running": 8,
"selectionWeight": 0.32756844108988264,
"selectionWeight": 0.29216583805068036,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 28.833333333333332,
"waiting": 4344
"throughputPerHour": 29.333333333333332,
"waiting": 4354
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1112.6052631578948,
"backlogHours": 1070.5822784810127,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.5507101697219634,
"queueFactor": 0.9298212341423254,
"queueWeight": 0.9298212341423254,
"recentSuccess": 21,
"recentSuccessRate": 0.27631578947368424,
"recentTerminal": 76,
"recentWilsonLowerBound": 0.18840105352742306,
"qualityFactor": 0.5292744402721313,
"queueFactor": 0.9350445246069062,
"queueWeight": 0.9350445246069062,
"recentSuccess": 22,
"recentSuccessRate": 0.27848101265822783,
"recentTerminal": 79,
"recentWilsonLowerBound": 0.19168037554546477,
"running": 7,
"selectionWeight": 0.5120620096656056,
"selectionWeight": 0.49489516739084144,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.666666666666666,
"waiting": 14093
"throughputPerHour": 13.166666666666666,
"waiting": 14096
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 543.40206185567,
"backlogHours": 507.11538461538464,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.620563945395201,
"queueFactor": 1.0353386671728393,
"queueWeight": 1.0353386671728393,
"recentSuccess": 27,
"recentSuccessRate": 0.27835051546391754,
"recentTerminal": 97,
"recentWilsonLowerBound": 0.19891045889682296,
"qualityFactor": 0.5393557985854078,
"queueFactor": 1.0459460424944433,
"queueWeight": 1.0459460424944433,
"recentSuccess": 28,
"recentSuccessRate": 0.2692307692307692,
"recentTerminal": 104,
"recentWilsonLowerBound": 0.19333139862414106,
"running": 7,
"selectionWeight": 0.642493848120986,
"selectionWeight": 0.5641370630268374,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 16.166666666666668,
"waiting": 8785
"throughputPerHour": 17.333333333333332,
"waiting": 8790
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 58.25409836065574,
"backlogHours": 59.57322175732217,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 24,
"qualityFactor": 0.05,
"qualityFactor": 0.05486591246869853,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 22,
"recentSuccessRate": 0.09016393442622951,
"recentTerminal": 244,
"recentWilsonLowerBound": 0.060296236846364724,
"running": 2,
"selectionWeight": 0.065,
"recentSuccess": 24,
"recentSuccessRate": 0.100418410041841,
"recentTerminal": 239,
"recentWilsonLowerBound": 0.0684121064538453,
"running": 1,
"selectionWeight": 0.07132568620930808,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 40.666666666666664,
"waiting": 2369
"throughputPerHour": 39.833333333333336,
"waiting": 2373
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 68.43243243243244,
"backlogHours": 71.8307210031348,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.12869585939934974,
"qualityFactor": 0.147157623117348,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 43,
"recentSuccessRate": 0.12912912912912913,
"recentTerminal": 333,
"recentWilsonLowerBound": 0.09729761181764289,
"running": 0,
"selectionWeight": 0.16730461721915468,
"recentSuccess": 45,
"recentSuccessRate": 0.14106583072100312,
"recentTerminal": 319,
"recentWilsonLowerBound": 0.10712643959066792,
"running": 1,
"selectionWeight": 0.19130491005255243,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 55.5,
"waiting": 3798
"throughputPerHour": 53.166666666666664,
"waiting": 3819
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2484.162162162162,
"backlogHours": 2419.421052631579,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.3871717963468964,
"queueFactor": 0.8242778601593579,
"queueWeight": 0.8242778601593579,
"recentSuccess": 16,
"recentSuccessRate": 0.43243243243243246,
"recentTerminal": 37,
"recentWilsonLowerBound": 0.2867148684035131,
"qualityFactor": 1.4332457281012336,
"queueFactor": 0.8274058376226368,
"queueWeight": 0.8274058376226368,
"recentSuccess": 17,
"recentSuccessRate": 0.4473684210526316,
"recentTerminal": 38,
"recentWilsonLowerBound": 0.3014616531155089,
"running": 2,
"selectionWeight": 1.1434149999662324,
"selectionWeight": 1.185875882178667,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 6.166666666666667,
"waiting": 15319
"throughputPerHour": 6.333333333333333,
"waiting": 15323
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 637.0588235294117,
"backlogHours": 624.8653846153846,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.4032687853836176,
"queueFactor": 1.0109360786409838,
"queueWeight": 1.0109360786409838,
"recentSuccess": 24,
"recentSuccessRate": 0.23529411764705882,
"recentTerminal": 102,
"recentWilsonLowerBound": 0.1635198113173856,
"qualityFactor": 0.3983468984870239,
"queueFactor": 1.0136950573316448,
"queueWeight": 1.0136950573316448,
"recentSuccess": 25,
"recentSuccessRate": 0.2403846153846154,
"recentTerminal": 104,
"recentWilsonLowerBound": 0.16845266546271026,
"running": 7,
"selectionWeight": 0.40767896453402686,
"selectionWeight": 0.4038022820996866,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.0,
"waiting": 10830
"throughputPerHour": 17.333333333333332,
"waiting": 10831
},
"MetaX_c-500": {
"available": true,
"backlogHours": 679.3663366336634,
"backlogHours": 659.7692307692308,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.4124328249838791,
"queueFactor": 1.0012326948260386,
"queueWeight": 1.0012326948260386,
"recentSuccess": 24,
"recentSuccessRate": 0.2376237623762376,
"recentTerminal": 101,
"recentWilsonLowerBound": 0.1651985046175726,
"qualityFactor": 0.3983468984870239,
"queueFactor": 1.005463918334034,
"queueWeight": 1.005463918334034,
"recentSuccess": 25,
"recentSuccessRate": 0.2403846153846154,
"recentTerminal": 104,
"recentWilsonLowerBound": 0.16845266546271026,
"running": 4,
"selectionWeight": 0.41294122879332523,
"selectionWeight": 0.40052343340897273,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 16.833333333333332,
"throughputPerHour": 17.333333333333332,
"waiting": 11436
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1786.732394366197,
"backlogHours": 1762.8333333333333,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 1.0372448180674316,
"queueFactor": 0.8660474746278862,
"queueWeight": 0.8660474746278862,
"qualityFactor": 0.9289694644574863,
"queueFactor": 0.8676480815797005,
"queueWeight": 0.8676480815797005,
"recentSuccess": 25,
"recentSuccessRate": 0.352112676056338,
"recentTerminal": 71,
"recentWilsonLowerBound": 0.2512258456160325,
"recentSuccessRate": 0.3472222222222222,
"recentTerminal": 72,
"recentWilsonLowerBound": 0.24753261631759219,
"running": 4,
"selectionWeight": 0.8983032552581605,
"selectionWeight": 0.8060185736826597,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 11.833333333333334,
"waiting": 21143
"throughputPerHour": 12.0,
"waiting": 21154
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 4649.0,
"backlogHours": 5233.875,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.9814405378385502,
"queueFactor": 0.7503202964393247,
"queueWeight": 0.7503202964393247,
"qualityFactor": 2.4746156073002155,
"queueFactor": 0.736973373063099,
"queueWeight": 0.736973373063099,
"recentSuccess": 10,
"recentSuccessRate": 0.5555555555555556,
"recentTerminal": 18,
"recentWilsonLowerBound": 0.33716069428251627,
"recentSuccessRate": 0.625,
"recentTerminal": 16,
"recentWilsonLowerBound": 0.38640647097934805,
"running": 2,
"selectionWeight": 1.486715051727916,
"selectionWeight": 1.8237258111466288,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 3.0,
"waiting": 13947
"throughputPerHour": 2.6666666666666665,
"waiting": 13957
},
"Vastai_va16": {
"available": true,
"backlogHours": 690.5714285714286,
"backlogHours": 708.5853658536586,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.8644900283072754,
"queueFactor": 0.9987788459408788,
"queueWeight": 0.9987788459408788,
"recentSuccess": 27,
"recentSuccessRate": 0.32142857142857145,
"recentTerminal": 84,
"recentWilsonLowerBound": 0.23125977350162447,
"qualityFactor": 0.7639631133133111,
"queueFactor": 0.994755781986833,
"queueWeight": 0.994755781986833,
"recentSuccess": 26,
"recentSuccessRate": 0.3170731707317073,
"recentTerminal": 82,
"recentWilsonLowerBound": 0.22647919829889349,
"running": 16,
"selectionWeight": 0.8634343528001382,
"selectionWeight": 0.7599567241930784,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 14.0,
"waiting": 9668
"throughputPerHour": 13.666666666666666,
"waiting": 9684
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 560.0645161290323,
"backlogHours": 578.8,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 2.5,
"queueFactor": 1.0306588045949345,
"queueWeight": 1.0306588045949345,
"queueFactor": 1.0254063926021162,
"queueWeight": 1.0254063926021162,
"recentSuccess": 44,
"recentSuccessRate": 0.4731182795698925,
"recentTerminal": 93,
"recentWilsonLowerBound": 0.3747376923069333,
"recentSuccessRate": 0.4888888888888889,
"recentTerminal": 90,
"recentWilsonLowerBound": 0.38820314979105425,
"running": 6,
"selectionWeight": 2.5766470114873363,
"selectionWeight": 2.5635159815052906,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 15.5,
"waiting": 8681
"throughputPerHour": 15.0,
"waiting": 8682
}
},
"queueAttemptedAt": "2026-09-10T05:37:44.914825+00:00",
"queueAttemptedAt": "2026-09-10T05:49:55.585375+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-10T05:37:44.914825+00:00",
"queueUpdatedAt": "2026-09-10T05:49:55.585375+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": "2026-09-10T05:27:18.664485+00:00",
"lastSyncTime": "2026-09-10T05:27:18.447582+00:00",
"generatedAt": "2026-09-10T05:49:48.836041+00:00",
"lastSyncTime": "2026-09-10T05:49:48.500487+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1484,13 +1484,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 37,
"failureBreakdown": {
"ambiguous_runtime": 25,
"ambiguous_runtime": 27,
"framework_architecture_unsupported": 33,
"memory_capacity": 1,
"repository_structure": 1,
"tokenizer_compatibility": 2
},
"failureCount": 62,
"failureCount": 64,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1500,8 +1500,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 62,
"unresolvedFailureCount": 25
"total": 64,
"unresolvedFailureCount": 27
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 24,
@@ -2331,7 +2331,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 230,
"failureBreakdown": {
"ambiguous_runtime": 138,
"ambiguous_runtime": 140,
"backend_operator": 24,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2342,15 +2342,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 390,
"failureCount": 392,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 390,
"unresolvedFailureCount": 159
"total": 392,
"unresolvedFailureCount": 161
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2453,7 +2453,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T05:27:18.659030+00:00",
"generatedAt": "2026-09-10T05:49:48.831661+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2484,7 +2484,7 @@
"decisionSuccessRate": 0.05,
"decisionTotal": 40,
"failureBreakdown": {
"ambiguous_runtime": 26,
"ambiguous_runtime": 28,
"framework_architecture_unsupported": 33,
"memory_capacity": 1,
"model_load": 1,
@@ -2493,15 +2493,15 @@
"参数/模板问题": 11,
"验证失败": 175
},
"failureCount": 250,
"failureCount": 252,
"failureRate": 0.9921,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0079,
"total": 252,
"unresolvedFailureCount": 212
"total": 254,
"unresolvedFailureCount": 214
},
"Biren_166m": {
"attributableFailureCount": 25,
@@ -4000,21 +4000,21 @@
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 9,
"consecutiveFailures": 9,
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 9,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 9
"ambiguous_runtime": 13,
"framework_architecture_unsupported": 7
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T04:27:58.701433+00:00",
"lastTerminalAt": "2026-09-10T05:49:48.500487+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4023,7 +4023,7 @@
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 11
"unresolvedFailureCount": 13
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 8,
@@ -4414,21 +4414,20 @@
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 6,
"backend_operator": 1,
"framework_architecture_unsupported": 1,
"model_load": 2,
"repository_structure": 1,
"model_load": 1,
"runtime_memory": 1
},
"failureCount": 12,
"failureCount": 10,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4440,7 +4439,7 @@
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 12,
"total": 10,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|unknown|text-generation": {
@@ -6880,15 +6879,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1508,
"totalRecords": 1595,
"terminalRecords": 1510,
"totalRecords": 1597,
"totals": {
"attributableFailureCount": 400,
"decisionFailureRate": 0.8909,
"decisionSuccessRate": 0.1091,
"decisionTotal": 449,
"failureBreakdown": {
"ambiguous_runtime": 289,
"ambiguous_runtime": 291,
"backend_operator": 29,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
@@ -6900,21 +6899,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1459,
"failureCount": 1461,
"failureRate": 0.9675,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 49,
"successRate": 0.0325,
"total": 1508,
"unresolvedFailureCount": 1057
"total": 1510,
"unresolvedFailureCount": 1059
},
"warnings": [
"GPU Cambricon_mlu-370-x8 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_mrv-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 Sunrise_pt-200-x1 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 MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
@@ -6922,7 +6921,7 @@
"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 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 Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"组合 Iluvatar_mrv-100|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 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 Biren_166m|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -6943,6 +6942,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1595,
"summarizedRecords": 1597,
"version": 1
}

View File

@@ -1,3 +1,5 @@
{"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": "2026-09-10T05:49:48.500487+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:45:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471903", "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": "2026-09-10T05:49:48.500463+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:43:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471905", "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": "2026-09-10T05:27:18.447582+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:19:22+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481721", "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"], "framework": "", "lastSyncTime": "2026-09-10T05:18:58.697108+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:13:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4609099", "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": "2026-09-10T05:18:58.697138+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:13:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610360", "taskType": "text-generation", "verifyResult": -1}
@@ -296,5 +298,3 @@
{"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": ["LlavaLlamaForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-07T11:12:18.209215+00:00", "modelId": "microsoft/llava-med-7b-delta", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T11:03:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079287", "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", "failureUnsupportedArchitectures": ["Phi4FlashForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-07T11:12:18.209201+00:00", "modelId": "microsoft/Phi-4-mini-flash-reasoning", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T10:57:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079234", "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": "2026-09-07T10:52:36.106582+00:00", "modelId": "Qwen/Qwen1.5-1.8B-Chat-AWQ", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T10:51:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4591616", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-07T10:52:36.106605+00:00", "modelId": "poolside/Laguna-XS-2.1-INT4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T10:43:22+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4609106", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "repository_structure", "failureAction": "require_framework_specific_root_files", "failureCategory": "repository_structure", "failureClassificationReason": "structured_missing_files", "failureCode": "MODEL_FILE_NOT_FOUND", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model", "framework": "vllm", "lastSyncTime": "2026-09-07T10:52:36.106615+00:00", "modelId": "Aimiliya0011/lora_4090", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T10:39:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4609107", "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": "a280ffbc94b9b29bb39aefadfaefbd075d9ec6ca602ab4fcdc8fdd24f2609d04",
".modelhub_state/architecture_history_backfill.json": "e16bc27a10b0232fde9dec56113708f9502f570db2257e4e40d1a1b4a400026f",
".modelhub_state/market_intelligence.json": "d5a4df3f1aa6bcc69839fc42898bffa0099b5b6ae4d2c174a5fd3b3882743e1b",
".modelhub_state/official_capabilities.json": "d5c953b5a5f80050769bb0f397fd4364d66a657f9428779fddc1edd0e4d79c1b",
".modelhub_state/outcome_checkpoint.json": "eeb493bef7ebd3782e556474b749cd8942e0f13510b2c532f18b625b6ec315a5",
".modelhub_state/architecture_compatibility_blacklist.json": "2d2088b5192d77be30a88b862d536eb50903afdec1403dfef7ea2a509e0ea729",
".modelhub_state/architecture_history_backfill.json": "48da035bf8394965399d0157a2eb6d0c1cc6b3b0001273b48e73cee8b0e62b4b",
".modelhub_state/market_intelligence.json": "0943cba42e80b2872b132586ff0d3adc147db89228e8b92c35ca7ac545c56adb",
".modelhub_state/official_capabilities.json": "abedf9bfe289a0d25d2917415989300496ffc0bfb4dadb1362cce7e32a8c8293",
".modelhub_state/outcome_checkpoint.json": "4a24ece16cd9ab81e05a82f2f92ec5ed16e21c84623a078d2d59482f9b28b660",
".modelhub_state/queue_cleanup_latest.json": "b251e2ff52f1e826ed4fc9723e1765d93287b92341cb7f593f01eb5e88982f99",
".modelhub_state/recent_outcomes.jsonl": "d6862e7500033b6a6910fa1bb54f5074cdfb5f0b1943ca367b284e9e01bd9bd0",
".modelhub_state/recovery_active_tasks.jsonl": "9fbaf0076675f26113ef092ae168dd5ce1044d1c6abaf79ffb7370c015f7d77d",
".modelhub_state/recovery_intents.jsonl": "c5c0afc526afda392ecd3f4656561c14a97b77e313a9b3cf58dbb41ff959effb",
".modelhub_state/recent_outcomes.jsonl": "9fbb92f0c6141cac281c5ef2fb77cc3a0730dd2b93034886348e899fb7cb40b9",
".modelhub_state/recovery_active_tasks.jsonl": "b1eaa8a1d16e332946575c06a9265ec7a9fb9022276e713f273a8b8ff6eafdc8",
".modelhub_state/recovery_intents.jsonl": "859e25c702307afcad5e9fcaae78911a212514a54b16cdbf3069ca207c56a838",
".modelhub_state/routing_intelligence.json": "807c5c3342874465f1c4c1b0c444a80b9cd7f114ea6d240baeb04d73df3f3aa4",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "f3b53566b9d86bb0ce23f1215ab99ddba965d5586ee6c5815e891cb0b61d8ed9",
"outcomes/submissions.jsonl": "d39f31a2bf30b82ccf381260e7042ad0c5de73a1a02a47f5cd7075a74a69ce38"
},
"generation": 4986,
"generation": 4987,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T05:48:47.814735+00:00",
"updatedAt": "2026-09-10T05:51:30.975609+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}