state: generation 8687 (cycle)

This commit is contained in:
2026-09-17 10:46:46 +00:00
parent 2779677273
commit 4585311c41
10 changed files with 2291 additions and 2105 deletions

View File

@@ -1741,7 +1741,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-17T10:43:58.779863+00:00",
"generatedAt": "2026-09-17T10:46:45.724419+00:00",
"summary": {
"activeBlockCount": 84,
"byGpuFramework": {

View File

@@ -51,7 +51,7 @@
"4": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 635,
"listingErrors": 636,
"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": 4,
"nextAccountIndex": 5,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-17T10:43:58.751875+00:00",
"updatedAt": "2026-09-17T10:46:45.692317+00:00",
"version": 1
}

View File

@@ -416,121 +416,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-17T10:41:36.514984+00:00",
"generatedAt": "2026-09-17T10:45:07.677772+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 1042.9051094890513,
"backlogHours": 999.1048951048951,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.9749799054863395,
"queueFactor": 0.9837149535821921,
"queueWeight": 0.9837149535821921,
"recentSuccess": 48,
"recentSuccessRate": 0.35036496350364965,
"recentTerminal": 137,
"recentWilsonLowerBound": 0.27554813520811977,
"running": 10,
"selectionWeight": 0.9591023124690645,
"qualityFactor": 0.8412094784443451,
"queueFactor": 0.9873573263302654,
"queueWeight": 0.9873573263302654,
"recentSuccess": 49,
"recentSuccessRate": 0.34265734265734266,
"recentTerminal": 143,
"recentWilsonLowerBound": 0.2698994070063999,
"running": 8,
"selectionWeight": 0.8305743415204856,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.833333333333332,
"waiting": 23813
"throughputPerHour": 23.833333333333332,
"waiting": 23812
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1374.9268292682927,
"backlogHours": 1331.4330708661416,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.9402229533901075,
"queueFactor": 0.9437654068698834,
"queueWeight": 0.9437654068698834,
"recentSuccess": 43,
"recentSuccessRate": 0.34959349593495936,
"recentTerminal": 123,
"recentWilsonLowerBound": 0.27103891552996556,
"running": 9,
"selectionWeight": 0.8873498981546183,
"qualityFactor": 0.8874015322125974,
"queueFactor": 0.9457320672755255,
"queueWeight": 0.9457320672755255,
"recentSuccess": 45,
"recentSuccessRate": 0.3543307086614173,
"recentTerminal": 127,
"recentWilsonLowerBound": 0.2765379030036808,
"running": 10,
"selectionWeight": 0.8392440855628887,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 20.5,
"waiting": 28186
"throughputPerHour": 21.166666666666668,
"waiting": 28182
},
"Biren_166m": {
"available": true,
"backlogHours": 177.11475409836066,
"backlogHours": 183.01694915254237,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 5,
"qualityFactor": 0.1362869153502709,
"queueFactor": 1.2834169816811227,
"queueWeight": 1.2834169816811227,
"qualityFactor": 0.1326524991175358,
"queueFactor": 1.273627182144871,
"queueWeight": 1.273627182144871,
"recentSuccess": 29,
"recentSuccessRate": 0.15846994535519127,
"recentTerminal": 183,
"recentWilsonLowerBound": 0.11265994124570111,
"running": 7,
"selectionWeight": 0.17491294154147535,
"recentSuccessRate": 0.1638418079096045,
"recentTerminal": 177,
"recentWilsonLowerBound": 0.1165656778351223,
"running": 5,
"selectionWeight": 0.16894982865554212,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 30.5,
"waiting": 5402
"throughputPerHour": 29.5,
"waiting": 5399
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1410.923076923077,
"backlogHours": 1368.8955223880598,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.15883202472959726,
"queueFactor": 0.9401139389642292,
"queueWeight": 0.9401139389642292,
"recentSuccess": 13,
"recentSuccessRate": 0.2,
"recentTerminal": 65,
"recentWilsonLowerBound": 0.12077845770945214,
"qualityFactor": 0.16509960640478472,
"queueFactor": 0.9418038698663195,
"queueWeight": 0.9418038698663195,
"recentSuccess": 14,
"recentSuccessRate": 0.208955223880597,
"recentTerminal": 67,
"recentWilsonLowerBound": 0.12875568729828918,
"running": 7,
"selectionWeight": 0.14932020040220553,
"selectionWeight": 0.15549144822543243,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 10.833333333333334,
"waiting": 15285
"throughputPerHour": 11.166666666666666,
"waiting": 15286
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 594.8125,
"backlogHours": 553.8640776699028,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.3167028613461248,
"queueFactor": 1.0701606540487856,
"queueWeight": 1.0701606540487856,
"recentSuccess": 23,
"recentSuccessRate": 0.23958333333333334,
"recentTerminal": 96,
"recentWilsonLowerBound": 0.16528105536529172,
"running": 8,
"selectionWeight": 0.3389229412372908,
"qualityFactor": 0.30484976831502625,
"queueFactor": 1.0787120651701154,
"queueWeight": 1.0787120651701154,
"recentSuccess": 25,
"recentSuccessRate": 0.24271844660194175,
"recentTerminal": 103,
"recentWilsonLowerBound": 0.17014922730424603,
"running": 7,
"selectionWeight": 0.32884512314573316,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 16.0,
"waiting": 9517
"throughputPerHour": 17.166666666666668,
"waiting": 9508
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 25.82964224872232,
"backlogHours": 25.8839590443686,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -539,60 +539,60 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 17,
"recentSuccessRate": 0.028960817717206135,
"recentTerminal": 587,
"recentWilsonLowerBound": 0.018158870575656006,
"running": 26,
"recentSuccess": 19,
"recentSuccessRate": 0.032423208191126277,
"recentTerminal": 586,
"recentWilsonLowerBound": 0.020853538257202004,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 97.83333333333333,
"waiting": 2527
"throughputPerHour": 97.66666666666667,
"waiting": 2528
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 79.62461538461538,
"backlogHours": 77.51497005988024,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.07597597618633255,
"qualityFactor": 0.060277957241126945,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 38,
"recentSuccessRate": 0.11692307692307692,
"recentTerminal": 325,
"recentWilsonLowerBound": 0.08638054537443333,
"running": 4,
"selectionWeight": 0.09876876904223232,
"recentSuccess": 37,
"recentSuccessRate": 0.11077844311377245,
"recentTerminal": 334,
"recentWilsonLowerBound": 0.08144473358243734,
"running": 2,
"selectionWeight": 0.07836134441346503,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 54.166666666666664,
"waiting": 4313
"throughputPerHour": 55.666666666666664,
"waiting": 4315
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2592.324324324324,
"backlogHours": 2459.076923076923,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.8833732791737288,
"queueFactor": 0.858129026240539,
"queueWeight": 0.858129026240539,
"recentSuccess": 15,
"recentSuccessRate": 0.40540540540540543,
"recentTerminal": 37,
"recentWilsonLowerBound": 0.2634629583994014,
"qualityFactor": 0.8473343942499606,
"queueFactor": 0.8625816180570133,
"queueWeight": 0.8625816180570133,
"recentSuccess": 16,
"recentSuccessRate": 0.41025641025641024,
"recentTerminal": 39,
"recentWilsonLowerBound": 0.2707908943540048,
"running": 2,
"selectionWeight": 0.7580482518642637,
"selectionWeight": 0.7308950728274902,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 6.166666666666667,
"waiting": 15986
"throughputPerHour": 6.5,
"waiting": 15984
},
"Kunlunxin_p-800": {
"available": true,
@@ -602,15 +602,15 @@
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.3645021033025656,
"queueFactor": 1.0904782428615243,
"queueWeight": 1.0904782428615243,
"qualityFactor": 0.32915369310243114,
"queueFactor": 1.0874943982812042,
"queueWeight": 1.0874943982812042,
"recentSuccess": 31,
"recentSuccessRate": 0.2421875,
"recentTerminal": 128,
"recentWilsonLowerBound": 0.17618632286113767,
"running": 9,
"selectionWeight": 0.39748161312871155,
"running": 8,
"selectionWeight": 0.3579527974224645,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 21.333333333333332,
@@ -618,24 +618,24 @@
},
"MetaX_c-500": {
"available": true,
"backlogHours": 826.6428571428571,
"backlogHours": 836.6024096385541,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.4299833768786161,
"queueFactor": 1.018610866427511,
"queueWeight": 1.018610866427511,
"recentSuccess": 23,
"recentSuccessRate": 0.27380952380952384,
"recentTerminal": 84,
"recentWilsonLowerBound": 0.18992693848374492,
"qualityFactor": 0.44793132605517705,
"queueFactor": 1.0140004538813934,
"queueWeight": 1.0140004538813934,
"recentSuccess": 24,
"recentSuccessRate": 0.2891566265060241,
"recentTerminal": 83,
"recentWilsonLowerBound": 0.20267311749093844,
"running": 4,
"selectionWeight": 0.43798574007175417,
"selectionWeight": 0.4542025679276439,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 14.0,
"throughputPerHour": 13.833333333333334,
"waiting": 11573
},
"Mthreads_s4000": {
@@ -647,14 +647,14 @@
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 2.5,
"queueFactor": 0.8364853909390233,
"queueWeight": 0.8364853909390233,
"recentSuccess": 27,
"recentSuccessRate": 0.5625,
"queueFactor": 0.83419653977064,
"queueWeight": 0.83419653977064,
"recentSuccess": 28,
"recentSuccessRate": 0.5833333333333334,
"recentTerminal": 48,
"recentWilsonLowerBound": 0.4227477150100165,
"recentWilsonLowerBound": 0.4428108221536465,
"running": 4,
"selectionWeight": 2.091213477347558,
"selectionWeight": 2.0854913494266,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 8.0,
@@ -668,15 +668,15 @@
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.1855919544640272,
"queueFactor": 0.7526698135905469,
"queueWeight": 0.7526698135905469,
"recentSuccess": 8,
"recentSuccessRate": 0.5333333333333333,
"qualityFactor": 1.5608894212235742,
"queueFactor": 0.7506103046010238,
"queueWeight": 0.7506103046010238,
"recentSuccess": 9,
"recentSuccessRate": 0.6,
"recentTerminal": 15,
"recentWilsonLowerBound": 0.3011663015105079,
"recentWilsonLowerBound": 0.357464427565077,
"running": 2,
"selectionWeight": 0.8923592753608914,
"selectionWeight": 1.1716196839131428,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 2.5,
@@ -684,52 +684,52 @@
},
"Vastai_va16": {
"available": true,
"backlogHours": 1962.9767441860465,
"backlogHours": 2009.857142857143,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.09898088930742914,
"queueFactor": 0.8946820399799635,
"queueWeight": 0.8946820399799635,
"qualityFactor": 0.09430353844430844,
"queueFactor": 0.8890808123019953,
"queueWeight": 0.8890808123019953,
"recentSuccess": 8,
"recentSuccessRate": 0.18604651162790697,
"recentTerminal": 43,
"recentWilsonLowerBound": 0.09741635580105981,
"recentSuccessRate": 0.19047619047619047,
"recentTerminal": 42,
"recentWilsonLowerBound": 0.09981889609856437,
"running": 16,
"selectionWeight": 0.08855642396460166,
"selectionWeight": 0.08384346656301819,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 7.166666666666667,
"waiting": 14068
"throughputPerHour": 7.0,
"waiting": 14069
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 788.0571428571428,
"backlogHours": 773.158878504673,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 0.48027401990534074,
"queueFactor": 1.0259408819095848,
"queueWeight": 1.0259408819095848,
"recentSuccess": 29,
"recentSuccessRate": 0.2761904761904762,
"recentTerminal": 105,
"recentWilsonLowerBound": 0.19972009427826307,
"running": 6,
"selectionWeight": 0.4927327515399468,
"qualityFactor": 0.37832142734717467,
"queueFactor": 1.0260669615783442,
"queueWeight": 1.0260669615783442,
"recentSuccess": 28,
"recentSuccessRate": 0.2616822429906542,
"recentTerminal": 107,
"recentWilsonLowerBound": 0.1876959981258367,
"running": 7,
"selectionWeight": 0.3881831174580978,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.5,
"waiting": 13791
"throughputPerHour": 17.833333333333332,
"waiting": 13788
}
},
"queueAttemptedAt": "2026-09-17T10:33:01.367389+00:00",
"queueAttemptedAt": "2026-09-17T10:45:07.677772+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-17T10:33:01.367389+00:00",
"queueUpdatedAt": "2026-09-17T10:45:07.677772+00:00",
"supportedGpus": [
"Vastai_va16",
"Kunlunxin_p-800",

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-17T10:35:53.658808+00:00",
"lastSyncTime": "2026-09-17T10:35:53.413598+00:00",
"generatedAt": "2026-09-17T10:44:59.894261+00:00",
"lastSyncTime": "2026-09-17T10:44:59.509496+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2002,25 +2002,25 @@
"decisionSuccessRate": 0.1176,
"decisionTotal": 34,
"failureBreakdown": {
"ambiguous_runtime": 38,
"ambiguous_runtime": 39,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 1,
"验证失败": 39
},
"failureCount": 108,
"failureRate": 0.9643,
"failureCount": 109,
"failureRate": 0.9646,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 4,
"successRate": 0.0357,
"successRate": 0.0354,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 112,
"unresolvedFailureCount": 78
"total": 113,
"unresolvedFailureCount": 79
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
"attributableFailureCount": 1,
@@ -2028,10 +2028,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 4,
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 1
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm-mlu",
"pendingCount": 0,
@@ -2041,8 +2041,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 4
"total": 6,
"unresolvedFailureCount": 5
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 8,
@@ -2076,23 +2076,23 @@
"decisionSuccessRate": 0.1,
"decisionTotal": 10,
"failureBreakdown": {
"ambiguous_runtime": 27,
"ambiguous_runtime": 28,
"framework_architecture_unsupported": 8,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 39,
"failureRate": 0.975,
"failureCount": 40,
"failureRate": 0.9756,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.025,
"successRate": 0.0244,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 40,
"unresolvedFailureCount": 30
"total": 41,
"unresolvedFailureCount": 31
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -2721,17 +2721,17 @@
"unresolvedFailureCount": 29
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 7,
"attributableFailureCount": 9,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 3,
"framework_architecture_unsupported": 6,
"framework_architecture_unsupported": 8,
"runtime_memory": 1,
"参数/模板问题": 8
},
"failureCount": 18,
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"pendingCount": 0,
@@ -2741,7 +2741,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 18,
"total": 20,
"unresolvedFailureCount": 11
},
"hygon_k100-ai|vllm|text-generation": {
@@ -2815,7 +2815,7 @@
"decisionSuccessRate": 0.2677,
"decisionTotal": 254,
"failureBreakdown": {
"ambiguous_runtime": 160,
"ambiguous_runtime": 161,
"backend_operator": 4,
"framework_architecture_unsupported": 124,
"memory_capacity": 5,
@@ -2826,15 +2826,15 @@
"参数/模板问题": 73,
"验证失败": 673
},
"failureCount": 1093,
"failureRate": 0.9414,
"failureCount": 1094,
"failureRate": 0.9415,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 68,
"successRate": 0.0586,
"total": 1161,
"unresolvedFailureCount": 906
"successRate": 0.0585,
"total": 1162,
"unresolvedFailureCount": 907
},
"vllm": {
"attributableFailureCount": 394,
@@ -2869,40 +2869,40 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 11,
"failureBreakdown": {
"ambiguous_runtime": 31,
"ambiguous_runtime": 33,
"framework_architecture_unsupported": 9,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 44,
"failureRate": 0.9778,
"failureCount": 46,
"failureRate": 0.9787,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0222,
"total": 45,
"unresolvedFailureCount": 34
"successRate": 0.0213,
"total": 47,
"unresolvedFailureCount": 36
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 7,
"attributableFailureCount": 9,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 3,
"framework_architecture_unsupported": 6,
"framework_architecture_unsupported": 8,
"runtime_memory": 1,
"参数/模板问题": 8
},
"failureCount": 18,
"failureCount": 20,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 18,
"total": 20,
"unresolvedFailureCount": 11
},
"vllm_0_17_0_corex_4_4_0": {
@@ -2972,7 +2972,7 @@
"unresolvedFailureCount": 8
}
},
"generatedAt": "2026-09-17T10:35:53.653577+00:00",
"generatedAt": "2026-09-17T10:44:59.888269+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 56,
@@ -3054,22 +3054,22 @@
"decisionSuccessRate": 0.1143,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 42,
"ambiguous_runtime": 44,
"framework_architecture_unsupported": 28,
"memory_capacity": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 1,
"验证失败": 39
},
"failureCount": 113,
"failureRate": 0.9658,
"failureCount": 115,
"failureRate": 0.9664,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 4,
"successRate": 0.0342,
"total": 117,
"unresolvedFailureCount": 82
"successRate": 0.0336,
"total": 119,
"unresolvedFailureCount": 84
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 20,
@@ -3077,22 +3077,22 @@
"decisionSuccessRate": 0.1304,
"decisionTotal": 23,
"failureBreakdown": {
"ambiguous_runtime": 47,
"ambiguous_runtime": 48,
"framework_architecture_unsupported": 17,
"memory_capacity": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 18,
"验证失败": 22
},
"failureCount": 107,
"failureRate": 0.9727,
"failureCount": 108,
"failureRate": 0.973,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.0273,
"total": 110,
"unresolvedFailureCount": 87
"successRate": 0.027,
"total": 111,
"unresolvedFailureCount": 88
},
"Iluvatar_bi-100": {
"attributableFailureCount": 0,
@@ -3285,13 +3285,13 @@
"unresolvedFailureCount": 216
},
"hygon_k100-ai": {
"attributableFailureCount": 63,
"attributableFailureCount": 65,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 63,
"decisionTotal": 65,
"failureBreakdown": {
"ambiguous_runtime": 29,
"framework_architecture_unsupported": 50,
"framework_architecture_unsupported": 52,
"memory_capacity": 1,
"model_load": 5,
"repository_structure": 4,
@@ -3299,14 +3299,14 @@
"参数/模板问题": 10,
"验证失败": 27
},
"failureCount": 129,
"failureCount": 131,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 129,
"total": 131,
"unresolvedFailureCount": 66
}
},
@@ -4080,6 +4080,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|fp8": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|deepseek_v4_dspark|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -4446,6 +4469,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|fp8": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -6739,6 +6785,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5|none": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
@@ -6785,6 +6854,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|spark2_5|fp8": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|zaya|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -6975,25 +7067,25 @@
"decisionSuccessRate": 0.1667,
"decisionTotal": 12,
"failureBreakdown": {
"ambiguous_runtime": 5,
"ambiguous_runtime": 6,
"framework_architecture_unsupported": 9,
"tokenizer_compatibility": 1,
"参数/模板问题": 1
},
"failureCount": 16,
"failureRate": 0.8889,
"failureCount": 17,
"failureRate": 0.8947,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-16T19:09:33.045349+00:00",
"lastTerminalAt": "2026-09-17T10:44:59.509445+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.1111,
"successRate": 0.1053,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 18,
"unresolvedFailureCount": 6
"total": 19,
"unresolvedFailureCount": 7
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 1,
@@ -8529,6 +8621,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|deepseek_v4_dspark|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -9031,6 +9147,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -12522,6 +12662,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe|compressed-tensors|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -12594,6 +12758,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|zaya|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -12619,17 +12807,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2119,
"totalRecords": 2222,
"terminalRecords": 2124,
"totalRecords": 2227,
"totals": {
"attributableFailureCount": 693,
"decisionFailureRate": 0.8839,
"decisionSuccessRate": 0.1161,
"decisionTotal": 784,
"attributableFailureCount": 695,
"decisionFailureRate": 0.8842,
"decisionSuccessRate": 0.1158,
"decisionTotal": 786,
"failureBreakdown": {
"ambiguous_runtime": 519,
"ambiguous_runtime": 522,
"backend_operator": 48,
"framework_architecture_unsupported": 462,
"framework_architecture_unsupported": 464,
"memory_capacity": 12,
"model_load": 85,
"platform_infrastructure": 10,
@@ -12639,28 +12827,28 @@
"参数/模板问题": 133,
"验证失败": 673
},
"failureCount": 2028,
"failureRate": 0.9571,
"failureCount": 2033,
"failureRate": 0.9572,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 91,
"successRate": 0.0429,
"total": 2119,
"unresolvedFailureCount": 1325
"successRate": 0.0428,
"total": 2124,
"unresolvedFailureCount": 1328
},
"warnings": [
"GPU Mthreads_s4000 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 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 Cambricon_mlu-370-x8 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 hygon_k100-ai 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 Cambricon_mlu-370-x4 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 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。",
"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。",
"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。",
@@ -12687,6 +12875,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2222,
"summarizedRecords": 2227,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"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": "2026-09-17T10:44:59.509445+00:00", "modelId": "RedHatAI/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T10:41:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497070", "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": "2026-09-17T10:35:53.413598+00:00", "modelId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T10:29:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610367", "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": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-17T10:10:02.608119+00:00", "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T10:05:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4490374", "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": "2026-09-17T04:34:21.545391+00:00", "modelId": "BAAI/Law_Justice-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T04:33:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471925", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"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": "2026-09-11T11:19:08.306628+00:00", "modelId": "nm-testing/SmolLM-135M-Instruct-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T11:09:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457980", "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": "2026-09-11T11:08:14.809954+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T11:05:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457994", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-11T07:43:04.407471+00:00", "modelId": "deepreinforce-ai/Ornith-1.0-35B-FP8", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-11T07:38:33+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079996", "taskType": "text-generation", "verifyResult": null}
{"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": "2026-09-11T07:33:47.206168+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T07:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523220", "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