state: generation 6509 (cycle)

This commit is contained in:
2026-09-13 04:07:57 +00:00
parent 0287eccfb0
commit b0cc2295ab
9 changed files with 2269 additions and 2269 deletions

View File

@@ -1454,7 +1454,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-13T04:04:56.059194+00:00",
"generatedAt": "2026-09-13T04:07:56.315465+00:00",
"summary": {
"activeBlockCount": 73,
"byGpuFramework": {

View File

@@ -59,7 +59,7 @@
"5": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 471,
"listingErrors": 472,
"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": "2026-09-13T04:04:56.035285+00:00",
"updatedAt": "2026-09-13T04:07:56.289713+00:00",
"version": 1
}

View File

@@ -416,95 +416,95 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-13T04:02:57.966904+00:00",
"generatedAt": "2026-09-13T04:06:03.452938+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 856.2331288343557,
"backlogHours": 900.2709677419356,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.8612486497840655,
"queueFactor": 1.004025059417546,
"queueWeight": 1.004025059417546,
"recentSuccess": 49,
"recentSuccessRate": 0.3006134969325153,
"recentTerminal": 163,
"recentWilsonLowerBound": 0.23547598767139238,
"qualityFactor": 1.7141488394414282,
"queueFactor": 0.9962506256406534,
"queueWeight": 0.9962506256406534,
"recentSuccess": 47,
"recentSuccessRate": 0.3032258064516129,
"recentTerminal": 155,
"recentWilsonLowerBound": 0.23634352265430877,
"running": 8,
"selectionWeight": 1.8687402861902735,
"selectionWeight": 1.7077218537347227,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 27.166666666666668,
"waiting": 23261
"throughputPerHour": 25.833333333333332,
"waiting": 23257
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1050.8076923076924,
"backlogHours": 1057.3935483870969,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.8489682320296952,
"queueFactor": 0.9736544880639852,
"queueWeight": 0.9736544880639852,
"recentSuccess": 47,
"recentSuccessRate": 0.30128205128205127,
"recentTerminal": 156,
"recentWilsonLowerBound": 0.2347685044598138,
"qualityFactor": 1.9078648664585238,
"queueFactor": 0.9724988478222192,
"queueWeight": 0.9724988478222192,
"recentSuccess": 49,
"recentSuccessRate": 0.3161290322580645,
"recentTerminal": 155,
"recentWilsonLowerBound": 0.2481302142025571,
"running": 8,
"selectionWeight": 1.8002562174034447,
"selectionWeight": 1.8553963844314065,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 26.0,
"waiting": 27321
"throughputPerHour": 25.833333333333332,
"waiting": 27316
},
"Biren_166m": {
"available": true,
"backlogHours": 156.94736842105263,
"backlogHours": 160.67065868263472,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.3209872682466219,
"queueFactor": 1.2950014385343565,
"queueWeight": 1.2950014385343565,
"qualityFactor": 0.30926407319138444,
"queueFactor": 1.2901318821368757,
"queueWeight": 1.2901318821368757,
"recentSuccess": 26,
"recentSuccessRate": 0.15204678362573099,
"recentTerminal": 171,
"recentWilsonLowerBound": 0.10592160216555797,
"recentSuccessRate": 0.15568862275449102,
"recentTerminal": 167,
"recentWilsonLowerBound": 0.10851495315803455,
"running": 8,
"selectionWeight": 0.4156789741305887,
"selectionWeight": 0.3989914408237173,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 28.5,
"waiting": 4473
"throughputPerHour": 27.833333333333332,
"waiting": 4472
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1399.4516129032256,
"backlogHours": 1355.25,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 1.8256037088468484,
"queueFactor": 0.9326950535241181,
"queueWeight": 0.9326950535241181,
"qualityFactor": 1.5489541522176953,
"queueFactor": 0.9369613609146064,
"queueWeight": 0.9369613609146064,
"recentSuccess": 21,
"recentSuccessRate": 0.3387096774193548,
"recentTerminal": 62,
"recentWilsonLowerBound": 0.2334153463018197,
"recentSuccessRate": 0.328125,
"recentTerminal": 64,
"recentWilsonLowerBound": 0.2257039576708776,
"running": 7,
"selectionWeight": 1.7027315489367398,
"selectionWeight": 1.451310190456222,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 10.333333333333334,
"waiting": 14461
"throughputPerHour": 10.666666666666666,
"waiting": 14456
},
"Cambricon_mlu-370-x8": {
"available": true,
@@ -514,15 +514,15 @@
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.47411832422364353,
"queueFactor": 1.1070539675396862,
"queueWeight": 1.1070539675396862,
"recentSuccess": 22,
"recentSuccessRate": 0.1864406779661017,
"qualityFactor": 0.38199108655456027,
"queueFactor": 1.1067767568577,
"queueWeight": 1.1067767568577,
"recentSuccess": 21,
"recentSuccessRate": 0.17796610169491525,
"recentTerminal": 118,
"recentWilsonLowerBound": 0.12646899188610022,
"recentWilsonLowerBound": 0.119448913662713,
"running": 7,
"selectionWeight": 0.5248745719150519,
"selectionWeight": 0.4227788559254052,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 19.666666666666668,
@@ -530,7 +530,7 @@
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 43.895705521472394,
"backlogHours": 42.642857142857146,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -539,197 +539,197 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 21,
"recentSuccessRate": 0.06441717791411043,
"recentTerminal": 326,
"recentWilsonLowerBound": 0.042515119383828834,
"recentSuccess": 22,
"recentSuccessRate": 0.06547619047619048,
"recentTerminal": 336,
"recentWilsonLowerBound": 0.04363339834746094,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 54.333333333333336,
"waiting": 2385
"throughputPerHour": 56.0,
"waiting": 2388
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 192.04838709677418,
"backlogHours": 193.65853658536585,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.7331327903140651,
"queueFactor": 1.2563821482768132,
"queueWeight": 1.2563821482768132,
"recentSuccess": 27,
"recentSuccessRate": 0.21774193548387097,
"recentTerminal": 124,
"recentWilsonLowerBound": 0.15417986080833496,
"running": 1,
"selectionWeight": 0.9210949500669595,
"qualityFactor": 0.7513747167771614,
"queueFactor": 1.2544954689482741,
"queueWeight": 1.2544954689482741,
"recentSuccess": 28,
"recentSuccessRate": 0.22764227642276422,
"recentTerminal": 123,
"recentWilsonLowerBound": 0.16245354051668648,
"running": 0,
"selectionWeight": 0.9425961776792418,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 20.666666666666668,
"waiting": 3969
"throughputPerHour": 20.5,
"waiting": 3970
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 1824.7058823529412,
"backlogHours": 1899.795918367347,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.5978548291058705,
"queueFactor": 0.8963021243497097,
"queueWeight": 0.8963021243497097,
"qualityFactor": 1.602876254853671,
"queueFactor": 0.8906735416630829,
"queueWeight": 0.8906735416630829,
"recentSuccess": 17,
"recentSuccessRate": 0.3333333333333333,
"recentTerminal": 51,
"recentWilsonLowerBound": 0.21969755762722826,
"recentSuccessRate": 0.3469387755102041,
"recentTerminal": 49,
"recentWilsonLowerBound": 0.22924209609314436,
"running": 2,
"selectionWeight": 1.432160677730034,
"selectionWeight": 1.4276394707581774,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 8.5,
"waiting": 15510
"throughputPerHour": 8.166666666666666,
"waiting": 15515
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 902.7123287671234,
"backlogHours": 855.7402597402597,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.9496045427819622,
"queueFactor": 0.9960954366400551,
"queueWeight": 0.9960954366400551,
"recentSuccess": 19,
"recentSuccessRate": 0.2602739726027397,
"recentTerminal": 73,
"recentWilsonLowerBound": 0.17342050231153916,
"qualityFactor": 0.8837694043045385,
"queueFactor": 1.0038603458419952,
"queueWeight": 1.0038603458419952,
"recentSuccess": 20,
"recentSuccessRate": 0.2597402597402597,
"recentTerminal": 77,
"recentWilsonLowerBound": 0.17489066479540774,
"running": 7,
"selectionWeight": 0.9458967516777784,
"selectionWeight": 0.8871810598497282,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.166666666666666,
"waiting": 10983
"throughputPerHour": 12.833333333333334,
"waiting": 10982
},
"MetaX_c-500": {
"available": true,
"backlogHours": 808.2857142857143,
"backlogHours": 762.943820224719,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 1.1598778768674274,
"queueFactor": 1.0127415333343621,
"queueWeight": 1.0127415333343621,
"recentSuccess": 23,
"recentSuccessRate": 0.27380952380952384,
"recentTerminal": 84,
"recentWilsonLowerBound": 0.18992693848374492,
"qualityFactor": 1.1624312135409245,
"queueFactor": 1.0212938341633326,
"queueWeight": 1.0212938341633326,
"recentSuccess": 25,
"recentSuccessRate": 0.2808988764044944,
"recentTerminal": 89,
"recentWilsonLowerBound": 0.19809358040575942,
"running": 4,
"selectionWeight": 1.174656499499323,
"selectionWeight": 1.1871838310283465,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 14.0,
"waiting": 11316
"throughputPerHour": 14.833333333333334,
"waiting": 11317
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1635.493670886076,
"backlogHours": 1700.1315789473686,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 2.5,
"queueFactor": 0.9111419162142277,
"queueWeight": 0.9111419162142277,
"queueFactor": 0.9056329469415949,
"queueWeight": 0.9056329469415949,
"recentSuccess": 29,
"recentSuccessRate": 0.3670886075949367,
"recentTerminal": 79,
"recentWilsonLowerBound": 0.26927131273817784,
"recentSuccessRate": 0.3815789473684211,
"recentTerminal": 76,
"recentWilsonLowerBound": 0.2805690950914341,
"running": 4,
"selectionWeight": 2.277854790535569,
"selectionWeight": 2.2640823673539874,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 13.166666666666666,
"waiting": 21534
"throughputPerHour": 12.666666666666666,
"waiting": 21535
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 4334.7,
"backlogHours": 3942.0,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.045718344664993,
"queueFactor": 0.787208001342911,
"queueWeight": 0.787208001342911,
"recentSuccess": 7,
"recentSuccessRate": 0.35,
"recentTerminal": 20,
"recentWilsonLowerBound": 0.1811895478679446,
"qualityFactor": 1.152592836663562,
"queueFactor": 0.7983017860250737,
"queueWeight": 0.7983017860250737,
"recentSuccess": 8,
"recentSuccessRate": 0.36363636363636365,
"recentTerminal": 22,
"recentWilsonLowerBound": 0.19732972772607896,
"running": 2,
"selectionWeight": 0.8231978480713464,
"selectionWeight": 0.9201169200682277,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 3.3333333333333335,
"waiting": 14449
"throughputPerHour": 3.6666666666666665,
"waiting": 14454
},
"Vastai_va16": {
"available": true,
"backlogHours": 929.0571428571429,
"backlogHours": 935.1549295774647,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 1.2045925542576605,
"queueFactor": 0.9918065967712594,
"queueWeight": 0.9918065967712594,
"recentSuccess": 20,
"recentSuccessRate": 0.2857142857142857,
"recentTerminal": 70,
"recentWilsonLowerBound": 0.19322076591803128,
"qualityFactor": 1.2177907226409659,
"queueFactor": 0.9905857102927813,
"queueWeight": 0.9905857102927813,
"recentSuccess": 21,
"recentSuccessRate": 0.29577464788732394,
"recentTerminal": 71,
"recentWilsonLowerBound": 0.20232738733765723,
"running": 16,
"selectionWeight": 1.194722841734289,
"selectionWeight": 1.2063260879752606,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 11.666666666666666,
"waiting": 10839
"throughputPerHour": 11.833333333333334,
"waiting": 11066
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 530.3888888888889,
"backlogHours": 546.3333333333334,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 2.312148478763663,
"queueFactor": 1.078808088455489,
"queueWeight": 1.078808088455489,
"recentSuccess": 37,
"recentSuccessRate": 0.3425925925925926,
"qualityFactor": 2.265569218900968,
"queueFactor": 1.0737568293744097,
"queueWeight": 1.0737568293744097,
"recentSuccess": 38,
"recentSuccessRate": 0.35185185185185186,
"recentTerminal": 108,
"recentWilsonLowerBound": 0.25987826353874716,
"recentWilsonLowerBound": 0.26828862070909015,
"running": 6,
"selectionWeight": 2.494364480600294,
"selectionWeight": 2.4326704212153616,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.0,
"waiting": 9547
"waiting": 9834
}
},
"queueAttemptedAt": "2026-09-13T03:54:08.285745+00:00",
"queueAttemptedAt": "2026-09-13T04:06:03.452938+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-13T03:54:08.285745+00:00",
"queueUpdatedAt": "2026-09-13T04:06:03.452938+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": "2026-09-13T03:22:02.802525+00:00",
"lastSyncTime": "2026-09-13T03:22:02.529658+00:00",
"generatedAt": "2026-09-13T04:05:57.160347+00:00",
"lastSyncTime": "2026-09-13T04:05:56.910845+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1990,11 +1990,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 35,
"ambiguous_runtime": 36,
"memory_capacity": 1,
"验证失败": 22
},
"failureCount": 58,
"failureCount": 59,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
@@ -2004,8 +2004,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 58,
"unresolvedFailureCount": 57
"total": 59,
"unresolvedFailureCount": 58
},
"Kunlunxin_p-800|unknown|visual-multi-modal": {
"attributableFailureCount": 0,
@@ -2214,18 +2214,18 @@
"unresolvedFailureCount": 34
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 44,
"attributableFailureCount": 45,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 44,
"decisionTotal": 45,
"failureBreakdown": {
"backend_operator": 1,
"framework_architecture_unsupported": 4,
"platform_infrastructure": 2,
"tokenizer_compatibility": 39,
"tokenizer_compatibility": 40,
"参数/模板问题": 6
},
"failureCount": 52,
"failureCount": 53,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2235,7 +2235,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 52,
"total": 53,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -2468,7 +2468,7 @@
"decisionSuccessRate": 0.2647,
"decisionTotal": 204,
"failureBreakdown": {
"ambiguous_runtime": 139,
"ambiguous_runtime": 140,
"backend_operator": 4,
"framework_architecture_unsupported": 95,
"memory_capacity": 5,
@@ -2478,15 +2478,15 @@
"参数/模板问题": 61,
"验证失败": 673
},
"failureCount": 1024,
"failureRate": 0.9499,
"failureCount": 1025,
"failureRate": 0.95,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 54,
"successRate": 0.0501,
"total": 1078,
"unresolvedFailureCount": 873
"successRate": 0.05,
"total": 1079,
"unresolvedFailureCount": 874
},
"vllm": {
"attributableFailureCount": 292,
@@ -2575,27 +2575,27 @@
"unresolvedFailureCount": 4
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 47,
"attributableFailureCount": 48,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 47,
"decisionTotal": 48,
"failureBreakdown": {
"ambiguous_runtime": 37,
"backend_operator": 1,
"framework_architecture_unsupported": 6,
"model_load": 1,
"platform_infrastructure": 2,
"tokenizer_compatibility": 39,
"tokenizer_compatibility": 40,
"参数/模板问题": 7
},
"failureCount": 93,
"failureCount": 94,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"total": 93,
"total": 94,
"unresolvedFailureCount": 44
},
"vllm_tokenizer_patch": {
@@ -2617,7 +2617,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-13T03:22:02.797818+00:00",
"generatedAt": "2026-09-13T04:05:57.155917+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 31,
@@ -2810,20 +2810,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 70,
"ambiguous_runtime": 71,
"memory_capacity": 1,
"参数/模板问题": 1,
"验证失败": 23
},
"failureCount": 95,
"failureCount": 96,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 95,
"unresolvedFailureCount": 94
"total": 96,
"unresolvedFailureCount": 95
},
"MetaX_c-500": {
"attributableFailureCount": 53,
@@ -2877,27 +2877,27 @@
"unresolvedFailureCount": 77
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 48,
"decisionFailureRate": 0.9796,
"decisionSuccessRate": 0.0204,
"decisionTotal": 49,
"attributableFailureCount": 49,
"decisionFailureRate": 0.98,
"decisionSuccessRate": 0.02,
"decisionTotal": 50,
"failureBreakdown": {
"ambiguous_runtime": 1,
"backend_operator": 1,
"framework_architecture_unsupported": 5,
"platform_infrastructure": 3,
"tokenizer_compatibility": 42,
"tokenizer_compatibility": 43,
"参数/模板问题": 10,
"验证失败": 32
},
"failureCount": 94,
"failureRate": 0.9895,
"failureCount": 95,
"failureRate": 0.9896,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 1,
"successRate": 0.0105,
"total": 95,
"successRate": 0.0104,
"total": 96,
"unresolvedFailureCount": 43
},
"Vastai_va16": {
@@ -4708,13 +4708,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 6
"ambiguous_runtime": 7
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T23:00:13.841305+00:00",
"lastTerminalAt": "2026-09-13T04:05:56.910845+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4722,8 +4722,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 6
"total": 7,
"unresolvedFailureCount": 7
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 0,
@@ -4881,22 +4881,22 @@
"unresolvedFailureCount": 1
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 14,
"consecutiveFailures": 14,
"attributableFailureCount": 15,
"consecutiveFailures": 15,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 14,
"decisionTotal": 15,
"failureBreakdown": {
"framework_architecture_unsupported": 2,
"platform_infrastructure": 1,
"tokenizer_compatibility": 12
"tokenizer_compatibility": 13
},
"failureCount": 15,
"failureCount": 16,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-10T11:01:21+00:00",
"lastTerminalAt": "2026-09-12T06:34:23.913264+00:00",
"lastTerminalAt": "2026-09-13T04:05:56.910823+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -4904,7 +4904,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 15,
"total": 16,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -7393,15 +7393,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1759,
"totalRecords": 1846,
"terminalRecords": 1761,
"totalRecords": 1848,
"totals": {
"attributableFailureCount": 508,
"decisionFailureRate": 0.8959,
"decisionSuccessRate": 0.1041,
"decisionTotal": 567,
"attributableFailureCount": 509,
"decisionFailureRate": 0.8961,
"decisionSuccessRate": 0.1039,
"decisionTotal": 568,
"failureBreakdown": {
"ambiguous_runtime": 412,
"ambiguous_runtime": 413,
"backend_operator": 42,
"framework_architecture_unsupported": 320,
"memory_capacity": 11,
@@ -7409,24 +7409,25 @@
"platform_infrastructure": 4,
"repository_structure": 8,
"runtime_memory": 6,
"tokenizer_compatibility": 48,
"tokenizer_compatibility": 49,
"参数/模板问题": 103,
"验证失败": 673
},
"failureCount": 1700,
"failureCount": 1702,
"failureRate": 0.9665,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 59,
"successRate": 0.0335,
"total": 1759,
"unresolvedFailureCount": 1188
"total": 1761,
"unresolvedFailureCount": 1189
},
"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。",
@@ -7435,7 +7436,6 @@
"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。",
@@ -7458,6 +7458,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1846,
"summarizedRecords": 1848,
"version": 1
}

View File

@@ -1,3 +1,5 @@
{"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": "2026-09-13T04:05:56.910845+00:00", "modelId": "RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T04:05:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4332432", "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": "2026-09-13T04:05:56.910823+00:00", "modelId": "whcl412/mlx-LycheeAI-coder-1.7b", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T03:57:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458813", "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": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-13T03:22:02.529658+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T03:21:22+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4558358", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-13T03:22:02.529638+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-13T03:15:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523217", "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": "2026-09-13T03:12:57.550578+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T03:11:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4549641", "taskType": "text-generation", "verifyResult": -1}
@@ -296,5 +298,3 @@
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "", "lastSyncTime": "2026-09-09T10:14:08.904917+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T10:11:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4421471", "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": "2026-09-09T09:03:44.512406+00:00", "modelId": "amd/Qwen3-4B-awq-quant-onnx-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T09:01:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079256", "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": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "llamacpp", "lastSyncTime": "2026-09-09T08:32:12.414501+00:00", "modelId": "ewinregirgojr/MiniCPM5-1B-Agentic-Tooluse-v3-GGUF", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T08:31:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4574708", "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": "2026-09-09T05:56:37.494948+00:00", "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T05:53:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471931", "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": "2026-09-09T05:56:37.494970+00:00", "modelId": "nm-testing/SmolLM-135M-Instruct-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T05:53:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471929", "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": "f4d3f480c080d3928689d80038e9a31c4e90bdc5f05e17098d413e448679c12b",
".modelhub_state/architecture_history_backfill.json": "bd9f0f280dee069d1a33628daa864864626426dc0c62694ab84f7ddaffbe45dd",
".modelhub_state/market_intelligence.json": "48963d8c81de9816cadf6c102ad654d5a0235403a895f64dd90f38ddcd99e70c",
".modelhub_state/official_capabilities.json": "2afa67a77d11ed17d1eca71245d6b6cdc8551b0bb65b52f3fefc1093cd8759d2",
".modelhub_state/outcome_checkpoint.json": "c2d8b0be3034aa55d9eaac80f9d9e4689cb6eda194c5f21b95f821dcb1e9c975",
".modelhub_state/architecture_compatibility_blacklist.json": "b244a61889da1da385d0aa0d9f59f1947737212e96df8bf4b1757c0cbd88f0ae",
".modelhub_state/architecture_history_backfill.json": "70ed060802cf7c6ab59f987209c6b49cd24e354e461c47f539ddb4730ac62228",
".modelhub_state/market_intelligence.json": "ec4d32e19889c2764e11c6ef29ec5ff6c576d868ca2fc59e8dac3b4392ab551c",
".modelhub_state/official_capabilities.json": "a767dae9a53619275f54b096fa48ab98d394f9070ef64ec3dee054d5789408ea",
".modelhub_state/outcome_checkpoint.json": "69367c4e9b3bc8796278e9a5d93048a2dd5e28705bc20db5bfb2755d251e2c21",
".modelhub_state/queue_cleanup_latest.json": "51e7d1585319177976584ac9d97c18e02335e06fbd17bfdd6be748f1310ef4da",
".modelhub_state/recent_outcomes.jsonl": "5478cf093f7408a1969eeecc8eea1561ffe0b8f4ec090ce4d647fd4af9310a0f",
".modelhub_state/recovery_active_tasks.jsonl": "32fff3bed8a7a4518318a5dc99c6bc1ed9b3e1ad762d8ef8168a9c14eef78fdd",
".modelhub_state/recovery_intents.jsonl": "b1f23d8b602894c81f4e2ad294ea3dca1f737175ef7c4c030d1ae749ce3b824a",
".modelhub_state/recent_outcomes.jsonl": "0c55572f448fa6cb316e6207fa9f1bda381185c47737650346b7056dce4e34cb",
".modelhub_state/recovery_active_tasks.jsonl": "2cdeedfc83e7ff91814a7092776dfed93cf84fd0691b49fbaaa8ea2fd6e30770",
".modelhub_state/recovery_intents.jsonl": "bd5afcf68503a77b08db832558927abf0bc9064f65dbd74222b7d0a3408be538",
".modelhub_state/routing_intelligence.json": "cdd3341d66484775862c4a1f5c766a7fc0200b1a3a204a76975162502e1d3457",
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
"ledger/submissions.jsonl": "8f12d75f773632785dd64de0467afe57dcae00a4cf0c7c019d8a956931e393a1",
"outcomes/submissions.jsonl": "52eb59d3f79d7002ef2c21ead04124871025575876c40b3c89e753c66cc8d521"
},
"generation": 6508,
"generation": 6509,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-13T04:04:56.155350+00:00",
"updatedAt": "2026-09-13T04:07:57.080325+00:00",
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
}