state: generation 5152 (cycle)

This commit is contained in:
2026-09-10 12:07:59 +00:00
parent b128772182
commit 50a2cad333
9 changed files with 2187 additions and 2185 deletions

View File

@@ -1313,7 +1313,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T12:05:08.299580+00:00",
"generatedAt": "2026-09-10T12:07:58.801659+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -51,7 +51,7 @@
"4": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 366,
"listingErrors": 367,
"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": "2026-09-10T12:05:08.240989+00:00",
"updatedAt": "2026-09-10T12:07:58.775856+00:00",
"version": 1
}

View File

@@ -416,121 +416,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T12:03:38.646216+00:00",
"generatedAt": "2026-09-10T12:06:15.406817+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 974.7916666666666,
"backlogHours": 995.6170212765958,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.021443346653475,
"queueFactor": 0.9608099120081378,
"queueWeight": 0.9608099120081378,
"recentSuccess": 56,
"recentSuccessRate": 0.3888888888888889,
"recentTerminal": 144,
"recentWilsonLowerBound": 0.31313968172670287,
"qualityFactor": 0.8570817980313793,
"queueFactor": 0.959539296413968,
"queueWeight": 0.959539296413968,
"recentSuccess": 53,
"recentSuccessRate": 0.375886524822695,
"recentTerminal": 141,
"recentWilsonLowerBound": 0.3002292151562218,
"running": 8,
"selectionWeight": 0.981412892019423,
"selectionWeight": 0.8224036654522483,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 24.0,
"waiting": 23395
"throughputPerHour": 23.5,
"waiting": 23397
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1005.2560975609756,
"backlogHours": 987.1616766467066,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.791871348450922,
"queueFactor": 0.9563849614565053,
"queueWeight": 0.9563849614565053,
"qualityFactor": 0.6992181035803156,
"queueFactor": 0.9607676447825316,
"queueWeight": 0.9607676447825316,
"recentSuccess": 57,
"recentSuccessRate": 0.3475609756097561,
"recentTerminal": 164,
"recentWilsonLowerBound": 0.27892260810607894,
"recentSuccessRate": 0.3413173652694611,
"recentTerminal": 167,
"recentWilsonLowerBound": 0.2736949382303017,
"running": 8,
"selectionWeight": 0.757333849066746,
"selectionWeight": 0.671786130566168,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 27.333333333333332,
"waiting": 27477
"throughputPerHour": 27.833333333333332,
"waiting": 27476
},
"Biren_166m": {
"available": true,
"backlogHours": 120.6787330316742,
"backlogHours": 123.36111111111111,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.21991978497447676,
"qualityFactor": 0.17864385584698908,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 45,
"recentSuccessRate": 0.20361990950226244,
"recentTerminal": 221,
"recentWilsonLowerBound": 0.1558041506696963,
"recentSuccess": 42,
"recentSuccessRate": 0.19444444444444445,
"recentTerminal": 216,
"recentWilsonLowerBound": 0.1471946266613268,
"running": 8,
"selectionWeight": 0.28589572046681977,
"selectionWeight": 0.2322370126010858,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 36.833333333333336,
"waiting": 4445
"throughputPerHour": 36.0,
"waiting": 4441
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 933.4945054945056,
"backlogHours": 885.25,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.0875604369534539,
"queueFactor": 0.9670690424515638,
"queueWeight": 0.9670690424515638,
"recentSuccess": 15,
"recentSuccessRate": 0.16483516483516483,
"recentTerminal": 91,
"recentWilsonLowerBound": 0.10251340708451503,
"qualityFactor": 0.08545205491907827,
"queueFactor": 0.9766000043511033,
"queueWeight": 0.9766000043511033,
"recentSuccess": 16,
"recentSuccessRate": 0.16666666666666666,
"recentTerminal": 96,
"recentWilsonLowerBound": 0.10527292644504677,
"running": 7,
"selectionWeight": 0.08467698792121718,
"selectionWeight": 0.08345247720578255,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 15.166666666666666,
"waiting": 14158
"throughputPerHour": 16.0,
"waiting": 14164
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 486.5504587155963,
"backlogHours": 473.35714285714283,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.34860830526265546,
"queueFactor": 1.0663629881307133,
"queueWeight": 1.0663629881307133,
"recentSuccess": 29,
"recentSuccessRate": 0.26605504587155965,
"recentTerminal": 109,
"recentWilsonLowerBound": 0.19209740149947543,
"qualityFactor": 0.32996556427911,
"queueFactor": 1.0727493794026557,
"queueWeight": 1.0727493794026557,
"recentSuccess": 30,
"recentSuccessRate": 0.26785714285714285,
"recentTerminal": 112,
"recentWilsonLowerBound": 0.19454473061185254,
"running": 7,
"selectionWeight": 0.3717429940870691,
"selectionWeight": 0.35397035430466234,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.166666666666668,
"waiting": 8839
"throughputPerHour": 18.666666666666668,
"waiting": 8836
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 44.84905660377358,
"backlogHours": 45.98709677419355,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -539,170 +539,170 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 22,
"recentSuccessRate": 0.06918238993710692,
"recentTerminal": 318,
"recentWilsonLowerBound": 0.046127303534686415,
"running": 7,
"recentSuccess": 20,
"recentSuccessRate": 0.06451612903225806,
"recentTerminal": 310,
"recentWilsonLowerBound": 0.04214868788366702,
"running": 4,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 53.0,
"waiting": 2377
"throughputPerHour": 51.666666666666664,
"waiting": 2376
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 72.60952380952381,
"backlogHours": 73.0926517571885,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.09922518436749515,
"qualityFactor": 0.0979729566749854,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 45,
"recentSuccessRate": 0.14285714285714285,
"recentTerminal": 315,
"recentWilsonLowerBound": 0.10850977101682924,
"running": 2,
"selectionWeight": 0.12899273967774372,
"recentSuccess": 46,
"recentSuccessRate": 0.14696485623003194,
"recentTerminal": 313,
"recentWilsonLowerBound": 0.11202353896888702,
"running": 1,
"selectionWeight": 0.12736484367748102,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 52.5,
"waiting": 3812
"throughputPerHour": 52.166666666666664,
"waiting": 3813
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 1934.0,
"backlogHours": 1894.530612244898,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.11777635682289814,
"queueFactor": 0.8669734050826391,
"queueWeight": 0.8669734050826391,
"qualityFactor": 0.10342884139193667,
"queueFactor": 0.8712672067783878,
"queueWeight": 0.8712672067783878,
"recentSuccess": 10,
"recentSuccessRate": 0.20833333333333334,
"recentTerminal": 48,
"recentWilsonLowerBound": 0.11730147795889814,
"recentSuccessRate": 0.20408163265306123,
"recentTerminal": 49,
"recentWilsonLowerBound": 0.11481727042813812,
"running": 2,
"selectionWeight": 0.10210896911297591,
"selectionWeight": 0.09011415773987756,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 8.0,
"throughputPerHour": 8.166666666666666,
"waiting": 15472
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 632.7961165048544,
"backlogHours": 626.7115384615385,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.21330588364595693,
"queueFactor": 1.0251435301173164,
"queueWeight": 1.0251435301173164,
"recentSuccess": 23,
"recentSuccessRate": 0.22330097087378642,
"recentTerminal": 103,
"recentWilsonLowerBound": 0.1536565519868537,
"qualityFactor": 0.21540650787266347,
"queueFactor": 1.0285288039167522,
"queueWeight": 1.0285288039167522,
"recentSuccess": 24,
"recentSuccessRate": 0.23076923076923078,
"recentTerminal": 104,
"recentWilsonLowerBound": 0.1602629748785753,
"running": 7,
"selectionWeight": 0.21866914655560984,
"selectionWeight": 0.22155179789815502,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.166666666666668,
"throughputPerHour": 17.333333333333332,
"waiting": 10863
},
"MetaX_c-500": {
"available": true,
"backlogHours": 540.3307086614172,
"backlogHours": 536.203125,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.2934174255216794,
"queueFactor": 1.0497244149334761,
"queueWeight": 1.0497244149334761,
"recentSuccess": 31,
"recentSuccessRate": 0.2440944881889764,
"recentTerminal": 127,
"recentWilsonLowerBound": 0.17762248116708082,
"qualityFactor": 0.24332862506323158,
"queueFactor": 1.052875963403256,
"queueWeight": 1.052875963403256,
"recentSuccess": 30,
"recentSuccessRate": 0.234375,
"recentTerminal": 128,
"recentWilsonLowerBound": 0.16939254101487963,
"running": 4,
"selectionWeight": 0.3080074353370317,
"selectionWeight": 0.2561948605370396,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 21.166666666666668,
"waiting": 11437
"throughputPerHour": 21.333333333333332,
"waiting": 11439
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1688.3684210526317,
"backlogHours": 1757.3424657534247,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.7297368675445186,
"queueFactor": 0.8848184356725644,
"queueWeight": 0.8848184356725644,
"recentSuccess": 28,
"recentSuccessRate": 0.3684210526315789,
"recentTerminal": 76,
"recentWilsonLowerBound": 0.268752586837069,
"qualityFactor": 0.6688694249529608,
"queueFactor": 0.881146563155052,
"queueWeight": 0.881146563155052,
"recentSuccess": 27,
"recentSuccessRate": 0.3698630136986301,
"recentTerminal": 73,
"recentWilsonLowerBound": 0.26822983017391167,
"running": 4,
"selectionWeight": 0.6456846335933383,
"selectionWeight": 0.5893719949967974,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.666666666666666,
"waiting": 21386
"throughputPerHour": 12.166666666666666,
"waiting": 21381
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 4706.666666666667,
"backlogHours": 4236.3,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.24218390995353942,
"queueFactor": 0.7586950133589607,
"queueWeight": 0.7586950133589607,
"qualityFactor": 0.17408525349035445,
"queueFactor": 0.7721978818892602,
"queueWeight": 0.7721978818892602,
"recentSuccess": 6,
"recentSuccessRate": 0.3333333333333333,
"recentTerminal": 18,
"recentWilsonLowerBound": 0.16278554363662856,
"recentSuccessRate": 0.3,
"recentTerminal": 20,
"recentWilsonLowerBound": 0.14547527396899385,
"running": 2,
"selectionWeight": 0.18374372479752593,
"selectionWeight": 0.13442826401340666,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 3.0,
"waiting": 14120
"submissionEligible": true,
"throughputPerHour": 3.3333333333333335,
"waiting": 14121
},
"Vastai_va16": {
"available": true,
"backlogHours": 860.6571428571428,
"backlogHours": 899.2835820895523,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.35310901838861,
"queueFactor": 0.9789256751616038,
"queueWeight": 0.9789256751616038,
"qualityFactor": 0.3596507797485249,
"queueFactor": 0.9742986762542366,
"queueWeight": 0.9742986762542366,
"recentSuccess": 20,
"recentSuccessRate": 0.2857142857142857,
"recentTerminal": 70,
"recentWilsonLowerBound": 0.19322076591803128,
"recentSuccessRate": 0.29850746268656714,
"recentTerminal": 67,
"recentWilsonLowerBound": 0.20231361154976887,
"running": 16,
"selectionWeight": 0.34566748423172117,
"selectionWeight": 0.3504072786227918,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 11.666666666666666,
"waiting": 10041
"throughputPerHour": 11.166666666666666,
"waiting": 10042
},
"hygon_k100-ai": {
"available": true,
@@ -713,23 +713,23 @@
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 2.5,
"queueFactor": 1.0708287890410404,
"queueWeight": 1.0708287890410404,
"recentSuccess": 62,
"recentSuccessRate": 0.5636363636363636,
"queueFactor": 1.072808991739469,
"queueWeight": 1.072808991739469,
"recentSuccess": 64,
"recentSuccessRate": 0.5818181818181818,
"recentTerminal": 110,
"recentWilsonLowerBound": 0.4703613379728413,
"recentWilsonLowerBound": 0.48840398059035006,
"running": 6,
"selectionWeight": 2.677071972602601,
"selectionWeight": 2.6820224793486727,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.333333333333332,
"waiting": 8675
}
},
"queueAttemptedAt": "2026-09-10T11:54:40.812637+00:00",
"queueAttemptedAt": "2026-09-10T12:06:15.406817+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-10T11:54:40.812637+00:00",
"queueUpdatedAt": "2026-09-10T12:06:15.406817+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": "2026-09-10T11:57:54.886814+00:00",
"lastSyncTime": "2026-09-10T11:57:54.623286+00:00",
"generatedAt": "2026-09-10T12:06:09.429869+00:00",
"lastSyncTime": "2026-09-10T12:06:09.109223+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1793,29 +1793,29 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 69,
"decisionFailureRate": 0.8734,
"decisionSuccessRate": 0.1266,
"decisionTotal": 79,
"attributableFailureCount": 70,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 80,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 46,
"memory_capacity": 1,
"model_load": 22,
"model_load": 23,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 135,
"failureRate": 0.931,
"failureCount": 136,
"failureRate": 0.9315,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 10,
"successRate": 0.069,
"successRate": 0.0685,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 145,
"total": 146,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2075,11 +2075,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 1,
"platform_infrastructure": 1,
"参数/模板问题": 2
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2089,8 +2090,8 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 2
"total": 5,
"unresolvedFailureCount": 3
},
"Vastai_va16|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2291,28 +2292,28 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 122,
"decisionFailureRate": 0.7176,
"decisionSuccessRate": 0.2824,
"decisionTotal": 170,
"attributableFailureCount": 123,
"decisionFailureRate": 0.7193,
"decisionSuccessRate": 0.2807,
"decisionTotal": 171,
"failureBreakdown": {
"ambiguous_runtime": 115,
"backend_operator": 3,
"framework_architecture_unsupported": 87,
"memory_capacity": 5,
"model_load": 24,
"model_load": 25,
"tokenizer_compatibility": 3,
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 966,
"failureCount": 967,
"failureRate": 0.9527,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 48,
"successRate": 0.0473,
"total": 1014,
"total": 1015,
"unresolvedFailureCount": 844
},
"vllm": {
@@ -2321,7 +2322,7 @@
"decisionSuccessRate": 0.0042,
"decisionTotal": 236,
"failureBreakdown": {
"ambiguous_runtime": 166,
"ambiguous_runtime": 167,
"backend_operator": 29,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2332,15 +2333,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 423,
"failureCount": 424,
"failureRate": 0.9976,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 1,
"successRate": 0.0024,
"total": 424,
"unresolvedFailureCount": 187
"total": 425,
"unresolvedFailureCount": 188
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2443,7 +2444,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T11:57:54.880413+00:00",
"generatedAt": "2026-09-10T12:06:09.421970+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2606,26 +2607,26 @@
"unresolvedFailureCount": 43
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 69,
"decisionFailureRate": 0.8734,
"decisionSuccessRate": 0.1266,
"decisionTotal": 79,
"attributableFailureCount": 70,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 80,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 46,
"memory_capacity": 1,
"model_load": 22,
"model_load": 23,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 135,
"failureRate": 0.931,
"failureCount": 136,
"failureRate": 0.9315,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 10,
"successRate": 0.069,
"total": 145,
"successRate": 0.0685,
"total": 146,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800": {
@@ -2705,21 +2706,22 @@
"decisionSuccessRate": 0.0278,
"decisionTotal": 36,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 3,
"platform_infrastructure": 3,
"tokenizer_compatibility": 32,
"参数/模板问题": 9,
"验证失败": 32
},
"failureCount": 79,
"failureRate": 0.9875,
"failureCount": 80,
"failureRate": 0.9877,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 1,
"successRate": 0.0125,
"total": 80,
"unresolvedFailureCount": 41
"successRate": 0.0123,
"total": 81,
"unresolvedFailureCount": 42
},
"Vastai_va16": {
"attributableFailureCount": 47,
@@ -4060,20 +4062,20 @@
"unresolvedFailureCount": 16
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 7,
"attributableFailureCount": 6,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 8,
"decisionFailureRate": 0.8571,
"decisionSuccessRate": 0.1429,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 10,
"backend_operator": 3,
"framework_architecture_unsupported": 3,
"framework_architecture_unsupported": 2,
"model_load": 1
},
"failureCount": 17,
"failureRate": 0.9444,
"failureCount": 16,
"failureRate": 0.9412,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T11:57:54.623286+00:00",
@@ -4081,10 +4083,10 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0556,
"successRate": 0.0588,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 18,
"total": 17,
"unresolvedFailureCount": 10
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -4248,21 +4250,21 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 16,
"consecutiveFailures": 2,
"consecutiveFailures": 3,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8421,
"decisionSuccessRate": 0.1579,
"decisionTotal": 19,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 10,
"model_load": 6
"framework_architecture_unsupported": 9,
"model_load": 7
},
"failureCount": 17,
"failureRate": 0.85,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T05:18:58.697108+00:00",
"lastTerminalAt": "2026-09-10T12:06:09.109223+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4480,18 +4482,19 @@
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1,
"platform_infrastructure": 1
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": "2026-09-09T17:17:21+00:00",
"lastTerminalAt": "2026-09-09T17:24:58.529055+00:00",
"lastTerminalAt": "2026-09-10T12:06:09.109198+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -4499,8 +4502,8 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
"total": 2,
"unresolvedFailureCount": 1
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 1,
@@ -7002,19 +7005,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1570,
"totalRecords": 1657,
"terminalRecords": 1572,
"totalRecords": 1659,
"totals": {
"attributableFailureCount": 411,
"decisionFailureRate": 0.8896,
"decisionSuccessRate": 0.1104,
"decisionTotal": 462,
"attributableFailureCount": 412,
"decisionFailureRate": 0.8898,
"decisionSuccessRate": 0.1102,
"decisionTotal": 463,
"failureBreakdown": {
"ambiguous_runtime": 337,
"ambiguous_runtime": 338,
"backend_operator": 35,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
"model_load": 46,
"model_load": 47,
"platform_infrastructure": 3,
"repository_structure": 5,
"runtime_memory": 5,
@@ -7022,21 +7025,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1519,
"failureRate": 0.9675,
"failureCount": 1521,
"failureRate": 0.9676,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 51,
"successRate": 0.0325,
"total": 1570,
"unresolvedFailureCount": 1105
"successRate": 0.0324,
"total": 1572,
"unresolvedFailureCount": 1106
},
"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 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。",
"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。",
@@ -7044,7 +7047,7 @@
"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 Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"组合 Iluvatar_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。",
@@ -7065,6 +7068,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1657,
"summarizedRecords": 1659,
"version": 1
}

View File

@@ -1,3 +1,5 @@
{"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": "2026-09-10T12:06:09.109223+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:05:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523306", "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": "2026-09-10T12:06:09.109198+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:03:22+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4490278", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T11:57:54.623286+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:53:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610381", "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": "2026-09-10T11:48:57.307255+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:45:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458000", "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": "2026-09-10T11:40:52.603333+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:39:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505113", "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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-07T23:33:45.147699+00:00", "modelId": "mlx-community/Qwen-AgentWorld-35B-A3B-oQ4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:31:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080039", "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": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "llamacpp", "lastSyncTime": "2026-09-07T23:33:45.147733+00:00", "modelId": "kurakurai/Luth-LFM2-700M-GGUF", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:31:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "3986792", "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": "2026-09-07T23:33:45.147723+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332995", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-07T23:25:25.308759+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:21:22+00:00", "targetGpu": "Biren_166m", "taskId": "4610397", "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": ["nemotron_h"], "framework": "", "lastSyncTime": "2026-09-07T23:25:25.308783+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:19:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4133677", "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": "550d9e8a364427403f43ca904033d82ca0e9d698d4581253d1434937f6fca49d",
".modelhub_state/architecture_history_backfill.json": "a9e2e62f10cc4f46c7aa6ce97c7dd7e40ad725d390fc32cc82842110db09c343",
".modelhub_state/market_intelligence.json": "390345701457bcddbf1ac0b8e0dda17e0ef064fb7d8b5cfa2aaebec710d54783",
".modelhub_state/official_capabilities.json": "67301f4148ead65e384e8ab8896ed66be848ff17569495b92e21fb88487c3b53",
".modelhub_state/outcome_checkpoint.json": "28a6abe45f9ed784de541fb0778d7d726ec313aad1ac62ba423630858be6ef7a",
".modelhub_state/architecture_compatibility_blacklist.json": "e58775dddc3fabe3078148e93ab97eb02db912697a7ac61f32ffbbc8cf5a9f52",
".modelhub_state/architecture_history_backfill.json": "4cb55502001b9ffc4c9f0fe051c1583abefffca82833132dbcd0349c49890fc3",
".modelhub_state/market_intelligence.json": "70049ce1a5a578a3d524befbce0222e044e8794461c1005004cb21548f2d739f",
".modelhub_state/official_capabilities.json": "98f1c4796622032cd8fbbd91da8e10754cf7b688add8028c184f92bc51bcc7b1",
".modelhub_state/outcome_checkpoint.json": "f70df639228afadcc434c5740d4bc3c8299e4938de374429b87ccac3316d76c3",
".modelhub_state/queue_cleanup_latest.json": "b9038630dc67feced29c6931cb43d6d94c28bb175e6dcf80fac9c625a52887d5",
".modelhub_state/recent_outcomes.jsonl": "366c2dc586e59f851d8fb493dac147099a3aaa74465191acb8986ca31badc1bb",
".modelhub_state/recovery_active_tasks.jsonl": "43dc3075a8cf3477a6aeb39c4ac1fedd11d42c14f11236c9ebe8b198cba86cda",
".modelhub_state/recovery_intents.jsonl": "ee3e078cb8694844902519493c6811d2676793f9eee94c56f00534bb21d2cc19",
".modelhub_state/recent_outcomes.jsonl": "6d878b8b8aac1da3ee9e17bb4b67e245778c2ab336e44c9ae4ef80d49597916b",
".modelhub_state/recovery_active_tasks.jsonl": "7106eedc75cbad87e864f49eac2a423d8bb6b35335d5ce930c8532a6c4d10bc0",
".modelhub_state/recovery_intents.jsonl": "454118b75f1a473e9e1698927828fed2179216993d9449b1e72dcd0d05599052",
".modelhub_state/routing_intelligence.json": "f36cfaf9f9ff191164b0ce0a73a3ce4bbc3a2dc4589f252d583e33b427807fc0",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "8a621da5637d481c7de4b4e3375f2a68cbdabf71fe459244a727034f36ab3eb9",
"outcomes/submissions.jsonl": "eaa6922265ab874d46282c8353419da53665ddca2baca53c5b4240e410666d50"
},
"generation": 5151,
"generation": 5152,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T12:05:08.451794+00:00",
"updatedAt": "2026-09-10T12:07:59.764668+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}