state: generation 5580 (cycle)
This commit is contained in:
@@ -1307,7 +1307,7 @@
|
|||||||
"taskType": "text-generation"
|
"taskType": "text-generation"
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"generatedAt": "2026-09-11T07:04:26.298199+00:00",
|
"generatedAt": "2026-09-11T07:08:10.161744+00:00",
|
||||||
"summary": {
|
"summary": {
|
||||||
"activeBlockCount": 66,
|
"activeBlockCount": 66,
|
||||||
"byGpuFramework": {
|
"byGpuFramework": {
|
||||||
|
|||||||
@@ -27,7 +27,7 @@
|
|||||||
"11": {
|
"11": {
|
||||||
"complete": false,
|
"complete": false,
|
||||||
"lastError": "ModelHubAPIError: 系统错误",
|
"lastError": "ModelHubAPIError: 系统错误",
|
||||||
"listingErrors": 398,
|
"listingErrors": 399,
|
||||||
"nextPage": 1,
|
"nextPage": 1,
|
||||||
"recordsScanned": 0,
|
"recordsScanned": 0,
|
||||||
"uniqueRecords": 0
|
"uniqueRecords": 0
|
||||||
@@ -102,12 +102,12 @@
|
|||||||
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
|
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
|
||||||
"failureLogsInspected": 0,
|
"failureLogsInspected": 0,
|
||||||
"mode": "incremental_decision_only",
|
"mode": "incremental_decision_only",
|
||||||
"nextAccountIndex": 11,
|
"nextAccountIndex": 0,
|
||||||
"recordsScanned": 0,
|
"recordsScanned": 0,
|
||||||
"seenTaskIds": [],
|
"seenTaskIds": [],
|
||||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||||
"terminalRecords": 0,
|
"terminalRecords": 0,
|
||||||
"uniqueRecords": 0,
|
"uniqueRecords": 0,
|
||||||
"updatedAt": "2026-09-11T07:04:26.274584+00:00",
|
"updatedAt": "2026-09-11T07:08:10.138166+00:00",
|
||||||
"version": 1
|
"version": 1
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -387,138 +387,138 @@
|
|||||||
}
|
}
|
||||||
},
|
},
|
||||||
"frameworkUpdatedAt": null,
|
"frameworkUpdatedAt": null,
|
||||||
"generatedAt": "2026-09-11T07:02:06.801385+00:00",
|
"generatedAt": "2026-09-11T07:05:37.815373+00:00",
|
||||||
"gpuStats": {
|
"gpuStats": {
|
||||||
"Ascend_910-b4": {
|
"Ascend_910-b4": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 1124.5068493150686,
|
"backlogHours": 1140.0833333333333,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Ascend_910-b4",
|
"gpu": "Ascend_910-b4",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 8,
|
"maxConcurrentTasks": 8,
|
||||||
"qualityFactor": 2.048441326161014,
|
"qualityFactor": 2.1145577565900093,
|
||||||
"queueFactor": 0.9234385990232294,
|
"queueFactor": 0.922928243217504,
|
||||||
"queueWeight": 0.9234385990232294,
|
"queueWeight": 0.922928243217504,
|
||||||
"recentSuccess": 51,
|
"recentSuccess": 51,
|
||||||
"recentSuccessRate": 0.3493150684931507,
|
"recentSuccessRate": 0.3541666666666667,
|
||||||
"recentTerminal": 146,
|
"recentTerminal": 144,
|
||||||
"recentWilsonLowerBound": 0.2767438059072339,
|
"recentWilsonLowerBound": 0.2807687889835203,
|
||||||
"running": 8,
|
"running": 8,
|
||||||
"selectionWeight": 1.8916097884114131,
|
"selectionWeight": 1.9515850754715638,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 24.333333333333332,
|
"throughputPerHour": 24.0,
|
||||||
"waiting": 27363
|
"waiting": 27362
|
||||||
},
|
},
|
||||||
"Biren_166m": {
|
"Biren_166m": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 133.8341968911917,
|
"backlogHours": 132.27692307692308,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Biren_166m",
|
"gpu": "Biren_166m",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 8,
|
"maxConcurrentTasks": 8,
|
||||||
"qualityFactor": 0.2997297549196236,
|
"qualityFactor": 0.26877822586769706,
|
||||||
"queueFactor": 1.270770940388867,
|
"queueFactor": 1.274928452247279,
|
||||||
"queueWeight": 1.270770940388867,
|
"queueWeight": 1.274928452247279,
|
||||||
"recentSuccess": 31,
|
"recentSuccess": 30,
|
||||||
"recentSuccessRate": 0.16062176165803108,
|
"recentSuccessRate": 0.15384615384615385,
|
||||||
"recentTerminal": 193,
|
"recentTerminal": 195,
|
||||||
"recentWilsonLowerBound": 0.11552386104400723,
|
"recentWilsonLowerBound": 0.10993992435978557,
|
||||||
"running": 8,
|
"running": 8,
|
||||||
"selectionWeight": 0.38088786252173473,
|
"selectionWeight": 0.34267300750327256,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 32.166666666666664,
|
"throughputPerHour": 32.5,
|
||||||
"waiting": 4305
|
"waiting": 4299
|
||||||
},
|
},
|
||||||
"Cambricon_mlu-370-x4": {
|
"Cambricon_mlu-370-x4": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 1074.4556962025317,
|
"backlogHours": 1102.2857142857142,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Cambricon_mlu-370-x4",
|
"gpu": "Cambricon_mlu-370-x4",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 7,
|
"maxConcurrentTasks": 7,
|
||||||
"qualityFactor": 0.9131097119771553,
|
"qualityFactor": 0.968640347242462,
|
||||||
"queueFactor": 0.9297668604666357,
|
"queueFactor": 0.9276076017879596,
|
||||||
"queueWeight": 0.9297668604666357,
|
"queueWeight": 0.9276076017879596,
|
||||||
"recentSuccess": 22,
|
"recentSuccess": 22,
|
||||||
"recentSuccessRate": 0.27848101265822783,
|
"recentSuccessRate": 0.2857142857142857,
|
||||||
"recentTerminal": 79,
|
"recentTerminal": 77,
|
||||||
"recentWilsonLowerBound": 0.19168037554546477,
|
"recentWilsonLowerBound": 0.1968937869371719,
|
||||||
"running": 7,
|
"running": 7,
|
||||||
"selectionWeight": 0.8489791501665936,
|
"selectionWeight": 0.8985181495006366,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 13.166666666666666,
|
"throughputPerHour": 12.833333333333334,
|
||||||
"waiting": 14147
|
"waiting": 14146
|
||||||
},
|
},
|
||||||
"Cambricon_mlu-370-x8": {
|
"Cambricon_mlu-370-x8": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 505.5576923076923,
|
"backlogHours": 495.73584905660374,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Cambricon_mlu-370-x8",
|
"gpu": "Cambricon_mlu-370-x8",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 7,
|
"maxConcurrentTasks": 7,
|
||||||
"qualityFactor": 1.0216621953305691,
|
"qualityFactor": 0.8084620689568671,
|
||||||
"queueFactor": 1.0410862990897614,
|
"queueFactor": 1.045733153640359,
|
||||||
"queueWeight": 1.0410862990897614,
|
"queueWeight": 1.045733153640359,
|
||||||
"recentSuccess": 29,
|
"recentSuccess": 27,
|
||||||
"recentSuccessRate": 0.27884615384615385,
|
"recentSuccessRate": 0.25471698113207547,
|
||||||
"recentTerminal": 104,
|
"recentTerminal": 106,
|
||||||
"recentWilsonLowerBound": 0.20172158008187036,
|
"recentWilsonLowerBound": 0.18136307591306167,
|
||||||
"running": 7,
|
"running": 7,
|
||||||
"selectionWeight": 1.0636385138566231,
|
"selectionWeight": 0.8454355889688739,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 17.333333333333332,
|
"throughputPerHour": 17.666666666666668,
|
||||||
"waiting": 8763
|
"waiting": 8758
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-100": {
|
"Iluvatar_bi-100": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 82.3859649122807,
|
"backlogHours": 76.91803278688525,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Iluvatar_bi-100",
|
"gpu": "Iluvatar_bi-100",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 24,
|
"maxConcurrentTasks": 24,
|
||||||
"qualityFactor": 0.1400360331454473,
|
"qualityFactor": 0.15350717023373273,
|
||||||
"queueFactor": 1.3,
|
"queueFactor": 1.3,
|
||||||
"queueWeight": 1.3,
|
"queueWeight": 1.3,
|
||||||
"recentSuccess": 21,
|
"recentSuccess": 23,
|
||||||
"recentSuccessRate": 0.12280701754385964,
|
"recentSuccessRate": 0.12568306010928962,
|
||||||
"recentTerminal": 171,
|
"recentTerminal": 183,
|
||||||
"recentWilsonLowerBound": 0.08174269302489041,
|
"recentWilsonLowerBound": 0.08522759712476838,
|
||||||
"running": 1,
|
"running": 3,
|
||||||
"selectionWeight": 0.1820468430890815,
|
"selectionWeight": 0.19955932130385254,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 28.5,
|
"throughputPerHour": 30.5,
|
||||||
"waiting": 2348
|
"waiting": 2346
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-150": {
|
"Iluvatar_bi-150": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 101.55458515283843,
|
"backlogHours": 98.12658227848101,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Iluvatar_bi-150",
|
"gpu": "Iluvatar_bi-150",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 50,
|
"maxConcurrentTasks": 50,
|
||||||
"qualityFactor": 0.37016455275820476,
|
"qualityFactor": 0.3205181082820727,
|
||||||
"queueFactor": 1.3,
|
"queueFactor": 1.3,
|
||||||
"queueWeight": 1.3,
|
"queueWeight": 1.3,
|
||||||
"recentSuccess": 39,
|
"recentSuccess": 38,
|
||||||
"recentSuccessRate": 0.1703056768558952,
|
"recentSuccessRate": 0.16033755274261605,
|
||||||
"recentTerminal": 229,
|
"recentTerminal": 237,
|
||||||
"recentWilsonLowerBound": 0.12715621461714224,
|
"recentWilsonLowerBound": 0.11909932276574142,
|
||||||
"running": 3,
|
"running": 4,
|
||||||
"selectionWeight": 0.4812139185856662,
|
"selectionWeight": 0.41667354076669455,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 38.166666666666664,
|
"throughputPerHour": 39.5,
|
||||||
"waiting": 3876
|
"waiting": 3876
|
||||||
},
|
},
|
||||||
"Iluvatar_mrv-100": {
|
"Iluvatar_mrv-100": {
|
||||||
@@ -530,14 +530,14 @@
|
|||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 2,
|
"maxConcurrentTasks": 2,
|
||||||
"qualityFactor": 1.6223760499506996,
|
"qualityFactor": 1.6223760499506996,
|
||||||
"queueFactor": 0.8245424679390466,
|
"queueFactor": 0.8257890412133724,
|
||||||
"queueWeight": 0.8245424679390466,
|
"queueWeight": 0.8257890412133724,
|
||||||
"recentSuccess": 15,
|
"recentSuccess": 15,
|
||||||
"recentSuccessRate": 0.38461538461538464,
|
"recentSuccessRate": 0.38461538461538464,
|
||||||
"recentTerminal": 39,
|
"recentTerminal": 39,
|
||||||
"recentWilsonLowerBound": 0.24891162547007062,
|
"recentWilsonLowerBound": 0.24891162547007062,
|
||||||
"running": 2,
|
"running": 2,
|
||||||
"selectionWeight": 1.3377179521515519,
|
"selectionWeight": 1.3397403627763265,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 6.5,
|
"throughputPerHour": 6.5,
|
||||||
@@ -545,140 +545,140 @@
|
|||||||
},
|
},
|
||||||
"Kunlunxin_p-800": {
|
"Kunlunxin_p-800": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 661.2244897959184,
|
"backlogHours": 667.9175257731958,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Kunlunxin_p-800",
|
"gpu": "Kunlunxin_p-800",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 7,
|
"maxConcurrentTasks": 7,
|
||||||
"qualityFactor": 0.5575770723655764,
|
"qualityFactor": 0.5707594117834665,
|
||||||
"queueFactor": 1.0,
|
"queueFactor": 1.0,
|
||||||
"queueWeight": 1.0,
|
"queueWeight": 1.0,
|
||||||
"recentSuccess": 22,
|
"recentSuccess": 22,
|
||||||
"recentSuccessRate": 0.22448979591836735,
|
"recentSuccessRate": 0.2268041237113402,
|
||||||
"recentTerminal": 98,
|
"recentTerminal": 97,
|
||||||
"recentWilsonLowerBound": 0.1531813203076455,
|
"recentWilsonLowerBound": 0.15481698841986685,
|
||||||
"running": 7,
|
"running": 7,
|
||||||
"selectionWeight": 0.5575770723655764,
|
"selectionWeight": 0.5707594117834665,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 16.333333333333332,
|
"throughputPerHour": 16.166666666666668,
|
||||||
"waiting": 10800
|
"waiting": 10798
|
||||||
},
|
},
|
||||||
"MetaX_c-500": {
|
"MetaX_c-500": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 693.2448979591837,
|
"backlogHours": 686.2424242424242,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "MetaX_c-500",
|
"gpu": "MetaX_c-500",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 4,
|
"maxConcurrentTasks": 4,
|
||||||
"qualityFactor": 0.9675635819745967,
|
"qualityFactor": 0.9452986672344887,
|
||||||
"queueFactor": 0.9929316112245137,
|
"queueFactor": 0.9959482926196432,
|
||||||
"queueWeight": 0.9929316112245137,
|
"queueWeight": 0.9959482926196432,
|
||||||
"recentSuccess": 27,
|
"recentSuccess": 27,
|
||||||
"recentSuccessRate": 0.2755102040816326,
|
"recentSuccessRate": 0.2727272727272727,
|
||||||
"recentTerminal": 98,
|
"recentTerminal": 99,
|
||||||
"recentWilsonLowerBound": 0.19679426941928946,
|
"recentWilsonLowerBound": 0.1947227886340705,
|
||||||
"running": 4,
|
"running": 4,
|
||||||
"selectionWeight": 0.9607244664121981,
|
"selectionWeight": 0.9414685936478133,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 16.333333333333332,
|
"throughputPerHour": 16.5,
|
||||||
"waiting": 11323
|
"waiting": 11323
|
||||||
},
|
},
|
||||||
"Mthreads_s4000": {
|
"Mthreads_s4000": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 623.0926829268293,
|
"backlogHours": 616.9855072463768,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Mthreads_s4000",
|
"gpu": "Mthreads_s4000",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 4,
|
"maxConcurrentTasks": 4,
|
||||||
"qualityFactor": 0.05,
|
"qualityFactor": 0.05,
|
||||||
"queueFactor": 1.008949528770926,
|
"queueFactor": 1.0119689363024833,
|
||||||
"queueWeight": 1.008949528770926,
|
"queueWeight": 1.0119689363024833,
|
||||||
"recentSuccess": 12,
|
"recentSuccess": 13,
|
||||||
"recentSuccessRate": 0.05853658536585366,
|
"recentSuccessRate": 0.06280193236714976,
|
||||||
"recentTerminal": 205,
|
"recentTerminal": 207,
|
||||||
"recentWilsonLowerBound": 0.033798684212660135,
|
"recentWilsonLowerBound": 0.03706523966421769,
|
||||||
"running": 4,
|
"running": 4,
|
||||||
"selectionWeight": 0.0504474764385463,
|
"selectionWeight": 0.05059844681512417,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": false,
|
"submissionEligible": false,
|
||||||
"throughputPerHour": 34.166666666666664,
|
"throughputPerHour": 34.5,
|
||||||
"waiting": 21289
|
"waiting": 21286
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1": {
|
"Sunrise_pt-200-x1": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 3432.9599999999996,
|
"backlogHours": 4086.8571428571427,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Sunrise_pt-200-x1",
|
"gpu": "Sunrise_pt-200-x1",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 2,
|
"maxConcurrentTasks": 2,
|
||||||
"qualityFactor": 1.4166150600667744,
|
"qualityFactor": 1.5625543320911626,
|
||||||
"queueFactor": 0.7810917091755144,
|
"queueFactor": 0.7620790228748598,
|
||||||
"queueWeight": 0.7810917091755144,
|
"queueWeight": 0.7620790228748598,
|
||||||
"recentSuccess": 10,
|
"recentSuccess": 9,
|
||||||
"recentSuccessRate": 0.4,
|
"recentSuccessRate": 0.42857142857142855,
|
||||||
"recentTerminal": 25,
|
"recentTerminal": 21,
|
||||||
"recentWilsonLowerBound": 0.23403057664190918,
|
"recentWilsonLowerBound": 0.24469699486521046,
|
||||||
"running": 2,
|
"running": 2,
|
||||||
"selectionWeight": 1.1065062785113309,
|
"selectionWeight": 1.1907898785889124,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 4.166666666666667,
|
"throughputPerHour": 3.5,
|
||||||
"waiting": 14304
|
"waiting": 14304
|
||||||
},
|
},
|
||||||
"Vastai_va16": {
|
"Vastai_va16": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 959.53125,
|
"backlogHours": 974.6666666666666,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Vastai_va16",
|
"gpu": "Vastai_va16",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 16,
|
"maxConcurrentTasks": 16,
|
||||||
"qualityFactor": 1.4867759935546234,
|
"qualityFactor": 1.5424126565557446,
|
||||||
"queueFactor": 0.9456784032168085,
|
"queueFactor": 0.9448872936265521,
|
||||||
"queueWeight": 0.9456784032168085,
|
"queueWeight": 0.9448872936265521,
|
||||||
"recentSuccess": 22,
|
"recentSuccess": 22,
|
||||||
"recentSuccessRate": 0.34375,
|
"recentSuccessRate": 0.3492063492063492,
|
||||||
"recentTerminal": 64,
|
"recentTerminal": 63,
|
||||||
"recentWilsonLowerBound": 0.2392297503546903,
|
"recentWilsonLowerBound": 0.2432581939635419,
|
||||||
"running": 16,
|
"running": 16,
|
||||||
"selectionWeight": 1.4060119475258204,
|
"selectionWeight": 1.457406120708298,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 10.666666666666666,
|
"throughputPerHour": 10.5,
|
||||||
"waiting": 10235
|
"waiting": 10234
|
||||||
},
|
},
|
||||||
"hygon_k100-ai": {
|
"hygon_k100-ai": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 638.4146341463415,
|
"backlogHours": 638.2682926829268,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "hygon_k100-ai",
|
"gpu": "hygon_k100-ai",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 6,
|
"maxConcurrentTasks": 6,
|
||||||
"qualityFactor": 2.5,
|
"qualityFactor": 2.5,
|
||||||
"queueFactor": 1.0052797039680088,
|
"queueFactor": 1.0068341446775488,
|
||||||
"queueWeight": 1.0052797039680088,
|
"queueWeight": 1.0068341446775488,
|
||||||
"recentSuccess": 33,
|
"recentSuccess": 33,
|
||||||
"recentSuccessRate": 0.4024390243902439,
|
"recentSuccessRate": 0.4024390243902439,
|
||||||
"recentTerminal": 82,
|
"recentTerminal": 82,
|
||||||
"recentWilsonLowerBound": 0.30297275905176574,
|
"recentWilsonLowerBound": 0.30297275905176574,
|
||||||
"running": 6,
|
"running": 6,
|
||||||
"selectionWeight": 2.513199259920022,
|
"selectionWeight": 2.517085361693872,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 13.666666666666666,
|
"throughputPerHour": 13.666666666666666,
|
||||||
"waiting": 8725
|
"waiting": 8723
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"queueAttemptedAt": "2026-09-11T06:52:46.207250+00:00",
|
"queueAttemptedAt": "2026-09-11T07:05:37.815373+00:00",
|
||||||
"queueError": null,
|
"queueError": null,
|
||||||
"queueUpdatedAt": "2026-09-11T06:52:46.207250+00:00",
|
"queueUpdatedAt": "2026-09-11T07:05:37.815373+00:00",
|
||||||
"supportedGpus": [
|
"supportedGpus": [
|
||||||
"Vastai_va16",
|
"Vastai_va16",
|
||||||
"Iluvatar_mrv-100",
|
"Iluvatar_mrv-100",
|
||||||
|
|||||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"generatedAt": "2026-09-11T05:08:00.294271+00:00",
|
"generatedAt": "2026-09-11T07:05:27.225930+00:00",
|
||||||
"lastSyncTime": "2026-09-11T05:08:00.009961+00:00",
|
"lastSyncTime": "2026-09-11T07:05:27.006934+00:00",
|
||||||
"recentLimit": 300,
|
"recentLimit": 300,
|
||||||
"report": {
|
"report": {
|
||||||
"architectureCompatibilityBlocks": {
|
"architectureCompatibilityBlocks": {
|
||||||
@@ -1787,30 +1787,30 @@
|
|||||||
"unresolvedFailureCount": 7
|
"unresolvedFailureCount": 7
|
||||||
},
|
},
|
||||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||||
"attributableFailureCount": 78,
|
"attributableFailureCount": 79,
|
||||||
"decisionFailureRate": 0.8864,
|
"decisionFailureRate": 0.8876,
|
||||||
"decisionSuccessRate": 0.1136,
|
"decisionSuccessRate": 0.1124,
|
||||||
"decisionTotal": 88,
|
"decisionTotal": 89,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 18,
|
"ambiguous_runtime": 18,
|
||||||
"framework_architecture_unsupported": 48,
|
"framework_architecture_unsupported": 48,
|
||||||
"memory_capacity": 1,
|
"memory_capacity": 1,
|
||||||
"model_load": 29,
|
"model_load": 30,
|
||||||
"platform_infrastructure": 1,
|
"platform_infrastructure": 1,
|
||||||
"参数/模板问题": 2,
|
"参数/模板问题": 2,
|
||||||
"验证失败": 47
|
"验证失败": 47
|
||||||
},
|
},
|
||||||
"failureCount": 146,
|
"failureCount": 147,
|
||||||
"failureRate": 0.9359,
|
"failureRate": 0.9363,
|
||||||
"framework": "unknown",
|
"framework": "unknown",
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 1,
|
"platformFailureCount": 1,
|
||||||
"successCount": 10,
|
"successCount": 10,
|
||||||
"successRate": 0.0641,
|
"successRate": 0.0637,
|
||||||
"targetGpu": "Iluvatar_mrv-100",
|
"targetGpu": "Iluvatar_mrv-100",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 156,
|
"total": 157,
|
||||||
"unresolvedFailureCount": 67
|
"unresolvedFailureCount": 67
|
||||||
},
|
},
|
||||||
"Kunlunxin_p-800|unknown|text-generation": {
|
"Kunlunxin_p-800|unknown|text-generation": {
|
||||||
@@ -2288,29 +2288,29 @@
|
|||||||
"unresolvedFailureCount": 5
|
"unresolvedFailureCount": 5
|
||||||
},
|
},
|
||||||
"unknown": {
|
"unknown": {
|
||||||
"attributableFailureCount": 132,
|
"attributableFailureCount": 133,
|
||||||
"decisionFailureRate": 0.7333,
|
"decisionFailureRate": 0.7348,
|
||||||
"decisionSuccessRate": 0.2667,
|
"decisionSuccessRate": 0.2652,
|
||||||
"decisionTotal": 180,
|
"decisionTotal": 181,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 128,
|
"ambiguous_runtime": 128,
|
||||||
"backend_operator": 4,
|
"backend_operator": 4,
|
||||||
"framework_architecture_unsupported": 89,
|
"framework_architecture_unsupported": 89,
|
||||||
"memory_capacity": 5,
|
"memory_capacity": 5,
|
||||||
"model_load": 31,
|
"model_load": 32,
|
||||||
"platform_infrastructure": 1,
|
"platform_infrastructure": 1,
|
||||||
"tokenizer_compatibility": 3,
|
"tokenizer_compatibility": 3,
|
||||||
"参数/模板问题": 56,
|
"参数/模板问题": 56,
|
||||||
"验证失败": 673
|
"验证失败": 673
|
||||||
},
|
},
|
||||||
"failureCount": 990,
|
"failureCount": 991,
|
||||||
"failureRate": 0.9538,
|
"failureRate": 0.9538,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 1,
|
"platformFailureCount": 1,
|
||||||
"successCount": 48,
|
"successCount": 48,
|
||||||
"successRate": 0.0462,
|
"successRate": 0.0462,
|
||||||
"total": 1038,
|
"total": 1039,
|
||||||
"unresolvedFailureCount": 857
|
"unresolvedFailureCount": 857
|
||||||
},
|
},
|
||||||
"vllm": {
|
"vllm": {
|
||||||
@@ -2441,7 +2441,7 @@
|
|||||||
"unresolvedFailureCount": 1
|
"unresolvedFailureCount": 1
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"generatedAt": "2026-09-11T05:08:00.290509+00:00",
|
"generatedAt": "2026-09-11T07:05:27.222026+00:00",
|
||||||
"gpuSummaries": {
|
"gpuSummaries": {
|
||||||
"Ascend_910-b3": {
|
"Ascend_910-b3": {
|
||||||
"attributableFailureCount": 26,
|
"attributableFailureCount": 26,
|
||||||
@@ -2604,27 +2604,27 @@
|
|||||||
"unresolvedFailureCount": 43
|
"unresolvedFailureCount": 43
|
||||||
},
|
},
|
||||||
"Iluvatar_mrv-100": {
|
"Iluvatar_mrv-100": {
|
||||||
"attributableFailureCount": 78,
|
"attributableFailureCount": 79,
|
||||||
"decisionFailureRate": 0.8864,
|
"decisionFailureRate": 0.8876,
|
||||||
"decisionSuccessRate": 0.1136,
|
"decisionSuccessRate": 0.1124,
|
||||||
"decisionTotal": 88,
|
"decisionTotal": 89,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 18,
|
"ambiguous_runtime": 18,
|
||||||
"framework_architecture_unsupported": 48,
|
"framework_architecture_unsupported": 48,
|
||||||
"memory_capacity": 1,
|
"memory_capacity": 1,
|
||||||
"model_load": 29,
|
"model_load": 30,
|
||||||
"platform_infrastructure": 1,
|
"platform_infrastructure": 1,
|
||||||
"参数/模板问题": 2,
|
"参数/模板问题": 2,
|
||||||
"验证失败": 47
|
"验证失败": 47
|
||||||
},
|
},
|
||||||
"failureCount": 146,
|
"failureCount": 147,
|
||||||
"failureRate": 0.9359,
|
"failureRate": 0.9363,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 1,
|
"platformFailureCount": 1,
|
||||||
"successCount": 10,
|
"successCount": 10,
|
||||||
"successRate": 0.0641,
|
"successRate": 0.0637,
|
||||||
"total": 156,
|
"total": 157,
|
||||||
"unresolvedFailureCount": 67
|
"unresolvedFailureCount": 67
|
||||||
},
|
},
|
||||||
"Kunlunxin_p-800": {
|
"Kunlunxin_p-800": {
|
||||||
@@ -4190,9 +4190,9 @@
|
|||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 0,
|
"decisionTotal": 0,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"参数/模板问题": 2
|
"参数/模板问题": 1
|
||||||
},
|
},
|
||||||
"failureCount": 2,
|
"failureCount": 1,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm",
|
"framework": "vllm",
|
||||||
"lastPlatformFailureAt": null,
|
"lastPlatformFailureAt": null,
|
||||||
@@ -4204,8 +4204,8 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Cambricon_mlu-370-x8",
|
"targetGpu": "Cambricon_mlu-370-x8",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 2,
|
"total": 1,
|
||||||
"unresolvedFailureCount": 2
|
"unresolvedFailureCount": 1
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-100|transformers|text-generation": {
|
"Iluvatar_bi-100|transformers|text-generation": {
|
||||||
"attributableFailureCount": 0,
|
"attributableFailureCount": 0,
|
||||||
@@ -4261,7 +4261,7 @@
|
|||||||
},
|
},
|
||||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||||
"attributableFailureCount": 17,
|
"attributableFailureCount": 17,
|
||||||
"consecutiveFailures": 11,
|
"consecutiveFailures": 12,
|
||||||
"consecutivePlatformFailures": 0,
|
"consecutivePlatformFailures": 0,
|
||||||
"decisionFailureRate": 0.9444,
|
"decisionFailureRate": 0.9444,
|
||||||
"decisionSuccessRate": 0.0556,
|
"decisionSuccessRate": 0.0556,
|
||||||
@@ -4276,7 +4276,7 @@
|
|||||||
"failureRate": 0.95,
|
"failureRate": 0.95,
|
||||||
"framework": "unknown",
|
"framework": "unknown",
|
||||||
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
|
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
|
||||||
"lastTerminalAt": "2026-09-10T23:11:46.109095+00:00",
|
"lastTerminalAt": "2026-09-11T07:05:27.006934+00:00",
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 1,
|
"platformFailureCount": 1,
|
||||||
@@ -6936,19 +6936,19 @@
|
|||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"terminalRecords": 1646,
|
"terminalRecords": 1647,
|
||||||
"totalRecords": 1733,
|
"totalRecords": 1734,
|
||||||
"totals": {
|
"totals": {
|
||||||
"attributableFailureCount": 427,
|
"attributableFailureCount": 428,
|
||||||
"decisionFailureRate": 0.8896,
|
"decisionFailureRate": 0.8898,
|
||||||
"decisionSuccessRate": 0.1104,
|
"decisionSuccessRate": 0.1102,
|
||||||
"decisionTotal": 480,
|
"decisionTotal": 481,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 391,
|
"ambiguous_runtime": 391,
|
||||||
"backend_operator": 40,
|
"backend_operator": 40,
|
||||||
"framework_architecture_unsupported": 273,
|
"framework_architecture_unsupported": 273,
|
||||||
"memory_capacity": 11,
|
"memory_capacity": 11,
|
||||||
"model_load": 53,
|
"model_load": 54,
|
||||||
"platform_infrastructure": 4,
|
"platform_infrastructure": 4,
|
||||||
"repository_structure": 5,
|
"repository_structure": 5,
|
||||||
"runtime_memory": 6,
|
"runtime_memory": 6,
|
||||||
@@ -6956,30 +6956,31 @@
|
|||||||
"参数/模板问题": 98,
|
"参数/模板问题": 98,
|
||||||
"验证失败": 673
|
"验证失败": 673
|
||||||
},
|
},
|
||||||
"failureCount": 1593,
|
"failureCount": 1594,
|
||||||
"failureRate": 0.9678,
|
"failureRate": 0.9678,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 4,
|
"platformFailureCount": 4,
|
||||||
"successCount": 53,
|
"successCount": 53,
|
||||||
"successRate": 0.0322,
|
"successRate": 0.0322,
|
||||||
"total": 1646,
|
"total": 1647,
|
||||||
"unresolvedFailureCount": 1162
|
"unresolvedFailureCount": 1162
|
||||||
},
|
},
|
||||||
"warnings": [
|
"warnings": [
|
||||||
"GPU Ascend_910-b3 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 Vastai_va16 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 Iluvatar_mrv-100 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 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 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 Sunrise_pt-200-x1 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。",
|
"GPU MetaX_c-500 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 Biren_166m 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 hygon_k100-ai 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 Iluvatar_bi-150 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 Cambricon_mlu-370-x4 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 Ascend_910-b4 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 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-x4|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 Mthreads_s4000|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 Mthreads_s4000|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 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 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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||||
@@ -6994,11 +6995,10 @@
|
|||||||
"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 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 Iluvatar_bi-150|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 Iluvatar_bi-150|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 Vastai_va16|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 Vastai_va16|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 Cambricon_mlu-370-x4|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 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-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
"storageMode": "decision_state_only",
|
"storageMode": "decision_state_only",
|
||||||
"summarizedRecords": 1733,
|
"summarizedRecords": 1734,
|
||||||
"version": 1
|
"version": 1
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -1,3 +1,4 @@
|
|||||||
|
{"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": "2026-09-11T07:05:27.006934+00:00", "modelId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T06:57:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523318", "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": "2026-09-11T05:08:00.009961+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T05:05:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477832", "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": "2026-09-11T05:08:00.009961+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T05:05:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477832", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-11T03:33:48.898214+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T03:29:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497066", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-11T03:33:48.898214+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T03:29:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497066", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-11T03:25:05.807699+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T03:23:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497054", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-11T03:25:05.807699+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T03:23:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497054", "taskType": "text-generation", "verifyResult": -1}
|
||||||
@@ -297,4 +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": "2026-09-08T07:47:20.009326+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T07:39:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4478473", "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": "2026-09-08T07:47:20.009326+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T07:39:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4478473", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T07:22:29.130684+00:00", "modelId": "nightmedia/Mistral-Nemo-Instruct-2407-12B-Thinking-M-Claude-Opus-High-Reasoning-mxfp4-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T07:19:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079225", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T07:22:29.130684+00:00", "modelId": "nightmedia/Mistral-Nemo-Instruct-2407-12B-Thinking-M-Claude-Opus-High-Reasoning-mxfp4-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T07:19:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079225", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831495+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.934706+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712836", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831495+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.934706+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712836", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831446+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.928754+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712837", "taskType": "text-generation", "verifyResult": null}
|
|
||||||
|
|||||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -1,24 +1,24 @@
|
|||||||
{
|
{
|
||||||
"agentVersion": "2026.09.04.4",
|
"agentVersion": "2026.09.04.4",
|
||||||
"checksums": {
|
"checksums": {
|
||||||
".modelhub_state/architecture_compatibility_blacklist.json": "aead5ffeb442b7f10ee82f69905fe839d044d3116601bed01b6302663a212bbc",
|
".modelhub_state/architecture_compatibility_blacklist.json": "0bf0525e54e3afcb5b9e5f4c02b52381d0d87c79413bcad8e02c85e564ab7685",
|
||||||
".modelhub_state/architecture_history_backfill.json": "9ac9e22cddc55e5725c43a78371e78c0f4b075c097a27044b1c93d213dbb0b98",
|
".modelhub_state/architecture_history_backfill.json": "55ab1be9cff53981d8cd4c828c1b5846d60e1186b1974afb18d91e1496d197ff",
|
||||||
".modelhub_state/market_intelligence.json": "7cf460746457d41c49057b79c57c0fc653421d7850590659eb36b89c0429c17b",
|
".modelhub_state/market_intelligence.json": "dd7659892163de0ec6b4585d26249a31cde7a2f5452883f8ed51106cecc73d41",
|
||||||
".modelhub_state/official_capabilities.json": "b07c6c09eac3d00e39e232ca0402d61f21a690e9169f9fa30a766f2b0967c911",
|
".modelhub_state/official_capabilities.json": "9ec37e4f4accabbcbd5cbe4d7e360fa41a70dab70dff5c57d631ab30a1e65dd8",
|
||||||
".modelhub_state/outcome_checkpoint.json": "59f7925f7bc93a51dafff6540fd40899e0cd19560b646bc83bb5d2cb2c782be9",
|
".modelhub_state/outcome_checkpoint.json": "19ce09da372093a638920952e034c98e6eaad3a9bca9403076f195ec4bf9d432",
|
||||||
".modelhub_state/queue_cleanup_latest.json": "757bb52cd4c1e398d565b25c01e1a394e97727dc87500e4184be2784f229ae2a",
|
".modelhub_state/queue_cleanup_latest.json": "757bb52cd4c1e398d565b25c01e1a394e97727dc87500e4184be2784f229ae2a",
|
||||||
".modelhub_state/recent_outcomes.jsonl": "7c2662958c0ac747f257cd875beaae8d50ba1d8906059ef8dd0f40f93392eb0c",
|
".modelhub_state/recent_outcomes.jsonl": "796c6e8d248a155b5498d9b59bedef3eceb69eb00ed8abed3b55fdf67a8756b9",
|
||||||
".modelhub_state/recovery_active_tasks.jsonl": "4b1970d1836de4c8f08b3b193c0f350b26def4675d4d5a0f5281ff3d6508e3e8",
|
".modelhub_state/recovery_active_tasks.jsonl": "8c3e88f5d63fa1c9d3f0d0b85b1cb83345a77023b1e884269595e717a3306319",
|
||||||
".modelhub_state/recovery_intents.jsonl": "6c57b333da35bf7b90189d5a5e1e1e651959cad6ef325983ccb92047a5374e9c",
|
".modelhub_state/recovery_intents.jsonl": "ebff3ca0dd37bdfd2920e9dcc7f0d91213b1f85af395d76acf6de860aa2a69cc",
|
||||||
".modelhub_state/routing_intelligence.json": "a7d892e1ccda118f72a13ee212ed5aad3be9d65cdbf4c8218d696761745235b0",
|
".modelhub_state/routing_intelligence.json": "a7d892e1ccda118f72a13ee212ed5aad3be9d65cdbf4c8218d696761745235b0",
|
||||||
".modelhub_state/submission_exclusions.jsonl": "a07e1a02840754257cdff556f0bbb75a93364d6fc493705741531a86b71b768e",
|
".modelhub_state/submission_exclusions.jsonl": "a07e1a02840754257cdff556f0bbb75a93364d6fc493705741531a86b71b768e",
|
||||||
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
|
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
|
||||||
"ledger/submissions.jsonl": "369d50ba323fae299168a3afc0597ce8bc04a737b67af19154a569c0c08db4aa",
|
"ledger/submissions.jsonl": "369d50ba323fae299168a3afc0597ce8bc04a737b67af19154a569c0c08db4aa",
|
||||||
"outcomes/submissions.jsonl": "e73ee02e18c7cb77e8d2a8a683d96a85963b8bb5e720d1be855002e1480be466"
|
"outcomes/submissions.jsonl": "e73ee02e18c7cb77e8d2a8a683d96a85963b8bb5e720d1be855002e1480be466"
|
||||||
},
|
},
|
||||||
"generation": 5579,
|
"generation": 5580,
|
||||||
"phase": "cycle",
|
"phase": "cycle",
|
||||||
"schemaVersion": 1,
|
"schemaVersion": 1,
|
||||||
"updatedAt": "2026-09-11T07:04:26.373991+00:00",
|
"updatedAt": "2026-09-11T07:08:10.917497+00:00",
|
||||||
"writerId": "18252d8a8ef94333abd55823b2d81c42"
|
"writerId": "18252d8a8ef94333abd55823b2d81c42"
|
||||||
}
|
}
|
||||||
|
|||||||
Reference in New Issue
Block a user