state: generation 21783 (cycle)
This commit is contained in:
@@ -2606,27 +2606,6 @@
|
||||
"targetGpu": "Vastai_va16",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"vastai_va16|vllm|text-generation|architectures:gptneoforcausallm": {
|
||||
"architectureSignature": "architectures:gptneoforcausallm",
|
||||
"architectures": [
|
||||
"gptneoforcausallm"
|
||||
],
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-10-07T09:45:21+00:00",
|
||||
"framework": "vllm",
|
||||
"latestFailureAt": "2026-09-07T09:45:21+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "architectures",
|
||||
"modelType": null,
|
||||
"sourceModelIds": [
|
||||
"KoboldAI/GPT-Neo-2.7B-Janeway"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"4079146"
|
||||
],
|
||||
"targetGpu": "Vastai_va16",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"vastai_va16|vllm|text-generation|architectures:llavallamaforcausallm": {
|
||||
"architectureSignature": "architectures:llavallamaforcausallm",
|
||||
"architectures": [
|
||||
@@ -2836,9 +2815,9 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-07T09:37:05.051528+00:00",
|
||||
"generatedAt": "2026-10-07T09:53:21.538410+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 143,
|
||||
"activeBlockCount": 142,
|
||||
"byGpuFramework": {
|
||||
"Ascend_910-b3|vllm": 9,
|
||||
"Ascend_910-b3|vllm_tokenizer_patch": 7,
|
||||
@@ -2862,7 +2841,7 @@
|
||||
"Mthreads_s4000|vllm": 6,
|
||||
"Sunrise_pt-200-x1|vllm": 3,
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 4,
|
||||
"Vastai_va16|vllm": 12,
|
||||
"Vastai_va16|vllm": 11,
|
||||
"Vastai_va16|vllm_fix_tokenizer": 2,
|
||||
"hygon_k100-ai|vllm": 8,
|
||||
"hygon_k100-ai|vllm-patch-tokenizer": 4
|
||||
|
||||
@@ -434,121 +434,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-10-07T09:48:38.069449+00:00",
|
||||
"generatedAt": "2026-10-07T09:54:41.656922+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 1005.548780487805,
|
||||
"backlogHours": 1037.0566037735848,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.0445040272123471,
|
||||
"queueFactor": 1.0022639422411619,
|
||||
"queueWeight": 1.0022639422411619,
|
||||
"recentSuccess": 51,
|
||||
"recentSuccessRate": 0.31097560975609756,
|
||||
"recentTerminal": 164,
|
||||
"recentWilsonLowerBound": 0.2451381121786042,
|
||||
"running": 7,
|
||||
"selectionWeight": 1.046868724000617,
|
||||
"qualityFactor": 1.017558172125273,
|
||||
"queueFactor": 0.9981367712594166,
|
||||
"queueWeight": 0.9981367712594166,
|
||||
"recentSuccess": 48,
|
||||
"recentSuccessRate": 0.3018867924528302,
|
||||
"recentTerminal": 159,
|
||||
"recentWilsonLowerBound": 0.23589451878319367,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.0156622284937538,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 27.333333333333332,
|
||||
"waiting": 27485
|
||||
"throughputPerHour": 26.5,
|
||||
"waiting": 27482
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1268.5774647887324,
|
||||
"backlogHours": 1305.0434782608695,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.9679324035959381,
|
||||
"queueWeight": 0.9679324035959381,
|
||||
"recentSuccess": 63,
|
||||
"recentSuccessRate": 0.44366197183098594,
|
||||
"recentTerminal": 142,
|
||||
"recentWilsonLowerBound": 0.364499679538778,
|
||||
"running": 7,
|
||||
"selectionWeight": 2.419831008989845,
|
||||
"queueFactor": 0.9643100152802925,
|
||||
"queueWeight": 0.9643100152802925,
|
||||
"recentSuccess": 60,
|
||||
"recentSuccessRate": 0.43478260869565216,
|
||||
"recentTerminal": 138,
|
||||
"recentWilsonLowerBound": 0.3549471151477231,
|
||||
"running": 8,
|
||||
"selectionWeight": 2.410775038200731,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 23.666666666666668,
|
||||
"waiting": 30023
|
||||
"throughputPerHour": 23.0,
|
||||
"waiting": 30016
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 132.79591836734696,
|
||||
"backlogHours": 135.46875,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.26443705263165873,
|
||||
"qualityFactor": 0.29367512186355976,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 35,
|
||||
"recentSuccessRate": 0.17857142857142858,
|
||||
"recentTerminal": 196,
|
||||
"recentWilsonLowerBound": 0.13129088009696172,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.3437681684211564,
|
||||
"recentSuccessRate": 0.18229166666666666,
|
||||
"recentTerminal": 192,
|
||||
"recentWilsonLowerBound": 0.13409212213072985,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.38177765842262773,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 32.666666666666664,
|
||||
"waiting": 4338
|
||||
"throughputPerHour": 32.0,
|
||||
"waiting": 4335
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1369.6,
|
||||
"backlogHours": 1351.657894736842,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.23786361378953835,
|
||||
"queueFactor": 0.9568712714501738,
|
||||
"queueWeight": 0.9568712714501738,
|
||||
"qualityFactor": 0.24469146368413294,
|
||||
"queueFactor": 0.9592469050401333,
|
||||
"queueWeight": 0.9592469050401333,
|
||||
"recentSuccess": 15,
|
||||
"recentSuccessRate": 0.2,
|
||||
"recentTerminal": 75,
|
||||
"recentWilsonLowerBound": 0.12512038203120296,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.22760485855852866,
|
||||
"recentSuccessRate": 0.19736842105263158,
|
||||
"recentTerminal": 76,
|
||||
"recentWilsonLowerBound": 0.12341879212336242,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.2347195292287447,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.5,
|
||||
"waiting": 17120
|
||||
"throughputPerHour": 12.666666666666666,
|
||||
"waiting": 17121
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 461.1219512195122,
|
||||
"backlogHours": 468.694214876033,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.5530662588572335,
|
||||
"queueFactor": 1.126601197035025,
|
||||
"queueWeight": 1.126601197035025,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.25203252032520324,
|
||||
"recentTerminal": 123,
|
||||
"recentWilsonLowerBound": 0.18360980012600733,
|
||||
"qualityFactor": 0.6618560988702369,
|
||||
"queueFactor": 1.124415918899644,
|
||||
"queueWeight": 1.124415918899644,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.2644628099173554,
|
||||
"recentTerminal": 121,
|
||||
"recentWilsonLowerBound": 0.1940040187978015,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.6230851092682422,
|
||||
"selectionWeight": 0.7442015335905111,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 20.5,
|
||||
"waiting": 9453
|
||||
"throughputPerHour": 20.166666666666668,
|
||||
"waiting": 9452
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 46.80893300248139,
|
||||
"backlogHours": 44.93586698337292,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -557,197 +557,197 @@
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 13,
|
||||
"recentSuccessRate": 0.03225806451612903,
|
||||
"recentTerminal": 403,
|
||||
"recentWilsonLowerBound": 0.018946835349343365,
|
||||
"running": 12,
|
||||
"recentSuccess": 14,
|
||||
"recentSuccessRate": 0.0332541567695962,
|
||||
"recentTerminal": 421,
|
||||
"recentWilsonLowerBound": 0.019910173557583847,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 67.16666666666667,
|
||||
"waiting": 3144
|
||||
"throughputPerHour": 70.16666666666667,
|
||||
"waiting": 3153
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 195.84615384615384,
|
||||
"backlogHours": 174.3835616438356,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.35395336189694093,
|
||||
"queueFactor": 1.2810182613963137,
|
||||
"queueWeight": 1.2810182613963137,
|
||||
"recentSuccess": 39,
|
||||
"recentSuccessRate": 0.2,
|
||||
"recentTerminal": 195,
|
||||
"recentWilsonLowerBound": 0.14989626176513593,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.4534207202725995,
|
||||
"qualityFactor": 0.25221108845506984,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 37,
|
||||
"recentSuccessRate": 0.1689497716894977,
|
||||
"recentTerminal": 219,
|
||||
"recentWilsonLowerBound": 0.12512856219683152,
|
||||
"running": 5,
|
||||
"selectionWeight": 0.3278744149915908,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 32.5,
|
||||
"throughputPerHour": 36.5,
|
||||
"waiting": 6365
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 1636.1052631578948,
|
||||
"backlogHours": 1608.0,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.6336774410609467,
|
||||
"queueFactor": 0.931688836096815,
|
||||
"queueWeight": 0.931688836096815,
|
||||
"recentSuccess": 17,
|
||||
"recentSuccessRate": 0.2982456140350877,
|
||||
"recentTerminal": 57,
|
||||
"recentWilsonLowerBound": 0.19532392409243257,
|
||||
"qualityFactor": 0.7570153048131438,
|
||||
"queueFactor": 0.9345822270485478,
|
||||
"queueWeight": 0.9345822270485478,
|
||||
"recentSuccess": 18,
|
||||
"recentSuccessRate": 0.3103448275862069,
|
||||
"recentTerminal": 58,
|
||||
"recentWilsonLowerBound": 0.20621934414805676,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.5903901975228815,
|
||||
"selectionWeight": 0.7074930494821032,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 9.5,
|
||||
"waiting": 15543
|
||||
"throughputPerHour": 9.666666666666666,
|
||||
"waiting": 15544
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 404.82608695652175,
|
||||
"backlogHours": 401.9136690647482,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.15088693832642197,
|
||||
"queueFactor": 1.1488208375074558,
|
||||
"queueWeight": 1.1488208375074558,
|
||||
"qualityFactor": 0.1573869182913337,
|
||||
"queueFactor": 1.1506427567217319,
|
||||
"queueWeight": 1.1506427567217319,
|
||||
"recentSuccess": 21,
|
||||
"recentSuccessRate": 0.15217391304347827,
|
||||
"recentTerminal": 138,
|
||||
"recentWilsonLowerBound": 0.101736119387597,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.17334205885709592,
|
||||
"recentSuccessRate": 0.1510791366906475,
|
||||
"recentTerminal": 139,
|
||||
"recentWilsonLowerBound": 0.10098748819284317,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.18109611753467816,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 23.0,
|
||||
"throughputPerHour": 23.166666666666668,
|
||||
"waiting": 9311
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 681.1546391752577,
|
||||
"backlogHours": 688.0625,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.7269289141117421,
|
||||
"queueFactor": 1.062565522438012,
|
||||
"queueWeight": 1.062565522438012,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.28865979381443296,
|
||||
"recentTerminal": 97,
|
||||
"recentWilsonLowerBound": 0.20790125991766098,
|
||||
"running": 3,
|
||||
"selectionWeight": 0.77240960139844,
|
||||
"qualityFactor": 0.7160731979439665,
|
||||
"queueFactor": 1.0614908161951635,
|
||||
"queueWeight": 1.0614908161951635,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.28125,
|
||||
"recentTerminal": 96,
|
||||
"recentWilsonLowerBound": 0.20107282637501533,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.7601051233410219,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 16.166666666666668,
|
||||
"waiting": 11012
|
||||
"throughputPerHour": 16.0,
|
||||
"waiting": 11009
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 1921.941176470588,
|
||||
"backlogHours": 1950.44776119403,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.001582560737856,
|
||||
"queueFactor": 0.9094557312657439,
|
||||
"queueWeight": 0.9094557312657439,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.4411764705882353,
|
||||
"recentTerminal": 68,
|
||||
"recentWilsonLowerBound": 0.329460449863809,
|
||||
"qualityFactor": 2.004535585847546,
|
||||
"queueFactor": 0.9079047243428812,
|
||||
"queueWeight": 0.9079047243428812,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.43283582089552236,
|
||||
"recentTerminal": 67,
|
||||
"recentWilsonLowerBound": 0.32104123341736546,
|
||||
"running": 4,
|
||||
"selectionWeight": 1.820350731464607,
|
||||
"selectionWeight": 1.8199273285044122,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 11.333333333333334,
|
||||
"waiting": 21782
|
||||
"throughputPerHour": 11.166666666666666,
|
||||
"waiting": 21780
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 2008.7058823529412,
|
||||
"backlogHours": 1932.6792452830186,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.062412612828517296,
|
||||
"queueFactor": 0.9034520863876111,
|
||||
"queueWeight": 0.9034520863876111,
|
||||
"qualityFactor": 0.06067161018244557,
|
||||
"queueFactor": 0.9091519132705788,
|
||||
"queueWeight": 0.9091519132705788,
|
||||
"recentSuccess": 7,
|
||||
"recentSuccessRate": 0.13725490196078433,
|
||||
"recentTerminal": 51,
|
||||
"recentWilsonLowerBound": 0.06811015331542725,
|
||||
"running": 1,
|
||||
"selectionWeight": 0.05638680527682613,
|
||||
"recentSuccessRate": 0.1320754716981132,
|
||||
"recentTerminal": 53,
|
||||
"recentWilsonLowerBound": 0.0654777020068957,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.05515971047857712,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 8.5,
|
||||
"waiting": 17074
|
||||
"throughputPerHour": 8.833333333333334,
|
||||
"waiting": 17072
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 1349.842105263158,
|
||||
"backlogHours": 1465.5428571428572,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 0.9589592049209992,
|
||||
"queueWeight": 0.9589592049209992,
|
||||
"queueFactor": 0.9476776666377522,
|
||||
"queueWeight": 0.9476776666377522,
|
||||
"recentSuccess": 2,
|
||||
"recentSuccessRate": 0.02631578947368421,
|
||||
"recentTerminal": 76,
|
||||
"recentWilsonLowerBound": 0.00724650713060782,
|
||||
"recentSuccessRate": 0.02857142857142857,
|
||||
"recentTerminal": 70,
|
||||
"recentWilsonLowerBound": 0.007870446893806289,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.04794796024604996,
|
||||
"selectionWeight": 0.047383883331887616,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 12.666666666666666,
|
||||
"throughputPerHour": 11.666666666666666,
|
||||
"waiting": 17098
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 1036.0975609756097,
|
||||
"backlogHours": 1011.4285714285714,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.3469101253791057,
|
||||
"queueFactor": 0.9977746829557308,
|
||||
"queueWeight": 0.9977746829557308,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.21138211382113822,
|
||||
"recentTerminal": 123,
|
||||
"recentWilsonLowerBound": 0.1485330315397392,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.34613814036427004,
|
||||
"qualityFactor": 0.4653473855150459,
|
||||
"queueFactor": 1.0018902305172956,
|
||||
"queueWeight": 1.0018902305172956,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.23015873015873015,
|
||||
"recentTerminal": 126,
|
||||
"recentWilsonLowerBound": 0.16529948502667766,
|
||||
"running": 5,
|
||||
"selectionWeight": 0.4662269993442902,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 20.5,
|
||||
"throughputPerHour": 21.0,
|
||||
"waiting": 21240
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-10-07T09:43:22.567627+00:00",
|
||||
"queueAttemptedAt": "2026-10-07T09:54:41.656922+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-10-07T09:43:22.567627+00:00",
|
||||
"queueUpdatedAt": "2026-10-07T09:54:41.656922+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Cambricon_mlu-370-x4",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-10-07T08:25:52.297334+00:00",
|
||||
"lastSyncTime": "2026-10-07T08:25:52.062262+00:00",
|
||||
"generatedAt": "2026-10-07T09:53:21.435952+00:00",
|
||||
"lastSyncTime": "2026-10-07T09:53:21.160613+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2610,27 +2610,6 @@
|
||||
"targetGpu": "Vastai_va16",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"vastai_va16|vllm|text-generation|architectures:gptneoforcausallm": {
|
||||
"architectureSignature": "architectures:gptneoforcausallm",
|
||||
"architectures": [
|
||||
"gptneoforcausallm"
|
||||
],
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-10-07T09:45:21+00:00",
|
||||
"framework": "vllm",
|
||||
"latestFailureAt": "2026-09-07T09:45:21+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "architectures",
|
||||
"modelType": null,
|
||||
"sourceModelIds": [
|
||||
"KoboldAI/GPT-Neo-2.7B-Janeway"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"4079146"
|
||||
],
|
||||
"targetGpu": "Vastai_va16",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"vastai_va16|vllm|text-generation|architectures:llavallamaforcausallm": {
|
||||
"architectureSignature": "architectures:llavallamaforcausallm",
|
||||
"architectures": [
|
||||
@@ -2841,7 +2820,7 @@
|
||||
}
|
||||
},
|
||||
"architectureCompatibilitySummary": {
|
||||
"activeBlockCount": 143,
|
||||
"activeBlockCount": 142,
|
||||
"byGpuFramework": {
|
||||
"Ascend_910-b3|vllm": 9,
|
||||
"Ascend_910-b3|vllm_tokenizer_patch": 7,
|
||||
@@ -2865,7 +2844,7 @@
|
||||
"Mthreads_s4000|vllm": 6,
|
||||
"Sunrise_pt-200-x1|vllm": 3,
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 4,
|
||||
"Vastai_va16|vllm": 12,
|
||||
"Vastai_va16|vllm": 11,
|
||||
"Vastai_va16|vllm_fix_tokenizer": 2,
|
||||
"hygon_k100-ai|vllm": 8,
|
||||
"hygon_k100-ai|vllm-patch-tokenizer": 4
|
||||
@@ -4142,10 +4121,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 9,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 47,
|
||||
"ambiguous_runtime": 48,
|
||||
"memory_capacity": 9
|
||||
},
|
||||
"failureCount": 56,
|
||||
"failureCount": 57,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
@@ -4155,8 +4134,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 56,
|
||||
"unresolvedFailureCount": 47
|
||||
"total": 57,
|
||||
"unresolvedFailureCount": 48
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 10,
|
||||
@@ -5691,7 +5670,7 @@
|
||||
"decisionSuccessRate": 0.0281,
|
||||
"decisionTotal": 178,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 364,
|
||||
"ambiguous_runtime": 365,
|
||||
"backend_operator": 9,
|
||||
"framework_architecture_unsupported": 47,
|
||||
"memory_capacity": 10,
|
||||
@@ -5700,15 +5679,15 @@
|
||||
"tokenizer_compatibility": 95,
|
||||
"参数/模板问题": 13
|
||||
},
|
||||
"failureCount": 575,
|
||||
"failureCount": 576,
|
||||
"failureRate": 0.9914,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 25,
|
||||
"successCount": 5,
|
||||
"successRate": 0.0086,
|
||||
"total": 580,
|
||||
"unresolvedFailureCount": 377
|
||||
"total": 581,
|
||||
"unresolvedFailureCount": 378
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 153,
|
||||
@@ -5739,7 +5718,7 @@
|
||||
"unresolvedFailureCount": 237
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-07T08:25:52.279800+00:00",
|
||||
"generatedAt": "2026-10-07T09:53:21.417055+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 119,
|
||||
@@ -5909,7 +5888,7 @@
|
||||
"decisionSuccessRate": 0.1639,
|
||||
"decisionTotal": 915,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 660,
|
||||
"ambiguous_runtime": 661,
|
||||
"architecture_compatibility": 15,
|
||||
"backend_operator": 12,
|
||||
"context_length": 29,
|
||||
@@ -5924,15 +5903,15 @@
|
||||
"日志缺失": 155,
|
||||
"验证失败": 30
|
||||
},
|
||||
"failureCount": 1952,
|
||||
"failureRate": 0.9286,
|
||||
"failureCount": 1953,
|
||||
"failureRate": 0.9287,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 21,
|
||||
"successCount": 150,
|
||||
"successRate": 0.0714,
|
||||
"total": 2102,
|
||||
"unresolvedFailureCount": 1166
|
||||
"successRate": 0.0713,
|
||||
"total": 2103,
|
||||
"unresolvedFailureCount": 1167
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"attributableFailureCount": 984,
|
||||
@@ -16846,9 +16825,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 6,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"memory_capacity": 6
|
||||
},
|
||||
"failureCount": 6,
|
||||
"failureCount": 7,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "qwen3_5",
|
||||
@@ -16860,8 +16840,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 6,
|
||||
"unresolvedFailureCount": 0
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|spark2_5|fp8": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -25230,9 +25210,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"参数/模板问题": 2
|
||||
"参数/模板问题": 1
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -25244,8 +25224,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -25590,14 +25570,14 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 14,
|
||||
"ambiguous_runtime": 15,
|
||||
"memory_capacity": 2
|
||||
},
|
||||
"failureCount": 16,
|
||||
"failureCount": 17,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-22T02:26:33.565797+00:00",
|
||||
"lastTerminalAt": "2026-10-07T09:53:21.160613+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -25605,8 +25585,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 16,
|
||||
"unresolvedFailureCount": 14
|
||||
"total": 17,
|
||||
"unresolvedFailureCount": 15
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 7,
|
||||
@@ -27788,12 +27768,13 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"memory_capacity": 2
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastTerminalAt": "2026-09-22T02:26:33.565797+00:00",
|
||||
"lastTerminalAt": "2026-10-07T09:53:21.160613+00:00",
|
||||
"modelType": "qwen3_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
@@ -27803,8 +27784,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -45877,9 +45858,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"memory_capacity": 3
|
||||
},
|
||||
"failureCount": 3,
|
||||
"failureCount": 4,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 34,
|
||||
@@ -45892,8 +45874,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 0
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|spark2_5|fp8|32": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -58397,15 +58379,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17362,
|
||||
"totalRecords": 17619,
|
||||
"terminalRecords": 17363,
|
||||
"totalRecords": 17620,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6244,
|
||||
"decisionFailureRate": 0.8646,
|
||||
"decisionSuccessRate": 0.1354,
|
||||
"decisionTotal": 7222,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4560,
|
||||
"ambiguous_runtime": 4561,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 129,
|
||||
@@ -58421,15 +58403,15 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16384,
|
||||
"failureCount": 16385,
|
||||
"failureRate": 0.9437,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 952,
|
||||
"successCount": 978,
|
||||
"successRate": 0.0563,
|
||||
"total": 17362,
|
||||
"unresolvedFailureCount": 9188
|
||||
"total": 17363,
|
||||
"unresolvedFailureCount": 9189
|
||||
},
|
||||
"warnings": [
|
||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
@@ -58438,14 +58420,14 @@
|
||||
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b3 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_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Kunlunxin_p-800 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 Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-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 Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"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 Ascend_910-b3|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_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -58490,6 +58472,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17619,
|
||||
"summarizedRecords": 17620,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -62,6 +62,7 @@
|
||||
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-22T01:23:49.082807+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:23:32+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4881076", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-22T01:23:49.082789+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:23:31+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4925021", "taskType": "text-generation", "verifyResult": null}
|
||||
{"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": "vllm-customized", "lastSyncTime": "2026-09-25T01:41:30.953868+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"ambiguous_runtime": 4, "model_load": 1}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T19:49:37.657075+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 4}, "repositoryOnDiskBytes": 955857175}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:49:53.770533+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006460", "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_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T09:53:21.160613+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 3, "consecutiveFailures": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": {"memory_capacity": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-20T12:21:49.901832+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 19329296879}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:21:51.849661+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5006201", "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": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-23T23:59:25.752461+00:00", "modelId": "nm-testing/Qwen2-1.5B-Instruct-FP8W8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2245332464, "estimatedRequiredGiB": 2.522, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 2256814377, "modelscopeLicense": null, "modelscopeParams": 1777088000, "modelscopeTags": ["model_type:qwen2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2256814377}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:50:52.437033+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005783", "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": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-23T19:08:31.650327+00:00", "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1047023664, "estimatedRequiredGiB": 1.172, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1048871402, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1048871402}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:50:52.306184+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005756", "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": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-22T04:16:12.463726+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788663591}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:32:49.780633+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005549", "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": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-22T20:46:09.364297+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21561882284, "estimatedRequiredGiB": 24.122, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 21583784354, "modelscopeLicense": "other", "modelscopeParams": 17820210764, "modelscopeTags": ["license:other", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21583784354}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T04:55:59.067045+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4994201", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-23T10:44:10.250908+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124576, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124576}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T04:55:59.065763+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4994202", "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", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-22T16:03:02.581809+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8239718268, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8239718268}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T04:55:59.063595+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4994203", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164989+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:49:27+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4895729", "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
Reference in New Issue
Block a user