state: generation 11676 (intent)

This commit is contained in:
2026-09-21 19:57:32 +00:00
parent f97efea204
commit 4a115df36a
9 changed files with 376 additions and 292 deletions

View File

@@ -1199,6 +1199,25 @@
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation"
},
"cambricon_mlu-370-x8|vllm|text-generation|model_type:qwen3_vl": {
"architectureSignature": "model_type:qwen3_vl",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-20T03:58:35.455197+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-20T03:58:35.455197+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_vl",
"sourceModelIds": [
"BAAI/RoboBrain2.5-8B-MT"
],
"sourceTaskIds": [
"4970358"
],
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation"
},
"cambricon_mlu-370-x8|vllm|text-generation|model_type:zaya": {
"architectureSignature": "model_type:zaya",
"architectures": [],
@@ -2768,9 +2787,9 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-21T19:54:03.658008+00:00",
"generatedAt": "2026-09-21T19:57:12.255712+00:00",
"summary": {
"activeBlockCount": 139,
"activeBlockCount": 140,
"byGpuFramework": {
"Ascend_910-b3|vllm": 13,
"Ascend_910-b3|vllm_tokenizer_patch": 5,
@@ -2778,7 +2797,7 @@
"Ascend_910-b4|vllm_tokenizer_patch": 5,
"Biren_166m|vllm": 3,
"Cambricon_mlu-370-x4|vllm": 2,
"Cambricon_mlu-370-x8|vllm": 14,
"Cambricon_mlu-370-x8|vllm": 15,
"Cambricon_mlu-370-x8|vllm-customized": 2,
"Cambricon_mlu-370-x8|vllm-mlu": 5,
"Iluvatar_bi-150|transformers": 4,

View File

@@ -434,121 +434,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-21T19:56:10.169860+00:00",
"generatedAt": "2026-09-21T19:57:30.800910+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 929.2105263157895,
"backlogHours": 923.0980392156863,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.1979361109181033,
"queueFactor": 0.9259023881211839,
"queueWeight": 0.9259023881211839,
"recentSuccess": 49,
"recentSuccessRate": 0.3223684210526316,
"recentTerminal": 152,
"recentWilsonLowerBound": 0.2532349895684616,
"qualityFactor": 1.5553566454179326,
"queueFactor": 0.9270529210260141,
"queueWeight": 0.9270529210260141,
"recentSuccess": 50,
"recentSuccessRate": 0.32679738562091504,
"recentTerminal": 153,
"recentWilsonLowerBound": 0.25751021482630554,
"running": 8,
"selectionWeight": 1.1091719059156753,
"selectionWeight": 1.441897921371917,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 25.333333333333332,
"waiting": 23540
"throughputPerHour": 25.5,
"waiting": 23539
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1147.7432432432431,
"backlogHours": 1117.8157894736842,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.082389778474143,
"queueFactor": 0.8970271970857644,
"queueWeight": 0.8970271970857644,
"recentSuccess": 46,
"recentSuccessRate": 0.3108108108108108,
"recentTerminal": 148,
"recentWilsonLowerBound": 0.24182488869231053,
"qualityFactor": 1.346809979880656,
"queueFactor": 0.9008161525985883,
"queueWeight": 0.9008161525985883,
"recentSuccess": 47,
"recentSuccessRate": 0.3092105263157895,
"recentTerminal": 152,
"recentWilsonLowerBound": 0.24119850644698562,
"running": 8,
"selectionWeight": 0.970933069138942,
"selectionWeight": 1.2132281843574746,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 24.666666666666668,
"waiting": 28311
"throughputPerHour": 25.333333333333332,
"waiting": 28318
},
"Biren_166m": {
"available": true,
"backlogHours": 165.68478260869566,
"backlogHours": 164.82162162162163,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.10780943019103657,
"queueFactor": 1.1991953312870915,
"queueWeight": 1.1991953312870915,
"recentSuccess": 23,
"recentSuccessRate": 0.125,
"recentTerminal": 184,
"recentWilsonLowerBound": 0.084756023564723,
"qualityFactor": 0.11835048942061369,
"queueFactor": 1.2004375547181838,
"queueWeight": 1.2004375547181838,
"recentSuccess": 22,
"recentSuccessRate": 0.11891891891891893,
"recentTerminal": 185,
"recentWilsonLowerBound": 0.07985694179220525,
"running": 8,
"selectionWeight": 0.12928456535381266,
"selectionWeight": 0.14207237211978177,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 30.666666666666668,
"waiting": 5081
"throughputPerHour": 30.833333333333332,
"waiting": 5082
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 496.25274725274727,
"backlogHours": 496.31868131868134,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.05,
"queueFactor": 1.0172480916302264,
"queueWeight": 1.0172480916302264,
"queueFactor": 1.017484044376508,
"queueWeight": 1.017484044376508,
"recentSuccess": 14,
"recentSuccessRate": 0.07692307692307693,
"recentTerminal": 182,
"recentWilsonLowerBound": 0.0463713966696411,
"running": 7,
"selectionWeight": 0.050862404581511325,
"selectionWeight": 0.05087420221882541,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 30.333333333333332,
"waiting": 15053
"waiting": 15055
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 387.8450704225352,
"backlogHours": 369.94630872483225,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.21619746699449016,
"queueFactor": 1.055561595771937,
"queueWeight": 1.055561595771937,
"recentSuccess": 24,
"recentSuccessRate": 0.16901408450704225,
"recentTerminal": 142,
"recentWilsonLowerBound": 0.11628706631227818,
"qualityFactor": 0.2706579774314779,
"queueFactor": 1.0633369272014068,
"queueWeight": 1.0633369272014068,
"recentSuccess": 25,
"recentSuccessRate": 0.16778523489932887,
"recentTerminal": 149,
"recentWilsonLowerBound": 0.11630770351545354,
"running": 7,
"selectionWeight": 0.22820974326255475,
"selectionWeight": 0.28780062204453544,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 23.666666666666668,
"waiting": 9179
"throughputPerHour": 24.833333333333332,
"waiting": 9187
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 38.66489361702128,
"backlogHours": 38.67914438502674,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -558,129 +558,129 @@
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 21,
"recentSuccessRate": 0.05585106382978723,
"recentTerminal": 376,
"recentWilsonLowerBound": 0.03681667599288761,
"running": 24,
"recentSuccessRate": 0.05614973262032086,
"recentTerminal": 374,
"recentWilsonLowerBound": 0.037015123146307144,
"running": 26,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 62.666666666666664,
"waiting": 2423
"throughputPerHour": 62.333333333333336,
"waiting": 2411
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 111.1245283018868,
"backlogHours": 112.23664122137406,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.13312808001661144,
"queueFactor": 1.273241638527949,
"queueWeight": 1.273241638527949,
"recentSuccess": 34,
"recentSuccessRate": 0.12830188679245283,
"recentTerminal": 265,
"recentWilsonLowerBound": 0.0932852132110488,
"running": 7,
"selectionWeight": 0.16950421473443025,
"qualityFactor": 0.1842073881825004,
"queueFactor": 1.2716614373863284,
"queueWeight": 1.2716614373863284,
"recentSuccess": 35,
"recentSuccessRate": 0.13358778625954199,
"recentTerminal": 262,
"recentWilsonLowerBound": 0.09764447356554912,
"running": 5,
"selectionWeight": 0.23424943203333984,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 44.166666666666664,
"waiting": 4908
"throughputPerHour": 43.666666666666664,
"waiting": 4901
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 729.6818181818181,
"backlogHours": 740.9076923076923,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.05,
"queueFactor": 0.9600907680361976,
"queueWeight": 0.9600907680361976,
"recentSuccess": 12,
"recentSuccessRate": 0.09090909090909091,
"recentTerminal": 132,
"recentWilsonLowerBound": 0.05276868798185061,
"running": 2,
"selectionWeight": 0.04800453840180988,
"queueFactor": 0.9581358392935574,
"queueWeight": 0.9581358392935574,
"recentSuccess": 11,
"recentSuccessRate": 0.08461538461538462,
"recentTerminal": 130,
"recentWilsonLowerBound": 0.047903387035414836,
"running": 3,
"selectionWeight": 0.04790679196467787,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.0,
"submissionEligible": false,
"throughputPerHour": 21.666666666666668,
"waiting": 16053
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 477.0676691729323,
"backlogHours": 469.8666666666667,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.27950214533336765,
"queueFactor": 1.0232819760005352,
"queueWeight": 1.0232819760005352,
"recentSuccess": 25,
"recentSuccessRate": 0.18796992481203006,
"recentTerminal": 133,
"recentWilsonLowerBound": 0.13068596058578308,
"qualityFactor": 0.3032425396874696,
"queueFactor": 1.0258775016243378,
"queueWeight": 1.0258775016243378,
"recentSuccess": 24,
"recentSuccessRate": 0.17777777777777778,
"recentTerminal": 135,
"recentWilsonLowerBound": 0.12247545696005419,
"running": 8,
"selectionWeight": 0.2860095075731172,
"selectionWeight": 0.3110896990008004,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.166666666666668,
"waiting": 10575
"throughputPerHour": 22.5,
"waiting": 10572
},
"MetaX_c-500": {
"available": true,
"backlogHours": 608.9719626168225,
"backlogHours": 597.4678899082569,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.508607241126908,
"queueFactor": 0.9864900920111269,
"queueWeight": 0.9864900920111269,
"recentSuccess": 26,
"recentSuccessRate": 0.24299065420560748,
"recentTerminal": 107,
"recentWilsonLowerBound": 0.17155744423820674,
"qualityFactor": 0.7435278304250804,
"queueFactor": 0.9895654310354465,
"queueWeight": 0.9895654310354465,
"recentSuccess": 28,
"recentSuccessRate": 0.25688073394495414,
"recentTerminal": 109,
"recentWilsonLowerBound": 0.18411863732206865,
"running": 4,
"selectionWeight": 0.501736004096809,
"selectionWeight": 0.735769438001445,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.833333333333332,
"waiting": 10860
"throughputPerHour": 18.166666666666668,
"waiting": 10854
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 2574.3529411764707,
"backlogHours": 2680.2857142857147,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 2.041547163943165,
"queueFactor": 0.7946613837998101,
"queueWeight": 0.7946613837998101,
"recentSuccess": 23,
"recentSuccessRate": 0.45098039215686275,
"recentTerminal": 51,
"recentWilsonLowerBound": 0.3226730501113224,
"qualityFactor": 2.4831426856003276,
"queueFactor": 0.7900681185897798,
"queueWeight": 0.7900681185897798,
"recentSuccess": 22,
"recentSuccessRate": 0.4489795918367347,
"recentTerminal": 49,
"recentWilsonLowerBound": 0.31852624929636336,
"running": 4,
"selectionWeight": 1.6223386943916531,
"selectionWeight": 1.9618518698022238,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 8.5,
"waiting": 21882
"throughputPerHour": 8.166666666666666,
"waiting": 21889
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 8617.09090909091,
"backlogHours": 7899.0,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
@@ -690,64 +690,64 @@
"queueFactor": 0.7,
"queueWeight": 0.7,
"recentSuccess": 7,
"recentSuccessRate": 0.6363636363636364,
"recentTerminal": 11,
"recentWilsonLowerBound": 0.35379677689163724,
"recentSuccessRate": 0.5833333333333334,
"recentTerminal": 12,
"recentWilsonLowerBound": 0.3195073356553728,
"running": 2,
"selectionWeight": 1.75,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 1.8333333333333333,
"throughputPerHour": 2.0,
"waiting": 15798
},
"Vastai_va16": {
"available": true,
"backlogHours": 511.2352941176471,
"backlogHours": 520.5628742514971,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.05,
"queueFactor": 1.0127195598592438,
"queueWeight": 1.0127195598592438,
"queueFactor": 1.010231072131324,
"queueWeight": 1.010231072131324,
"recentSuccess": 9,
"recentSuccessRate": 0.052941176470588235,
"recentTerminal": 170,
"recentWilsonLowerBound": 0.028099063443071427,
"recentSuccessRate": 0.05389221556886228,
"recentTerminal": 167,
"recentWilsonLowerBound": 0.02860843346782246,
"running": 16,
"selectionWeight": 0.05063597799296219,
"selectionWeight": 0.0505115536065662,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 28.333333333333332,
"waiting": 14485
"throughputPerHour": 27.833333333333332,
"waiting": 14489
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 601.125,
"backlogHours": 593.6666666666666,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 0.0761241074866858,
"queueFactor": 0.9884110770796999,
"queueWeight": 0.9884110770796999,
"recentSuccess": 18,
"recentSuccessRate": 0.1125,
"recentTerminal": 160,
"recentWilsonLowerBound": 0.07235575112573997,
"qualityFactor": 0.10731637073610716,
"queueFactor": 0.9905132768694215,
"queueWeight": 0.9905132768694215,
"recentSuccess": 19,
"recentSuccessRate": 0.11728395061728394,
"recentTerminal": 162,
"recentWilsonLowerBound": 0.07638228346042165,
"running": 6,
"selectionWeight": 0.07524191107264595,
"selectionWeight": 0.10629829003955518,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 26.666666666666668,
"waiting": 16030
"throughputPerHour": 27.0,
"waiting": 16029
}
},
"queueAttemptedAt": "2026-09-21T19:47:15.264791+00:00",
"queueAttemptedAt": "2026-09-21T19:57:30.800910+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-21T19:47:15.264791+00:00",
"queueUpdatedAt": "2026-09-21T19:57:30.800910+00:00",
"supportedGpus": [
"Vastai_va16",
"Kunlunxin_p-800",

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-09-21T19:56:10.169860+00:00",
"catalogUpdatedAt": "2026-09-21T19:57:30.800910+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-09-21T19:56:10.169860+00:00",
"generatedAt": "2026-09-21T19:57:30.800910+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6886,6 +6886,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-09-21T19:56:10.169860+00:00",
"taskTreeUpdatedAt": "2026-09-21T19:57:30.800910+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T19:52:34.453108+00:00",
"lastSyncTime": "2026-09-21T19:52:34.157602+00:00",
"generatedAt": "2026-09-21T19:57:12.166601+00:00",
"lastSyncTime": "2026-09-21T19:57:11.769139+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1203,6 +1203,25 @@
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation"
},
"cambricon_mlu-370-x8|vllm|text-generation|model_type:qwen3_vl": {
"architectureSignature": "model_type:qwen3_vl",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-20T03:58:35.455197+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-20T03:58:35.455197+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_vl",
"sourceModelIds": [
"BAAI/RoboBrain2.5-8B-MT"
],
"sourceTaskIds": [
"4970358"
],
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation"
},
"cambricon_mlu-370-x8|vllm|text-generation|model_type:zaya": {
"architectureSignature": "model_type:zaya",
"architectures": [],
@@ -2773,7 +2792,7 @@
}
},
"architectureCompatibilitySummary": {
"activeBlockCount": 139,
"activeBlockCount": 140,
"byGpuFramework": {
"Ascend_910-b3|vllm": 13,
"Ascend_910-b3|vllm_tokenizer_patch": 5,
@@ -2781,7 +2800,7 @@
"Ascend_910-b4|vllm_tokenizer_patch": 5,
"Biren_166m|vllm": 3,
"Cambricon_mlu-370-x4|vllm": 2,
"Cambricon_mlu-370-x8|vllm": 14,
"Cambricon_mlu-370-x8|vllm": 15,
"Cambricon_mlu-370-x8|vllm-customized": 2,
"Cambricon_mlu-370-x8|vllm-mlu": 5,
"Iluvatar_bi-150|transformers": 4,
@@ -3077,13 +3096,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 24,
"failureBreakdown": {
"ambiguous_runtime": 45,
"ambiguous_runtime": 46,
"framework_architecture_unsupported": 23,
"platform_infrastructure": 1,
"repository_structure": 1,
"参数/模板问题": 6
},
"failureCount": 76,
"failureCount": 77,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
@@ -3093,8 +3112,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 76,
"unresolvedFailureCount": 51
"total": 77,
"unresolvedFailureCount": 52
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 204,
@@ -3446,37 +3465,37 @@
"decisionSuccessRate": 0.48,
"decisionTotal": 25,
"failureBreakdown": {
"ambiguous_runtime": 39,
"ambiguous_runtime": 40,
"framework_architecture_unsupported": 11,
"model_load": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 55,
"failureRate": 0.8209,
"failureCount": 56,
"failureRate": 0.8235,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 12,
"successRate": 0.1791,
"successRate": 0.1765,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 67,
"unresolvedFailureCount": 42
"total": 68,
"unresolvedFailureCount": 43
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 19,
"attributableFailureCount": 20,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 19,
"decisionTotal": 20,
"failureBreakdown": {
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 18,
"framework_architecture_unsupported": 19,
"memory_capacity": 1,
"参数/模板问题": 12
},
"failureCount": 50,
"failureCount": 51,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -3486,7 +3505,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 50,
"total": 51,
"unresolvedFailureCount": 31
},
"Iluvatar_bi-100|transformers|text-generation": {
@@ -5421,17 +5440,17 @@
"unresolvedFailureCount": 6446
},
"vllm": {
"attributableFailureCount": 3542,
"attributableFailureCount": 3543,
"decisionFailureRate": 0.9758,
"decisionSuccessRate": 0.0242,
"decisionTotal": 3630,
"decisionTotal": 3631,
"failureBreakdown": {
"ambiguous_runtime": 1497,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
"context_length": 161,
"framework_architecture_unsupported": 1309,
"framework_architecture_unsupported": 1310,
"memory_capacity": 722,
"model_load": 207,
"platform_infrastructure": 865,
@@ -5440,14 +5459,14 @@
"tokenizer_compatibility": 412,
"参数/模板问题": 46
},
"failureCount": 5950,
"failureCount": 5951,
"failureRate": 0.9854,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 865,
"successCount": 88,
"successRate": 0.0146,
"total": 6038,
"total": 6039,
"unresolvedFailureCount": 1543
},
"vllm-customized": {
@@ -5477,22 +5496,22 @@
"decisionSuccessRate": 0.4878,
"decisionTotal": 41,
"failureBreakdown": {
"ambiguous_runtime": 58,
"ambiguous_runtime": 59,
"framework_architecture_unsupported": 18,
"model_load": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 3,
"验证失败": 1
},
"failureCount": 83,
"failureRate": 0.8058,
"failureCount": 84,
"failureRate": 0.8077,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 20,
"successRate": 0.1942,
"total": 103,
"unresolvedFailureCount": 62
"successRate": 0.1923,
"total": 104,
"unresolvedFailureCount": 63
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 31,
@@ -5572,7 +5591,7 @@
"decisionSuccessRate": 0.0263,
"decisionTotal": 76,
"failureBreakdown": {
"ambiguous_runtime": 80,
"ambiguous_runtime": 81,
"backend_operator": 1,
"context_length": 3,
"framework_architecture_unsupported": 63,
@@ -5583,18 +5602,18 @@
"tokenizer_compatibility": 1,
"参数/模板问题": 27
},
"failureCount": 182,
"failureRate": 0.9891,
"failureCount": 183,
"failureRate": 0.9892,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 2,
"successRate": 0.0109,
"total": 184,
"unresolvedFailureCount": 107
"successRate": 0.0108,
"total": 185,
"unresolvedFailureCount": 108
}
},
"generatedAt": "2026-09-21T19:52:34.442165+00:00",
"generatedAt": "2026-09-21T19:57:12.116575+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 99,
@@ -5628,7 +5647,7 @@
"decisionSuccessRate": 0.1636,
"decisionTotal": 385,
"failureBreakdown": {
"ambiguous_runtime": 181,
"ambiguous_runtime": 182,
"context_length": 1,
"framework_architecture_unsupported": 178,
"memory_capacity": 19,
@@ -5640,15 +5659,15 @@
"日志缺失": 14,
"验证失败": 175
},
"failureCount": 962,
"failureRate": 0.9385,
"failureCount": 963,
"failureRate": 0.9386,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 63,
"successRate": 0.0615,
"total": 1025,
"unresolvedFailureCount": 638
"successRate": 0.0614,
"total": 1026,
"unresolvedFailureCount": 639
},
"Biren_166m": {
"attributableFailureCount": 186,
@@ -5710,28 +5729,28 @@
"unresolvedFailureCount": 774
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 50,
"decisionFailureRate": 0.7812,
"decisionSuccessRate": 0.2188,
"decisionTotal": 64,
"attributableFailureCount": 51,
"decisionFailureRate": 0.7846,
"decisionSuccessRate": 0.2154,
"decisionTotal": 65,
"failureBreakdown": {
"ambiguous_runtime": 108,
"framework_architecture_unsupported": 41,
"ambiguous_runtime": 109,
"framework_architecture_unsupported": 42,
"memory_capacity": 4,
"model_load": 3,
"tokenizer_compatibility": 2,
"参数/模板问题": 34,
"验证失败": 22
},
"failureCount": 214,
"failureRate": 0.9386,
"failureCount": 216,
"failureRate": 0.9391,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 14,
"successRate": 0.0614,
"total": 228,
"unresolvedFailureCount": 164
"successRate": 0.0609,
"total": 230,
"unresolvedFailureCount": 165
},
"Iluvatar_bi-100": {
"attributableFailureCount": 194,
@@ -7460,10 +7479,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2,
"ambiguous_runtime": 3,
"platform_infrastructure": 1
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "qwen2",
@@ -7475,8 +7494,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 2
"total": 4,
"unresolvedFailureCount": 3
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_moe|compressed-tensors": {
"attributableFailureCount": 3,
@@ -9877,9 +9896,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "lfm2",
@@ -9891,8 +9910,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|awq": {
"attributableFailureCount": 0,
@@ -10884,6 +10903,29 @@
"total": 2,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm|text-generation|qwen3_vl|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_vl",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm|text-generation|qwen3|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -17463,12 +17505,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 8,
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 1,
"model_load": 4,
"tokenizer_compatibility": 1
},
"failureCount": 14,
"failureCount": 13,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -17480,8 +17522,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 14,
"unresolvedFailureCount": 8
"total": 13,
"unresolvedFailureCount": 7
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -17569,9 +17611,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 6
"ambiguous_runtime": 7
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastPlatformFailureAt": null,
@@ -17583,8 +17625,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 6
"total": 7,
"unresolvedFailureCount": 7
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 6,
@@ -18640,9 +18682,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-21T05:07:16.468545+00:00",
@@ -18655,8 +18697,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm|text-generation|lfm2|none": {
"attributableFailureCount": 2,
@@ -19019,12 +19061,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-21T08:44:09.587559+00:00",
"lastTerminalAt": "2026-09-21T19:57:11.769116+00:00",
"modelType": "lfm2",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -19034,8 +19076,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|phi3|compressed-tensors": {
"attributableFailureCount": 0,
@@ -19487,6 +19529,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm|text-generation|qwen3_vl|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-21T19:57:11.769130+00:00",
"modelType": "qwen3_vl",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm|text-generation|qwen3|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -19962,31 +20029,6 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|transformers|text-generation|mpt|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "transformers",
"lastTerminalAt": "2026-09-20T14:14:39.678925+00:00",
"modelType": "mpt",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|transformers|text-generation|nemotron_h|compressed-tensors": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -23497,9 +23539,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 29,
@@ -23512,8 +23554,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen2|compressed-tensors|31": {
"attributableFailureCount": 0,
@@ -26943,9 +26985,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 29,
@@ -26958,8 +27000,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|awq|30": {
"attributableFailureCount": 0,
@@ -28373,6 +28415,30 @@
"total": 2,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm|text-generation|qwen3_vl|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_vl",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm|text-generation|qwen3|none|29": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -37637,20 +37703,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16388,
"totalRecords": 16582,
"terminalRecords": 16391,
"totalRecords": 16585,
"totals": {
"attributableFailureCount": 5909,
"attributableFailureCount": 5910,
"decisionFailureRate": 0.862,
"decisionSuccessRate": 0.138,
"decisionTotal": 6855,
"decisionTotal": 6856,
"failureBreakdown": {
"ambiguous_runtime": 4024,
"ambiguous_runtime": 4026,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 104,
"context_length": 321,
"framework_architecture_unsupported": 2087,
"framework_architecture_unsupported": 2088,
"memory_capacity": 1199,
"model_load": 499,
"platform_infrastructure": 925,
@@ -37661,31 +37727,31 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15442,
"failureCount": 15445,
"failureRate": 0.9423,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 946,
"successRate": 0.0577,
"total": 16388,
"unresolvedFailureCount": 8608
"total": 16391,
"unresolvedFailureCount": 8610
},
"warnings": [
"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。",
"GPU Cambricon_mlu-370-x8 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 MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-100 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-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 Cambricon_mlu-370-x4 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-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 Ascend_910-b4 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 Vastai_va16 本地统计失败率偏高≥50%),建议重点关注。",
"组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Sunrise_pt-200-x1|vllm_fix_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 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -37725,6 +37791,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16582,
"summarizedRecords": 16585,
"version": 1
}

View File

@@ -14,13 +14,13 @@
100
],
"accounts": 12,
"activeScanned": 1163,
"activeScanned": 1198,
"ageCleanupMode": "admission_only",
"agePolicySkipped": {
"cleanupDisabled": true,
"reason": "admission_only"
},
"architectureBlockCount": 139,
"architectureBlockCount": 140,
"architectureFrameworkCatalog": {
"ascend_910-b3|text-generation": [
"llamacpp",
@@ -98,7 +98,7 @@
"frameworkCatalogUnknown": 0,
"frameworkContextUnknown": 63,
"modelArchitectureUnknown": 133,
"noMatchingBlock": 1010,
"noMatchingBlock": 1045,
"partiallyBlockedFrameworkSet": 20,
"runningMatchedProtected": 0,
"submissionContextMismatch": 0,
@@ -146,5 +146,5 @@
"repositorySizeUnknown": 0
},
"stopErrors": [],
"uniqueModels": 384
"uniqueModels": 383
}

View File

@@ -217,6 +217,7 @@
{"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": "2026-09-20T13:30:42.155984+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 23556606333}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T05:16:13.136785+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971300", "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_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-21T11:15:42.052921+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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, "repositoryOnDiskBytes": 955857175}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T05:00:40.870810+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971125", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T20:49:19.683254+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-20T04:46:07.939821+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970952", "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-mlu", "lastSyncTime": "2026-09-21T19:57:11.769116+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "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, "repositoryOnDiskBytes": 955857175}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:44:53.386157+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970949", "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": ["mistral3"], "framework": "vllm", "lastSyncTime": "2026-09-21T04:36:00.569168+00:00", "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelProfile": {"architectures": ["Mistral3ForConditionalGeneration"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17367755740, "estimatedRequiredGiB": 19.429, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral3", "modelscopeFileSize": 17385072379, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4929899520, "modelscopeTags": ["license:apache-2.0", "model_type:mistral3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:mistral", "custom_tag:mistral3", "custom_tag:devstral"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17385072379}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:42:19.140494+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970923", "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": "2026-09-20T12:58:28.353121+00:00", "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7486327132, "estimatedRequiredGiB": 8.403, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 7518908360, "modelscopeLicense": "gemma", "modelscopeParams": 2227418442, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7518908360}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:42:19.137834+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970925", "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": ["gemma4_unified"], "framework": "vllm", "lastSyncTime": "2026-09-21T15:02:24.876330+00:00", "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9003966484, "estimatedRequiredGiB": 10.099, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 9036402901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2463563824, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9036402901}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:42:19.135971+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970924", "taskType": "text-generation", "verifyResult": -1}
@@ -276,6 +277,7 @@
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["gemma4"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:21:49.902144+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 23556606333}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:35.460457+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970350", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-21T01:35:45.556133+00:00", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-20T03:58:35.458351+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970351", "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", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.902097+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-20T03:58:35.457045+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970357", "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_vl"], "framework": "vllm", "lastSyncTime": "2026-09-21T19:57:11.769130+00:00", "modelId": "BAAI/RoboBrain2.5-8B-MT", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918174, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918174}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:35.455197+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970358", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["gemma4"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:21:49.901805+00:00", "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21855018733, "estimatedRequiredGiB": 24.461, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 21887495988, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6144703054, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21887495988}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:35.451794+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970348", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901895+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683241105, "estimatedRequiredGiB": 23.138, "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": 20703487237, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703487237}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:35.449495+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970352", "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": "2026-09-21T19:49:37.657161+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "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, "repositoryOnDiskBytes": 663396475}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:35.441724+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970354", "taskType": "text-generation", "verifyResult": -1}
@@ -296,5 +298,3 @@
{"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_tokenizer_patch", "lastSyncTime": "2026-09-21T15:02:24.876345+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16564748304, "estimatedRequiredGiB": 18.516, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 16568142341, "modelscopeLicense": "other", "modelscopeParams": 15957889024, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 16568142341}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:57:31.484685+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970312", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "repository_structure", "failureAction": "require_framework_specific_root_files", "failureCategory": "repository_structure", "failureClassificationReason": "structured_missing_files", "failureCode": "MODEL_FILE_NOT_FOUND", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T16:21:18.661407+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-Research", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "ecd31d4ed4e0e92b9deabe3de0f18c75dc252004ba68826e4cfd561549549074", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008118474, "modelscopeLicense": "cc-by-nc-sa-4.0", "modelscopeParams": 7501651968, "modelscopeTags": ["license:cc-by-nc-sa-4.0", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008118474}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:53:33.643969+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970234", "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", "lastSyncTime": "2026-09-20T22:43:47.754882+00:00", "modelId": "IntervitensInc/kek_mk3", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3289069288, "estimatedRequiredGiB": 3.683, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 3295875324, "modelscopeLicense": null, "modelscopeParams": 1644515328, "modelscopeTags": ["model_type:stablelm", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3295875324}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:46:35.813804+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970120", "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": "2026-09-20T14:14:39.678925+00:00", "modelId": "aisingapore/SEA-LION-v1-7B", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "0335c7e4668aaa963303ebe91f80d6eb1e7e8d0299011bd85f7e05a4df031dc7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008115847, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008115847}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:46:35.801267+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970119", "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", "lastSyncTime": "2026-09-20T17:09:45.266093+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29274355224, "estimatedRequiredGiB": 32.761, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 29314389092, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 29314389092}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:46:35.789758+00:00", "targetGpu": "Biren_166m", "taskId": "4970118", "taskType": "text-generation", "verifyResult": -1}

View File

@@ -2286,6 +2286,8 @@
{"batchId": "af01956827ff4c169cbafc6bc6e203fe", "completedAt": "2026-09-21T19:52:49.937981+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:52:48.876602+00:00", "framework": "vllm", "intentId": "27db0d5b0ed2446a9087527b204e962b", "lastModified": "2026-09-21T18:48:50+00:00", "modelAddress": "https://modelscope.cn/models/prithivMLmods/Nexus-9B-CodeCore-Merge", "reason": null, "reconciledAt": "2026-09-21T19:54:21.694882+00:00", "repoId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_mrv-100", "taskId": "5006513", "taskType": "text-generation"}
{"batchId": "af01956827ff4c169cbafc6bc6e203fe", "completedAt": "2026-09-21T19:52:49.937983+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:52:48.876654+00:00", "framework": "vllm", "intentId": "a805e242301145ed90037bde1881f57f", "lastModified": "2026-09-21T18:24:38+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block2-v1_B", "reason": null, "reconciledAt": "2026-09-21T19:54:21.693692+00:00", "repoId": "nkkbr/Mini-K3-1H-attnres-block2-v1_B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "5006517", "taskType": "text-generation"}
{"batchId": "af01956827ff4c169cbafc6bc6e203fe", "completedAt": "2026-09-21T19:52:49.937985+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:52:48.876728+00:00", "framework": "vllm", "intentId": "e77e8806b18040e1be44cfa579fd0eed", "lastModified": "2026-09-21T18:27:54+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g1-v2_B", "reason": null, "reconciledAt": "2026-09-21T19:54:21.693963+00:00", "repoId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "5006515", "taskType": "text-generation"}
{"batchId": "f3bf040e0b724f75a3a10b60f89f5ff7", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:57:32.018229+00:00", "framework": "vllm", "intentId": "7372e9b97294486d8562e867a0c2000d", "lastModified": "2026-09-21T18:34:41+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "repoId": "nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"}
{"batchId": "f3bf040e0b724f75a3a10b60f89f5ff7", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:57:32.018364+00:00", "framework": "vllm", "intentId": "a04a2eacdcd84031a868f37216f583a8", "lastModified": "2026-09-21T18:33:37+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-8-v2_D", "repoId": "nkkbr/Mini-K3-1H-kda-kernel-8-v2_D", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"}
{"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691781+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.137064+00:00", "framework": "vllm", "intentId": "64b834dd640742a0b32535bde02b94ad", "repoId": "CohereLabs/tiny-aya-base-32K", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691779+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.137007+00:00", "framework": "vllm", "intentId": "d6229ef4ac9942078baa35e312133d9d", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691776+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.136949+00:00", "framework": "vllm", "intentId": "cff6b666a842431faf928f94c2086fdf", "repoId": "nm-testing/llama-3-instruct-w8a8-dyn-per-token-test", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}