state: generation 21986 (cycle)

This commit is contained in:
2026-10-07 22:12:32 +00:00
parent af80f63eef
commit 7b138ba989
11 changed files with 3433 additions and 3571 deletions

View File

@@ -1747,6 +1747,25 @@
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation"
},
"iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|model_type:mini_k3": {
"architectureSignature": "model_type:mini_k3",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-22T00:26:48.653700+00:00",
"framework": "vllm_0_17_0_corex_4_4_0",
"latestFailureAt": "2026-09-22T00:26:48.653700+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "mini_k3",
"sourceModelIds": [
"nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B"
],
"sourceTaskIds": [
"5009624"
],
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation"
},
"iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|model_type:zaya": {
"architectureSignature": "model_type:zaya",
"architectures": [],
@@ -2857,9 +2876,9 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-10-07T21:44:07.606864+00:00",
"generatedAt": "2026-10-07T22:01:50.563485+00:00",
"summary": {
"activeBlockCount": 144,
"activeBlockCount": 145,
"byGpuFramework": {
"Ascend_910-b3|vllm": 9,
"Ascend_910-b3|vllm_tokenizer_patch": 8,
@@ -2873,7 +2892,7 @@
"Cambricon_mlu-370-x8|vllm-mlu": 5,
"Iluvatar_bi-150|transformers": 5,
"Iluvatar_bi-150|vllm": 6,
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 3,
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 4,
"Iluvatar_bi-150|vllm_tokenizer_patch": 2,
"Iluvatar_mrv-100|vllm": 1,
"Kunlunxin_p-800|vllm": 10,

View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-10-07T21:44:07.626352+00:00",
"communityAttemptedAt": "2026-10-07T22:06:14.943870+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-10-07T21:44:07.626352+00:00",
"communityUpdatedAt": "2026-10-07T22:06:14.943870+00:00",
"frameworkAttemptedAt": "2026-10-07T20:58:42.772583+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -434,121 +434,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-07T21:58:15.762622+00:00",
"generatedAt": "2026-10-07T22:06:14.943870+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 932.1136363636364,
"backlogHours": 901.1868131868132,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.6653406195402906,
"queueFactor": 0.9605197085092887,
"queueWeight": 0.9605197085092887,
"recentSuccess": 46,
"recentSuccessRate": 0.26136363636363635,
"recentTerminal": 176,
"recentWilsonLowerBound": 0.2020423125292209,
"running": 9,
"selectionWeight": 0.6390727779402294,
"qualityFactor": 0.6499178433674951,
"queueFactor": 0.9698555657966959,
"queueWeight": 0.9698555657966959,
"recentSuccess": 48,
"recentSuccessRate": 0.26373626373626374,
"recentTerminal": 182,
"recentWilsonLowerBound": 0.2050764164335114,
"running": 6,
"selectionWeight": 0.6303264377005503,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 29.333333333333332,
"waiting": 27342
"throughputPerHour": 30.333333333333332,
"waiting": 27336
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 755.493670886076,
"backlogHours": 775.1168831168832,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.4864062527162382,
"queueFactor": 0.9912700508286517,
"queueWeight": 0.9912700508286517,
"recentSuccess": 53,
"recentSuccessRate": 0.22362869198312235,
"recentTerminal": 237,
"recentWilsonLowerBound": 0.1752280970977904,
"running": 9,
"selectionWeight": 0.48215995085339947,
"qualityFactor": 0.4642618688351079,
"queueFactor": 0.9920286325499899,
"queueWeight": 0.9920286325499899,
"recentSuccess": 52,
"recentSuccessRate": 0.22510822510822512,
"recentTerminal": 231,
"recentWilsonLowerBound": 0.17599839172296025,
"running": 7,
"selectionWeight": 0.46056106688559484,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 39.5,
"throughputPerHour": 38.5,
"waiting": 29842
},
"Biren_166m": {
"available": true,
"backlogHours": 149.24571428571429,
"backlogHours": 155.42857142857142,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.38446870809194117,
"queueFactor": 1.2642743569235995,
"queueWeight": 1.2642743569235995,
"recentSuccess": 37,
"recentSuccessRate": 0.21142857142857144,
"recentTerminal": 175,
"recentWilsonLowerBound": 0.1574625617081521,
"running": 9,
"selectionWeight": 0.486073928680186,
"qualityFactor": 0.3712449148418302,
"queueFactor": 1.262407768475335,
"queueWeight": 1.262407768475335,
"recentSuccess": 36,
"recentSuccessRate": 0.21428571428571427,
"recentTerminal": 168,
"recentWilsonLowerBound": 0.15899050854374325,
"running": 8,
"selectionWeight": 0.46866246450329063,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 29.166666666666668,
"waiting": 4353
"throughputPerHour": 28.0,
"waiting": 4352
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 735.1942446043165,
"backlogHours": 811.1904761904761,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.09524558560566401,
"queueFactor": 0.9953281679439071,
"queueWeight": 0.9953281679439071,
"recentSuccess": 18,
"recentSuccessRate": 0.12949640287769784,
"recentTerminal": 139,
"recentWilsonLowerBound": 0.0835055671190142,
"qualityFactor": 0.06796636933522154,
"queueFactor": 0.985282706538412,
"queueWeight": 0.985282706538412,
"recentSuccess": 15,
"recentSuccessRate": 0.11904761904761904,
"recentTerminal": 126,
"recentWilsonLowerBound": 0.07348600427891416,
"running": 7,
"selectionWeight": 0.09480061422563013,
"selectionWeight": 0.06696608833219642,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 23.166666666666668,
"waiting": 17032
"throughputPerHour": 21.0,
"waiting": 17035
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 287.90721649484533,
"backlogHours": 289.1813471502591,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.14721239262010533,
"queueFactor": 1.145615093965986,
"queueWeight": 1.145615093965986,
"recentSuccess": 28,
"recentSuccessRate": 0.14432989690721648,
"recentTerminal": 194,
"recentWilsonLowerBound": 0.10178171275842926,
"qualityFactor": 0.1687500248168813,
"queueFactor": 1.1501480440702219,
"queueWeight": 1.1501480440702219,
"recentSuccess": 30,
"recentSuccessRate": 0.15544041450777202,
"recentTerminal": 193,
"recentWilsonLowerBound": 0.11110337669376555,
"running": 7,
"selectionWeight": 0.16864873900443958,
"selectionWeight": 0.19408751097993743,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 32.333333333333336,
"waiting": 9309
"throughputPerHour": 32.166666666666664,
"waiting": 9302
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 94.26865671641791,
"backlogHours": 95.09547738693468,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -558,196 +558,196 @@
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 6,
"recentSuccessRate": 0.029850746268656716,
"recentTerminal": 201,
"recentWilsonLowerBound": 0.01375101316224606,
"running": 25,
"recentSuccessRate": 0.03015075376884422,
"recentTerminal": 199,
"recentWilsonLowerBound": 0.013889936753968386,
"running": 23,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 33.5,
"waiting": 3158
"throughputPerHour": 33.166666666666664,
"waiting": 3154
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 251.45454545454544,
"backlogHours": 255.49668874172184,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.2715172663724352,
"queueFactor": 1.1691162205377654,
"queueWeight": 1.1691162205377654,
"recentSuccess": 29,
"recentSuccessRate": 0.18831168831168832,
"recentTerminal": 154,
"recentWilsonLowerBound": 0.13443491114368336,
"running": 7,
"selectionWeight": 0.31743524027208714,
"qualityFactor": 0.29339433689835015,
"queueFactor": 1.1717136661336893,
"queueWeight": 1.1717136661336893,
"recentSuccess": 30,
"recentSuccessRate": 0.1986754966887417,
"recentTerminal": 151,
"recentWilsonLowerBound": 0.14286066225462393,
"running": 2,
"selectionWeight": 0.3437741541100286,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 25.666666666666668,
"waiting": 6454
"throughputPerHour": 25.166666666666668,
"waiting": 6430
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2447.0526315789475,
"backlogHours": 2512.8648648648646,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.7405602236024369,
"queueFactor": 0.831055662727187,
"queueWeight": 0.831055662727187,
"qualityFactor": 0.7453513345009397,
"queueFactor": 0.8315797718483877,
"queueWeight": 0.8315797718483877,
"recentSuccess": 13,
"recentSuccessRate": 0.34210526315789475,
"recentTerminal": 38,
"recentWilsonLowerBound": 0.21212220026458956,
"recentSuccessRate": 0.35135135135135137,
"recentTerminal": 37,
"recentWilsonLowerBound": 0.21825406631100872,
"running": 2,
"selectionWeight": 0.615446767415317,
"selectionWeight": 0.6198190926911827,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 6.333333333333333,
"waiting": 15498
"throughputPerHour": 6.166666666666667,
"waiting": 15496
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 395.61428571428576,
"backlogHours": 401.30434782608694,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.3683499984643415,
"queueFactor": 1.0922846104421942,
"queueWeight": 1.0922846104421942,
"recentSuccess": 30,
"recentSuccessRate": 0.21428571428571427,
"recentTerminal": 140,
"recentWilsonLowerBound": 0.1544267810692068,
"qualityFactor": 0.2998187989170572,
"queueFactor": 1.0949850934024186,
"queueWeight": 1.0949850934024186,
"recentSuccess": 28,
"recentSuccessRate": 0.2028985507246377,
"recentTerminal": 138,
"recentWilsonLowerBound": 0.14427418466892433,
"running": 8,
"selectionWeight": 0.4023430345790061,
"selectionWeight": 0.32829711553599483,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 23.333333333333332,
"waiting": 9231
"throughputPerHour": 23.0,
"waiting": 9230
},
"MetaX_c-500": {
"available": true,
"backlogHours": 488.05970149253733,
"backlogHours": 491.63909774436087,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.07486230961020289,
"queueFactor": 1.058414222647907,
"queueWeight": 1.058414222647907,
"recentSuccess": 16,
"recentSuccessRate": 0.11940298507462686,
"recentTerminal": 134,
"recentWilsonLowerBound": 0.07484767651122064,
"running": 6,
"selectionWeight": 0.07923533323170982,
"qualityFactor": 0.060210999617852215,
"queueFactor": 1.0621413699321418,
"queueWeight": 1.0621413699321418,
"recentSuccess": 15,
"recentSuccessRate": 0.11278195488721804,
"recentTerminal": 133,
"recentWilsonLowerBound": 0.06954841785435961,
"running": 3,
"selectionWeight": 0.06395259361908921,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.333333333333332,
"waiting": 10900
"throughputPerHour": 22.166666666666668,
"waiting": 10898
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1789.6438356164385,
"backlogHours": 1893.391304347826,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 2.5,
"queueFactor": 0.8709868903988912,
"queueWeight": 0.8709868903988912,
"recentSuccess": 35,
"recentSuccessRate": 0.4794520547945205,
"recentTerminal": 73,
"recentWilsonLowerBound": 0.36877263024700824,
"queueFactor": 0.867647320583523,
"queueWeight": 0.867647320583523,
"recentSuccess": 34,
"recentSuccessRate": 0.4927536231884058,
"recentTerminal": 69,
"recentWilsonLowerBound": 0.3783222449110343,
"running": 4,
"selectionWeight": 2.177467225997228,
"selectionWeight": 2.1691183014588074,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.166666666666666,
"throughputPerHour": 11.5,
"waiting": 21774
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 2565.75,
"backlogHours": 2565.45,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.05,
"queueFactor": 0.8251719545152607,
"queueWeight": 0.8251719545152607,
"queueFactor": 0.8290004255296309,
"queueWeight": 0.8290004255296309,
"recentSuccess": 4,
"recentSuccessRate": 0.1,
"recentTerminal": 40,
"recentWilsonLowerBound": 0.03957888759557486,
"running": 2,
"selectionWeight": 0.04125859772576304,
"selectionWeight": 0.04145002127648155,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 6.666666666666667,
"waiting": 17105
"waiting": 17103
},
"Vastai_va16": {
"available": true,
"backlogHours": 690.0,
"backlogHours": 694.5714285714286,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.05,
"queueFactor": 1.0048453937273973,
"queueWeight": 1.0048453937273973,
"queueFactor": 1.008490356057712,
"queueWeight": 1.008490356057712,
"recentSuccess": 2,
"recentSuccessRate": 0.013513513513513514,
"recentTerminal": 148,
"recentWilsonLowerBound": 0.003713671821030592,
"running": 16,
"selectionWeight": 0.05024226968636987,
"recentSuccessRate": 0.013605442176870748,
"recentTerminal": 147,
"recentWilsonLowerBound": 0.0037389889438848847,
"running": 15,
"selectionWeight": 0.05042451780288561,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 24.666666666666668,
"waiting": 17020
"throughputPerHour": 24.5,
"waiting": 17017
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 1062.05,
"backlogHours": 1118.0,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 0.4355816024990896,
"queueFactor": 0.9419001480015697,
"queueWeight": 0.9419001480015697,
"qualityFactor": 0.4627997293188505,
"queueFactor": 0.9389944301468925,
"queueWeight": 0.9389944301468925,
"recentSuccess": 28,
"recentSuccessRate": 0.23333333333333334,
"recentTerminal": 120,
"recentWilsonLowerBound": 0.16665469513089648,
"recentSuccessRate": 0.24561403508771928,
"recentTerminal": 114,
"recentWilsonLowerBound": 0.17574622644308974,
"running": 6,
"selectionWeight": 0.4102743758606534,
"selectionWeight": 0.43456636810389015,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 20.0,
"waiting": 21241
"throughputPerHour": 19.0,
"waiting": 21242
}
},
"queueAttemptedAt": "2026-10-07T21:52:02.968321+00:00",
"queueAttemptedAt": "2026-10-07T22:06:14.943870+00:00",
"queueError": null,
"queueUpdatedAt": "2026-10-07T21:52:02.968321+00:00",
"queueUpdatedAt": "2026-10-07T22:06:14.943870+00:00",
"supportedGpus": [
"Vastai_va16",
"Cambricon_mlu-370-x4",

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-07T20:51:18.537061+00:00",
"lastSyncTime": "2026-10-07T20:51:18.470436+00:00",
"generatedAt": "2026-10-07T22:06:14.844664+00:00",
"lastSyncTime": "2026-10-07T22:06:14.776284+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1751,6 +1751,25 @@
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation"
},
"iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|model_type:mini_k3": {
"architectureSignature": "model_type:mini_k3",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-22T00:26:48.653700+00:00",
"framework": "vllm_0_17_0_corex_4_4_0",
"latestFailureAt": "2026-09-22T00:26:48.653700+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "mini_k3",
"sourceModelIds": [
"nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B"
],
"sourceTaskIds": [
"5009624"
],
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation"
},
"iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|model_type:zaya": {
"architectureSignature": "model_type:zaya",
"architectures": [],
@@ -2862,7 +2881,7 @@
}
},
"architectureCompatibilitySummary": {
"activeBlockCount": 144,
"activeBlockCount": 145,
"byGpuFramework": {
"Ascend_910-b3|vllm": 9,
"Ascend_910-b3|vllm_tokenizer_patch": 8,
@@ -2876,7 +2895,7 @@
"Cambricon_mlu-370-x8|vllm-mlu": 5,
"Iluvatar_bi-150|transformers": 5,
"Iluvatar_bi-150|vllm": 6,
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 3,
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 4,
"Iluvatar_bi-150|vllm_tokenizer_patch": 2,
"Iluvatar_mrv-100|vllm": 1,
"Kunlunxin_p-800|vllm": 10,
@@ -4131,30 +4150,30 @@
"unresolvedFailureCount": 82
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 48,
"decisionFailureRate": 0.7164,
"decisionSuccessRate": 0.2836,
"decisionTotal": 67,
"attributableFailureCount": 49,
"decisionFailureRate": 0.7206,
"decisionSuccessRate": 0.2794,
"decisionTotal": 68,
"failureBreakdown": {
"ambiguous_runtime": 32,
"backend_operator": 6,
"framework_architecture_unsupported": 23,
"framework_architecture_unsupported": 24,
"memory_capacity": 1,
"model_load": 8,
"runtime_memory": 10,
"参数/模板问题": 2
},
"failureCount": 82,
"failureRate": 0.8119,
"failureCount": 83,
"failureRate": 0.8137,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 19,
"successRate": 0.1881,
"successRate": 0.1863,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 101,
"total": 102,
"unresolvedFailureCount": 34
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": {
@@ -4528,10 +4547,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 166,
"ambiguous_runtime": 168,
"参数/模板问题": 3
},
"failureCount": 169,
"failureCount": 171,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -4541,8 +4560,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 169,
"unresolvedFailureCount": 169
"total": 171,
"unresolvedFailureCount": 171
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 61,
@@ -5685,27 +5704,27 @@
"unresolvedFailureCount": 73
},
"vllm_0_17_0_corex_4_4_0": {
"attributableFailureCount": 48,
"decisionFailureRate": 0.7164,
"decisionSuccessRate": 0.2836,
"decisionTotal": 67,
"attributableFailureCount": 49,
"decisionFailureRate": 0.7206,
"decisionSuccessRate": 0.2794,
"decisionTotal": 68,
"failureBreakdown": {
"ambiguous_runtime": 32,
"backend_operator": 6,
"framework_architecture_unsupported": 23,
"framework_architecture_unsupported": 24,
"memory_capacity": 1,
"model_load": 8,
"runtime_memory": 10,
"参数/模板问题": 2
},
"failureCount": 82,
"failureRate": 0.8119,
"failureCount": 83,
"failureRate": 0.8137,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 19,
"successRate": 0.1881,
"total": 101,
"successRate": 0.1863,
"total": 102,
"unresolvedFailureCount": 34
},
"vllm_fix_tokenizer": {
@@ -5714,7 +5733,7 @@
"decisionSuccessRate": 0.0275,
"decisionTotal": 182,
"failureBreakdown": {
"ambiguous_runtime": 378,
"ambiguous_runtime": 380,
"backend_operator": 9,
"framework_architecture_unsupported": 49,
"memory_capacity": 10,
@@ -5723,15 +5742,15 @@
"tokenizer_compatibility": 96,
"参数/模板问题": 13
},
"failureCount": 595,
"failureCount": 597,
"failureRate": 0.9917,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 27,
"successCount": 5,
"successRate": 0.0083,
"total": 600,
"unresolvedFailureCount": 391
"total": 602,
"unresolvedFailureCount": 393
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 158,
@@ -5762,7 +5781,7 @@
"unresolvedFailureCount": 257
}
},
"generatedAt": "2026-10-07T20:51:18.520624+00:00",
"generatedAt": "2026-10-07T22:06:14.826753+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 120,
@@ -5927,16 +5946,16 @@
"unresolvedFailureCount": 571
},
"Iluvatar_bi-150": {
"attributableFailureCount": 765,
"decisionFailureRate": 0.8361,
"decisionSuccessRate": 0.1639,
"decisionTotal": 915,
"attributableFailureCount": 766,
"decisionFailureRate": 0.8362,
"decisionSuccessRate": 0.1638,
"decisionTotal": 916,
"failureBreakdown": {
"ambiguous_runtime": 665,
"architecture_compatibility": 15,
"backend_operator": 12,
"context_length": 29,
"framework_architecture_unsupported": 256,
"framework_architecture_unsupported": 257,
"memory_capacity": 153,
"model_load": 128,
"platform_infrastructure": 21,
@@ -5947,14 +5966,14 @@
"日志缺失": 155,
"验证失败": 30
},
"failureCount": 1957,
"failureCount": 1958,
"failureRate": 0.9288,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 21,
"successCount": 150,
"successRate": 0.0712,
"total": 2107,
"total": 2108,
"unresolvedFailureCount": 1171
},
"Iluvatar_mrv-100": {
@@ -5994,7 +6013,7 @@
"decisionSuccessRate": 0.066,
"decisionTotal": 106,
"failureBreakdown": {
"ambiguous_runtime": 255,
"ambiguous_runtime": 257,
"backend_operator": 23,
"framework_architecture_unsupported": 37,
"memory_capacity": 3,
@@ -6007,15 +6026,15 @@
"日志缺失": 1,
"验证失败": 23
},
"failureCount": 426,
"failureRate": 0.9838,
"failureCount": 428,
"failureRate": 0.9839,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 7,
"successRate": 0.0162,
"total": 433,
"unresolvedFailureCount": 326
"successRate": 0.0161,
"total": 435,
"unresolvedFailureCount": 328
},
"Kunlunxin_r-200-8f": {
"attributableFailureCount": 0,
@@ -6203,7 +6222,7 @@
"hygon_k100-ai": 64.0
},
"pendingRecords": 0,
"policyCancelledRecords": 364,
"policyCancelledRecords": 382,
"profileCombinationStats": {
"Ascend_910-b3|llamacpp|text-generation|smollm3|none": {
"attributableFailureCount": 0,
@@ -15801,6 +15820,29 @@
"total": 5,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|mini_k3|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "mini_k3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|mistral3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -18613,6 +18655,29 @@
"total": 6,
"unresolvedFailureCount": 6
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|mini_k3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "mini_k3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|minicpm|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -25504,10 +25569,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 3,
"ambiguous_runtime": 2,
"framework_architecture_unsupported": 2
},
"failureCount": 5,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -25519,8 +25584,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 3
"total": 4,
"unresolvedFailureCount": 2
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 2,
@@ -25683,10 +25748,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 7,
"ambiguous_runtime": 6,
"参数/模板问题": 1
},
"failureCount": 8,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastPlatformFailureAt": null,
@@ -25698,8 +25763,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 8
"total": 7,
"unresolvedFailureCount": 7
},
"Cambricon_mlu-370-x4|vllm|text-generation": {
"attributableFailureCount": 2,
@@ -25832,6 +25897,31 @@
"total": 16,
"unresolvedFailureCount": 11
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-10-07T22:01:50.158773+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
@@ -25972,9 +26062,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 8
"ambiguous_runtime": 9
},
"failureCount": 8,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -25986,8 +26076,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 8
"total": 9,
"unresolvedFailureCount": 9
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 16,
@@ -26539,9 +26629,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-22T08:01:56.366395+00:00",
@@ -26554,8 +26644,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|gpt_oss|none": {
"attributableFailureCount": 0,
@@ -26957,31 +27047,6 @@
"total": 4,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|mistral|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-27T13:43:22.766786+00:00",
"modelType": "mistral",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|phi3|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -27732,6 +27797,31 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|mini_k3|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_0_17_0_corex_4_4_0",
"lastTerminalAt": "2026-10-07T22:01:50.158773+00:00",
"modelType": "mini_k3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -28315,9 +28405,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 2
},
"failureCount": 3,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-23T19:08:31.650327+00:00",
@@ -28330,8 +28420,33 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|mini_k3|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-10-07T22:01:50.158710+00:00",
"modelType": "mini_k3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen2|compressed-tensors": {
"attributableFailureCount": 0,
@@ -44267,6 +44382,30 @@
"total": 4,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|mini_k3|none|30": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 30,
"modelType": "mini_k3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|mistral3|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -48387,6 +48526,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|mini_k3|none|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 30,
"modelType": "mini_k3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|minicpm|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -58881,20 +59044,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17431,
"totalRecords": 17795,
"terminalRecords": 17434,
"totalRecords": 17816,
"totals": {
"attributableFailureCount": 6259,
"decisionFailureRate": 0.8647,
"decisionSuccessRate": 0.1353,
"decisionTotal": 7238,
"attributableFailureCount": 6260,
"decisionFailureRate": 0.8648,
"decisionSuccessRate": 0.1352,
"decisionTotal": 7239,
"failureBreakdown": {
"ambiguous_runtime": 4577,
"ambiguous_runtime": 4579,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 130,
"context_length": 327,
"framework_architecture_unsupported": 2277,
"framework_architecture_unsupported": 2278,
"memory_capacity": 1206,
"model_load": 571,
"platform_infrastructure": 955,
@@ -58905,15 +59068,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16452,
"failureCount": 16455,
"failureRate": 0.9438,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 955,
"successCount": 979,
"successRate": 0.0562,
"total": 17431,
"unresolvedFailureCount": 9238
"total": 17434,
"unresolvedFailureCount": 9240
},
"warnings": [
"GPU MetaX_c-500 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -58975,6 +59138,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17795,
"summarizedRecords": 17816,
"version": 1
}

File diff suppressed because it is too large Load Diff

View File

@@ -98,6 +98,7 @@
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-22T01:23:49.082798+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:23:32+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4850852", "taskType": "text-generation", "verifyResult": null}
{"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": "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": ["mini_k3"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T22:01:50.158773+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2037838088, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2041445091}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T00:26:48.653700+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5009624", "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": "2026-10-07T18:18:51.743129+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039076183}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T22:21:59.843515+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5008078", "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": ["mini_k3"], "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T20:23:14.668330+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T22:14:33.594032+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5008009", "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": "2026-10-07T20:46:38.448901+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039076183}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T20:38:42.647821+00:00", "targetGpu": "Biren_166m", "taskId": "5007028", "taskType": "text-generation", "verifyResult": -1}
@@ -114,6 +115,8 @@
{"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": ["mini_k3"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T19:02:02.168317+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:37:12.447446+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006364", "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": "2026-10-07T13:06:44.750866+00:00", "modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35196531592, "estimatedRequiredGiB": 39.403, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": 1411666624, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:text-generation-inference", "custom_tag:qwen3_5", "custom_tag:mlx-vlm", "custom_tag:prompt-rewriter", "custom_tag:prompt enhancer", "custom_tag:apple-silicon", "custom_tag:4-bit", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 5}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T16:50:30.559192+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5}, "repositoryOnDiskBytes": 35256868927}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:21:51.848154+00:00", "targetGpu": "Biren_166m", "taskId": "5006202", "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": "2026-10-07T22:01:50.158710+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:21:51.640501+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006192", "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": "2026-10-07T22:01:50.158742+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:21:51.639396+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006187", "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": "2026-10-07T14:46:46.372736+00:00", "modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35196531592, "estimatedRequiredGiB": 39.403, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": 1411666624, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:text-generation-inference", "custom_tag:qwen3_5", "custom_tag:mlx-vlm", "custom_tag:prompt-rewriter", "custom_tag:prompt enhancer", "custom_tag:apple-silicon", "custom_tag:4-bit", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 35256868927}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:05:50.963205+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006057", "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": "2026-10-07T14:24:51.661617+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": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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, "repositoryOnDiskBytes": 19329296879}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:05:50.745520+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006056", "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": ["mini_k3"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T17:46:09.953381+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:05:50.437924+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5006050", "taskType": "text-generation", "verifyResult": -1}
@@ -295,6 +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": "2026-09-24T09:55:55.960246+00:00", "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1047023664, "estimatedRequiredGiB": 1.172, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-21T09:40:34.489077+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4998299", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T09:54:21.980336+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T09:35:50+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969372", "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": "2026-09-22T21:50:30.559334+00:00", "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10261168632, "estimatedRequiredGiB": 11.478, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 10270608122, "modelscopeLicense": "other", "modelscopeParams": 16754741248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible - mergekit - merge - facebook - meta - pytorch - llama - llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 10270608122}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:33:26.659264+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4998167", "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": "2026-09-23T10:48:31.671315+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231252716, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233101396, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T08:44:09.587569+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 1233101396}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:19:32.876555+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4997864", "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-mlu", "lastSyncTime": "2026-09-27T13:43:22.766786+00:00", "modelId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13594088584, "estimatedRequiredGiB": 15.203, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 13603621925, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12247782400, "modelscopeTags": ["license:apache-2.0", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 13603621925}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:19:32.873304+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4997863", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-10-02T10:43:40.858838+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231270112, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233118759, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1233118759}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:19:32.868721+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997865", "taskType": "text-generation", "verifyResult": -1}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff