state: generation 10623 (intent)
This commit is contained in:
@@ -1531,7 +1531,7 @@
|
||||
"sunrise_pt-200-x1|vllm|text-generation|model_type:qwen3_5_moe": {
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectures": [],
|
||||
"evidenceCount": 2,
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-10-14T00:43:21+00:00",
|
||||
"framework": "vllm",
|
||||
"latestFailureAt": "2026-09-14T00:43:21+00:00",
|
||||
@@ -1539,12 +1539,10 @@
|
||||
"matchType": "model_type",
|
||||
"modelType": "qwen3_5_moe",
|
||||
"sourceModelIds": [
|
||||
"apodex/Apodex-1.1-mini-GPTQ-Int4",
|
||||
"mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B"
|
||||
"apodex/Apodex-1.1-mini-GPTQ-Int4"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"4490280",
|
||||
"4490277"
|
||||
"4490280"
|
||||
],
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation"
|
||||
@@ -1939,7 +1937,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T14:18:03.645070+00:00",
|
||||
"generatedAt": "2026-09-20T14:32:15.686497+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 94,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
{
|
||||
"communityAttemptedAt": "2026-09-20T14:11:59.257830+00:00",
|
||||
"communityAttemptedAt": "2026-09-20T14:32:15.696895+00:00",
|
||||
"communityError": null,
|
||||
"communitySample": {},
|
||||
"communityUpdatedAt": "2026-09-20T14:11:59.257830+00:00",
|
||||
"communityUpdatedAt": "2026-09-20T14:32:15.696895+00:00",
|
||||
"frameworkAttemptedAt": "2026-09-20T11:15:54.454361+00:00",
|
||||
"frameworkError": null,
|
||||
"frameworkStats": {
|
||||
@@ -425,121 +425,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-20T14:20:27.786078+00:00",
|
||||
"generatedAt": "2026-09-20T14:32:15.696895+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 982.3216783216784,
|
||||
"backlogHours": 1040.1333333333334,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.5762005371441155,
|
||||
"queueFactor": 0.9870141036213258,
|
||||
"queueWeight": 0.9870141036213258,
|
||||
"recentSuccess": 45,
|
||||
"recentSuccessRate": 0.3146853146853147,
|
||||
"recentTerminal": 143,
|
||||
"recentWilsonLowerBound": 0.2442641903306046,
|
||||
"qualityFactor": 1.4912057285700442,
|
||||
"queueFactor": 0.983204097073644,
|
||||
"queueWeight": 0.983204097073644,
|
||||
"recentSuccess": 44,
|
||||
"recentSuccessRate": 0.32592592592592595,
|
||||
"recentTerminal": 135,
|
||||
"recentWilsonLowerBound": 0.2526269752404716,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.5557321602967513,
|
||||
"selectionWeight": 1.4661595819097557,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 23.833333333333332,
|
||||
"waiting": 23412
|
||||
"throughputPerHour": 22.5,
|
||||
"waiting": 23403
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1410.7,
|
||||
"backlogHours": 1376.0487804878048,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.9348592245827515,
|
||||
"queueWeight": 0.9348592245827515,
|
||||
"recentSuccess": 46,
|
||||
"recentSuccessRate": 0.38333333333333336,
|
||||
"recentTerminal": 120,
|
||||
"recentWilsonLowerBound": 0.30124387764148153,
|
||||
"qualityFactor": 2.193192799994165,
|
||||
"queueFactor": 0.9427834656000597,
|
||||
"queueWeight": 0.9427834656000597,
|
||||
"recentSuccess": 47,
|
||||
"recentSuccessRate": 0.3821138211382114,
|
||||
"recentTerminal": 123,
|
||||
"recentWilsonLowerBound": 0.30104673808099086,
|
||||
"running": 8,
|
||||
"selectionWeight": 2.3371480614568787,
|
||||
"selectionWeight": 2.0677059087075973,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 20.0,
|
||||
"waiting": 28214
|
||||
"throughputPerHour": 20.5,
|
||||
"waiting": 28209
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 175.26506024096383,
|
||||
"backlogHours": 179.14814814814815,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.39105486705633086,
|
||||
"queueFactor": 1.2782244358499573,
|
||||
"queueWeight": 1.2782244358499573,
|
||||
"qualityFactor": 0.3629933843037956,
|
||||
"queueFactor": 1.2800448401379467,
|
||||
"queueWeight": 1.2800448401379467,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.18072289156626506,
|
||||
"recentTerminal": 166,
|
||||
"recentWilsonLowerBound": 0.12962533896650527,
|
||||
"recentSuccessRate": 0.18518518518518517,
|
||||
"recentTerminal": 162,
|
||||
"recentWilsonLowerBound": 0.13290856549831656,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.49985588682945853,
|
||||
"selectionWeight": 0.46464780858228427,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 27.666666666666668,
|
||||
"waiting": 4849
|
||||
"throughputPerHour": 27.0,
|
||||
"waiting": 4837
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1626.8727272727274,
|
||||
"backlogHours": 1626.6545454545455,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.11938963355497317,
|
||||
"queueFactor": 0.9150785616420115,
|
||||
"queueWeight": 0.9150785616420115,
|
||||
"recentSuccess": 8,
|
||||
"recentSuccessRate": 0.14545454545454545,
|
||||
"qualityFactor": 0.20222586668390247,
|
||||
"queueFactor": 0.9194174287901848,
|
||||
"queueWeight": 0.9194174287901848,
|
||||
"recentSuccess": 10,
|
||||
"recentSuccessRate": 0.18181818181818182,
|
||||
"recentTerminal": 55,
|
||||
"recentWilsonLowerBound": 0.07559199016771778,
|
||||
"recentWilsonLowerBound": 0.10187561448030713,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.10925089414845168,
|
||||
"selectionWeight": 0.1859299863813803,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 9.166666666666666,
|
||||
"waiting": 14913
|
||||
"waiting": 14911
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 530.7692307692308,
|
||||
"backlogHours": 530.3076923076924,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.3808749271328514,
|
||||
"queueFactor": 1.0824941472374927,
|
||||
"queueWeight": 1.0824941472374927,
|
||||
"qualityFactor": 0.3346144212965884,
|
||||
"queueFactor": 1.087746871241264,
|
||||
"queueWeight": 1.087746871241264,
|
||||
"recentSuccess": 20,
|
||||
"recentSuccessRate": 0.19230769230769232,
|
||||
"recentTerminal": 104,
|
||||
"recentWilsonLowerBound": 0.12808047966842862,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.41229487945081816,
|
||||
"selectionWeight": 0.3639757898375702,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.333333333333332,
|
||||
"waiting": 9200
|
||||
"waiting": 9192
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 43.83529411764706,
|
||||
"backlogHours": 45.34756097560976,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -549,196 +549,196 @@
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 8,
|
||||
"recentSuccessRate": 0.023529411764705882,
|
||||
"recentTerminal": 340,
|
||||
"recentWilsonLowerBound": 0.011969765378944437,
|
||||
"recentSuccessRate": 0.024390243902439025,
|
||||
"recentTerminal": 328,
|
||||
"recentWilsonLowerBound": 0.012409482100511864,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 56.666666666666664,
|
||||
"waiting": 2484
|
||||
"throughputPerHour": 54.666666666666664,
|
||||
"waiting": 2479
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 97.7,
|
||||
"backlogHours": 100.0136518771331,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.14373064221983012,
|
||||
"qualityFactor": 0.1047379118763751,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 34,
|
||||
"recentSuccessRate": 0.11333333333333333,
|
||||
"recentTerminal": 300,
|
||||
"recentWilsonLowerBound": 0.082244014467736,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.18684983488577916,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.10580204778156997,
|
||||
"recentTerminal": 293,
|
||||
"recentWilsonLowerBound": 0.07554256005576392,
|
||||
"running": 5,
|
||||
"selectionWeight": 0.13615928543928763,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 50.0,
|
||||
"waiting": 4885
|
||||
"throughputPerHour": 48.833333333333336,
|
||||
"waiting": 4884
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 3823.68,
|
||||
"backlogHours": 3822.9599999999996,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 2.482982027832847,
|
||||
"queueFactor": 0.8049875929556839,
|
||||
"queueWeight": 0.8049875929556839,
|
||||
"qualityFactor": 2.1814026997983915,
|
||||
"queueFactor": 0.808811036455579,
|
||||
"queueWeight": 0.808811036455579,
|
||||
"recentSuccess": 12,
|
||||
"recentSuccessRate": 0.48,
|
||||
"recentTerminal": 25,
|
||||
"recentWilsonLowerBound": 0.30031003928960015,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.9987697259373864,
|
||||
"selectionWeight": 1.7643425785509352,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 4.166666666666667,
|
||||
"waiting": 15932
|
||||
"waiting": 15929
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 548.7179487179487,
|
||||
"backlogHours": 553.396551724138,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.7200376660517962,
|
||||
"queueFactor": 1.0771074821364857,
|
||||
"queueWeight": 1.0771074821364857,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.23931623931623933,
|
||||
"recentTerminal": 117,
|
||||
"recentWilsonLowerBound": 0.17107945919158843,
|
||||
"qualityFactor": 0.5855905705198401,
|
||||
"queueFactor": 1.080815500507691,
|
||||
"queueWeight": 1.080815500507691,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.23275862068965517,
|
||||
"recentTerminal": 116,
|
||||
"recentWilsonLowerBound": 0.16518094816137183,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.7755579575244819,
|
||||
"selectionWeight": 0.6329153655689852,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 19.5,
|
||||
"waiting": 10700
|
||||
"throughputPerHour": 19.333333333333332,
|
||||
"waiting": 10699
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 818.3703703703703,
|
||||
"backlogHours": 818.0,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.9852159896853607,
|
||||
"queueFactor": 1.014422639623632,
|
||||
"queueWeight": 1.014422639623632,
|
||||
"qualityFactor": 0.8655531114173936,
|
||||
"queueFactor": 1.0192812522036898,
|
||||
"queueWeight": 1.0192812522036898,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.2839506172839506,
|
||||
"recentTerminal": 81,
|
||||
"recentWilsonLowerBound": 0.19728595019327252,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.9994254048560326,
|
||||
"selectionWeight": 0.8822420592543208,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 13.5,
|
||||
"waiting": 11048
|
||||
"waiting": 11043
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 2269.7894736842104,
|
||||
"backlogHours": 1990.3384615384614,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.233077181065672,
|
||||
"queueFactor": 0.8704895883753879,
|
||||
"queueWeight": 0.8704895883753879,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.40350877192982454,
|
||||
"recentTerminal": 57,
|
||||
"recentWilsonLowerBound": 0.2861732352653998,
|
||||
"qualityFactor": 1.8109361726551496,
|
||||
"queueFactor": 0.8920064433281091,
|
||||
"queueWeight": 0.8920064433281091,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.38461538461538464,
|
||||
"recentTerminal": 65,
|
||||
"recentWilsonLowerBound": 0.27594829385374525,
|
||||
"running": 4,
|
||||
"selectionWeight": 1.9438704361563284,
|
||||
"selectionWeight": 1.6153667344643385,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 9.5,
|
||||
"waiting": 21563
|
||||
"throughputPerHour": 10.833333333333334,
|
||||
"waiting": 21562
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 8494.909090909092,
|
||||
"backlogHours": 7785.5,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 2.1299380710938753,
|
||||
"queueFactor": 0.7141469855277628,
|
||||
"queueWeight": 0.7141469855277628,
|
||||
"recentSuccess": 6,
|
||||
"recentSuccessRate": 0.5454545454545454,
|
||||
"recentTerminal": 11,
|
||||
"recentWilsonLowerBound": 0.2800877556899882,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.7269659262393937,
|
||||
"queueWeight": 0.7269659262393937,
|
||||
"recentSuccess": 7,
|
||||
"recentSuccessRate": 0.5833333333333334,
|
||||
"recentTerminal": 12,
|
||||
"recentWilsonLowerBound": 0.3195073356553728,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.5210888528325088,
|
||||
"selectionWeight": 1.8174148155984842,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 1.8333333333333333,
|
||||
"waiting": 15574
|
||||
"throughputPerHour": 2.0,
|
||||
"waiting": 15571
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 1892.9333333333334,
|
||||
"backlogHours": 1851.5217391304348,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.12595260771563374,
|
||||
"queueFactor": 0.894522193003335,
|
||||
"queueWeight": 0.894522193003335,
|
||||
"qualityFactor": 0.10528560698176376,
|
||||
"queueFactor": 0.9017324725400675,
|
||||
"queueWeight": 0.9017324725400675,
|
||||
"recentSuccess": 7,
|
||||
"recentSuccessRate": 0.15555555555555556,
|
||||
"recentTerminal": 45,
|
||||
"recentWilsonLowerBound": 0.07745325311328675,
|
||||
"recentSuccessRate": 0.15217391304347827,
|
||||
"recentTerminal": 46,
|
||||
"recentWilsonLowerBound": 0.07572186234017478,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.11266740286827746,
|
||||
"selectionWeight": 0.09493945070654762,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 7.5,
|
||||
"waiting": 14197
|
||||
"throughputPerHour": 7.666666666666667,
|
||||
"waiting": 14195
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 351.2342007434944,
|
||||
"backlogHours": 349.93333333333334,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.0736434351724161,
|
||||
"queueFactor": 1.1516536755436881,
|
||||
"queueWeight": 1.1516536755436881,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.08921933085501858,
|
||||
"recentTerminal": 269,
|
||||
"recentWilsonLowerBound": 0.060687232600694176,
|
||||
"qualityFactor": 0.05730934704311466,
|
||||
"queueFactor": 1.157735191658623,
|
||||
"queueWeight": 1.157735191658623,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.08518518518518518,
|
||||
"recentTerminal": 270,
|
||||
"recentWilsonLowerBound": 0.05743227753280504,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.08481173279597633,
|
||||
"selectionWeight": 0.06634904788279089,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 44.833333333333336,
|
||||
"throughputPerHour": 45.0,
|
||||
"waiting": 15747
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-20T14:11:59.257830+00:00",
|
||||
"queueAttemptedAt": "2026-09-20T14:32:15.696895+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-20T14:11:59.257830+00:00",
|
||||
"queueUpdatedAt": "2026-09-20T14:32:15.696895+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Kunlunxin_p-800",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-20T14:18:03.550019+00:00",
|
||||
"lastSyncTime": "2026-09-20T14:18:03.259028+00:00",
|
||||
"generatedAt": "2026-09-20T14:32:15.633088+00:00",
|
||||
"lastSyncTime": "2026-09-20T14:32:15.260773+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1535,7 +1535,7 @@
|
||||
"sunrise_pt-200-x1|vllm|text-generation|model_type:qwen3_5_moe": {
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectures": [],
|
||||
"evidenceCount": 2,
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-10-14T00:43:21+00:00",
|
||||
"framework": "vllm",
|
||||
"latestFailureAt": "2026-09-14T00:43:21+00:00",
|
||||
@@ -1543,12 +1543,10 @@
|
||||
"matchType": "model_type",
|
||||
"modelType": "qwen3_5_moe",
|
||||
"sourceModelIds": [
|
||||
"apodex/Apodex-1.1-mini-GPTQ-Int4",
|
||||
"mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B"
|
||||
"apodex/Apodex-1.1-mini-GPTQ-Int4"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"4490280",
|
||||
"4490277"
|
||||
"4490280"
|
||||
],
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation"
|
||||
@@ -2359,9 +2357,9 @@
|
||||
},
|
||||
"Biren_166m|vllm|text-generation": {
|
||||
"attributableFailureCount": 34,
|
||||
"decisionFailureRate": 0.7083,
|
||||
"decisionSuccessRate": 0.2917,
|
||||
"decisionTotal": 48,
|
||||
"decisionFailureRate": 0.6939,
|
||||
"decisionSuccessRate": 0.3061,
|
||||
"decisionTotal": 49,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 26,
|
||||
@@ -2369,16 +2367,16 @@
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 35,
|
||||
"failureRate": 0.7143,
|
||||
"failureRate": 0.7,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 14,
|
||||
"successRate": 0.2857,
|
||||
"successCount": 15,
|
||||
"successRate": 0.3,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 49,
|
||||
"total": 50,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
@@ -3486,10 +3484,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 80,
|
||||
"ambiguous_runtime": 82,
|
||||
"参数/模板问题": 2
|
||||
},
|
||||
"failureCount": 82,
|
||||
"failureCount": 84,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
@@ -3499,8 +3497,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 82,
|
||||
"unresolvedFailureCount": 82
|
||||
"total": 84,
|
||||
"unresolvedFailureCount": 84
|
||||
},
|
||||
"Kunlunxin_r-200-8f|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -3647,7 +3645,7 @@
|
||||
"decisionSuccessRate": 0.0359,
|
||||
"decisionTotal": 641,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 125,
|
||||
"ambiguous_runtime": 126,
|
||||
"architecture_compatibility": 20,
|
||||
"backend_operator": 43,
|
||||
"context_length": 46,
|
||||
@@ -3659,18 +3657,18 @@
|
||||
"tokenizer_compatibility": 78,
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 755,
|
||||
"failureRate": 0.9704,
|
||||
"failureCount": 756,
|
||||
"failureRate": 0.9705,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 23,
|
||||
"successRate": 0.0296,
|
||||
"successRate": 0.0295,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 778,
|
||||
"unresolvedFailureCount": 134
|
||||
"total": 779,
|
||||
"unresolvedFailureCount": 135
|
||||
},
|
||||
"MetaX_c-500|vllm|unknown": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -4457,11 +4455,11 @@
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3474,
|
||||
"decisionFailureRate": 0.9783,
|
||||
"decisionSuccessRate": 0.0217,
|
||||
"decisionTotal": 3551,
|
||||
"decisionFailureRate": 0.978,
|
||||
"decisionSuccessRate": 0.022,
|
||||
"decisionTotal": 3552,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1430,
|
||||
"ambiguous_runtime": 1431,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 84,
|
||||
@@ -4475,15 +4473,15 @@
|
||||
"tokenizer_compatibility": 408,
|
||||
"参数/模板问题": 40
|
||||
},
|
||||
"failureCount": 5808,
|
||||
"failureRate": 0.9869,
|
||||
"failureCount": 5809,
|
||||
"failureRate": 0.9868,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 864,
|
||||
"successCount": 77,
|
||||
"successRate": 0.0131,
|
||||
"total": 5885,
|
||||
"unresolvedFailureCount": 1470
|
||||
"successCount": 78,
|
||||
"successRate": 0.0132,
|
||||
"total": 5887,
|
||||
"unresolvedFailureCount": 1471
|
||||
},
|
||||
"vllm-customized": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -4577,7 +4575,7 @@
|
||||
"decisionSuccessRate": 0.0167,
|
||||
"decisionTotal": 120,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 115,
|
||||
"ambiguous_runtime": 117,
|
||||
"backend_operator": 8,
|
||||
"framework_architecture_unsupported": 20,
|
||||
"memory_capacity": 7,
|
||||
@@ -4586,15 +4584,15 @@
|
||||
"tokenizer_compatibility": 82,
|
||||
"参数/模板问题": 8
|
||||
},
|
||||
"failureCount": 257,
|
||||
"failureCount": 259,
|
||||
"failureRate": 0.9923,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 16,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0077,
|
||||
"total": 259,
|
||||
"unresolvedFailureCount": 123
|
||||
"total": 261,
|
||||
"unresolvedFailureCount": 125
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -4616,7 +4614,7 @@
|
||||
"unresolvedFailureCount": 24
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T14:18:03.541951+00:00",
|
||||
"generatedAt": "2026-09-20T14:32:15.624688+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 75,
|
||||
@@ -4673,9 +4671,9 @@
|
||||
},
|
||||
"Biren_166m": {
|
||||
"attributableFailureCount": 172,
|
||||
"decisionFailureRate": 0.8776,
|
||||
"decisionSuccessRate": 0.1224,
|
||||
"decisionTotal": 196,
|
||||
"decisionFailureRate": 0.8731,
|
||||
"decisionSuccessRate": 0.1269,
|
||||
"decisionTotal": 197,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 131,
|
||||
"backend_operator": 4,
|
||||
@@ -4692,13 +4690,13 @@
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 608,
|
||||
"failureRate": 0.962,
|
||||
"failureRate": 0.9605,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 24,
|
||||
"successRate": 0.038,
|
||||
"total": 632,
|
||||
"successCount": 25,
|
||||
"successRate": 0.0395,
|
||||
"total": 633,
|
||||
"unresolvedFailureCount": 434
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
@@ -4845,21 +4843,21 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 154,
|
||||
"ambiguous_runtime": 156,
|
||||
"memory_capacity": 1,
|
||||
"参数/模板问题": 2,
|
||||
"日志缺失": 1,
|
||||
"验证失败": 23
|
||||
},
|
||||
"failureCount": 181,
|
||||
"failureCount": 183,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 181,
|
||||
"unresolvedFailureCount": 180
|
||||
"total": 183,
|
||||
"unresolvedFailureCount": 182
|
||||
},
|
||||
"Kunlunxin_r-200-8f": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -4886,7 +4884,7 @@
|
||||
"decisionSuccessRate": 0.1807,
|
||||
"decisionTotal": 797,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 297,
|
||||
"ambiguous_runtime": 298,
|
||||
"architecture_compatibility": 21,
|
||||
"backend_operator": 43,
|
||||
"context_length": 59,
|
||||
@@ -4900,15 +4898,15 @@
|
||||
"日志缺失": 15,
|
||||
"验证失败": 48
|
||||
},
|
||||
"failureCount": 1416,
|
||||
"failureRate": 0.9077,
|
||||
"failureCount": 1417,
|
||||
"failureRate": 0.9078,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 5,
|
||||
"successCount": 144,
|
||||
"successRate": 0.0923,
|
||||
"total": 1560,
|
||||
"unresolvedFailureCount": 758
|
||||
"successRate": 0.0922,
|
||||
"total": 1561,
|
||||
"unresolvedFailureCount": 759
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"attributableFailureCount": 69,
|
||||
@@ -6102,7 +6100,7 @@
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 9,
|
||||
"decisionTotal": 10,
|
||||
"failureBreakdown": {},
|
||||
"failureCount": 0,
|
||||
"failureRate": 0.0,
|
||||
@@ -6112,11 +6110,11 @@
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 9,
|
||||
"successCount": 10,
|
||||
"successRate": 1.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 9,
|
||||
"total": 10,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|rwkv7|none": {
|
||||
@@ -8744,6 +8742,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|cohere2|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "cohere2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -8767,6 +8788,29 @@
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gpt_oss|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "gpt_oss",
|
||||
"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
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gpt_oss|mxfp4": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -11155,27 +11199,27 @@
|
||||
},
|
||||
"Biren_166m|vllm|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"consecutiveFailures": 0,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionFailureRate": 0.5,
|
||||
"decisionSuccessRate": 0.5,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"failureRate": 0.5,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-20T06:27:54.872414+00:00",
|
||||
"lastTerminalAt": "2026-09-20T14:32:15.260751+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.5,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
@@ -11452,15 +11496,15 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"ambiguous_runtime": 2,
|
||||
"backend_operator": 1,
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 3,
|
||||
"failureCount": 4,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-20T14:18:03.259001+00:00",
|
||||
"lastTerminalAt": "2026-09-20T14:32:15.260773+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -11468,8 +11512,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 1
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Mthreads_s4000|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -11551,18 +11595,18 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 8,
|
||||
"consecutiveFailures": 8,
|
||||
"attributableFailureCount": 7,
|
||||
"consecutiveFailures": 7,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 8,
|
||||
"decisionTotal": 7,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 2,
|
||||
"framework_architecture_unsupported": 1,
|
||||
"platform_infrastructure": 3,
|
||||
"tokenizer_compatibility": 6
|
||||
},
|
||||
"failureCount": 11,
|
||||
"failureCount": 10,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": "2026-09-16T02:03:21+00:00",
|
||||
@@ -11574,23 +11618,23 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 11,
|
||||
"total": 10,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
"attributableFailureCount": 5,
|
||||
"consecutiveFailures": 5,
|
||||
"attributableFailureCount": 4,
|
||||
"consecutiveFailures": 4,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 5,
|
||||
"decisionTotal": 4,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 1,
|
||||
"framework_architecture_unsupported": 3,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"memory_capacity": 1,
|
||||
"platform_infrastructure": 1
|
||||
},
|
||||
"failureCount": 6,
|
||||
"failureCount": 5,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": "2026-09-15T06:15:21+00:00",
|
||||
@@ -11602,7 +11646,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 6,
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Vastai_va16|unknown|text-generation": {
|
||||
@@ -11810,6 +11854,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|qwen3|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {},
|
||||
"failureCount": 0,
|
||||
"failureRate": 0.0,
|
||||
"framework": "vllm",
|
||||
"lastTerminalAt": "2026-09-20T14:32:15.260751+00:00",
|
||||
"modelType": "qwen3",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 1,
|
||||
"successRate": 1.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|sophia_hybrid|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
@@ -14559,6 +14626,28 @@
|
||||
"total": 8,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|qwen3|none|33": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {},
|
||||
"failureCount": 0,
|
||||
"failureRate": 0.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "qwen3",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 1,
|
||||
"successRate": 1.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|rwkv7|none|32": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -18312,6 +18401,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|cohere2|none|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "cohere2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -18360,6 +18473,30 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gpt_oss|compressed-tensors|35": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 35,
|
||||
"modelType": "gpt_oss",
|
||||
"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
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gpt_oss|mxfp4|34": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -21965,15 +22102,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 15864,
|
||||
"totalRecords": 15969,
|
||||
"terminalRecords": 15868,
|
||||
"totalRecords": 15973,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5755,
|
||||
"decisionFailureRate": 0.8617,
|
||||
"decisionSuccessRate": 0.1383,
|
||||
"decisionTotal": 6679,
|
||||
"decisionFailureRate": 0.8615,
|
||||
"decisionSuccessRate": 0.1385,
|
||||
"decisionTotal": 6680,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3761,
|
||||
"ambiguous_runtime": 3764,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 102,
|
||||
@@ -21989,15 +22126,15 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 14940,
|
||||
"failureRate": 0.9418,
|
||||
"failureCount": 14943,
|
||||
"failureRate": 0.9417,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 922,
|
||||
"successCount": 924,
|
||||
"successRate": 0.0582,
|
||||
"total": 15864,
|
||||
"unresolvedFailureCount": 8263
|
||||
"successCount": 925,
|
||||
"successRate": 0.0583,
|
||||
"total": 15868,
|
||||
"unresolvedFailureCount": 8266
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
@@ -22042,12 +22179,12 @@
|
||||
"组合 Cambricon_mlu-370-x4|unknown|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 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-150|transformers|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
|
||||
"组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 15969,
|
||||
"summarizedRecords": 15973,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T14:32:15.260773+00:00", "modelId": "AI-ModelScope/granite-20b-code-base", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T14:25:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079181", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T14:18:03.259001+00:00", "modelId": "QuantTrio/Kimi-Dev-72B-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T14:17:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079164", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-20T13:34:22.859864+00:00", "modelId": "AI-ModelScope/granite-20b-code-instruct-8k", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-20T13:31:22+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079142", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-20T13:34:22.859810+00:00", "modelId": "KenDual3090tiNvlink/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-W4A16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T13:31:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079137", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -77,6 +78,7 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600306+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:19.045622+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969391", "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", "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600018+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26090095180, "modelscopeLicense": "apache-2.0", "modelscopeParams": 21416999792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26090095180}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:18.989339+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969386", "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": ["zaya"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T11:30:54.600365+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463599, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463599}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:18.452113+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969361", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T14:32:15.260751+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16779959304, "estimatedRequiredGiB": 18.777, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16801630203, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8389956608, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16801630203}, "outcome": "success", "status": "success", "submitTime": "2026-09-20T03:09:18.440547+00:00", "targetGpu": "Biren_166m", "taskId": "4969359", "taskType": "text-generation", "verifyResult": 1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-19T23:13:47.695492+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-19T23:07:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477839", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-19T23:13:47.695526+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-19T23:07:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458016", "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": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-19T23:04:02.598845+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-19T23:03:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4609086", "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": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-13T21:45:41.613474+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:39:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4559290", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-13T21:36:16.709712+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:33:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523305", "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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 64.0, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-13T21:27:15.041934+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:21:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4581573", "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_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["mellum"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-13T21:09:24.912761+00:00", "modelId": "JetBrains/Mellum2-12B-A2.5B-Instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:09:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4152538", "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": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-09-13T21:09:24.912775+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:05:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4490277", "taskType": "text-generation", "verifyResult": -1}
|
||||
|
||||
@@ -1675,6 +1675,8 @@
|
||||
{"batchId": "57a3a03d0f5c4c76a11572c78594f230", "completedAt": "2026-09-20T14:28:10.211887+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:21:54.558997+00:00", "framework": "vllm", "intentId": "8f50ca962288481a83368caec118ffbe", "lastModified": "2026-08-24T22:06:31+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "reason": null, "reconciledAt": "2026-09-20T14:32:12.334698+00:00", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "4980428", "taskType": "text-generation"}
|
||||
{"batchId": "4d04dc039f5549cf9371389c1b1f706e", "completedAt": "2026-09-20T14:32:10.395454+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:28:11.011811+00:00", "framework": "vllm-patch-tokenizer", "intentId": "81d888aa0e354cc2b043e447b5206927", "lastModified": "2026-08-24T20:15:22+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "reason": null, "reconciledAt": "2026-09-20T14:32:12.332103+00:00", "repoId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "4980451", "taskType": "text-generation"}
|
||||
{"batchId": "4d04dc039f5549cf9371389c1b1f706e", "completedAt": "2026-09-20T14:32:10.395505+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:28:11.012921+00:00", "framework": "vllm", "intentId": "01dd835e58d249ee9137f604480faec1", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "reason": null, "reconciledAt": "2026-09-20T14:32:12.332420+00:00", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "4980489", "taskType": "text-generation"}
|
||||
{"batchId": "655a3776a5f5467d867743d63c39ab57", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:32:38.493560+00:00", "framework": "vllm-customized", "intentId": "2f2a2469a3634a43a18f5c90c0f70640", "lastModified": "2026-09-20T14:29:29+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "repoId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
|
||||
{"batchId": "655a3776a5f5467d867743d63c39ab57", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:32:38.493699+00:00", "framework": "vllm-customized", "intentId": "00e2cddb8d974ff4b1a5834fadafa747", "lastModified": "2026-09-19T14:37:29+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "repoId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
|
||||
{"batchId": "4d04dc039f5549cf9371389c1b1f706e", "completedAt": "2026-09-20T14:32:10.395520+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:28:11.013212+00:00", "framework": "vllm", "intentId": "067dad548ff249619ccb5015b035ac8a", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "4d04dc039f5549cf9371389c1b1f706e", "completedAt": "2026-09-20T14:32:10.395517+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:28:11.013153+00:00", "framework": "vllm", "intentId": "cae09738fa024159b29f694cd1b9c73a", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "4d04dc039f5549cf9371389c1b1f706e", "completedAt": "2026-09-20T14:32:10.395514+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T14:28:11.013095+00:00", "framework": "vllm", "intentId": "4dcca8fe8f654fa48aea4a2a3dcbc043", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
|
||||
|
||||
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.20.2",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "b8862deb8994239b880fd8e380c3e15113e5d06294e2354acc35329347eb827f",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "740b7c813cd082839df73e6d2c3947f73e9ab47ed15a8f7c1f23386834f96b64",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "6aaaec7add543b41b41322c1503b50be547f9034862159ed601e4c1a1c61984c",
|
||||
".modelhub_state/official_capabilities.json": "9c04914dd6dd0ec5c686251f5d8d569aa756305743a35a5aa19746d4cde797ab",
|
||||
".modelhub_state/outcome_checkpoint.json": "4b00d785cc5862e528d9c09b67d593e6c88c8c837839923b1bd4a440c329e0ae",
|
||||
".modelhub_state/market_intelligence.json": "e8c19853ac96af4dc2814d0019ae96f6941af99efd7be9dcd0021841a1551070",
|
||||
".modelhub_state/official_capabilities.json": "677aabaf51b5a79bb8dc91c509c94ca0ec41b9b5d92c3d112b13c55759c1a110",
|
||||
".modelhub_state/outcome_checkpoint.json": "1edd803c74d18223d460dabfed7765055373a9fff2f167548cdaf4841af803d9",
|
||||
".modelhub_state/queue_cleanup_latest.json": "eb01f106d0cd4018a0346c4a81182d6a9e67f5d4d14db22f5d0c685667977bc3",
|
||||
".modelhub_state/recent_outcomes.jsonl": "fad94d7ea1d6962f0fe7650d214b0e1aa90a82232ba2448ec1e4c44e89010e61",
|
||||
".modelhub_state/recent_outcomes.jsonl": "e6f221e284e12aa8b2a013d8b066ee4e74e8b8bb745d2750c180a93c92ee9b0f",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "28c0d5e40b30398488d577fd23c5f0f384ee30c58066a72bf20f57f068867dd0",
|
||||
".modelhub_state/recovery_intents.jsonl": "4b92c757a77e6dcd2798d273604657f77402961424c8cf4079b6c4e098186bac",
|
||||
".modelhub_state/recovery_intents.jsonl": "a7de550cc32439a684bb7aba767f33b417ad600eb2ad255e31f034347985476b",
|
||||
".modelhub_state/routing_intelligence.json": "b240146b30dc6d22a338fc0973e8d7e2f34f0be86582e225c0aa2155b3858442",
|
||||
".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7",
|
||||
".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
|
||||
"ledger/submissions.jsonl": "ed173d439711c1c5289b20fb5d9674b4af75880c31d96351c3c5a1c22067b09a",
|
||||
"outcomes/submissions.jsonl": "32a8a46b66fc21be6c344802b2ef95b95893512adf44f28bd217c0ba9e5a1806"
|
||||
"outcomes/submissions.jsonl": "96ef503f05eafd54cc93eeb5223f523c63aac1f9863c49f45f9dae2e46bfc609"
|
||||
},
|
||||
"generation": 10622,
|
||||
"phase": "cycle",
|
||||
"generation": 10623,
|
||||
"phase": "intent",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-20T14:32:12.535855+00:00",
|
||||
"updatedAt": "2026-09-20T14:32:38.615572+00:00",
|
||||
"writerId": "fc715c06e24c4db2ae3e425e435db996"
|
||||
}
|
||||
|
||||
@@ -12,7 +12,6 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T10:41:43.740753+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5700679600, "estimatedRequiredGiB": 6.381, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5709884743, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5709884743}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T02:38:10.748196+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4639409", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T12:40:37.707812+00:00", "modelId": "empero-ai/Qwen3.8-2B-Distill-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "8dbcfce641caa83ec7080451f0410ae2c4732d92c35c6ea116cea836d3424ea2", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2076674432, "estimatedRequiredGiB": 11.564, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10347343046, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1942653248, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:quantized", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:gated-deltanet", "custom_tag:edge", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10347343046}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T04:38:07.789820+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641229", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T12:57:50.112723+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "7fcefcc66e6b781d939ce31d9aa1c7a89bdfb773b9556e6dcde4e21754b1189f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4610579744, "estimatedRequiredGiB": 25.463, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 22784105135, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4326350848, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:quantized", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:gated-deltanet", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22784105135}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T04:56:19.745119+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641463", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T14:51:17.315106+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 44221632439, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T06:48:32.398253+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4643046", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T17:06:08.800571+00:00", "modelId": "LiquidAI/LFM2.5-230M-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "c331f3d8906467b7947cec00daebfec4ccad1f351223a1eced4dea452a1012df", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 149080928, "estimatedRequiredGiB": 2.218, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1984559598, "modelscopeLicense": "other", "modelscopeParams": 229693184, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:gguf", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1984559598}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T09:04:21.884770+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4645136", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T20:12:28.913845+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "e023b149992af42872de3c0c0c07dafd6a98d965e5bdb5a29ec5869e58d45725", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T12:03:37.084154+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4648146", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T20:12:28.913926+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31263441624, "estimatedRequiredGiB": 34.958, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 31280205657, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 30554505408, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_moe", "library:safetensors", "library:other", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 31280205657}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T12:03:37.105603+00:00", "targetGpu": "MetaX_c-500", "taskId": "4648141", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -160,7 +159,6 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T14:29:51.626244+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:28:56.134725+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754659", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T15:03:19.195695+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:56:12.042564+00:00", "targetGpu": "Vastai_va16", "taskId": "4755190", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T15:19:40.009053+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 38162746086, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 38162746086}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:12:26.204766+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755596", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T15:19:40.009045+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:12:26.209710+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755597", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T15:19:40.009069+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "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": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "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": "2026-09-09T14:21:21.949441+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:12:26.214438+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755598", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-10T15:40:28.508808+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:33:41.787375+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4756078", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T15:56:47.546297+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:50:25.385741+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4756398", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -611,7 +609,6 @@
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:10:38.766095+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-Research", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:18.384232+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969360", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:10:38.766040+00:00", "modelId": "aisingapore/SEA-LION-v1-7B", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:18.376994+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969352", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T11:10:38.766149+00:00", "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8046243744, "estimatedRequiredGiB": 9.01, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8062181376, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4023098880, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8062181376}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:18.382878+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969355", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16779959304, "estimatedRequiredGiB": 18.777, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16801630203, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8389956608, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16801630203}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T03:09:18.440547+00:00", "targetGpu": "Biren_166m", "taskId": "4969359", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:10:38.766239+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {"architectures": ["AquilaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6968, "estimatedRequiredGiB": 18.386, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "aquila3", "modelscopeFileSize": 16451477782, "modelscopeLicense": "other", "modelscopeParams": 8223748096, "modelscopeTags": ["license:other", "model_type:aquila3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:arxiv:2406.12182"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16451477782}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:18.437418+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969353", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:10:38.766466+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.742, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663548868, "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": 663548868}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:18.435716+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969354", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:10:38.766339+00:00", "modelId": "sapientinc/HRM-Text-1B", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2365606568, "estimatedRequiredGiB": 2.651, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 2371660433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1182795264, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:hrm", "custom_tag:hierarchical-reasoning", "custom_tag:prefix-lm", "custom_tag:pre-alignment", "custom_tag:non-chat", "custom_tag:non-instruction-tuned"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2371660433}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:18.447188+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969356", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -981,7 +978,7 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T14:18:03.258951+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T06:16:07.269550+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4972172", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658310, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658310}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:17:57.834294+00:00", "targetGpu": "Biren_166m", "taskId": "4972230", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:19:35.394755+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4972231", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2024670536, "estimatedRequiredGiB": 2.273, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033824885, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2033824885}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:31:52.552038+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4972399", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T14:32:15.260743+00:00", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2024670536, "estimatedRequiredGiB": 2.273, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033824885, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2033824885}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T06:31:52.552038+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4972399", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124714, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124714}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:32:07.434077+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4972417", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:33:31.623471+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4972418", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221588, "modelscopeLicense": "llama2", "modelscopeParams": 12247782400, "modelscopeTags": ["license:llama2", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8338221588}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T06:34:00.535697+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4972450", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user