state: generation 21972 (cycle)
This commit is contained in:
@@ -938,6 +938,27 @@
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:mini_k3": {
|
||||
"architectureSignature": "model_type:mini_k3",
|
||||
"architectures": [],
|
||||
"evidenceCount": 2,
|
||||
"expiresAt": "2026-10-21T19:52:49.757664+00:00",
|
||||
"framework": "vllm-mlu",
|
||||
"latestFailureAt": "2026-09-21T19:52:49.757664+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "model_type",
|
||||
"modelType": "mini_k3",
|
||||
"sourceModelIds": [
|
||||
"nkkbr/Mini-K3-1H-decay-g16-v2_B",
|
||||
"nkkbr/Mini-K3-1H-decay-g2-v2_C"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"5006516",
|
||||
"5006512"
|
||||
],
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:nemotron_h": {
|
||||
"architectureSignature": "model_type:nemotron_h",
|
||||
"architectures": [],
|
||||
@@ -2610,25 +2631,6 @@
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"sunrise_pt-200-x1|vllm|text-generation|model_type:qwen3_5_mtp": {
|
||||
"architectureSignature": "model_type:qwen3_5_mtp",
|
||||
"architectures": [],
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-10-07T20:41:21+00:00",
|
||||
"framework": "vllm",
|
||||
"latestFailureAt": "2026-09-07T20:41:21+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "model_type",
|
||||
"modelType": "qwen3_5_mtp",
|
||||
"sourceModelIds": [
|
||||
"mlx-community/Qwen3.8-27B-MTP-4bit"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"4585069"
|
||||
],
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"vastai_va16|vllm_fix_tokenizer|text-generation|model_type:qwen3_5": {
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectures": [],
|
||||
@@ -2855,7 +2857,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-07T20:23:15.150370+00:00",
|
||||
"generatedAt": "2026-10-07T20:46:39.020748+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 144,
|
||||
"byGpuFramework": {
|
||||
@@ -2868,7 +2870,7 @@
|
||||
"Cambricon_mlu-370-x4|vllm-customized": 1,
|
||||
"Cambricon_mlu-370-x8|vllm": 16,
|
||||
"Cambricon_mlu-370-x8|vllm-customized": 6,
|
||||
"Cambricon_mlu-370-x8|vllm-mlu": 4,
|
||||
"Cambricon_mlu-370-x8|vllm-mlu": 5,
|
||||
"Iluvatar_bi-150|transformers": 5,
|
||||
"Iluvatar_bi-150|vllm": 6,
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 3,
|
||||
@@ -2879,7 +2881,7 @@
|
||||
"MetaX_c-500|vllm": 1,
|
||||
"MetaX_c-500|vllm_tokenizer_patch": 2,
|
||||
"Mthreads_s4000|vllm": 6,
|
||||
"Sunrise_pt-200-x1|vllm": 3,
|
||||
"Sunrise_pt-200-x1|vllm": 2,
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 4,
|
||||
"Vastai_va16|vllm": 9,
|
||||
"Vastai_va16|vllm_fix_tokenizer": 2,
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
{
|
||||
"communityAttemptedAt": "2026-10-07T20:34:35.583542+00:00",
|
||||
"communityAttemptedAt": "2026-10-07T20:51:18.638265+00:00",
|
||||
"communityError": null,
|
||||
"communitySample": {},
|
||||
"communityUpdatedAt": "2026-10-07T20:34:35.583542+00:00",
|
||||
"communityUpdatedAt": "2026-10-07T20:51:18.638265+00:00",
|
||||
"frameworkAttemptedAt": "2026-10-07T14:52:53.254460+00:00",
|
||||
"frameworkError": null,
|
||||
"frameworkStats": {
|
||||
@@ -434,121 +434,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-10-07T20:42:02.475394+00:00",
|
||||
"generatedAt": "2026-10-07T20:51:18.638265+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 994.8727272727273,
|
||||
"backlogHours": 1025.5874999999999,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.5841073061902127,
|
||||
"queueFactor": 0.972773473954283,
|
||||
"queueWeight": 0.972773473954283,
|
||||
"recentSuccess": 44,
|
||||
"recentSuccessRate": 0.26666666666666666,
|
||||
"recentTerminal": 165,
|
||||
"recentWilsonLowerBound": 0.20506076068355067,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.5682040934047313,
|
||||
"qualityFactor": 0.631661838609014,
|
||||
"queueFactor": 0.967704595994652,
|
||||
"queueWeight": 0.967704595994652,
|
||||
"recentSuccess": 42,
|
||||
"recentSuccessRate": 0.2625,
|
||||
"recentTerminal": 160,
|
||||
"recentWilsonLowerBound": 0.2004653439900378,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.611262064336375,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 27.5,
|
||||
"waiting": 27359
|
||||
"throughputPerHour": 26.666666666666668,
|
||||
"waiting": 27349
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 865.8840579710145,
|
||||
"backlogHours": 849.2132701421801,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.5091496563333221,
|
||||
"queueFactor": 0.993248428996033,
|
||||
"queueWeight": 0.993248428996033,
|
||||
"recentSuccess": 51,
|
||||
"recentSuccessRate": 0.2463768115942029,
|
||||
"recentTerminal": 207,
|
||||
"recentWilsonLowerBound": 0.19265052989448375,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.5057120962769424,
|
||||
"qualityFactor": 0.5822291150932932,
|
||||
"queueFactor": 0.9954883816225188,
|
||||
"queueWeight": 0.9954883816225188,
|
||||
"recentSuccess": 52,
|
||||
"recentSuccessRate": 0.24644549763033174,
|
||||
"recentTerminal": 211,
|
||||
"recentWilsonLowerBound": 0.19317575228452327,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.5796023195177338,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 34.5,
|
||||
"waiting": 29873
|
||||
"throughputPerHour": 35.166666666666664,
|
||||
"waiting": 29864
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 151.1791907514451,
|
||||
"backlogHours": 153.56470588235294,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.35929270717908796,
|
||||
"queueFactor": 1.2904852527813118,
|
||||
"queueWeight": 1.2904852527813118,
|
||||
"qualityFactor": 0.42491407600529085,
|
||||
"queueFactor": 1.2866043034010424,
|
||||
"queueWeight": 1.2866043034010424,
|
||||
"recentSuccess": 38,
|
||||
"recentSuccessRate": 0.21965317919075145,
|
||||
"recentTerminal": 173,
|
||||
"recentWilsonLowerBound": 0.16441951609425054,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.46366194004648714,
|
||||
"recentSuccessRate": 0.2235294117647059,
|
||||
"recentTerminal": 170,
|
||||
"recentWilsonLowerBound": 0.1674071744406511,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.5466962787640848,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 28.833333333333332,
|
||||
"waiting": 4359
|
||||
"throughputPerHour": 28.333333333333332,
|
||||
"waiting": 4351
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 845.0578512396694,
|
||||
"backlogHours": 831.4146341463414,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 0.9968822936021922,
|
||||
"queueWeight": 0.9968822936021922,
|
||||
"recentSuccess": 13,
|
||||
"recentSuccessRate": 0.10743801652892562,
|
||||
"recentTerminal": 121,
|
||||
"recentWilsonLowerBound": 0.06386907603931685,
|
||||
"qualityFactor": 0.060502550843924315,
|
||||
"queueFactor": 0.9986563362637034,
|
||||
"queueWeight": 0.9986563362637034,
|
||||
"recentSuccess": 14,
|
||||
"recentSuccessRate": 0.11382113821138211,
|
||||
"recentTerminal": 123,
|
||||
"recentWilsonLowerBound": 0.06902221140662215,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.04984411468010961,
|
||||
"selectionWeight": 0.060421255760401894,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 20.166666666666668,
|
||||
"waiting": 17042
|
||||
"throughputPerHour": 20.5,
|
||||
"waiting": 17044
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 320.0571428571428,
|
||||
"backlogHours": 317.4886363636364,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.1729468301061454,
|
||||
"queueFactor": 1.1531683648818816,
|
||||
"queueWeight": 1.1531683648818816,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.1657142857142857,
|
||||
"recentTerminal": 175,
|
||||
"recentWilsonLowerBound": 0.1179285376204559,
|
||||
"qualityFactor": 0.17695802801742005,
|
||||
"queueFactor": 1.1537972079943721,
|
||||
"queueWeight": 1.1537972079943721,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.1590909090909091,
|
||||
"recentTerminal": 176,
|
||||
"recentWilsonLowerBound": 0.11242190844886836,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.19943681328500826,
|
||||
"selectionWeight": 0.20417367865868913,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 29.166666666666668,
|
||||
"waiting": 9335
|
||||
"throughputPerHour": 29.333333333333332,
|
||||
"waiting": 9313
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 111.5028901734104,
|
||||
"backlogHours": 110.3103448275862,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -558,196 +558,196 @@
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 5,
|
||||
"recentSuccessRate": 0.028901734104046242,
|
||||
"recentTerminal": 173,
|
||||
"recentWilsonLowerBound": 0.012406768562089943,
|
||||
"running": 23,
|
||||
"recentSuccessRate": 0.028735632183908046,
|
||||
"recentTerminal": 174,
|
||||
"recentWilsonLowerBound": 0.012335107894271426,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 28.833333333333332,
|
||||
"waiting": 3215
|
||||
"throughputPerHour": 29.0,
|
||||
"waiting": 3199
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 244.97468354430382,
|
||||
"backlogHours": 247.96153846153845,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.21773829945306789,
|
||||
"queueFactor": 1.2003521303700717,
|
||||
"queueWeight": 1.2003521303700717,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.18354430379746836,
|
||||
"recentTerminal": 158,
|
||||
"recentWilsonLowerBound": 0.13094338351791776,
|
||||
"running": 1,
|
||||
"selectionWeight": 0.26136263161164663,
|
||||
"qualityFactor": 0.23220427777392894,
|
||||
"queueFactor": 1.1973774177362513,
|
||||
"queueWeight": 1.1973774177362513,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.1794871794871795,
|
||||
"recentTerminal": 156,
|
||||
"recentWilsonLowerBound": 0.12720005313332733,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.27803615850825825,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 26.333333333333332,
|
||||
"waiting": 6451
|
||||
"throughputPerHour": 26.0,
|
||||
"waiting": 6447
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 3100.0,
|
||||
"backlogHours": 2906.4375,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.8710339491869156,
|
||||
"queueFactor": 0.8202997785483847,
|
||||
"queueWeight": 0.8202997785483847,
|
||||
"recentSuccess": 12,
|
||||
"recentSuccessRate": 0.4,
|
||||
"recentTerminal": 30,
|
||||
"recentWilsonLowerBound": 0.24590394326083398,
|
||||
"qualityFactor": 1.0742695736437782,
|
||||
"queueFactor": 0.8277221235518403,
|
||||
"queueWeight": 0.8277221235518403,
|
||||
"recentSuccess": 13,
|
||||
"recentSuccessRate": 0.40625,
|
||||
"recentTerminal": 32,
|
||||
"recentWilsonLowerBound": 0.25519402480313796,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.7145089556261518,
|
||||
"selectionWeight": 0.8891966927635582,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 5.0,
|
||||
"waiting": 15500
|
||||
"throughputPerHour": 5.333333333333333,
|
||||
"waiting": 15501
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 380.13698630136986,
|
||||
"backlogHours": 393.531914893617,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.3372189150304138,
|
||||
"queueFactor": 1.1237917235058272,
|
||||
"queueWeight": 1.1237917235058272,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.2191780821917808,
|
||||
"recentTerminal": 146,
|
||||
"recentWilsonLowerBound": 0.1597484989176162,
|
||||
"qualityFactor": 0.3500907489630994,
|
||||
"queueFactor": 1.1172277588057893,
|
||||
"queueWeight": 1.1172277588057893,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.2127659574468085,
|
||||
"recentTerminal": 141,
|
||||
"recentWilsonLowerBound": 0.15329835090284474,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.37896382572079385,
|
||||
"selectionWeight": 0.3911311028426837,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 24.333333333333332,
|
||||
"waiting": 9250
|
||||
"throughputPerHour": 23.5,
|
||||
"waiting": 9248
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 606.3333333333334,
|
||||
"backlogHours": 589.9459459459459,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.16557877999049375,
|
||||
"queueFactor": 1.0477800659663077,
|
||||
"queueWeight": 1.0477800659663077,
|
||||
"qualityFactor": 0.17691190556587755,
|
||||
"queueFactor": 1.0513973507455043,
|
||||
"queueWeight": 1.0513973507455043,
|
||||
"recentSuccess": 19,
|
||||
"recentSuccessRate": 0.17592592592592593,
|
||||
"recentTerminal": 108,
|
||||
"recentWilsonLowerBound": 0.11561771988481864,
|
||||
"recentSuccessRate": 0.17117117117117117,
|
||||
"recentTerminal": 111,
|
||||
"recentWilsonLowerBound": 0.11240858853979097,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.17349014502106028,
|
||||
"selectionWeight": 0.1860047088273025,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.0,
|
||||
"throughputPerHour": 18.5,
|
||||
"waiting": 10914
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 1979.6363636363637,
|
||||
"backlogHours": 2009.5384615384614,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.8773826356093474,
|
||||
"queueWeight": 0.8773826356093474,
|
||||
"recentSuccess": 34,
|
||||
"recentSuccessRate": 0.5151515151515151,
|
||||
"recentTerminal": 66,
|
||||
"recentWilsonLowerBound": 0.39710384843935753,
|
||||
"running": 4,
|
||||
"selectionWeight": 2.1934565890233686,
|
||||
"queueFactor": 0.8748311995589921,
|
||||
"queueWeight": 0.8748311995589921,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.49230769230769234,
|
||||
"recentTerminal": 65,
|
||||
"recentWilsonLowerBound": 0.3746363604246928,
|
||||
"running": 5,
|
||||
"selectionWeight": 2.1870779988974802,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 11.0,
|
||||
"waiting": 21776
|
||||
"throughputPerHour": 10.833333333333334,
|
||||
"waiting": 21770
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 2566.35,
|
||||
"backlogHours": 2503.756097560976,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 0.8438776126516989,
|
||||
"queueWeight": 0.8438776126516989,
|
||||
"queueFactor": 0.8464472698273912,
|
||||
"queueWeight": 0.8464472698273912,
|
||||
"recentSuccess": 5,
|
||||
"recentSuccessRate": 0.125,
|
||||
"recentTerminal": 40,
|
||||
"recentWilsonLowerBound": 0.05459419773541283,
|
||||
"recentSuccessRate": 0.12195121951219512,
|
||||
"recentTerminal": 41,
|
||||
"recentWilsonLowerBound": 0.05323257997340823,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.042193880632584946,
|
||||
"selectionWeight": 0.04232236349136956,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 6.666666666666667,
|
||||
"throughputPerHour": 6.833333333333333,
|
||||
"waiting": 17109
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 810.2380952380952,
|
||||
"backlogHours": 816.576,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.0031940544074367,
|
||||
"queueWeight": 1.0031940544074367,
|
||||
"queueFactor": 1.0013576495373988,
|
||||
"queueWeight": 1.0013576495373988,
|
||||
"recentSuccess": 2,
|
||||
"recentSuccessRate": 0.015873015873015872,
|
||||
"recentTerminal": 126,
|
||||
"recentWilsonLowerBound": 0.004363710388782352,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.05015970272037184,
|
||||
"recentSuccessRate": 0.016,
|
||||
"recentTerminal": 125,
|
||||
"recentWilsonLowerBound": 0.004398708009065916,
|
||||
"running": 18,
|
||||
"selectionWeight": 0.05006788247686994,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 21.0,
|
||||
"waiting": 17015
|
||||
"throughputPerHour": 20.833333333333332,
|
||||
"waiting": 17012
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 1080.1525423728813,
|
||||
"backlogHours": 1089.3846153846155,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.2548702183220512,
|
||||
"queueFactor": 0.9608466593943009,
|
||||
"queueWeight": 0.9608466593943009,
|
||||
"qualityFactor": 0.2953582887152072,
|
||||
"queueFactor": 0.9589843633405856,
|
||||
"queueWeight": 0.9589843633405856,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.2033898305084746,
|
||||
"recentTerminal": 118,
|
||||
"recentWilsonLowerBound": 0.14065893187319645,
|
||||
"recentSuccessRate": 0.20512820512820512,
|
||||
"recentTerminal": 117,
|
||||
"recentWilsonLowerBound": 0.14189847337772166,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.24489119785383903,
|
||||
"selectionWeight": 0.2832439804609178,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 19.666666666666668,
|
||||
"throughputPerHour": 19.5,
|
||||
"waiting": 21243
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-10-07T20:34:35.583542+00:00",
|
||||
"queueAttemptedAt": "2026-10-07T20:51:18.638265+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-10-07T20:34:35.583542+00:00",
|
||||
"queueUpdatedAt": "2026-10-07T20:51:18.638265+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Cambricon_mlu-370-x4",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-10-07T20:27:38.228192+00:00",
|
||||
"lastSyncTime": "2026-10-07T20:27:38.158968+00:00",
|
||||
"generatedAt": "2026-10-07T20:51:18.537061+00:00",
|
||||
"lastSyncTime": "2026-10-07T20:51:18.470436+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -942,6 +942,27 @@
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:mini_k3": {
|
||||
"architectureSignature": "model_type:mini_k3",
|
||||
"architectures": [],
|
||||
"evidenceCount": 2,
|
||||
"expiresAt": "2026-10-21T19:52:49.757664+00:00",
|
||||
"framework": "vllm-mlu",
|
||||
"latestFailureAt": "2026-09-21T19:52:49.757664+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "model_type",
|
||||
"modelType": "mini_k3",
|
||||
"sourceModelIds": [
|
||||
"nkkbr/Mini-K3-1H-decay-g16-v2_B",
|
||||
"nkkbr/Mini-K3-1H-decay-g2-v2_C"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"5006516",
|
||||
"5006512"
|
||||
],
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:nemotron_h": {
|
||||
"architectureSignature": "model_type:nemotron_h",
|
||||
"architectures": [],
|
||||
@@ -2614,25 +2635,6 @@
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"sunrise_pt-200-x1|vllm|text-generation|model_type:qwen3_5_mtp": {
|
||||
"architectureSignature": "model_type:qwen3_5_mtp",
|
||||
"architectures": [],
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-10-07T20:41:21+00:00",
|
||||
"framework": "vllm",
|
||||
"latestFailureAt": "2026-09-07T20:41:21+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "model_type",
|
||||
"modelType": "qwen3_5_mtp",
|
||||
"sourceModelIds": [
|
||||
"mlx-community/Qwen3.8-27B-MTP-4bit"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"4585069"
|
||||
],
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"vastai_va16|vllm_fix_tokenizer|text-generation|model_type:qwen3_5": {
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectures": [],
|
||||
@@ -2871,7 +2873,7 @@
|
||||
"Cambricon_mlu-370-x4|vllm-customized": 1,
|
||||
"Cambricon_mlu-370-x8|vllm": 16,
|
||||
"Cambricon_mlu-370-x8|vllm-customized": 6,
|
||||
"Cambricon_mlu-370-x8|vllm-mlu": 4,
|
||||
"Cambricon_mlu-370-x8|vllm-mlu": 5,
|
||||
"Iluvatar_bi-150|transformers": 5,
|
||||
"Iluvatar_bi-150|vllm": 6,
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 3,
|
||||
@@ -2882,7 +2884,7 @@
|
||||
"MetaX_c-500|vllm": 1,
|
||||
"MetaX_c-500|vllm_tokenizer_patch": 2,
|
||||
"Mthreads_s4000|vllm": 6,
|
||||
"Sunrise_pt-200-x1|vllm": 3,
|
||||
"Sunrise_pt-200-x1|vllm": 2,
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 4,
|
||||
"Vastai_va16|vllm": 9,
|
||||
"Vastai_va16|vllm_fix_tokenizer": 2,
|
||||
@@ -3297,10 +3299,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 131,
|
||||
"ambiguous_runtime": 133,
|
||||
"memory_capacity": 1
|
||||
},
|
||||
"failureCount": 132,
|
||||
"failureCount": 134,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
@@ -3310,8 +3312,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 132,
|
||||
"unresolvedFailureCount": 131
|
||||
"total": 134,
|
||||
"unresolvedFailureCount": 133
|
||||
},
|
||||
"Biren_166m|vllm|text-generation": {
|
||||
"attributableFailureCount": 50,
|
||||
@@ -3562,28 +3564,28 @@
|
||||
"unresolvedFailureCount": 47
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
|
||||
"attributableFailureCount": 19,
|
||||
"decisionFailureRate": 0.5938,
|
||||
"decisionSuccessRate": 0.4062,
|
||||
"decisionTotal": 32,
|
||||
"attributableFailureCount": 21,
|
||||
"decisionFailureRate": 0.6176,
|
||||
"decisionSuccessRate": 0.3824,
|
||||
"decisionTotal": 34,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 54,
|
||||
"framework_architecture_unsupported": 15,
|
||||
"framework_architecture_unsupported": 17,
|
||||
"model_load": 3,
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 3
|
||||
},
|
||||
"failureCount": 76,
|
||||
"failureRate": 0.8539,
|
||||
"failureCount": 78,
|
||||
"failureRate": 0.8571,
|
||||
"framework": "vllm-mlu",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 13,
|
||||
"successRate": 0.1461,
|
||||
"successRate": 0.1429,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 89,
|
||||
"total": 91,
|
||||
"unresolvedFailureCount": 57
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm|text-generation": {
|
||||
@@ -5053,14 +5055,14 @@
|
||||
"unresolvedFailureCount": 7
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
"attributableFailureCount": 621,
|
||||
"attributableFailureCount": 622,
|
||||
"decisionFailureRate": 0.9904,
|
||||
"decisionSuccessRate": 0.0096,
|
||||
"decisionTotal": 627,
|
||||
"decisionTotal": 628,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 109,
|
||||
"architecture_compatibility": 43,
|
||||
"backend_operator": 29,
|
||||
"backend_operator": 30,
|
||||
"context_length": 34,
|
||||
"framework_architecture_unsupported": 146,
|
||||
"memory_capacity": 113,
|
||||
@@ -5070,7 +5072,7 @@
|
||||
"tokenizer_compatibility": 180,
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 955,
|
||||
"failureCount": 956,
|
||||
"failureRate": 0.9938,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -5080,7 +5082,7 @@
|
||||
"successRate": 0.0062,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 961,
|
||||
"total": 962,
|
||||
"unresolvedFailureCount": 118
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|unknown": {
|
||||
@@ -5583,15 +5585,15 @@
|
||||
"unresolvedFailureCount": 6477
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3669,
|
||||
"attributableFailureCount": 3670,
|
||||
"decisionFailureRate": 0.9719,
|
||||
"decisionSuccessRate": 0.0281,
|
||||
"decisionTotal": 3775,
|
||||
"decisionTotal": 3776,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1602,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 94,
|
||||
"backend_operator": 95,
|
||||
"context_length": 161,
|
||||
"framework_architecture_unsupported": 1390,
|
||||
"memory_capacity": 725,
|
||||
@@ -5602,14 +5604,14 @@
|
||||
"tokenizer_compatibility": 420,
|
||||
"参数/模板问题": 50
|
||||
},
|
||||
"failureCount": 6201,
|
||||
"failureCount": 6202,
|
||||
"failureRate": 0.9832,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 880,
|
||||
"successCount": 106,
|
||||
"successRate": 0.0168,
|
||||
"total": 6307,
|
||||
"total": 6308,
|
||||
"unresolvedFailureCount": 1652
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -5636,27 +5638,27 @@
|
||||
"unresolvedFailureCount": 51
|
||||
},
|
||||
"vllm-mlu": {
|
||||
"attributableFailureCount": 45,
|
||||
"decisionFailureRate": 0.6716,
|
||||
"decisionSuccessRate": 0.3284,
|
||||
"decisionTotal": 67,
|
||||
"attributableFailureCount": 47,
|
||||
"decisionFailureRate": 0.6812,
|
||||
"decisionSuccessRate": 0.3188,
|
||||
"decisionTotal": 69,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 103,
|
||||
"framework_architecture_unsupported": 37,
|
||||
"framework_architecture_unsupported": 39,
|
||||
"model_load": 7,
|
||||
"platform_infrastructure": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 4,
|
||||
"验证失败": 3
|
||||
},
|
||||
"failureCount": 156,
|
||||
"failureRate": 0.8764,
|
||||
"failureCount": 158,
|
||||
"failureRate": 0.8778,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 22,
|
||||
"successRate": 0.1236,
|
||||
"total": 178,
|
||||
"successRate": 0.1222,
|
||||
"total": 180,
|
||||
"unresolvedFailureCount": 110
|
||||
},
|
||||
"vllm-patch-tokenizer": {
|
||||
@@ -5712,7 +5714,7 @@
|
||||
"decisionSuccessRate": 0.0275,
|
||||
"decisionTotal": 182,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 376,
|
||||
"ambiguous_runtime": 378,
|
||||
"backend_operator": 9,
|
||||
"framework_architecture_unsupported": 49,
|
||||
"memory_capacity": 10,
|
||||
@@ -5721,15 +5723,15 @@
|
||||
"tokenizer_compatibility": 96,
|
||||
"参数/模板问题": 13
|
||||
},
|
||||
"failureCount": 593,
|
||||
"failureRate": 0.9916,
|
||||
"failureCount": 595,
|
||||
"failureRate": 0.9917,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 27,
|
||||
"successCount": 5,
|
||||
"successRate": 0.0084,
|
||||
"total": 598,
|
||||
"unresolvedFailureCount": 389
|
||||
"successRate": 0.0083,
|
||||
"total": 600,
|
||||
"unresolvedFailureCount": 391
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 158,
|
||||
@@ -5760,7 +5762,7 @@
|
||||
"unresolvedFailureCount": 257
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-07T20:27:38.211324+00:00",
|
||||
"generatedAt": "2026-10-07T20:51:18.520624+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 120,
|
||||
@@ -5823,7 +5825,7 @@
|
||||
"decisionSuccessRate": 0.1147,
|
||||
"decisionTotal": 218,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 275,
|
||||
"ambiguous_runtime": 277,
|
||||
"backend_operator": 4,
|
||||
"context_length": 10,
|
||||
"framework_architecture_unsupported": 125,
|
||||
@@ -5837,15 +5839,15 @@
|
||||
"日志缺失": 62,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 773,
|
||||
"failureRate": 0.9687,
|
||||
"failureCount": 775,
|
||||
"failureRate": 0.9688,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 25,
|
||||
"successRate": 0.0313,
|
||||
"total": 798,
|
||||
"unresolvedFailureCount": 578
|
||||
"successRate": 0.0312,
|
||||
"total": 800,
|
||||
"unresolvedFailureCount": 580
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"attributableFailureCount": 759,
|
||||
@@ -5877,13 +5879,13 @@
|
||||
"unresolvedFailureCount": 856
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"attributableFailureCount": 65,
|
||||
"decisionFailureRate": 0.8125,
|
||||
"decisionSuccessRate": 0.1875,
|
||||
"decisionTotal": 80,
|
||||
"attributableFailureCount": 67,
|
||||
"decisionFailureRate": 0.8171,
|
||||
"decisionSuccessRate": 0.1829,
|
||||
"decisionTotal": 82,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 158,
|
||||
"framework_architecture_unsupported": 52,
|
||||
"framework_architecture_unsupported": 54,
|
||||
"memory_capacity": 4,
|
||||
"model_load": 6,
|
||||
"platform_infrastructure": 2,
|
||||
@@ -5891,14 +5893,14 @@
|
||||
"参数/模板问题": 41,
|
||||
"验证失败": 22
|
||||
},
|
||||
"failureCount": 288,
|
||||
"failureRate": 0.9505,
|
||||
"failureCount": 290,
|
||||
"failureRate": 0.9508,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 15,
|
||||
"successRate": 0.0495,
|
||||
"total": 303,
|
||||
"successRate": 0.0492,
|
||||
"total": 305,
|
||||
"unresolvedFailureCount": 221
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
@@ -6096,14 +6098,14 @@
|
||||
"unresolvedFailureCount": 303
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"attributableFailureCount": 769,
|
||||
"decisionFailureRate": 0.8859,
|
||||
"decisionSuccessRate": 0.1141,
|
||||
"decisionTotal": 868,
|
||||
"attributableFailureCount": 770,
|
||||
"decisionFailureRate": 0.8861,
|
||||
"decisionSuccessRate": 0.1139,
|
||||
"decisionTotal": 869,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 163,
|
||||
"architecture_compatibility": 44,
|
||||
"backend_operator": 38,
|
||||
"backend_operator": 39,
|
||||
"context_length": 39,
|
||||
"framework_architecture_unsupported": 172,
|
||||
"memory_capacity": 113,
|
||||
@@ -6114,14 +6116,14 @@
|
||||
"参数/模板问题": 228,
|
||||
"验证失败": 32
|
||||
},
|
||||
"failureCount": 1435,
|
||||
"failureCount": 1436,
|
||||
"failureRate": 0.9355,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 243,
|
||||
"successCount": 99,
|
||||
"successRate": 0.0645,
|
||||
"total": 1534,
|
||||
"total": 1535,
|
||||
"unresolvedFailureCount": 423
|
||||
},
|
||||
"Vastai_va16": {
|
||||
@@ -6201,7 +6203,7 @@
|
||||
"hygon_k100-ai": 64.0
|
||||
},
|
||||
"pendingRecords": 0,
|
||||
"policyCancelledRecords": 340,
|
||||
"policyCancelledRecords": 364,
|
||||
"profileCombinationStats": {
|
||||
"Ascend_910-b3|llamacpp|text-generation|smollm3|none": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -9288,9 +9290,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2
|
||||
"ambiguous_runtime": 4
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 4,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "mini_k3",
|
||||
@@ -9302,8 +9304,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation|mistral3|none": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -13403,6 +13405,29 @@
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|mini_k3|none": {
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 2
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"modelType": "mini_k3",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|mistral|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -22943,14 +22968,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|llama|awq": {
|
||||
"attributableFailureCount": 1,
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 1
|
||||
"backend_operator": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "llama",
|
||||
@@ -22962,7 +22987,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|llama|bitsandbytes": {
|
||||
@@ -25531,23 +25556,22 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3,
|
||||
"platform_infrastructure": 1
|
||||
"ambiguous_runtime": 2
|
||||
},
|
||||
"failureCount": 4,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": "2026-09-21T09:13:58.610056+00:00",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-23T11:53:41.349992+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 3
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 2,
|
||||
@@ -25583,9 +25607,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 12
|
||||
"ambiguous_runtime": 14
|
||||
},
|
||||
"failureCount": 12,
|
||||
"failureCount": 14,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -25597,8 +25621,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 12,
|
||||
"unresolvedFailureCount": 12
|
||||
"total": 14,
|
||||
"unresolvedFailureCount": 14
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -25737,10 +25761,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 17,
|
||||
"ambiguous_runtime": 16,
|
||||
"参数/模板问题": 1
|
||||
},
|
||||
"failureCount": 18,
|
||||
"failureCount": 17,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-customized",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -25752,21 +25776,21 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 18,
|
||||
"unresolvedFailureCount": 18
|
||||
"total": 17,
|
||||
"unresolvedFailureCount": 17
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"attributableFailureCount": 3,
|
||||
"consecutiveFailures": 3,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 1
|
||||
"framework_architecture_unsupported": 3
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 4,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -25778,7 +25802,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Iluvatar_bi-150|transformers|text-generation": {
|
||||
@@ -25808,31 +25832,6 @@
|
||||
"total": 16,
|
||||
"unresolvedFailureCount": 11
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_0_17_0_corex_4_4_0",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-21T18:39:29.750819+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 2,
|
||||
"consecutiveFailures": 2,
|
||||
@@ -26640,9 +26639,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastTerminalAt": "2026-09-23T05:33:38.855687+00:00",
|
||||
@@ -26655,33 +26654,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation|qwen2|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"platform_infrastructure": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastTerminalAt": "2026-09-23T12:29:42.455438+00:00",
|
||||
"modelType": "qwen2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation|qwen3|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -26790,12 +26764,12 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2
|
||||
"ambiguous_runtime": 4
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 4,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastTerminalAt": "2026-10-07T16:12:59.741949+00:00",
|
||||
"lastTerminalAt": "2026-10-07T20:46:38.448901+00:00",
|
||||
"modelType": "mini_k3",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
@@ -26805,8 +26779,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation|muse_glimmer|none": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -27383,31 +27357,6 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-customized|text-generation|spark2_5|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-customized",
|
||||
"lastTerminalAt": "2026-09-22T01:48:12.547533+00:00",
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-customized|text-generation|starcoder2|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -27433,6 +27382,31 @@
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|mini_k3|none": {
|
||||
"attributableFailureCount": 2,
|
||||
"consecutiveFailures": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 2
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"lastTerminalAt": "2026-10-07T20:46:38.448824+00:00",
|
||||
"modelType": "mini_k3",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|mistral|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -27758,31 +27732,6 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|starcoder2|compressed-tensors": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_0_17_0_corex_4_4_0",
|
||||
"lastTerminalAt": "2026-09-21T18:39:29.750819+00:00",
|
||||
"modelType": "starcoder2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -34739,9 +34688,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2
|
||||
"ambiguous_runtime": 4
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 4,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 30,
|
||||
@@ -34754,8 +34703,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Biren_166m|vllm_fix_tokenizer|text-generation|mistral3|none|34": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -41011,6 +40960,30 @@
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|mini_k3|none|30": {
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 2
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"loadSizeLog2Bucket": 30,
|
||||
"modelType": "mini_k3",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|mistral|compressed-tensors|33": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -55186,6 +55159,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|llama|awq|33": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "awq",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|llama|bitsandbytes|31": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -58884,20 +58881,20 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17426,
|
||||
"totalRecords": 17766,
|
||||
"terminalRecords": 17431,
|
||||
"totalRecords": 17795,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6256,
|
||||
"attributableFailureCount": 6259,
|
||||
"decisionFailureRate": 0.8647,
|
||||
"decisionSuccessRate": 0.1353,
|
||||
"decisionTotal": 7235,
|
||||
"decisionTotal": 7238,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4575,
|
||||
"ambiguous_runtime": 4577,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 129,
|
||||
"backend_operator": 130,
|
||||
"context_length": 327,
|
||||
"framework_architecture_unsupported": 2275,
|
||||
"framework_architecture_unsupported": 2277,
|
||||
"memory_capacity": 1206,
|
||||
"model_load": 571,
|
||||
"platform_infrastructure": 955,
|
||||
@@ -58908,15 +58905,15 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16447,
|
||||
"failureCount": 16452,
|
||||
"failureRate": 0.9438,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 955,
|
||||
"successCount": 979,
|
||||
"successRate": 0.0562,
|
||||
"total": 17426,
|
||||
"unresolvedFailureCount": 9236
|
||||
"total": 17431,
|
||||
"unresolvedFailureCount": 9238
|
||||
},
|
||||
"warnings": [
|
||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
@@ -58965,6 +58962,7 @@
|
||||
"组合 Ascend_910-b4|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_mrv-100|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 Cambricon_mlu-370-x8|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x4|vllm-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-150|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -58977,6 +58975,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17766,
|
||||
"summarizedRecords": 17795,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -100,11 +100,15 @@
|
||||
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-22T01:23:49.082789+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:23:31+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4925021", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T18:18:51.743129+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039076183}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T22:21:59.843515+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5008078", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["mini_k3"], "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T20:23:14.668330+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T22:14:33.594032+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5008009", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T20:46:38.448901+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039076183}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T20:38:42.647821+00:00", "targetGpu": "Biren_166m", "taskId": "5007028", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T16:12:59.741949+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T20:38:42.646739+00:00", "targetGpu": "Biren_166m", "taskId": "5007027", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T16:12:59.741980+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T20:37:39.964394+00:00", "targetGpu": "Biren_166m", "taskId": "5007017", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T20:46:38.448886+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042280856}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T20:37:39.963184+00:00", "targetGpu": "Biren_166m", "taskId": "5007018", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T20:23:14.668297+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042280856}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T20:22:32.047761+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5006825", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T15:52:48.873111+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T20:16:38.547857+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5006761", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T13:29:11.757302+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T20:12:49.394711+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5006730", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["mini_k3"], "framework": "vllm-mlu", "lastSyncTime": "2026-10-07T20:46:38.448824+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:52:49.757664+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006516", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["mini_k3"], "framework": "vllm-mlu", "lastSyncTime": "2026-10-07T20:46:38.448855+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039076183}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:52:49.749531+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006512", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-25T01:41:30.953868+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"ambiguous_runtime": 4, "model_load": 1}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T19:49:37.657075+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 4}, "repositoryOnDiskBytes": 955857175}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:49:53.770533+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006460", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164621+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 5}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T16:50:30.559192+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5}, "repositoryOnDiskBytes": 19329296879}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:37:12.653471+00:00", "targetGpu": "Biren_166m", "taskId": "5006368", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["mini_k3"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T19:02:02.168317+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:37:12.447446+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006364", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -294,7 +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": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-23T10:48:31.671315+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231252716, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233101396, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T08:44:09.587569+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 1233101396}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:19:32.876555+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4997864", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-09-27T13:43:22.766786+00:00", "modelId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13594088584, "estimatedRequiredGiB": 15.203, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 13603621925, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12247782400, "modelscopeTags": ["license:apache-2.0", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 13603621925}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:19:32.873304+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4997863", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-10-02T10:43:40.858838+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231270112, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233118759, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1233118759}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:19:32.868721+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997865", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "platform_infrastructure", "failureAction": "open_short_gpu_framework_circuit_and_retry_other_models", "failureCategory": "platform_infrastructure", "failureClassificationReason": "platform_io_transient", "failureCode": "STORAGE_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-23T12:29:42.455438+00:00", "modelId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2245331488, "estimatedRequiredGiB": 2.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 2256941144, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2256941144}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:13:58.610056+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4997803", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-24T10:43:18.860153+00:00", "modelId": "nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504988, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504988}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:13:51.958882+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4997802", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-22T01:48:12.547533+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430847031, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430847031}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:10:32.259004+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4997718", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-21T18:39:29.750819+00:00", "modelId": "RedHatAI/starcoder2-15b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16564748304, "estimatedRequiredGiB": 18.516, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 16568142065, "modelscopeLicense": "other", "modelscopeParams": 15957889024, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastTerminalAt": "2026-09-20T12:58:28.353096+00:00", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 16568142065}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:05:59.142974+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4997663", "taskType": "text-generation", "verifyResult": -1}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user