state: generation 18077 (cycle)

This commit is contained in:
2026-09-28 21:23:37 +00:00
parent a0efaa0800
commit be0d8e56f4
8 changed files with 1682 additions and 1683 deletions

View File

@@ -3280,7 +3280,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-28T21:11:50.064284+00:00",
"generatedAt": "2026-09-28T21:19:49.366356+00:00",
"summary": {
"activeBlockCount": 165,
"byGpuFramework": {

View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-09-28T21:05:57.164298+00:00",
"communityAttemptedAt": "2026-09-28T21:21:32.684343+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-09-28T21:05:57.164298+00:00",
"communityUpdatedAt": "2026-09-28T21:21:32.684343+00:00",
"frameworkAttemptedAt": "2026-09-28T21:05:57.164298+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -396,99 +396,99 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-28T21:18:46.960737+00:00",
"generatedAt": "2026-09-28T21:21:32.684343+00:00",
"gpuStats": {
"Ascend_910-b4": {
"available": true,
"backlogHours": 1359.75,
"backlogHours": 1318.4545454545455,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.19642164413464,
"queueFactor": 0.9524651722560814,
"queueWeight": 0.9524651722560814,
"qualityFactor": 2.023963406619132,
"queueFactor": 0.9569014848920977,
"queueWeight": 0.9569014848920977,
"recentSuccess": 56,
"recentSuccessRate": 0.4375,
"recentTerminal": 128,
"recentWilsonLowerBound": 0.3546216845248092,
"recentSuccessRate": 0.42424242424242425,
"recentTerminal": 132,
"recentWilsonLowerBound": 0.3432446996414888,
"running": 8,
"selectionWeight": 2.092015119627685,
"selectionWeight": 1.9367335891611157,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 21.333333333333332,
"waiting": 29008
"throughputPerHour": 22.0,
"waiting": 29006
},
"Biren_166m": {
"available": true,
"backlogHours": 140.76190476190476,
"backlogHours": 140.14736842105262,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.06955784102362571,
"qualityFactor": 0.06805564574278564,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 21,
"recentSuccessRate": 0.1111111111111111,
"recentTerminal": 189,
"recentWilsonLowerBound": 0.07383013159753107,
"recentSuccessRate": 0.11052631578947368,
"recentTerminal": 190,
"recentWilsonLowerBound": 0.07343524071279467,
"running": 8,
"selectionWeight": 0.09042519333071343,
"selectionWeight": 0.08847233946562133,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 31.5,
"waiting": 4434
"throughputPerHour": 31.666666666666668,
"waiting": 4438
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1083.139534883721,
"backlogHours": 1070.7586206896551,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.26971328299790587,
"queueFactor": 0.9855196845322598,
"queueWeight": 0.9855196845322598,
"qualityFactor": 0.2600887700078577,
"queueFactor": 0.9872411877216425,
"queueWeight": 0.9872411877216425,
"recentSuccess": 18,
"recentSuccessRate": 0.20930232558139536,
"recentTerminal": 86,
"recentWilsonLowerBound": 0.13669707033094278,
"recentSuccessRate": 0.20689655172413793,
"recentTerminal": 87,
"recentWilsonLowerBound": 0.13507251809274734,
"running": 7,
"selectionWeight": 0.2658077495742563,
"selectionWeight": 0.2567703462156185,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 14.333333333333334,
"waiting": 15525
"throughputPerHour": 14.5,
"waiting": 15526
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 372.50349650349654,
"backlogHours": 365.013698630137,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.05185564533557147,
"queueFactor": 1.1566405431709552,
"queueWeight": 1.1566405431709552,
"qualityFactor": 0.05,
"queueFactor": 1.1601940350026207,
"queueWeight": 1.1601940350026207,
"recentSuccess": 15,
"recentSuccessRate": 0.1048951048951049,
"recentTerminal": 143,
"recentWilsonLowerBound": 0.06460354458062817,
"recentSuccessRate": 0.10273972602739725,
"recentTerminal": 146,
"recentWilsonLowerBound": 0.06325439180443915,
"running": 7,
"selectionWeight": 0.0599783417874158,
"selectionWeight": 0.05800970175013104,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 23.833333333333332,
"waiting": 8878
"throughputPerHour": 24.333333333333332,
"waiting": 8882
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 43.26623376623377,
"backlogHours": 42.63461538461539,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -498,37 +498,37 @@
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 5,
"recentSuccessRate": 0.016233766233766232,
"recentTerminal": 308,
"recentWilsonLowerBound": 0.006953412609498495,
"recentSuccessRate": 0.016025641025641024,
"recentTerminal": 312,
"recentWilsonLowerBound": 0.0068640189915155185,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 51.333333333333336,
"waiting": 2221
"throughputPerHour": 52.0,
"waiting": 2217
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 136.9090909090909,
"backlogHours": 140.77570093457945,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.26867218855657177,
"qualityFactor": 0.2652141236906276,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 40,
"recentSuccessRate": 0.18181818181818182,
"recentTerminal": 220,
"recentWilsonLowerBound": 0.1364569758469753,
"running": 6,
"selectionWeight": 0.3492738451235433,
"recentSuccess": 39,
"recentSuccessRate": 0.1822429906542056,
"recentTerminal": 214,
"recentWilsonLowerBound": 0.13627597269107244,
"running": 7,
"selectionWeight": 0.3447783607978159,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 36.666666666666664,
"waiting": 5020
"throughputPerHour": 35.666666666666664,
"waiting": 5021
},
"Iluvatar_mrv-100": {
"available": true,
@@ -538,15 +538,15 @@
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.2098745516970382,
"queueFactor": 0.8791781078059884,
"queueWeight": 0.8791781078059884,
"qualityFactor": 1.1977949310243006,
"queueFactor": 0.879196405147463,
"queueWeight": 0.879196405147463,
"recentSuccess": 17,
"recentSuccessRate": 0.40476190476190477,
"recentTerminal": 42,
"recentWilsonLowerBound": 0.2704264767120908,
"running": 2,
"selectionWeight": 1.0636952190436204,
"selectionWeight": 1.0530969974604185,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 7.0,
@@ -554,140 +554,140 @@
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 372.0794701986755,
"backlogHours": 364.94805194805195,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.29719392657789334,
"queueFactor": 1.1568381657279596,
"queueWeight": 1.1568381657279596,
"qualityFactor": 0.28142672564288695,
"queueFactor": 1.1602253368824298,
"queueWeight": 1.1602253368824298,
"recentSuccess": 30,
"recentSuccessRate": 0.1986754966887417,
"recentTerminal": 151,
"recentWilsonLowerBound": 0.14286066225462393,
"recentSuccessRate": 0.19480519480519481,
"recentTerminal": 154,
"recentWilsonLowerBound": 0.14000138473607715,
"running": 8,
"selectionWeight": 0.34380527688786006,
"selectionWeight": 0.32651841756673766,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 25.166666666666668,
"waiting": 9364
"throughputPerHour": 25.666666666666668,
"waiting": 9367
},
"MetaX_c-500": {
"available": true,
"backlogHours": 532.6779661016949,
"backlogHours": 524.05,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.520343494149867,
"queueFactor": 1.096221345794341,
"queueWeight": 1.096221345794341,
"recentSuccess": 30,
"recentSuccessRate": 0.2542372881355932,
"recentTerminal": 118,
"recentWilsonLowerBound": 0.18428115742871232,
"qualityFactor": 0.45320932261417013,
"queueFactor": 1.0989326936146522,
"queueWeight": 1.0989326936146522,
"recentSuccess": 29,
"recentSuccessRate": 0.24166666666666667,
"recentTerminal": 120,
"recentWilsonLowerBound": 0.1738573324150334,
"running": 4,
"selectionWeight": 0.570411645432297,
"selectionWeight": 0.4980465416716619,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 19.666666666666668,
"waiting": 10476
"throughputPerHour": 20.0,
"waiting": 10481
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1789.5405405405404,
"backlogHours": 1742.3684210526317,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 2.5,
"queueFactor": 0.914022176988751,
"queueWeight": 0.914022176988751,
"recentSuccess": 36,
"recentSuccessRate": 0.4864864864864865,
"recentTerminal": 74,
"recentWilsonLowerBound": 0.37611598006562663,
"queueFactor": 0.917711141053905,
"queueWeight": 0.917711141053905,
"recentSuccess": 37,
"recentSuccessRate": 0.4868421052631579,
"recentTerminal": 76,
"recentWilsonLowerBound": 0.377835392150506,
"running": 4,
"selectionWeight": 2.2850554424718776,
"selectionWeight": 2.2942778526347625,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.333333333333334,
"waiting": 22071
"throughputPerHour": 12.666666666666666,
"waiting": 22070
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 3280.258064516129,
"backlogHours": 2905.5428571428574,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.18071861945015213,
"queueFactor": 0.8346064997953129,
"queueWeight": 0.8346064997953129,
"qualityFactor": 0.13549057309442036,
"queueFactor": 0.8499490834854267,
"queueWeight": 0.8499490834854267,
"recentSuccess": 7,
"recentSuccessRate": 0.22580645161290322,
"recentTerminal": 31,
"recentWilsonLowerBound": 0.113949915944988,
"recentSuccessRate": 0.2,
"recentTerminal": 35,
"recentWilsonLowerBound": 0.10042319445900805,
"running": 2,
"selectionWeight": 0.15082893442713263,
"selectionWeight": 0.1151600884225178,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 5.166666666666667,
"waiting": 16948
"throughputPerHour": 5.833333333333333,
"waiting": 16949
},
"Vastai_va16": {
"available": true,
"backlogHours": 982.7727272727274,
"backlogHours": 982.909090909091,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.3903450895825634,
"qualityFactor": 0.29398423067110313,
"queueFactor": 1.0,
"queueWeight": 1.0,
"recentSuccess": 21,
"recentSuccessRate": 0.23863636363636365,
"recentSuccess": 19,
"recentSuccessRate": 0.2159090909090909,
"recentTerminal": 88,
"recentWilsonLowerBound": 0.1617092401848666,
"recentWilsonLowerBound": 0.1428071398331893,
"running": 16,
"selectionWeight": 0.3903450895825634,
"selectionWeight": 0.29398423067110313,
"stale": false,
"submissionEligible": true,
"submissionEligible": false,
"throughputPerHour": 14.666666666666666,
"waiting": 14414
"waiting": 14416
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 1137.2164948453608,
"backlogHours": 1125.6734693877552,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 1.3228159321017594,
"queueFactor": 0.9783437881078657,
"queueWeight": 0.9783437881078657,
"recentSuccess": 36,
"recentSuccessRate": 0.3711340206185567,
"recentTerminal": 97,
"recentWilsonLowerBound": 0.2816222547757323,
"qualityFactor": 1.3747349074947788,
"queueFactor": 0.9798625021814785,
"queueWeight": 0.9798625021814785,
"recentSuccess": 37,
"recentSuccessRate": 0.37755102040816324,
"recentTerminal": 98,
"recentWilsonLowerBound": 0.2879039439886928,
"running": 6,
"selectionWeight": 1.2941687499818726,
"selectionWeight": 1.3470511862940573,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 16.166666666666668,
"waiting": 18385
"throughputPerHour": 16.333333333333332,
"waiting": 18386
}
},
"queueAttemptedAt": "2026-09-28T21:10:44.976587+00:00",
"queueAttemptedAt": "2026-09-28T21:21:32.684343+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-28T21:10:44.976587+00:00",
"queueUpdatedAt": "2026-09-28T21:21:32.684343+00:00",
"supportedGpus": [
"Vastai_va16",
"Cambricon_mlu-370-x4",

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-09-28T21:18:46.960737+00:00",
"catalogUpdatedAt": "2026-09-28T21:21:32.684343+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-09-28T21:18:46.960737+00:00",
"generatedAt": "2026-09-28T21:21:32.684343+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6458,6 +6458,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-09-28T21:18:46.960737+00:00",
"taskTreeUpdatedAt": "2026-09-28T21:21:32.684343+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-28T20:24:13.337116+00:00",
"lastSyncTime": "2026-09-28T20:24:13.064268+00:00",
"generatedAt": "2026-09-28T21:19:49.285383+00:00",
"lastSyncTime": "2026-09-28T21:19:49.057983+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4944,10 +4944,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 142,
"ambiguous_runtime": 143,
"参数/模板问题": 3
},
"failureCount": 145,
"failureCount": 146,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -4957,8 +4957,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 145,
"unresolvedFailureCount": 145
"total": 146,
"unresolvedFailureCount": 146
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 61,
@@ -6105,7 +6105,7 @@
"decisionSuccessRate": 0.0316,
"decisionTotal": 158,
"failureBreakdown": {
"ambiguous_runtime": 321,
"ambiguous_runtime": 322,
"backend_operator": 9,
"framework_architecture_unsupported": 34,
"memory_capacity": 10,
@@ -6114,15 +6114,15 @@
"tokenizer_compatibility": 91,
"参数/模板问题": 13
},
"failureCount": 507,
"failureRate": 0.9902,
"failureCount": 508,
"failureRate": 0.9903,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 20,
"successCount": 5,
"successRate": 0.0098,
"total": 512,
"unresolvedFailureCount": 334
"successRate": 0.0097,
"total": 513,
"unresolvedFailureCount": 335
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 129,
@@ -6153,7 +6153,7 @@
"unresolvedFailureCount": 197
}
},
"generatedAt": "2026-09-28T20:24:13.323532+00:00",
"generatedAt": "2026-09-28T21:19:49.269980+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -6384,7 +6384,7 @@
"decisionSuccessRate": 0.066,
"decisionTotal": 106,
"failureBreakdown": {
"ambiguous_runtime": 230,
"ambiguous_runtime": 231,
"backend_operator": 23,
"framework_architecture_unsupported": 37,
"memory_capacity": 3,
@@ -6397,15 +6397,15 @@
"日志缺失": 1,
"验证失败": 23
},
"failureCount": 400,
"failureCount": 401,
"failureRate": 0.9828,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 7,
"successRate": 0.0172,
"total": 407,
"unresolvedFailureCount": 300
"total": 408,
"unresolvedFailureCount": 301
},
"Kunlunxin_r-200-8f": {
"attributableFailureCount": 0,
@@ -17696,9 +17696,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 6
"ambiguous_runtime": 7
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5_moe",
@@ -17710,8 +17710,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 6
"total": 7,
"unresolvedFailureCount": 7
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none": {
"attributableFailureCount": 0,
@@ -43673,9 +43673,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
@@ -43688,8 +43688,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|35": {
"attributableFailureCount": 0,
@@ -51974,15 +51974,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17083,
"totalRecords": 17304,
"terminalRecords": 17084,
"totalRecords": 17305,
"totals": {
"attributableFailureCount": 6126,
"decisionFailureRate": 0.8638,
"decisionSuccessRate": 0.1362,
"decisionTotal": 7092,
"failureBreakdown": {
"ambiguous_runtime": 4430,
"ambiguous_runtime": 4431,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
@@ -51998,15 +51998,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16117,
"failureCount": 16118,
"failureRate": 0.9435,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 938,
"successCount": 966,
"successRate": 0.0565,
"total": 17083,
"unresolvedFailureCount": 9053
"total": 17084,
"unresolvedFailureCount": 9054
},
"warnings": [
"GPU Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -52035,7 +52035,6 @@
"组合 Kunlunxin_p-800|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 Ascend_910-b4|llamacpp|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 Kunlunxin_p-800|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 MetaX_c-500|vllm|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 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|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。",
@@ -52060,10 +52059,11 @@
"组合 hygon_k100-ai|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-x4|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_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 Vastai_va16|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
"组合 Vastai_va16|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Kunlunxin_p-800|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": 17304,
"summarizedRecords": 17305,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff