state: generation 21372 (cycle)

This commit is contained in:
2026-10-06 09:18:18 +00:00
parent ce3225f487
commit e661e880df
8 changed files with 2475 additions and 2476 deletions

View File

@@ -2815,7 +2815,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-10-06T08:57:40.063332+00:00",
"generatedAt": "2026-10-06T09:15:34.291863+00:00",
"summary": {
"activeBlockCount": 142,
"byGpuFramework": {

View File

@@ -434,121 +434,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-06T09:10:42.489328+00:00",
"generatedAt": "2026-10-06T09:15:34.311659+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 990.675,
"backlogHours": 1003.367088607595,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.1234624981400767,
"queueFactor": 0.9941577863646601,
"queueWeight": 0.9941577863646601,
"recentSuccess": 47,
"recentSuccessRate": 0.29375,
"recentTerminal": 160,
"recentWilsonLowerBound": 0.22867364459504114,
"qualityFactor": 0.9414345657638384,
"queueFactor": 0.9902967767551256,
"queueWeight": 0.9902967767551256,
"recentSuccess": 44,
"recentSuccessRate": 0.27848101265822783,
"recentTerminal": 158,
"recentWilsonLowerBound": 0.21447831071810888,
"running": 8,
"selectionWeight": 1.1168989902146498,
"selectionWeight": 0.9322996160017906,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 26.666666666666668,
"waiting": 26418
"throughputPerHour": 26.333333333333332,
"waiting": 26422
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1311.909090909091,
"backlogHours": 1254.9130434782608,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.5,
"queueFactor": 0.9531460175068664,
"queueWeight": 0.9531460175068664,
"recentSuccess": 54,
"recentSuccessRate": 0.4090909090909091,
"recentTerminal": 132,
"recentWilsonLowerBound": 0.32894005673952187,
"running": 8,
"selectionWeight": 2.382865043767166,
"queueFactor": 0.9576179944713418,
"queueWeight": 0.9576179944713418,
"recentSuccess": 57,
"recentSuccessRate": 0.41304347826086957,
"recentTerminal": 138,
"recentWilsonLowerBound": 0.33433263817940195,
"running": 9,
"selectionWeight": 2.3940449861783546,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.0,
"waiting": 28862
"throughputPerHour": 23.0,
"waiting": 28863
},
"Biren_166m": {
"available": true,
"backlogHours": 105.56756756756756,
"backlogHours": 107.73913043478261,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.6425492800999694,
"qualityFactor": 0.5552350520448115,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 43,
"recentSuccessRate": 0.23243243243243245,
"recentTerminal": 185,
"recentWilsonLowerBound": 0.177386141453544,
"recentSuccess": 41,
"recentSuccessRate": 0.22282608695652173,
"recentTerminal": 184,
"recentWilsonLowerBound": 0.16871359451367152,
"running": 8,
"selectionWeight": 0.8353140641299602,
"selectionWeight": 0.721805567658255,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 30.833333333333332,
"waiting": 3255
"throughputPerHour": 30.666666666666668,
"waiting": 3304
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1225.1538461538462,
"backlogHours": 1179.4814814814815,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.3264906403743427,
"queueFactor": 0.9629780870267635,
"queueWeight": 0.9629780870267635,
"recentSuccess": 16,
"recentSuccessRate": 0.20512820512820512,
"recentTerminal": 78,
"recentWilsonLowerBound": 0.13039684796163398,
"running": 6,
"selectionWeight": 0.31440333229982753,
"qualityFactor": 0.34205855533716534,
"queueFactor": 0.9665641304087409,
"queueWeight": 0.9665641304087409,
"recentSuccess": 17,
"recentSuccessRate": 0.20987654320987653,
"recentTerminal": 81,
"recentWilsonLowerBound": 0.1353706249001661,
"running": 8,
"selectionWeight": 0.3306215300883374,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 13.0,
"waiting": 15927
"throughputPerHour": 13.5,
"waiting": 15923
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 359.69784172661866,
"backlogHours": 352.09859154929575,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.48142890221084367,
"queueFactor": 1.1573223069145024,
"queueWeight": 1.1573223069145024,
"qualityFactor": 0.44256093109834077,
"queueFactor": 1.158736533861945,
"queueWeight": 1.158736533861945,
"recentSuccess": 30,
"recentSuccessRate": 0.2158273381294964,
"recentTerminal": 139,
"recentWilsonLowerBound": 0.15557197920756324,
"running": 7,
"selectionWeight": 0.55716840772197,
"recentSuccessRate": 0.2112676056338028,
"recentTerminal": 142,
"recentWilsonLowerBound": 0.15218632238107427,
"running": 9,
"selectionWeight": 0.5128115193236065,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 23.166666666666668,
"throughputPerHour": 23.666666666666668,
"waiting": 8333
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 47.66589327146172,
"backlogHours": 47.91724137931035,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -557,197 +557,197 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 9,
"recentSuccessRate": 0.02088167053364269,
"recentTerminal": 431,
"recentWilsonLowerBound": 0.011023911609149478,
"recentSuccess": 8,
"recentSuccessRate": 0.01839080459770115,
"recentTerminal": 435,
"recentWilsonLowerBound": 0.009347602897075263,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 71.83333333333333,
"waiting": 3424
"throughputPerHour": 72.5,
"waiting": 3474
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 176.41666666666666,
"backlogHours": 172.11659192825113,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.26637183920856644,
"queueFactor": 1.2878463666531665,
"queueWeight": 1.2878463666531665,
"recentSuccess": 35,
"recentSuccessRate": 0.16203703703703703,
"recentTerminal": 216,
"recentWilsonLowerBound": 0.1188757481806865,
"running": 1,
"selectionWeight": 0.3430460053034738,
"qualityFactor": 0.1895618741424275,
"queueFactor": 1.290063038696781,
"queueWeight": 1.290063038696781,
"recentSuccess": 32,
"recentSuccessRate": 0.14349775784753363,
"recentTerminal": 223,
"recentWilsonLowerBound": 0.10351468153737338,
"running": 10,
"selectionWeight": 0.2445467673772368,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 36.0,
"waiting": 6351
"throughputPerHour": 37.166666666666664,
"waiting": 6397
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2123.1818181818185,
"backlogHours": 1987.4042553191491,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.6762291370919148,
"queueFactor": 0.8867412686845147,
"queueWeight": 0.8867412686845147,
"recentSuccess": 13,
"recentSuccessRate": 0.29545454545454547,
"recentTerminal": 44,
"recentWilsonLowerBound": 0.18155360887243294,
"qualityFactor": 0.6923021533465007,
"queueFactor": 0.8938021828055901,
"queueWeight": 0.8938021828055901,
"recentSuccess": 14,
"recentSuccessRate": 0.2978723404255319,
"recentTerminal": 47,
"recentWilsonLowerBound": 0.18651084151016264,
"running": 2,
"selectionWeight": 0.5996402829463192,
"selectionWeight": 0.6187811758221127,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 7.333333333333333,
"waiting": 15570
"throughputPerHour": 7.833333333333333,
"waiting": 15568
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 275.43646408839777,
"backlogHours": 278.3463687150838,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.2009765536761621,
"queueFactor": 1.2045970178349212,
"queueWeight": 1.2045970178349212,
"qualityFactor": 0.19881491405406826,
"queueFactor": 1.2003185262945868,
"queueWeight": 1.2003185262945868,
"recentSuccess": 27,
"recentSuccessRate": 0.14917127071823205,
"recentTerminal": 181,
"recentWilsonLowerBound": 0.10458823825843333,
"running": 7,
"selectionWeight": 0.24209575721304485,
"recentSuccessRate": 0.15083798882681565,
"recentTerminal": 179,
"recentWilsonLowerBound": 0.10578159636160239,
"running": 9,
"selectionWeight": 0.23864122464276413,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 30.166666666666668,
"waiting": 8309
"throughputPerHour": 29.833333333333332,
"waiting": 8304
},
"MetaX_c-500": {
"available": true,
"backlogHours": 475.00800000000004,
"backlogHours": 478.83870967741933,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 1.8742656516224518,
"queueFactor": 1.1100431476452195,
"queueWeight": 1.1100431476452195,
"recentSuccess": 46,
"recentSuccessRate": 0.368,
"recentTerminal": 125,
"recentWilsonLowerBound": 0.2885686171370214,
"running": 4,
"selectionWeight": 2.080515743450305,
"qualityFactor": 1.948006670267187,
"queueFactor": 1.1065115600043274,
"queueWeight": 1.1065115600043274,
"recentSuccess": 47,
"recentSuccessRate": 0.3790322580645161,
"recentTerminal": 124,
"recentWilsonLowerBound": 0.2984894399920374,
"running": 5,
"selectionWeight": 2.1554918996161803,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 20.833333333333332,
"throughputPerHour": 20.666666666666668,
"waiting": 9896
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1959.9402985074628,
"backlogHours": 1960.4776119402986,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 1.9513373620261467,
"queueFactor": 0.8974465088604019,
"queueWeight": 0.8974465088604019,
"qualityFactor": 1.882764205039774,
"queueFactor": 0.8956329447248963,
"queueWeight": 0.8956329447248963,
"recentSuccess": 27,
"recentSuccessRate": 0.40298507462686567,
"recentTerminal": 67,
"recentWilsonLowerBound": 0.2939031193036935,
"running": 4,
"selectionWeight": 1.7512209031592316,
"selectionWeight": 1.686265649182401,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 11.166666666666666,
"waiting": 21886
"waiting": 21892
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 1796.0,
"backlogHours": 1765.448275862069,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.06089112372683311,
"queueFactor": 0.9092829527323988,
"queueWeight": 0.9092829527323988,
"qualityFactor": 0.05649795091812879,
"queueFactor": 0.9098212865199522,
"queueWeight": 0.9098212865199522,
"recentSuccess": 7,
"recentSuccessRate": 0.12280701754385964,
"recentTerminal": 57,
"recentWilsonLowerBound": 0.060779830035075,
"recentSuccessRate": 0.1206896551724138,
"recentTerminal": 58,
"recentWilsonLowerBound": 0.05970890244859669,
"running": 2,
"selectionWeight": 0.05536726077752864,
"selectionWeight": 0.051403038390073055,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 9.5,
"waiting": 17062
"throughputPerHour": 9.666666666666666,
"waiting": 17066
},
"Vastai_va16": {
"available": true,
"backlogHours": 919.1650485436893,
"backlogHours": 893.2641509433962,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.05,
"queueFactor": 1.0053932695124477,
"queueWeight": 1.0053932695124477,
"queueFactor": 1.0077141515683472,
"queueWeight": 1.0077141515683472,
"recentSuccess": 8,
"recentSuccessRate": 0.07766990291262135,
"recentTerminal": 103,
"recentWilsonLowerBound": 0.03987987936847962,
"running": 15,
"selectionWeight": 0.05026966347562239,
"recentSuccessRate": 0.07547169811320754,
"recentTerminal": 106,
"recentWilsonLowerBound": 0.03873637400565599,
"running": 16,
"selectionWeight": 0.050385707578417364,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 17.166666666666668,
"waiting": 15779
"throughputPerHour": 17.666666666666668,
"waiting": 15781
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 986.2809917355371,
"backlogHours": 987.1735537190082,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 0.9178137897312473,
"queueFactor": 0.9948208969404346,
"queueWeight": 0.9948208969404346,
"qualityFactor": 0.8855603258698531,
"queueFactor": 0.9927166738410689,
"queueWeight": 0.9927166738410689,
"recentSuccess": 34,
"recentSuccessRate": 0.2809917355371901,
"recentTerminal": 121,
"recentWilsonLowerBound": 0.2085956290113622,
"running": 6,
"selectionWeight": 0.9130603375247389,
"running": 7,
"selectionWeight": 0.8791105011831336,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 20.166666666666668,
"waiting": 19890
"waiting": 19908
}
},
"queueAttemptedAt": "2026-10-06T09:04:28.064988+00:00",
"queueAttemptedAt": "2026-10-06T09:15:34.311659+00:00",
"queueError": null,
"queueUpdatedAt": "2026-10-06T09:04:28.064988+00:00",
"queueUpdatedAt": "2026-10-06T09:15:34.311659+00:00",
"supportedGpus": [
"Vastai_va16",
"Cambricon_mlu-370-x4",

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-06T08:42:45.604534+00:00",
"lastSyncTime": "2026-10-06T08:42:45.361322+00:00",
"generatedAt": "2026-10-06T09:15:34.201863+00:00",
"lastSyncTime": "2026-10-06T09:15:33.969896+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3255,10 +3255,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 122,
"ambiguous_runtime": 123,
"memory_capacity": 1
},
"failureCount": 123,
"failureCount": 124,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -3268,8 +3268,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 123,
"unresolvedFailureCount": 122
"total": 124,
"unresolvedFailureCount": 123
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 50,
@@ -5646,7 +5646,7 @@
"decisionSuccessRate": 0.0284,
"decisionTotal": 176,
"failureBreakdown": {
"ambiguous_runtime": 354,
"ambiguous_runtime": 355,
"backend_operator": 9,
"framework_architecture_unsupported": 46,
"memory_capacity": 10,
@@ -5655,15 +5655,15 @@
"tokenizer_compatibility": 94,
"参数/模板问题": 13
},
"failureCount": 563,
"failureCount": 564,
"failureRate": 0.9912,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 25,
"successCount": 5,
"successRate": 0.0088,
"total": 568,
"unresolvedFailureCount": 367
"total": 569,
"unresolvedFailureCount": 368
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 150,
@@ -5694,7 +5694,7 @@
"unresolvedFailureCount": 233
}
},
"generatedAt": "2026-10-06T08:42:45.591131+00:00",
"generatedAt": "2026-10-06T09:15:34.186944+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 119,
@@ -5757,7 +5757,7 @@
"decisionSuccessRate": 0.1147,
"decisionTotal": 218,
"failureBreakdown": {
"ambiguous_runtime": 265,
"ambiguous_runtime": 266,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 125,
@@ -5771,15 +5771,15 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 763,
"failureCount": 764,
"failureRate": 0.9683,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.0317,
"total": 788,
"unresolvedFailureCount": 568
"total": 789,
"unresolvedFailureCount": 569
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 759,
@@ -9038,9 +9038,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 9
"ambiguous_runtime": 10
},
"failureCount": 9,
"failureCount": 10,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "lfm2",
@@ -9052,8 +9052,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 9,
"unresolvedFailureCount": 9
"total": 10,
"unresolvedFailureCount": 10
},
"Biren_166m|vllm_fix_tokenizer|text-generation|llama|awq": {
"attributableFailureCount": 0,
@@ -33657,9 +33657,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 30,
@@ -33672,8 +33672,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm_fix_tokenizer|text-generation|lfm2|none|31": {
"attributableFailureCount": 0,
@@ -57345,15 +57345,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17330,
"totalRecords": 17554,
"terminalRecords": 17331,
"totalRecords": 17555,
"totals": {
"attributableFailureCount": 6231,
"decisionFailureRate": 0.8643,
"decisionSuccessRate": 0.1357,
"decisionTotal": 7209,
"failureBreakdown": {
"ambiguous_runtime": 4542,
"ambiguous_runtime": 4543,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 129,
@@ -57369,15 +57369,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16352,
"failureCount": 16353,
"failureRate": 0.9436,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 951,
"successCount": 978,
"successRate": 0.0564,
"total": 17330,
"unresolvedFailureCount": 9170
"total": 17331,
"unresolvedFailureCount": 9171
},
"warnings": [
"GPU MetaX_c-500 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -57386,14 +57386,14 @@
"GPU hygon_k100-ai 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Kunlunxin_p-800 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_bi-100 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高(≥50%),建议重点关注。",
"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 Ascend_910-b3|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_mrv-100|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -57437,6 +57437,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17554,
"summarizedRecords": 17555,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff