state: generation 17706 (cycle)

This commit is contained in:
2026-09-28 03:33:52 +00:00
parent 815bb5e858
commit 5262e5d091
8 changed files with 1670 additions and 1624 deletions

View File

@@ -3261,7 +3261,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-28T03:23:38.621619+00:00",
"generatedAt": "2026-09-28T03:31:38.501829+00:00",
"summary": {
"activeBlockCount": 164,
"byGpuFramework": {

View File

@@ -396,99 +396,99 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-28T03:30:13.458839+00:00",
"generatedAt": "2026-09-28T03:33:04.447180+00:00",
"gpuStats": {
"Ascend_910-b4": {
"available": true,
"backlogHours": 690.936,
"backlogHours": 691.296,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.5,
"queueFactor": 0.9055735001214654,
"queueWeight": 0.9055735001214654,
"recentSuccess": 56,
"recentSuccessRate": 0.224,
"queueFactor": 0.9094910341347675,
"queueWeight": 0.9094910341347675,
"recentSuccess": 57,
"recentSuccessRate": 0.228,
"recentTerminal": 250,
"recentWilsonLowerBound": 0.17671751406074324,
"running": 7,
"selectionWeight": 2.2639337503036634,
"recentWilsonLowerBound": 0.1803405041462213,
"running": 6,
"selectionWeight": 2.2737275853369185,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 41.666666666666664,
"waiting": 28789
"waiting": 28804
},
"Biren_166m": {
"available": true,
"backlogHours": 83.56231003039514,
"backlogHours": 84.34862385321101,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.3782484610992606,
"queueFactor": 1.2431908724162317,
"queueWeight": 1.2431908724162317,
"recentSuccess": 34,
"recentSuccessRate": 0.1033434650455927,
"recentTerminal": 329,
"recentWilsonLowerBound": 0.07489939386975654,
"running": 8,
"selectionWeight": 0.47023503434408687,
"qualityFactor": 0.33942837076670185,
"queueFactor": 1.2469135043505413,
"queueWeight": 1.2469135043505413,
"recentSuccess": 33,
"recentSuccessRate": 0.10091743119266056,
"recentTerminal": 327,
"recentWilsonLowerBound": 0.07276376408079803,
"running": 7,
"selectionWeight": 0.423237819268703,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 54.833333333333336,
"waiting": 4582
"throughputPerHour": 54.5,
"waiting": 4597
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 436.67605633802816,
"backlogHours": 449.42028985507244,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.1850702846518203,
"queueFactor": 0.9700976924055631,
"queueWeight": 0.9700976924055631,
"recentSuccess": 18,
"recentSuccessRate": 0.08450704225352113,
"recentTerminal": 213,
"recentWilsonLowerBound": 0.05412139665927451,
"running": 7,
"selectionWeight": 0.17953625607357157,
"qualityFactor": 0.13675477531536706,
"queueFactor": 0.9701751073822051,
"queueWeight": 0.9701751073822051,
"recentSuccess": 16,
"recentSuccessRate": 0.07729468599033816,
"recentTerminal": 207,
"recentWilsonLowerBound": 0.048134675498749495,
"running": 6,
"selectionWeight": 0.13267607882661558,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 35.5,
"waiting": 15502
"throughputPerHour": 34.5,
"waiting": 15505
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 218.91497975708504,
"backlogHours": 217.2289156626506,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.47416235112681887,
"queueFactor": 1.0759647819727534,
"queueWeight": 1.0759647819727534,
"recentSuccess": 29,
"recentSuccessRate": 0.11740890688259109,
"recentTerminal": 247,
"recentWilsonLowerBound": 0.08300263756156351,
"qualityFactor": 0.4866481972318857,
"queueFactor": 1.081957952931069,
"queueWeight": 1.081957952931069,
"recentSuccess": 30,
"recentSuccessRate": 0.12048192771084337,
"recentTerminal": 249,
"recentWilsonLowerBound": 0.08571098998271487,
"running": 7,
"selectionWeight": 0.5101819907498558,
"selectionWeight": 0.5265328872746061,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 41.166666666666664,
"waiting": 9012
"throughputPerHour": 41.5,
"waiting": 9015
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 28.45346062052506,
"backlogHours": 26.36283185840708,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -497,197 +497,197 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 10,
"recentSuccessRate": 0.02386634844868735,
"recentTerminal": 419,
"recentWilsonLowerBound": 0.013014243826808108,
"running": 16,
"recentSuccess": 11,
"recentSuccessRate": 0.024336283185840708,
"recentTerminal": 452,
"recentWilsonLowerBound": 0.013642151273940728,
"running": 13,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 69.83333333333333,
"waiting": 1987
"throughputPerHour": 75.33333333333333,
"waiting": 1986
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 77.7081081081081,
"backlogHours": 76.61170212765958,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.414358563252322,
"queueFactor": 1.2568094227062372,
"queueWeight": 1.2568094227062372,
"qualityFactor": 0.38231561217833065,
"queueFactor": 1.265038555367772,
"queueWeight": 1.265038555367772,
"recentSuccess": 39,
"recentSuccessRate": 0.10540540540540541,
"recentTerminal": 370,
"recentWilsonLowerBound": 0.07806887412652973,
"running": 3,
"selectionWeight": 0.5207697466745367,
"recentSuccessRate": 0.10372340425531915,
"recentTerminal": 376,
"recentWilsonLowerBound": 0.07680744004963592,
"running": 2,
"selectionWeight": 0.4836439897246208,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 61.666666666666664,
"waiting": 4792
"throughputPerHour": 62.666666666666664,
"waiting": 4801
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 541.7666666666667,
"backlogHours": 541.7333333333333,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.3119971312514799,
"queueFactor": 0.9392204419671198,
"queueWeight": 0.9392204419671198,
"recentSuccess": 19,
"recentSuccessRate": 0.10555555555555556,
"qualityFactor": 0.342754221891898,
"queueFactor": 0.9433659459851603,
"queueWeight": 0.9433659459851603,
"recentSuccess": 20,
"recentSuccessRate": 0.1111111111111111,
"recentTerminal": 180,
"recentWilsonLowerBound": 0.0686224510893259,
"running": 2,
"selectionWeight": 0.2930340835064884,
"recentWilsonLowerBound": 0.07308697860315692,
"running": 1,
"selectionWeight": 0.3233426607754579,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 30.0,
"waiting": 16253
"waiting": 16252
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 253.40088105726872,
"backlogHours": 250.51304347826084,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.429725141702638,
"queueFactor": 1.0526116209334986,
"queueWeight": 1.0526116209334986,
"qualityFactor": 0.39907861464201894,
"queueFactor": 1.0590671008542556,
"queueWeight": 1.0590671008542556,
"recentSuccess": 26,
"recentSuccessRate": 0.1145374449339207,
"recentTerminal": 227,
"recentWilsonLowerBound": 0.07937181295688597,
"recentSuccessRate": 0.11304347826086956,
"recentTerminal": 230,
"recentWilsonLowerBound": 0.07832030892439182,
"running": 8,
"selectionWeight": 0.4523336779634911,
"selectionWeight": 0.42265103142185567,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 37.833333333333336,
"waiting": 9587
"throughputPerHour": 38.333333333333336,
"waiting": 9603
},
"MetaX_c-500": {
"available": true,
"backlogHours": 254.37096774193546,
"backlogHours": 250.45238095238096,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.6581332729408006,
"queueFactor": 1.0520084958140807,
"queueWeight": 1.0520084958140807,
"recentSuccess": 33,
"recentSuccessRate": 0.13306451612903225,
"recentTerminal": 248,
"recentWilsonLowerBound": 0.0963414451971256,
"running": 4,
"selectionWeight": 0.6923617945116495,
"qualityFactor": 0.6561439844748158,
"queueFactor": 1.059105574678724,
"queueWeight": 1.059105574678724,
"recentSuccess": 34,
"recentSuccessRate": 0.1349206349206349,
"recentTerminal": 252,
"recentWilsonLowerBound": 0.09818140744118609,
"running": 3,
"selectionWeight": 0.6949257517491875,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 41.333333333333336,
"waiting": 10514
"throughputPerHour": 42.0,
"waiting": 10519
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 639.5414634146342,
"backlogHours": 642.7647058823529,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 1.0087016281324261,
"queueFactor": 0.9161341504220472,
"queueWeight": 0.9161341504220472,
"qualityFactor": 0.975315398794197,
"queueFactor": 0.919475634982015,
"queueWeight": 0.919475634982015,
"recentSuccess": 33,
"recentSuccessRate": 0.16097560975609757,
"recentTerminal": 205,
"recentWilsonLowerBound": 0.1169790525430429,
"recentSuccessRate": 0.16176470588235295,
"recentTerminal": 204,
"recentWilsonLowerBound": 0.1175648254177297,
"running": 4,
"selectionWeight": 0.924106009118436,
"selectionWeight": 0.8967787456140315,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 34.166666666666664,
"waiting": 21851
"throughputPerHour": 34.0,
"waiting": 21854
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 604.9156626506024,
"backlogHours": 608.4727272727273,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.06251981805167338,
"queueFactor": 0.9238153071633751,
"queueWeight": 0.9238153071633751,
"recentSuccess": 10,
"recentSuccessRate": 0.060240963855421686,
"recentTerminal": 166,
"recentWilsonLowerBound": 0.033047080023101895,
"running": 2,
"selectionWeight": 0.05775676491720497,
"qualityFactor": 0.05,
"queueFactor": 0.9270685774216965,
"queueWeight": 0.9270685774216965,
"recentSuccess": 9,
"recentSuccessRate": 0.05454545454545454,
"recentTerminal": 165,
"recentWilsonLowerBound": 0.0289583998546884,
"running": 1,
"selectionWeight": 0.046353428871084824,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 27.666666666666668,
"waiting": 16736
"throughputPerHour": 27.5,
"waiting": 16733
},
"Vastai_va16": {
"available": true,
"backlogHours": 356.6666666666667,
"backlogHours": 367.2711864406779,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.3327461060171171,
"qualityFactor": 0.3048371099198743,
"queueFactor": 1.0,
"queueWeight": 1.0,
"recentSuccess": 25,
"recentSuccessRate": 0.102880658436214,
"recentTerminal": 243,
"recentWilsonLowerBound": 0.07066045010133101,
"running": 15,
"selectionWeight": 0.3327461060171171,
"recentSuccess": 24,
"recentSuccessRate": 0.1016949152542373,
"recentTerminal": 236,
"recentWilsonLowerBound": 0.06929419232185546,
"running": 16,
"selectionWeight": 0.3048371099198743,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 40.5,
"waiting": 14445
"throughputPerHour": 39.333333333333336,
"waiting": 14446
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 448.8,
"backlogHours": 449.25,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 0.4611828518939847,
"queueFactor": 0.9661208420407549,
"queueWeight": 0.9661208420407549,
"qualityFactor": 0.441045140879677,
"queueFactor": 0.9702302607610114,
"queueWeight": 0.9702302607610114,
"recentSuccess": 28,
"recentSuccessRate": 0.11666666666666667,
"recentTerminal": 240,
"recentWilsonLowerBound": 0.08196205521476754,
"running": 6,
"selectionWeight": 0.44555836520657327,
"selectionWeight": 0.427915342043066,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 40.0,
"waiting": 17952
"waiting": 17970
}
},
"queueAttemptedAt": "2026-09-28T03:22:33.350761+00:00",
"queueAttemptedAt": "2026-09-28T03:33:04.447180+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-28T03:22:33.350761+00:00",
"queueUpdatedAt": "2026-09-28T03:33:04.447180+00:00",
"supportedGpus": [
"Vastai_va16",
"Cambricon_mlu-370-x4",

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-09-28T03:30:13.458839+00:00",
"catalogUpdatedAt": "2026-09-28T03:33:04.447180+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-09-28T03:30:13.458839+00:00",
"generatedAt": "2026-09-28T03:33:04.447180+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6545,6 +6545,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-09-28T03:30:13.458839+00:00",
"taskTreeUpdatedAt": "2026-09-28T03:33:04.447180+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-28T03:23:38.538672+00:00",
"lastSyncTime": "2026-09-28T03:23:37.959151+00:00",
"generatedAt": "2026-09-28T03:31:38.420170+00:00",
"lastSyncTime": "2026-09-28T03:31:38.156601+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4529,30 +4529,30 @@
"unresolvedFailureCount": 82
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 39,
"decisionFailureRate": 0.6842,
"decisionSuccessRate": 0.3158,
"decisionTotal": 57,
"attributableFailureCount": 40,
"decisionFailureRate": 0.6897,
"decisionSuccessRate": 0.3103,
"decisionTotal": 58,
"failureBreakdown": {
"ambiguous_runtime": 23,
"backend_operator": 6,
"framework_architecture_unsupported": 17,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"model_load": 6,
"runtime_memory": 9,
"参数/模板问题": 2
},
"failureCount": 64,
"failureRate": 0.7805,
"failureCount": 65,
"failureRate": 0.7831,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 18,
"successRate": 0.2195,
"successRate": 0.2169,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 82,
"total": 83,
"unresolvedFailureCount": 25
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": {
@@ -6057,27 +6057,27 @@
"unresolvedFailureCount": 52
},
"vllm_0_17_0_corex_4_4_0": {
"attributableFailureCount": 39,
"decisionFailureRate": 0.6842,
"decisionSuccessRate": 0.3158,
"decisionTotal": 57,
"attributableFailureCount": 40,
"decisionFailureRate": 0.6897,
"decisionSuccessRate": 0.3103,
"decisionTotal": 58,
"failureBreakdown": {
"ambiguous_runtime": 23,
"backend_operator": 6,
"framework_architecture_unsupported": 17,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"model_load": 6,
"runtime_memory": 9,
"参数/模板问题": 2
},
"failureCount": 64,
"failureRate": 0.7805,
"failureCount": 65,
"failureRate": 0.7831,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 18,
"successRate": 0.2195,
"total": 82,
"successRate": 0.2169,
"total": 83,
"unresolvedFailureCount": 25
},
"vllm_fix_tokenizer": {
@@ -6134,7 +6134,7 @@
"unresolvedFailureCount": 197
}
},
"generatedAt": "2026-09-28T03:23:38.526090+00:00",
"generatedAt": "2026-09-28T03:31:38.406685+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -6298,16 +6298,16 @@
"unresolvedFailureCount": 568
},
"Iluvatar_bi-150": {
"attributableFailureCount": 756,
"decisionFailureRate": 0.8354,
"decisionSuccessRate": 0.1646,
"decisionTotal": 905,
"attributableFailureCount": 757,
"decisionFailureRate": 0.8355,
"decisionSuccessRate": 0.1645,
"decisionTotal": 906,
"failureBreakdown": {
"ambiguous_runtime": 650,
"architecture_compatibility": 15,
"backend_operator": 12,
"context_length": 29,
"framework_architecture_unsupported": 250,
"framework_architecture_unsupported": 251,
"memory_capacity": 153,
"model_load": 126,
"platform_infrastructure": 21,
@@ -6318,14 +6318,14 @@
"日志缺失": 155,
"验证失败": 30
},
"failureCount": 1932,
"failureCount": 1933,
"failureRate": 0.9284,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 21,
"successCount": 149,
"successRate": 0.0716,
"total": 2081,
"total": 2082,
"unresolvedFailureCount": 1155
},
"Iluvatar_mrv-100": {
@@ -15344,6 +15344,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "spark2_5",
"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_0_17_0_corex_4_4_0|text-generation|spark2_5|fp8": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -40084,6 +40107,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|compressed-tensors|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"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_0_17_0_corex_4_4_0|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -51432,20 +51479,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17067,
"totalRecords": 17288,
"terminalRecords": 17068,
"totalRecords": 17289,
"totals": {
"attributableFailureCount": 6115,
"attributableFailureCount": 6116,
"decisionFailureRate": 0.8636,
"decisionSuccessRate": 0.1364,
"decisionTotal": 7081,
"decisionTotal": 7082,
"failureBreakdown": {
"ambiguous_runtime": 4425,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
"context_length": 322,
"framework_architecture_unsupported": 2172,
"framework_architecture_unsupported": 2173,
"memory_capacity": 1206,
"model_load": 550,
"platform_infrastructure": 938,
@@ -51456,14 +51503,14 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16101,
"failureCount": 16102,
"failureRate": 0.9434,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 938,
"successCount": 966,
"successRate": 0.0566,
"total": 17067,
"total": 17068,
"unresolvedFailureCount": 9048
},
"warnings": [
@@ -51472,15 +51519,15 @@
"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 MetaX_c-500 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 Vastai_va16 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 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 Sunrise_pt-200-x1 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU hygon_k100-ai 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 Kunlunxin_p-800 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 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 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 Ascend_910-b3|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -51504,7 +51551,6 @@
"组合 Cambricon_mlu-370-x4|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-150|transformers|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 hygon_k100-ai|vllm-patch-tokenizer|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_fix_tokenizer|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 Mthreads_s4000|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_bi-100|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -51518,10 +51564,11 @@
"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 Mthreads_s4000|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_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|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_bi-150|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 Vastai_va16|vllm_fix_tokenizer|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": 17288,
"summarizedRecords": 17289,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.22.1",
"checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "04cd9d9fe71b11f0052b50e32391c7b9e642fb42278cad93a58b34aba6a658cc",
".modelhub_state/architecture_compatibility_blacklist.json": "517d429a6eb09412e7e581e6bed2727c9376b90f3f6cfed077bb6ca6c0155aa9",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "8aff21ceda424066841730e9d8906c49d06114ffb547af7ca827bf06db64d522",
".modelhub_state/official_capabilities.json": "e7a01c7f3bc835ecd38ec9b2ffc32ef73db4a0de20fddc701822539b0bbca7c8",
".modelhub_state/outcome_checkpoint.json": "a1c1b410b0e2f9759f083a9980ef59e2f9c3d92c42cb9805278dd3ae7cbae99a",
".modelhub_state/market_intelligence.json": "3ff01a11d6a3bba8156d357a6fc80013424c082473aa1c309ec28682e74a9cc4",
".modelhub_state/official_capabilities.json": "74e297b2d1706cd602fc9af85894d6fffa2faff89392aa820402678b42aca6ff",
".modelhub_state/outcome_checkpoint.json": "4670aca86be46f74ec9cb06456f89dc68aba61ef0b155325cbca3827efc74357",
".modelhub_state/queue_cleanup_latest.json": "7e38abadc6c9b9ae45cfe06be2960ed2213d70309667bb70f63d270b560bc760",
".modelhub_state/recent_outcomes.jsonl": "2745ae69199213460dae340cb59923de52e56d054e56d6c25ac1a3b571a88bfc",
".modelhub_state/recovery_active_tasks.jsonl": "ae2abadf42ee5022f73c343383cbb220f7ed55d0ab435e5a1680d8594c495480",
".modelhub_state/recovery_intents.jsonl": "074a4424fa4433090bc79952037103e29c5ca93f77ec6dc6f8b722754e1ebd92",
".modelhub_state/recovery_active_tasks.jsonl": "7447a82bba9b1d58a1034f76d0e073e57389c98fde650df3155937a7a670fce1",
".modelhub_state/recovery_intents.jsonl": "51b6d567809397aa01d016a559880ee9bbef4da2f020cf78fa85e16b51274f00",
".modelhub_state/routing_intelligence.json": "783dcdd18e65a6df1db492a367c1d1f213fdc7208da4dc91eec95f41c84a2df2",
".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799",
".modelhub_state/worker_crashes.jsonl": "8f862697b8c8286a6ac8130827f91487a3eb07ecaf4af7ee3de2915d925deb10",
"ledger/submissions.jsonl": "75e4e997bd1ea1aac943bbb2e5cac0c91313f6fa5431a4f8ba1868c9da27b3fc",
"outcomes/submissions.jsonl": "2ae28058250c28e6edf4fbf7f7a6cfe95e2cd220c8da71fa1e6e884fedf596dd"
"outcomes/submissions.jsonl": "d61e31bc05e287b849190b644cc42dd0d250b54646df00a76b8700d2cd32b5c4"
},
"generation": 17705,
"generation": 17706,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-28T03:30:36.740395+00:00",
"updatedAt": "2026-09-28T03:33:52.326504+00:00",
"writerId": "6e8ddfbd92ca45ccaf79298516f8a6ea"
}

View File

@@ -128,7 +128,6 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-13T13:17:31.149592+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "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": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T05:10:44.864092+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4817675", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-13T13:34:15.409837+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "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": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T05:29:18.044774+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4817992", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-13T13:43:30.144236+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "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": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T05:34:18.006195+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4818284", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-13T13:52:07.006302+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "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": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T05:44:36.060924+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4818885", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-13T14:08:03.641274+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "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": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T06:03:08.407319+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4819935", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-13T17:57:25.416298+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "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": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T09:53:52.905331+00:00", "targetGpu": "MetaX_c-500", "taskId": "4823778", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-13T18:17:59.899586+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "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": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T10:16:13.410881+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4824251", "taskType": "text-generation", "verifyResult": null}