state: generation 16718 (cycle)

This commit is contained in:
2026-09-26 17:58:33 +00:00
parent fe27c9686e
commit 85270c183d
8 changed files with 1656 additions and 1656 deletions

View File

@@ -3261,7 +3261,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-26T17:50:59.263120+00:00",
"generatedAt": "2026-09-26T17:57:36.576631+00:00",
"summary": {
"activeBlockCount": 164,
"byGpuFramework": {

View File

@@ -396,99 +396,99 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-26T17:56:32.847933+00:00",
"generatedAt": "2026-09-26T17:58:26.848553+00:00",
"gpuStats": {
"Ascend_910-b4": {
"available": true,
"backlogHours": 1408.081967213115,
"backlogHours": 1374.048,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.343705000576399,
"queueFactor": 0.9251636826009542,
"queueWeight": 0.9251636826009542,
"qualityFactor": 2.372863126298143,
"queueFactor": 0.9271941040324438,
"queueWeight": 0.9271941040324438,
"recentSuccess": 53,
"recentSuccessRate": 0.4344262295081967,
"recentTerminal": 122,
"recentWilsonLowerBound": 0.34979916036936143,
"running": 9,
"selectionWeight": 2.1683107492635325,
"recentSuccessRate": 0.424,
"recentTerminal": 125,
"recentWilsonLowerBound": 0.34090195211218616,
"running": 8,
"selectionWeight": 2.2001047003796304,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 20.333333333333332,
"waiting": 28631
"throughputPerHour": 20.833333333333332,
"waiting": 28626
},
"Biren_166m": {
"available": true,
"backlogHours": 127.82198952879581,
"backlogHours": 125.75257731958762,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.30948672243654285,
"qualityFactor": 0.34370635383966397,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 36,
"recentSuccessRate": 0.18848167539267016,
"recentTerminal": 191,
"recentWilsonLowerBound": 0.1393653166559651,
"recentSuccess": 37,
"recentSuccessRate": 0.19072164948453607,
"recentTerminal": 194,
"recentWilsonLowerBound": 0.1416534504648952,
"running": 8,
"selectionWeight": 0.4023327391675057,
"selectionWeight": 0.44681825999156316,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 31.833333333333332,
"waiting": 4069
"throughputPerHour": 32.333333333333336,
"waiting": 4066
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1226.8378378378377,
"backlogHours": 1210.56,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.417978154593534,
"queueFactor": 0.9444841896408226,
"queueWeight": 0.9444841896408226,
"qualityFactor": 0.43430324261784414,
"queueFactor": 0.9449808312476503,
"queueWeight": 0.9449808312476503,
"recentSuccess": 18,
"recentSuccessRate": 0.24324324324324326,
"recentTerminal": 74,
"recentWilsonLowerBound": 0.1597637123272753,
"recentSuccessRate": 0.24,
"recentTerminal": 75,
"recentWilsonLowerBound": 0.1575474872875825,
"running": 7,
"selectionWeight": 0.3947737586288404,
"selectionWeight": 0.4104082392225603,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.333333333333334,
"waiting": 15131
"throughputPerHour": 12.5,
"waiting": 15132
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 467.04424778761063,
"backlogHours": 450.9230769230769,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.3107926570481712,
"queueFactor": 1.0917144596211705,
"queueWeight": 1.0917144596211705,
"recentSuccess": 23,
"recentSuccessRate": 0.20353982300884957,
"recentTerminal": 113,
"recentWilsonLowerBound": 0.1396323173788541,
"qualityFactor": 0.34501565734007894,
"queueFactor": 1.0958612683674056,
"queueWeight": 1.0958612683674056,
"recentSuccess": 24,
"recentSuccessRate": 0.20512820512820512,
"recentTerminal": 117,
"recentWilsonLowerBound": 0.14189847337772166,
"running": 7,
"selectionWeight": 0.339296837643572,
"selectionWeight": 0.3780892958593131,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 18.833333333333332,
"waiting": 8796
"throughputPerHour": 19.5,
"waiting": 8793
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 39.94428969359331,
"backlogHours": 39.66298342541436,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -498,196 +498,196 @@
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 17,
"recentSuccessRate": 0.04735376044568245,
"recentTerminal": 359,
"recentWilsonLowerBound": 0.02977239671602438,
"running": 26,
"recentSuccessRate": 0.04696132596685083,
"recentTerminal": 362,
"recentWilsonLowerBound": 0.029523940753182577,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 59.833333333333336,
"waiting": 2390
"throughputPerHour": 60.333333333333336,
"waiting": 2393
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 109.90188679245284,
"backlogHours": 107.8,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.11843560607686504,
"qualityFactor": 0.1217092188819118,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 33,
"recentSuccessRate": 0.12452830188679245,
"recentTerminal": 265,
"recentWilsonLowerBound": 0.09006097505718481,
"running": 8,
"selectionWeight": 0.15396628789992456,
"recentSuccessRate": 0.12222222222222222,
"recentTerminal": 270,
"recentWilsonLowerBound": 0.0883667610866343,
"running": 7,
"selectionWeight": 0.15822198454648534,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 44.166666666666664,
"waiting": 4854
"throughputPerHour": 45.0,
"waiting": 4851
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2338.829268292683,
"backlogHours": 2458.6153846153848,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.6527241240122196,
"queueFactor": 0.8573595478316081,
"queueWeight": 0.8573595478316081,
"recentSuccess": 13,
"recentSuccessRate": 0.3170731707317073,
"recentTerminal": 41,
"recentWilsonLowerBound": 0.19564433205311735,
"qualityFactor": 0.4835684725655789,
"queueFactor": 0.8497034033090932,
"queueWeight": 0.8497034033090932,
"recentSuccess": 11,
"recentSuccessRate": 0.28205128205128205,
"recentTerminal": 39,
"recentWilsonLowerBound": 0.16543325013943294,
"running": 2,
"selectionWeight": 0.5596192598218991,
"selectionWeight": 0.4108897768719523,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 6.833333333333333,
"waiting": 15982
"throughputPerHour": 6.5,
"waiting": 15981
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 372.38709677419354,
"backlogHours": 377.05882352941177,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.4963562594739263,
"queueFactor": 1.1294410622780067,
"queueWeight": 1.1294410622780067,
"recentSuccess": 36,
"recentSuccessRate": 0.23225806451612904,
"recentTerminal": 155,
"recentWilsonLowerBound": 0.1727449576065253,
"running": 9,
"selectionWeight": 0.5606051409685693,
"qualityFactor": 0.47189759804447673,
"queueFactor": 1.1256660830249257,
"queueWeight": 1.1256660830249257,
"recentSuccess": 34,
"recentSuccessRate": 0.2222222222222222,
"recentTerminal": 153,
"recentWilsonLowerBound": 0.1636062832872712,
"running": 8,
"selectionWeight": 0.531199120779597,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 25.833333333333332,
"waiting": 9620
"throughputPerHour": 25.5,
"waiting": 9615
},
"MetaX_c-500": {
"available": true,
"backlogHours": 534.5042016806723,
"backlogHours": 548.1206896551724,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.6121254383634152,
"queueFactor": 1.0698431199833893,
"queueWeight": 1.0698431199833893,
"recentSuccess": 31,
"recentSuccessRate": 0.2605042016806723,
"recentTerminal": 119,
"recentWilsonLowerBound": 0.19001607594151526,
"qualityFactor": 0.5827457702443161,
"queueFactor": 1.0642398519009693,
"queueWeight": 1.0642398519009693,
"recentSuccess": 29,
"recentSuccessRate": 0.25,
"recentTerminal": 116,
"recentWilsonLowerBound": 0.18007382859915586,
"running": 4,
"selectionWeight": 0.654878188799916,
"selectionWeight": 0.6201812722207272,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 19.833333333333332,
"waiting": 10601
"throughputPerHour": 19.333333333333332,
"waiting": 10597
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1951.476923076923,
"backlogHours": 2045.9032258064515,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 2.5,
"queueFactor": 0.8809641867051905,
"queueWeight": 0.8809641867051905,
"recentSuccess": 31,
"recentSuccessRate": 0.47692307692307695,
"recentTerminal": 65,
"recentWilsonLowerBound": 0.36021590253064156,
"queueFactor": 0.8734502709728267,
"queueWeight": 0.8734502709728267,
"recentSuccess": 29,
"recentSuccessRate": 0.46774193548387094,
"recentTerminal": 62,
"recentWilsonLowerBound": 0.3490863086762221,
"running": 4,
"selectionWeight": 2.2024104667629762,
"selectionWeight": 2.1836256774320666,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 10.833333333333334,
"throughputPerHour": 10.333333333333334,
"waiting": 21141
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 3646.222222222222,
"backlogHours": 3786.692307692308,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.5870015094062974,
"queueFactor": 0.8021143695560023,
"queueWeight": 0.8021143695560023,
"recentSuccess": 9,
"recentSuccessRate": 0.3333333333333333,
"recentTerminal": 27,
"recentWilsonLowerBound": 0.1864305444359335,
"qualityFactor": 0.4808586111897862,
"queueFactor": 0.7964012707953023,
"queueWeight": 0.7964012707953023,
"recentSuccess": 8,
"recentSuccessRate": 0.3076923076923077,
"recentTerminal": 26,
"recentWilsonLowerBound": 0.1650112093979267,
"running": 2,
"selectionWeight": 0.470842345645854,
"selectionWeight": 0.3829564090244099,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 4.5,
"waiting": 16408
"throughputPerHour": 4.333333333333333,
"waiting": 16409
},
"Vastai_va16": {
"available": true,
"backlogHours": 838.3366336633663,
"backlogHours": 830.1176470588235,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 1.1388005138668627,
"qualityFactor": 1.2876714538376066,
"queueFactor": 1.0,
"queueWeight": 1.0,
"recentSuccess": 34,
"recentSuccessRate": 0.33663366336633666,
"recentTerminal": 101,
"recentWilsonLowerBound": 0.25196434238298415,
"recentSuccess": 35,
"recentSuccessRate": 0.3431372549019608,
"recentTerminal": 102,
"recentWilsonLowerBound": 0.25820365661589834,
"running": 16,
"selectionWeight": 1.1388005138668627,
"selectionWeight": 1.2876714538376066,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 16.833333333333332,
"throughputPerHour": 17.0,
"waiting": 14112
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 991.9428571428572,
"backlogHours": 973.2336448598131,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 0.8869143753301867,
"queueFactor": 0.9750789219252397,
"queueWeight": 0.9750789219252397,
"recentSuccess": 32,
"recentSuccessRate": 0.3047619047619048,
"recentTerminal": 105,
"recentWilsonLowerBound": 0.22490075875702692,
"qualityFactor": 0.9870934358919919,
"queueFactor": 0.9764238521217539,
"queueWeight": 0.9764238521217539,
"recentSuccess": 33,
"recentSuccessRate": 0.308411214953271,
"recentTerminal": 107,
"recentWilsonLowerBound": 0.2288160943036506,
"running": 6,
"selectionWeight": 0.8648115129369558,
"selectionWeight": 0.9638215750777562,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.5,
"waiting": 17359
"throughputPerHour": 17.833333333333332,
"waiting": 17356
}
},
"queueAttemptedAt": "2026-09-26T17:48:04.874286+00:00",
"queueAttemptedAt": "2026-09-26T17:58:26.848553+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-26T17:48:04.874286+00:00",
"queueUpdatedAt": "2026-09-26T17:58:26.848553+00:00",
"supportedGpus": [
"Vastai_va16",
"Cambricon_mlu-370-x4",

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-09-26T17:56:32.847933+00:00",
"catalogUpdatedAt": "2026-09-26T17:58:26.848553+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-09-26T17:56:32.847933+00:00",
"generatedAt": "2026-09-26T17:58:26.848553+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6265,6 +6265,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-09-26T17:56:32.847933+00:00",
"taskTreeUpdatedAt": "2026-09-26T17:58:26.848553+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-26T17:19:54.419455+00:00",
"lastSyncTime": "2026-09-26T17:19:54.158491+00:00",
"generatedAt": "2026-09-26T17:57:36.464760+00:00",
"lastSyncTime": "2026-09-26T17:57:36.159288+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -5402,18 +5402,18 @@
"unresolvedFailureCount": 296
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 111,
"attributableFailureCount": 112,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 111,
"decisionTotal": 112,
"failureBreakdown": {
"backend_operator": 9,
"framework_architecture_unsupported": 14,
"platform_infrastructure": 20,
"tokenizer_compatibility": 88,
"tokenizer_compatibility": 89,
"参数/模板问题": 6
},
"failureCount": 137,
"failureCount": 138,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -5423,7 +5423,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 137,
"total": 138,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -6080,10 +6080,10 @@
"unresolvedFailureCount": 25
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 148,
"decisionFailureRate": 0.9673,
"decisionSuccessRate": 0.0327,
"decisionTotal": 153,
"attributableFailureCount": 149,
"decisionFailureRate": 0.9675,
"decisionSuccessRate": 0.0325,
"decisionTotal": 154,
"failureBreakdown": {
"ambiguous_runtime": 319,
"backend_operator": 9,
@@ -6091,17 +6091,17 @@
"memory_capacity": 10,
"model_load": 9,
"platform_infrastructure": 20,
"tokenizer_compatibility": 88,
"tokenizer_compatibility": 89,
"参数/模板问题": 13
},
"failureCount": 500,
"failureCount": 501,
"failureRate": 0.9901,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 20,
"successCount": 5,
"successRate": 0.0099,
"total": 505,
"total": 506,
"unresolvedFailureCount": 332
},
"vllm_tokenizer_patch": {
@@ -6133,7 +6133,7 @@
"unresolvedFailureCount": 196
}
},
"generatedAt": "2026-09-26T17:19:54.406878+00:00",
"generatedAt": "2026-09-26T17:57:36.450612+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -6468,10 +6468,10 @@
"unresolvedFailureCount": 299
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 744,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 837,
"attributableFailureCount": 745,
"decisionFailureRate": 0.889,
"decisionSuccessRate": 0.111,
"decisionTotal": 838,
"failureBreakdown": {
"ambiguous_runtime": 162,
"architecture_compatibility": 44,
@@ -6482,18 +6482,18 @@
"platform_infrastructure": 225,
"repository_structure": 83,
"runtime_memory": 1,
"tokenizer_compatibility": 270,
"tokenizer_compatibility": 271,
"参数/模板问题": 228,
"验证失败": 32
},
"failureCount": 1391,
"failureRate": 0.9373,
"failureCount": 1392,
"failureRate": 0.9374,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 225,
"successCount": 93,
"successRate": 0.0627,
"total": 1484,
"successRate": 0.0626,
"total": 1485,
"unresolvedFailureCount": 422
},
"Vastai_va16": {
@@ -22773,10 +22773,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 11,
"ambiguous_runtime": 10,
"framework_architecture_unsupported": 1
},
"failureCount": 12,
"failureCount": 11,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -22788,8 +22788,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 12,
"unresolvedFailureCount": 11
"total": 11,
"unresolvedFailureCount": 10
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -23210,22 +23210,22 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 2,
"tokenizer_compatibility": 3
"tokenizer_compatibility": 4
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-23T02:14:08+00:00",
"lastTerminalAt": "2026-09-24T02:15:32.962539+00:00",
"lastTerminalAt": "2026-09-26T17:57:36.159288+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
@@ -23233,7 +23233,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 6,
"total": 7,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
@@ -23824,9 +23824,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 2
},
"failureCount": 3,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-26T07:10:36.169068+00:00",
@@ -23839,8 +23839,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x4|vllm|text-generation|mpt|none": {
"attributableFailureCount": 0,
@@ -50907,13 +50907,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17042,
"totalRecords": 17263,
"terminalRecords": 17043,
"totalRecords": 17264,
"totals": {
"attributableFailureCount": 6111,
"attributableFailureCount": 6112,
"decisionFailureRate": 0.8635,
"decisionSuccessRate": 0.1365,
"decisionTotal": 7077,
"decisionTotal": 7078,
"failureBreakdown": {
"ambiguous_runtime": 4407,
"architecture_compatibility": 212,
@@ -50926,35 +50926,35 @@
"platform_infrastructure": 936,
"repository_structure": 742,
"runtime_memory": 100,
"tokenizer_compatibility": 678,
"tokenizer_compatibility": 679,
"参数/模板问题": 3227,
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16076,
"failureCount": 16077,
"failureRate": 0.9433,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 936,
"successCount": 966,
"successRate": 0.0567,
"total": 17042,
"total": 17043,
"unresolvedFailureCount": 9029
},
"warnings": [
"GPU Biren_166m 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 Iluvatar_bi-100 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 MetaX_c-500 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 Mthreads_s4000 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 Ascend_910-b3 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 Ascend_910-b4 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 hygon_k100-ai 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 MetaX_c-500 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 Iluvatar_bi-150 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。",
"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 Sunrise_pt-200-x1|vllm|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -50967,7 +50967,6 @@
"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。",
"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 Cambricon_mlu-370-x4|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-x8|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 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 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 Cambricon_mlu-370-x8|vllm-customized|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -50993,10 +50992,11 @@
"组合 Cambricon_mlu-370-x4|unknown|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b4|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 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 MetaX_c-500|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": 17263,
"summarizedRecords": 17264,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-26T17:57:36.159288+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-Non-Uniform-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-26T17:52:08+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457999", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-26T17:14:27.552028+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-26T17:12:10+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458906", "taskType": "text-generation", "verifyResult": 1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-24T03:51:15.462039+00:00", "modelId": "BAAI/CareBot_Medical_multi-llama3-8b-rl", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-24T03:50:10+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457984", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-24T02:15:32.962539+00:00", "modelId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-24T02:14:08+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457989", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +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", "lastSyncTime": "2026-09-26T01:14:46.157779+00:00", "modelId": "neuralmagic/gemma-2-2b-it-quantized.w8a8", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4385522016, "estimatedRequiredGiB": 4.926, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 4407346497, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4407346497}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:09:48.974589+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991863", "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", "lastSyncTime": "2026-09-25T09:35:33.057165+00:00", "modelId": "neuralmagic/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7855165704, "estimatedRequiredGiB": 8.783, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7858541078, "modelscopeLicense": "other", "modelscopeParams": 7400416256, "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", "repositoryOnDiskBytes": 7858541078}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:09:37.383882+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991862", "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", "lastSyncTime": "2026-09-26T14:37:53.556324+00:00", "modelId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7686303632, "estimatedRequiredGiB": 8.592, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 7688299919, "modelscopeLicense": "llama2", "modelscopeParams": 13960238080, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7688299919}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:09:36.977617+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991858", "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", "lastSyncTime": "2026-09-26T01:14:46.157767+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014810120, "estimatedRequiredGiB": 2.256, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018195521, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2018195521}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:09:20.980304+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991857", "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

View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.22.1",
"checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "ab3fbc961a44cc0c0771ff74cb275f2d644c3075e31e6f2588e1b6c0753a832f",
".modelhub_state/architecture_compatibility_blacklist.json": "50b688ee16b7dfadec16ca7e8ed54eeea5ce21e764ef8e05662ed0e451675486",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "cb1bc322dd6240db74ed2dfd738b55f61ef85da7d31c9bbe8ae462e814cd9139",
".modelhub_state/official_capabilities.json": "a10c56761c70b5afa3d284cbbf1b74e6d9a004566b9cdbd55a532f334c62dcfb",
".modelhub_state/outcome_checkpoint.json": "87bc6b0ae19930fb62c6cb744e4bdcd55bf55e096e3ac77a4835757d2c96d4dd",
".modelhub_state/market_intelligence.json": "1c276cc3a4c0d7f6fab328661624ad58ad20a59fef0e9e73c4a0a246f7de7df3",
".modelhub_state/official_capabilities.json": "78f0ceb3b4fc0df122283e1188086905476382b0fe84578542a3935dd0cdaf09",
".modelhub_state/outcome_checkpoint.json": "5e8dd0e0381938adad29ee475a89387a6fbde5e1fb7e3042aef7d371284ac12f",
".modelhub_state/queue_cleanup_latest.json": "69b07b4c7f0e1a61310077a9b0cf5b45c959484d402ad60f0304381993afe5e7",
".modelhub_state/recent_outcomes.jsonl": "5bb3cb27e3f3907a8c702285032b948854e2231cc687129c54c45d75115b3d47",
".modelhub_state/recovery_active_tasks.jsonl": "6600822837f68b7f8d5b43e646ee70dee6973f734fc411b45373c1d9d7e16834",
".modelhub_state/recovery_intents.jsonl": "a05ed544a5c2c893f126d53e65b8b45a60a19d1c578094f35b79b8c1bcb31a64",
".modelhub_state/recent_outcomes.jsonl": "94cee511bdff3336099866fb3c6afdd345089bb56c8aa0e85ff9041c08254a57",
".modelhub_state/recovery_active_tasks.jsonl": "f7fe493d2f8461b74efbbb936f3b34fb8640074d26a8b05d0942e37142bcd6bc",
".modelhub_state/recovery_intents.jsonl": "961d8613fe21c61ef2e570f68bb44341121519f05eb5140a2ebfac0efae97073",
".modelhub_state/routing_intelligence.json": "519577e231ce3934d8378cbf1f13f1356f0576991f528675ded72ec2b8b3c804",
".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799",
".modelhub_state/worker_crashes.jsonl": "ccd40ad86ab5068ea1c3520a48fa733cf2e4b357ae5abb95ff00728d5d1b5487",
"ledger/submissions.jsonl": "6071510b13d7fa1186e155941f35e6810e50a687772bd3064a7286c5ba918d9c",
"outcomes/submissions.jsonl": "66ae7581811fcad3bc8f774f7b2268b56b4c41fa9933aa42807a381da20b20be"
},
"generation": 16717,
"generation": 16718,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-26T17:56:33.614790+00:00",
"updatedAt": "2026-09-26T17:58:33.350727+00:00",
"writerId": "08206cb1993a433e83f1d3e297db2d2e"
}