state: generation 11924 (cycle)

This commit is contained in:
2026-09-21 23:49:44 +00:00
parent c31ab7906f
commit df7a46930d
10 changed files with 2158 additions and 2090 deletions

View File

@@ -2871,7 +2871,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-21T23:47:10.180109+00:00",
"generatedAt": "2026-09-21T23:49:31.310894+00:00",
"summary": {
"activeBlockCount": 144,
"byGpuFramework": {

View File

@@ -434,121 +434,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-21T23:48:29.667437+00:00",
"generatedAt": "2026-09-21T23:49:41.847306+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 959.469387755102,
"backlogHours": 979.1666666666666,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.5245052596931628,
"queueFactor": 0.9966417567009521,
"queueWeight": 0.9966417567009521,
"recentSuccess": 37,
"recentSuccessRate": 0.25170068027210885,
"recentTerminal": 147,
"recentWilsonLowerBound": 0.18847735749857328,
"qualityFactor": 0.5892242841853491,
"queueFactor": 0.9972810192940773,
"queueWeight": 0.9972810192940773,
"recentSuccess": 38,
"recentSuccessRate": 0.2638888888888889,
"recentTerminal": 144,
"recentWilsonLowerBound": 0.1987136611938409,
"running": 8,
"selectionWeight": 0.5227438434194828,
"selectionWeight": 0.5876221947251881,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 24.5,
"waiting": 23507
"throughputPerHour": 24.0,
"waiting": 23500
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1247.9117647058822,
"backlogHours": 1220.8489208633093,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.5880177186993825,
"queueFactor": 0.9581117485768518,
"queueWeight": 0.9581117485768518,
"recentSuccess": 53,
"recentSuccessRate": 0.3897058823529412,
"recentTerminal": 136,
"recentWilsonLowerBound": 0.3118483860305096,
"qualityFactor": 1.7392347622955056,
"queueFactor": 0.9648210229809128,
"queueWeight": 0.9648210229809128,
"recentSuccess": 56,
"recentSuccessRate": 0.4028776978417266,
"recentTerminal": 139,
"recentWilsonLowerBound": 0.32501196368104285,
"running": 8,
"selectionWeight": 1.5214984332340884,
"selectionWeight": 1.6780502625619143,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.666666666666668,
"waiting": 28286
"throughputPerHour": 23.166666666666668,
"waiting": 28283
},
"Biren_166m": {
"available": true,
"backlogHours": 176.65116279069767,
"backlogHours": 180.53571428571428,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.3178865505407725,
"queueFactor": 1.2846247126700714,
"queueWeight": 1.2846247126700714,
"qualityFactor": 0.3352575809456031,
"queueFactor": 1.2851729534667333,
"queueWeight": 1.2851729534667333,
"recentSuccess": 35,
"recentSuccessRate": 0.20348837209302326,
"recentTerminal": 172,
"recentWilsonLowerBound": 0.15010863889106016,
"recentSuccessRate": 0.20833333333333334,
"recentTerminal": 168,
"recentWilsonLowerBound": 0.15378310320374775,
"running": 8,
"selectionWeight": 0.40836491865012,
"selectionWeight": 0.43086397547597316,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 28.666666666666668,
"waiting": 5064
"throughputPerHour": 28.0,
"waiting": 5055
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1963.9565217391303,
"backlogHours": 2101.6744186046512,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.65604723348485,
"queueFactor": 0.8951049670816492,
"queueWeight": 0.8951049670816492,
"recentSuccess": 15,
"recentSuccessRate": 0.32608695652173914,
"recentTerminal": 46,
"recentWilsonLowerBound": 0.20865764564493355,
"running": 7,
"selectionWeight": 0.5872311373324637,
"qualityFactor": 0.6305466178638047,
"queueFactor": 0.8893264943907511,
"queueWeight": 0.8893264943907511,
"recentSuccess": 14,
"recentSuccessRate": 0.32558139534883723,
"recentTerminal": 43,
"recentWilsonLowerBound": 0.20493115181779817,
"running": 8,
"selectionWeight": 0.560761813214762,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 7.666666666666667,
"waiting": 15057
"throughputPerHour": 7.166666666666667,
"waiting": 15062
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 487.27433628318585,
"backlogHours": 483.1578947368421,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.2711119888701423,
"queueFactor": 1.1032596039023446,
"queueWeight": 1.1032596039023446,
"qualityFactor": 0.2657477529253461,
"queueFactor": 1.10874757883722,
"queueWeight": 1.10874757883722,
"recentSuccess": 23,
"recentSuccessRate": 0.20353982300884957,
"recentTerminal": 113,
"recentWilsonLowerBound": 0.1396323173788541,
"recentSuccessRate": 0.20175438596491227,
"recentTerminal": 114,
"recentWilsonLowerBound": 0.13836966525548045,
"running": 7,
"selectionWeight": 0.29910690545405005,
"selectionWeight": 0.2946471776374092,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.833333333333332,
"waiting": 9177
"throughputPerHour": 19.0,
"waiting": 9180
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 42.339285714285715,
"backlogHours": 40.56410256410256,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -558,103 +558,103 @@
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 10,
"recentSuccessRate": 0.02976190476190476,
"recentTerminal": 336,
"recentWilsonLowerBound": 0.016244723626680543,
"running": 24,
"recentSuccessRate": 0.02849002849002849,
"recentTerminal": 351,
"recentWilsonLowerBound": 0.015547266406963859,
"running": 25,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 56.0,
"waiting": 2371
"throughputPerHour": 58.5,
"waiting": 2373
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 121.3941908713693,
"backlogHours": 117.44578313253012,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.0684518673346171,
"qualityFactor": 0.05149534516257742,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 26,
"recentSuccessRate": 0.1078838174273859,
"recentTerminal": 241,
"recentWilsonLowerBound": 0.07469220817077807,
"running": 2,
"selectionWeight": 0.08898742753500223,
"recentSuccess": 24,
"recentSuccessRate": 0.0963855421686747,
"recentTerminal": 249,
"recentWilsonLowerBound": 0.06562746137893503,
"running": 3,
"selectionWeight": 0.06694394871135065,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 40.166666666666664,
"waiting": 4876
"throughputPerHour": 41.5,
"waiting": 4874
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2916.3636363636365,
"backlogHours": 2830.235294117647,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.43856438200201087,
"queueFactor": 0.8435629488309275,
"queueWeight": 0.8435629488309275,
"recentSuccess": 10,
"recentSuccessRate": 0.30303030303030304,
"recentTerminal": 33,
"recentWilsonLowerBound": 0.17375347814547226,
"qualityFactor": 0.5420321664225047,
"queueFactor": 0.8504967632319744,
"queueWeight": 0.8504967632319744,
"recentSuccess": 11,
"recentSuccessRate": 0.3235294117647059,
"recentTerminal": 34,
"recentWilsonLowerBound": 0.19131451326458573,
"running": 2,
"selectionWeight": 0.36995666333382965,
"selectionWeight": 0.46099660310995516,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 5.5,
"waiting": 16040
"throughputPerHour": 5.666666666666667,
"waiting": 16038
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 673.0212765957447,
"backlogHours": 658.75,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.6346909765380557,
"queueFactor": 1.0510888482332497,
"queueWeight": 1.0510888482332497,
"recentSuccess": 27,
"recentSuccessRate": 0.2872340425531915,
"recentTerminal": 94,
"recentWilsonLowerBound": 0.20554230330818626,
"qualityFactor": 0.6665162636305064,
"queueFactor": 1.0583710508514597,
"queueWeight": 1.0583710508514597,
"recentSuccess": 28,
"recentSuccessRate": 0.2916666666666667,
"recentTerminal": 96,
"recentWilsonLowerBound": 0.21016461419964405,
"running": 8,
"selectionWeight": 0.6671166075134215,
"selectionWeight": 0.7054215183482077,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 15.666666666666666,
"waiting": 10544
"throughputPerHour": 16.0,
"waiting": 10540
},
"MetaX_c-500": {
"available": true,
"backlogHours": 684.1263157894737,
"backlogHours": 669.8969072164948,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.8208309412183821,
"queueFactor": 1.0485117531781447,
"queueWeight": 1.0485117531781447,
"qualityFactor": 0.7823269110878763,
"queueFactor": 1.0557105232681236,
"queueWeight": 1.0557105232681236,
"recentSuccess": 30,
"recentSuccessRate": 0.3157894736842105,
"recentTerminal": 95,
"recentWilsonLowerBound": 0.23103088128713048,
"recentSuccessRate": 0.30927835051546393,
"recentTerminal": 97,
"recentWilsonLowerBound": 0.22604022957947018,
"running": 4,
"selectionWeight": 0.8606508892397524,
"selectionWeight": 0.8259107526713168,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 15.833333333333334,
"waiting": 10832
"throughputPerHour": 16.166666666666668,
"waiting": 10830
},
"Mthreads_s4000": {
"available": true,
@@ -665,14 +665,14 @@
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 2.5,
"queueFactor": 0.8514756797278829,
"queueWeight": 0.8514756797278829,
"queueFactor": 0.85462294178185,
"queueWeight": 0.85462294178185,
"recentSuccess": 25,
"recentSuccessRate": 0.5208333333333334,
"recentTerminal": 48,
"recentWilsonLowerBound": 0.38328995635984375,
"running": 4,
"selectionWeight": 2.128689199319707,
"selectionWeight": 2.136557354454625,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 8.0,
@@ -680,74 +680,74 @@
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 4513.142857142857,
"backlogHours": 4308.0,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.42858669033054864,
"queueFactor": 0.790081486512571,
"queueWeight": 0.790081486512571,
"qualityFactor": 0.38417183556728784,
"queueFactor": 0.7985547408121914,
"queueWeight": 0.7985547408121914,
"recentSuccess": 7,
"recentSuccessRate": 0.3333333333333333,
"recentTerminal": 21,
"recentWilsonLowerBound": 0.17194536432683688,
"recentSuccessRate": 0.3181818181818182,
"recentTerminal": 22,
"recentWilsonLowerBound": 0.16360387354692477,
"running": 2,
"selectionWeight": 0.3386184093958628,
"selectionWeight": 0.30678224057877934,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 3.5,
"throughputPerHour": 3.6666666666666665,
"waiting": 15796
},
"Vastai_va16": {
"available": true,
"backlogHours": 1738.9199999999998,
"backlogHours": 1704.8235294117646,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.05,
"queueFactor": 0.9115947326666862,
"queueWeight": 0.9115947326666862,
"queueFactor": 0.9176860541809757,
"queueWeight": 0.9176860541809757,
"recentSuccess": 6,
"recentSuccessRate": 0.12,
"recentTerminal": 50,
"recentWilsonLowerBound": 0.05617523710624645,
"running": 16,
"selectionWeight": 0.04557973663333431,
"recentSuccessRate": 0.11764705882352941,
"recentTerminal": 51,
"recentWilsonLowerBound": 0.05504998764172767,
"running": 17,
"selectionWeight": 0.04588430270904879,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 8.333333333333334,
"throughputPerHour": 8.5,
"waiting": 14491
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 916.9142857142857,
"backlogHours": 943.9411764705883,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 0.19076964850271685,
"queueFactor": 1.0034469946921827,
"queueWeight": 1.0034469946921827,
"qualityFactor": 0.20371044052485024,
"queueFactor": 1.0027768673215995,
"queueWeight": 1.0027768673215995,
"recentSuccess": 19,
"recentSuccessRate": 0.18095238095238095,
"recentTerminal": 105,
"recentWilsonLowerBound": 0.11901573432473685,
"running": 6,
"selectionWeight": 0.19142723046853527,
"recentSuccessRate": 0.18627450980392157,
"recentTerminal": 102,
"recentWilsonLowerBound": 0.12261984082072329,
"running": 7,
"selectionWeight": 0.20427611739021234,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.5,
"waiting": 16046
"throughputPerHour": 17.0,
"waiting": 16047
}
},
"queueAttemptedAt": "2026-09-21T23:38:52.871112+00:00",
"queueAttemptedAt": "2026-09-21T23:49:41.847306+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-21T23:38:52.871112+00:00",
"queueUpdatedAt": "2026-09-21T23:49:41.847306+00:00",
"supportedGpus": [
"Vastai_va16",
"Kunlunxin_p-800",

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-09-21T23:48:29.667437+00:00",
"catalogUpdatedAt": "2026-09-21T23:49:41.847306+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-09-21T23:48:29.667437+00:00",
"generatedAt": "2026-09-21T23:49:41.847306+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6819,6 +6819,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-09-21T23:48:29.667437+00:00",
"taskTreeUpdatedAt": "2026-09-21T23:49:41.847306+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T23:47:10.105504+00:00",
"lastSyncTime": "2026-09-21T23:47:09.753992+00:00",
"generatedAt": "2026-09-21T23:49:31.238696+00:00",
"lastSyncTime": "2026-09-21T23:49:30.866198+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3206,7 +3206,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 204,
"failureBreakdown": {
"ambiguous_runtime": 109,
"ambiguous_runtime": 110,
"context_length": 1,
"framework_architecture_unsupported": 155,
"memory_capacity": 10,
@@ -3214,7 +3214,7 @@
"repository_structure": 27,
"tokenizer_compatibility": 11
},
"failureCount": 314,
"failureCount": 315,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -3224,8 +3224,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 314,
"unresolvedFailureCount": 109
"total": 315,
"unresolvedFailureCount": 110
},
"Biren_166m|unknown|feature_emb": {
"attributableFailureCount": 0,
@@ -3526,12 +3526,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 11,
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 4,
"model_load": 2,
"参数/模板问题": 4
},
"failureCount": 21,
"failureCount": 22,
"failureRate": 1.0,
"framework": "vllm-customized",
"pendingCount": 0,
@@ -3541,8 +3541,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 21,
"unresolvedFailureCount": 15
"total": 22,
"unresolvedFailureCount": 16
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 13,
@@ -5532,7 +5532,7 @@
"decisionSuccessRate": 0.0242,
"decisionTotal": 3635,
"failureBreakdown": {
"ambiguous_runtime": 1499,
"ambiguous_runtime": 1500,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
@@ -5546,15 +5546,15 @@
"tokenizer_compatibility": 412,
"参数/模板问题": 46
},
"failureCount": 5957,
"failureCount": 5958,
"failureRate": 0.9854,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 865,
"successCount": 88,
"successRate": 0.0146,
"total": 6045,
"unresolvedFailureCount": 1545
"total": 6046,
"unresolvedFailureCount": 1546
},
"vllm-customized": {
"attributableFailureCount": 6,
@@ -5562,20 +5562,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 11,
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 4,
"model_load": 2,
"参数/模板问题": 4
},
"failureCount": 21,
"failureCount": 22,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 21,
"unresolvedFailureCount": 15
"total": 22,
"unresolvedFailureCount": 16
},
"vllm-mlu": {
"attributableFailureCount": 21,
@@ -5700,7 +5700,7 @@
"unresolvedFailureCount": 121
}
},
"generatedAt": "2026-09-21T23:47:10.094226+00:00",
"generatedAt": "2026-09-21T23:49:31.228042+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 99,
@@ -5734,7 +5734,7 @@
"decisionSuccessRate": 0.1636,
"decisionTotal": 385,
"failureBreakdown": {
"ambiguous_runtime": 183,
"ambiguous_runtime": 184,
"context_length": 1,
"framework_architecture_unsupported": 178,
"memory_capacity": 19,
@@ -5746,15 +5746,15 @@
"日志缺失": 14,
"验证失败": 175
},
"failureCount": 964,
"failureCount": 965,
"failureRate": 0.9387,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 63,
"successRate": 0.0613,
"total": 1027,
"unresolvedFailureCount": 640
"total": 1028,
"unresolvedFailureCount": 641
},
"Biren_166m": {
"attributableFailureCount": 186,
@@ -5821,7 +5821,7 @@
"decisionSuccessRate": 0.209,
"decisionTotal": 67,
"failureBreakdown": {
"ambiguous_runtime": 111,
"ambiguous_runtime": 112,
"framework_architecture_unsupported": 44,
"memory_capacity": 4,
"model_load": 3,
@@ -5829,15 +5829,15 @@
"参数/模板问题": 34,
"验证失败": 22
},
"failureCount": 220,
"failureRate": 0.9402,
"failureCount": 221,
"failureRate": 0.9404,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 14,
"successRate": 0.0598,
"total": 234,
"unresolvedFailureCount": 167
"successRate": 0.0596,
"total": 235,
"unresolvedFailureCount": 168
},
"Iluvatar_bi-100": {
"attributableFailureCount": 194,
@@ -7956,9 +7956,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
"ambiguous_runtime": 5
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "llama",
@@ -7970,8 +7970,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
"total": 5,
"unresolvedFailureCount": 5
},
"Ascend_910-b4|vllm|text-generation|llama|none": {
"attributableFailureCount": 1,
@@ -9883,6 +9883,29 @@
"total": 4,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|mistral3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -18058,15 +18081,15 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 8,
"ambiguous_runtime": 9,
"model_load": 2,
"参数/模板问题": 4
},
"failureCount": 14,
"failureCount": 15,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T19:49:37.657075+00:00",
"lastTerminalAt": "2026-09-21T23:49:30.866184+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -18074,8 +18097,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 14,
"unresolvedFailureCount": 12
"total": 15,
"unresolvedFailureCount": 13
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 0,
@@ -19505,6 +19528,31 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastTerminalAt": "2026-09-21T23:49:30.866184+00:00",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|mistral3|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -19787,9 +19835,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 6
"ambiguous_runtime": 5
},
"failureCount": 6,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-21T17:22:47.256939+00:00",
@@ -19802,8 +19850,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 6
"total": 5,
"unresolvedFailureCount": 5
},
"Cambricon_mlu-370-x8|vllm|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0,
@@ -24485,9 +24533,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
@@ -24500,8 +24548,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Ascend_910-b4|vllm|text-generation|llama|awq|33": {
"attributableFailureCount": 0,
@@ -27229,6 +27277,30 @@
"total": 3,
"unresolvedFailureCount": 3
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|none|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|mistral3|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -38621,15 +38693,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16441,
"totalRecords": 16635,
"terminalRecords": 16443,
"totalRecords": 16637,
"totals": {
"attributableFailureCount": 5925,
"decisionFailureRate": 0.8619,
"decisionSuccessRate": 0.1381,
"decisionTotal": 6874,
"failureBreakdown": {
"ambiguous_runtime": 4054,
"ambiguous_runtime": 4056,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 105,
@@ -38645,31 +38717,31 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15492,
"failureCount": 15494,
"failureRate": 0.9423,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 949,
"successRate": 0.0577,
"total": 16441,
"unresolvedFailureCount": 8642
"total": 16443,
"unresolvedFailureCount": 8644
},
"warnings": [
"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。",
"GPU Cambricon_mlu-370-x8 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 MetaX_c-500 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 Iluvatar_bi-100 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-b3 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 Cambricon_mlu-370-x4 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 Cambricon_mlu-370-x8 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 Ascend_910-b4 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 Vastai_va16 本地统计失败率偏高(≥50%),建议重点关注。",
"组合 Iluvatar_bi-150|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 Sunrise_pt-200-x1|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 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。",
@@ -38709,6 +38781,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16635,
"summarizedRecords": 16637,
"version": 1
}

View File

@@ -78,6 +78,7 @@
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446712+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:07+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4923872", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-21T02:49:19.765032+00:00", "modelId": "BAAI/Aerospace-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-21T02:47:22+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457982", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "runtime_memory", "failureAction": "lower_memory_risk_or_reject_combination", "failureCategory": "runtime_memory", "failureClassificationReason": "structured_device_oom", "failureCode": "DEVICE_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-21T02:38:57.372787+00:00", "modelId": "nv-community/Llama-3_3-Nemotron-Super-49B-v1_5-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:37:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079201", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-21T23:49:30.866184+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426233716, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426233716}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:10:00.812814+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4991872", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-21T21:08:12.157607+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612744, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788612744}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:09:20.580117+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4991853", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-21T02:15:17.867390+00:00", "modelId": "BAAI/Automobile-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-21T02:07:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457986", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T22:22:17.565334+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504988, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504988}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T01:54:23.235347+00:00", "targetGpu": "Biren_166m", "taskId": "4991515", "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": "2026-09-21T04:51:55.164906+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109841981, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109841981}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.344449+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970441", "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": "2026-09-20T22:27:36.960842+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.342540+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970435", "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": "2026-09-21T04:51:55.164837+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426233716, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426233716}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.341085+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970438", "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": "2026-09-20T22:27:36.960871+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.338954+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970440", "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