state: generation 19499 (cycle)

This commit is contained in:
2026-10-02 04:10:45 +00:00
parent be35d072a6
commit 2832da1257
8 changed files with 1476 additions and 1430 deletions

View File

@@ -3322,7 +3322,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-10-02T03:58:36.568498+00:00",
"generatedAt": "2026-10-02T04:08:31.710240+00:00",
"summary": {
"activeBlockCount": 167,
"byGpuFramework": {

View File

@@ -434,121 +434,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-02T04:07:15.860540+00:00",
"generatedAt": "2026-10-02T04:10:34.076546+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 1220.9774436090224,
"backlogHours": 1220.842105263158,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.1412502742831583,
"queueFactor": 1.0010654440584255,
"queueWeight": 1.0010654440584255,
"qualityFactor": 0.9988711378289822,
"queueFactor": 1.002679257511967,
"queueWeight": 1.002679257511967,
"recentSuccess": 39,
"recentSuccessRate": 0.2932330827067669,
"recentTerminal": 133,
"recentWilsonLowerBound": 0.22254052641165156,
"running": 8,
"selectionWeight": 1.1424662126070697,
"selectionWeight": 1.0015473708284974,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.166666666666668,
"waiting": 27065
"waiting": 27062
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1368.046875,
"backlogHours": 1378.7244094488187,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.0230574381185025,
"queueFactor": 0.9841322628170425,
"queueWeight": 0.9841322628170425,
"recentSuccess": 47,
"recentSuccessRate": 0.3671875,
"recentTerminal": 128,
"recentWilsonLowerBound": 0.28868321179914996,
"qualityFactor": 2.008447717409049,
"queueFactor": 0.9845535352391447,
"queueWeight": 0.9845535352391447,
"recentSuccess": 49,
"recentSuccessRate": 0.3858267716535433,
"recentTerminal": 127,
"recentWilsonLowerBound": 0.3057003665190399,
"running": 8,
"selectionWeight": 1.9909560943844107,
"selectionWeight": 1.9774243005180698,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 21.333333333333332,
"waiting": 29185
"throughputPerHour": 21.166666666666668,
"waiting": 29183
},
"Biren_166m": {
"available": true,
"backlogHours": 150.15483870967742,
"backlogHours": 154.8,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.33826292839564465,
"qualityFactor": 0.2895653378204061,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 28,
"recentSuccessRate": 0.18064516129032257,
"recentTerminal": 155,
"recentWilsonLowerBound": 0.1280417541545077,
"recentSuccess": 27,
"recentSuccessRate": 0.18,
"recentTerminal": 150,
"recentWilsonLowerBound": 0.12675684863332679,
"running": 8,
"selectionWeight": 0.43974180691433806,
"selectionWeight": 0.376434939166528,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 25.833333333333332,
"waiting": 3879
"throughputPerHour": 25.0,
"waiting": 3870
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1540.0,
"backlogHours": 1711.111111111111,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.8921997173991513,
"queueFactor": 0.9668086072199157,
"queueWeight": 0.9668086072199157,
"recentSuccess": 18,
"recentSuccessRate": 0.3,
"recentTerminal": 60,
"recentWilsonLowerBound": 0.19898010252726894,
"qualityFactor": 0.7167128161444863,
"queueFactor": 0.9531674957401484,
"queueWeight": 0.9531674957401484,
"recentSuccess": 16,
"recentSuccessRate": 0.2962962962962963,
"recentTerminal": 54,
"recentWilsonLowerBound": 0.19137265695067046,
"running": 7,
"selectionWeight": 0.8625863661406759,
"selectionWeight": 0.6831473601293094,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 10.0,
"throughputPerHour": 9.0,
"waiting": 15400
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 410.5238095238095,
"backlogHours": 413.952,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.3998738017112776,
"queueFactor": 1.1788752873584276,
"queueWeight": 1.1788752873584276,
"qualityFactor": 0.3563614049536894,
"queueFactor": 1.1792841400537555,
"queueWeight": 1.1792841400537555,
"recentSuccess": 25,
"recentSuccessRate": 0.1984126984126984,
"recentTerminal": 126,
"recentWilsonLowerBound": 0.1381601427162113,
"recentSuccessRate": 0.2,
"recentTerminal": 125,
"recentWilsonLowerBound": 0.13929836507680304,
"running": 7,
"selectionWeight": 0.4714013428994893,
"selectionWeight": 0.4202513529891597,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 21.0,
"waiting": 8621
"throughputPerHour": 20.833333333333332,
"waiting": 8624
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 42.074766355140184,
"backlogHours": 37.98876404494382,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -557,197 +557,197 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 10,
"recentSuccessRate": 0.03115264797507788,
"recentTerminal": 321,
"recentWilsonLowerBound": 0.017007698797803106,
"recentSuccess": 9,
"recentSuccessRate": 0.025280898876404494,
"recentTerminal": 356,
"recentWilsonLowerBound": 0.013356098894040772,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 53.5,
"waiting": 2251
"throughputPerHour": 59.333333333333336,
"waiting": 2254
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 148.33333333333334,
"backlogHours": 128.16,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.20949917432140108,
"qualityFactor": 0.12133858101829592,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 31,
"recentSuccessRate": 0.14351851851851852,
"recentTerminal": 216,
"recentWilsonLowerBound": 0.10298486242763527,
"running": 5,
"selectionWeight": 0.2723489266178214,
"recentSuccess": 30,
"recentSuccessRate": 0.12,
"recentTerminal": 250,
"recentWilsonLowerBound": 0.08536266215857913,
"running": 2,
"selectionWeight": 0.15774015532378471,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 36.0,
"throughputPerHour": 41.666666666666664,
"waiting": 5340
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2699.4857142857145,
"backlogHours": 2862.7272727272725,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.577347992922699,
"queueFactor": 0.888743548700189,
"queueWeight": 0.888743548700189,
"qualityFactor": 0.5795129368558081,
"queueFactor": 0.8823562358299466,
"queueWeight": 0.8823562358299466,
"recentSuccess": 10,
"recentSuccessRate": 0.2857142857142857,
"recentTerminal": 35,
"recentWilsonLowerBound": 0.16326363398295565,
"recentSuccessRate": 0.30303030303030304,
"recentTerminal": 33,
"recentWilsonLowerBound": 0.17375347814547226,
"running": 2,
"selectionWeight": 0.5131143040650511,
"selectionWeight": 0.5113368535788483,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 5.833333333333333,
"waiting": 15747
"throughputPerHour": 5.5,
"waiting": 15745
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 331.27272727272725,
"backlogHours": 323.68888888888887,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.6919865999181947,
"queueFactor": 1.217420929716371,
"queueWeight": 1.217420929716371,
"recentSuccess": 32,
"recentSuccessRate": 0.24242424242424243,
"recentTerminal": 132,
"recentWilsonLowerBound": 0.17727358005868543,
"qualityFactor": 0.6238971092981886,
"queueFactor": 1.2236065323631367,
"queueWeight": 1.2236065323631367,
"recentSuccess": 33,
"recentSuccessRate": 0.24444444444444444,
"recentTerminal": 135,
"recentWilsonLowerBound": 0.17968077622878312,
"running": 8,
"selectionWeight": 0.8424389698236789,
"selectionWeight": 0.7634045784597415,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.0,
"waiting": 7288
"throughputPerHour": 22.5,
"waiting": 7283
},
"MetaX_c-500": {
"available": true,
"backlogHours": 651.7894736842105,
"backlogHours": 687.7333333333333,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.41570942326856325,
"queueFactor": 1.099898259773638,
"queueWeight": 1.099898259773638,
"recentSuccess": 20,
"recentSuccessRate": 0.21052631578947367,
"recentTerminal": 95,
"recentWilsonLowerBound": 0.14062079660997454,
"qualityFactor": 0.35763727961197805,
"queueFactor": 1.0928182635233192,
"queueWeight": 1.0928182635233192,
"recentSuccess": 19,
"recentSuccessRate": 0.2111111111111111,
"recentTerminal": 90,
"recentWilsonLowerBound": 0.13952483847594746,
"running": 4,
"selectionWeight": 0.4572380712245954,
"selectionWeight": 0.39083255087676566,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 15.833333333333334,
"waiting": 10320
"throughputPerHour": 15.0,
"waiting": 10316
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1812.082191780822,
"backlogHours": 1916.9565217391305,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 2.5,
"queueFactor": 0.9435000606608049,
"queueWeight": 0.9435000606608049,
"queueFactor": 0.937063703692904,
"queueWeight": 0.937063703692904,
"recentSuccess": 31,
"recentSuccessRate": 0.4246575342465753,
"recentTerminal": 73,
"recentWilsonLowerBound": 0.31784011426782005,
"recentSuccessRate": 0.4492753623188406,
"recentTerminal": 69,
"recentWilsonLowerBound": 0.3376866594343888,
"running": 4,
"selectionWeight": 2.3587501516520124,
"selectionWeight": 2.34265925923226,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.166666666666666,
"waiting": 22047
"throughputPerHour": 11.5,
"waiting": 22045
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 3097.2727272727275,
"backlogHours": 3194.0625,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.8776672563025557,
"queueFactor": 0.8706060864701384,
"queueWeight": 0.8706060864701384,
"recentSuccess": 11,
"recentSuccessRate": 0.3333333333333333,
"recentTerminal": 33,
"recentWilsonLowerBound": 0.197500294678037,
"qualityFactor": 1.067213194805599,
"queueFactor": 0.8679794520943293,
"queueWeight": 0.8679794520943293,
"recentSuccess": 12,
"recentSuccessRate": 0.375,
"recentTerminal": 32,
"recentWilsonLowerBound": 0.2293366846595921,
"running": 2,
"selectionWeight": 0.7641024552325519,
"selectionWeight": 0.9263191240952025,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 5.5,
"throughputPerHour": 5.333333333333333,
"waiting": 17035
},
"Vastai_va16": {
"available": true,
"backlogHours": 1408.3636363636363,
"backlogHours": 1452.28125,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.05,
"queueFactor": 0.9798540585402233,
"queueWeight": 0.9798540585402233,
"queueFactor": 0.976907280131287,
"queueWeight": 0.976907280131287,
"recentSuccess": 6,
"recentSuccessRate": 0.09090909090909091,
"recentTerminal": 66,
"recentWilsonLowerBound": 0.04233239859139771,
"recentSuccessRate": 0.09375,
"recentTerminal": 64,
"recentWilsonLowerBound": 0.04367765783128785,
"running": 16,
"selectionWeight": 0.04899270292701117,
"selectionWeight": 0.048845364006564355,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 11.0,
"waiting": 15492
"throughputPerHour": 10.666666666666666,
"waiting": 15491
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 1238.375,
"backlogHours": 1264.7872340425533,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 2.1099737670208354,
"queueFactor": 0.9989431884364505,
"queueWeight": 0.9989431884364505,
"recentSuccess": 37,
"recentSuccessRate": 0.3854166666666667,
"recentTerminal": 96,
"recentWilsonLowerBound": 0.29425614956558316,
"qualityFactor": 1.803994258332791,
"queueFactor": 0.9973746705076862,
"queueWeight": 0.9973746705076862,
"recentSuccess": 36,
"recentSuccessRate": 0.3829787234042553,
"recentTerminal": 94,
"recentWilsonLowerBound": 0.2911404875065257,
"running": 6,
"selectionWeight": 2.107743922345062,
"selectionWeight": 1.7992581790024254,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 16.0,
"waiting": 19814
"throughputPerHour": 15.666666666666666,
"waiting": 19815
}
},
"queueAttemptedAt": "2026-10-02T04:00:24.261389+00:00",
"queueAttemptedAt": "2026-10-02T04:10:34.076546+00:00",
"queueError": null,
"queueUpdatedAt": "2026-10-02T04:00:24.261389+00:00",
"queueUpdatedAt": "2026-10-02T04:10:34.076546+00:00",
"supportedGpus": [
"Vastai_va16",
"Cambricon_mlu-370-x4",

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-10-02T04:07:15.860540+00:00",
"catalogUpdatedAt": "2026-10-02T04:10:34.076546+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-10-02T04:07:15.860540+00:00",
"generatedAt": "2026-10-02T04:10:34.076546+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6577,6 +6577,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-10-02T04:07:15.860540+00:00",
"taskTreeUpdatedAt": "2026-10-02T04:10:34.076546+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-02T03:00:06.274687+00:00",
"lastSyncTime": "2026-10-02T03:00:05.603502+00:00",
"generatedAt": "2026-10-02T04:08:31.624363+00:00",
"lastSyncTime": "2026-10-02T04:08:31.346005+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4031,24 +4031,24 @@
"decisionSuccessRate": 0.4643,
"decisionTotal": 28,
"failureBreakdown": {
"ambiguous_runtime": 50,
"ambiguous_runtime": 51,
"framework_architecture_unsupported": 12,
"model_load": 2,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 68,
"failureRate": 0.8395,
"failureCount": 69,
"failureRate": 0.8415,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.1605,
"successRate": 0.1585,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 81,
"unresolvedFailureCount": 53
"total": 82,
"unresolvedFailureCount": 54
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 22,
@@ -6079,7 +6079,7 @@
"decisionSuccessRate": 0.3793,
"decisionTotal": 58,
"failureBreakdown": {
"ambiguous_runtime": 95,
"ambiguous_runtime": 96,
"framework_architecture_unsupported": 30,
"model_load": 5,
"platform_infrastructure": 1,
@@ -6087,15 +6087,15 @@
"参数/模板问题": 4,
"验证失败": 3
},
"failureCount": 139,
"failureRate": 0.8634,
"failureCount": 140,
"failureRate": 0.8642,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 22,
"successRate": 0.1366,
"total": 161,
"unresolvedFailureCount": 102
"successRate": 0.1358,
"total": 162,
"unresolvedFailureCount": 103
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 59,
@@ -6198,7 +6198,7 @@
"unresolvedFailureCount": 227
}
},
"generatedAt": "2026-10-02T03:00:06.260498+00:00",
"generatedAt": "2026-10-02T04:08:31.607627+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 114,
@@ -6320,7 +6320,7 @@
"decisionSuccessRate": 0.1974,
"decisionTotal": 76,
"failureBreakdown": {
"ambiguous_runtime": 154,
"ambiguous_runtime": 155,
"framework_architecture_unsupported": 49,
"memory_capacity": 4,
"model_load": 5,
@@ -6329,15 +6329,15 @@
"参数/模板问题": 41,
"验证失败": 22
},
"failureCount": 280,
"failureRate": 0.9492,
"failureCount": 281,
"failureRate": 0.9493,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 15,
"successRate": 0.0508,
"total": 295,
"unresolvedFailureCount": 217
"successRate": 0.0507,
"total": 296,
"unresolvedFailureCount": 218
},
"Iluvatar_bi-100": {
"attributableFailureCount": 194,
@@ -13541,6 +13541,29 @@
"total": 2,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_vl|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "qwen3_vl",
"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-mlu|text-generation|qwen3|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -39129,6 +39152,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_vl|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_vl",
"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-mlu|text-generation|qwen3|compressed-tensors|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -54855,15 +54902,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17226,
"totalRecords": 17447,
"terminalRecords": 17227,
"totalRecords": 17448,
"totals": {
"attributableFailureCount": 6175,
"decisionFailureRate": 0.8635,
"decisionSuccessRate": 0.1365,
"decisionTotal": 7151,
"failureBreakdown": {
"ambiguous_runtime": 4505,
"ambiguous_runtime": 4506,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
@@ -54879,30 +54926,30 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16250,
"failureCount": 16251,
"failureRate": 0.9433,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 947,
"successCount": 976,
"successRate": 0.0567,
"total": 17226,
"unresolvedFailureCount": 9128
"total": 17227,
"unresolvedFailureCount": 9129
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Biren_166m 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 Iluvatar_bi-100 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 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 Vastai_va16 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 Iluvatar_bi-150 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 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。",
"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 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。",
@@ -54947,6 +54994,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17447,
"summarizedRecords": 17448,
"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": "831d40d357c3dc89fd63ea4a34abe9e60abc9af65f1defb63b1e100beb03eaff",
".modelhub_state/architecture_compatibility_blacklist.json": "06749313958eb936d5114bd37b1030e8cc491b007b773d13a08e4fdec68652d7",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "3410b746736f45733055b7421edb35743f9e3c152e07385fcd586a91b41f1546",
".modelhub_state/official_capabilities.json": "d0ac631bbde73c66061d5a9ae31a6ca342bb6fec80f537e186f4ccca3c566028",
".modelhub_state/outcome_checkpoint.json": "b61eb59a88f9a87992faf5dbff0551452efe9513e24db9cbbcf5391199e35806",
".modelhub_state/market_intelligence.json": "b62fa4e8863ec4d2f9e2b232cbf2700eb6e28c68b2d25512d7afef533a4be47a",
".modelhub_state/official_capabilities.json": "630a8f7c74346a83d6fee586bdddab491c6d136f34959641b60bd7d7d3a7b0b0",
".modelhub_state/outcome_checkpoint.json": "d6c74d49c2a8b2d0b74433affbdfa909c7221a8aad6296f44bd271856a9b1f54",
".modelhub_state/queue_cleanup_latest.json": "74c13d4c59dfeb9a3fd710eaf91167f44612d72fa67412d9e8d243b8c87ff75d",
".modelhub_state/recent_outcomes.jsonl": "46ba903864c20bcb8c740303ed82aef3581120fbc65f1e55b14f49e961116871",
".modelhub_state/recovery_active_tasks.jsonl": "2ebb7aa8fe06edd735dfb04b22239edf0c0d9b06886bd86c05350e166b43a0e4",
".modelhub_state/recovery_intents.jsonl": "3a8bc8fa325d66dc49ecd9488ad4f33029b452cd2151faf301baf979565acc41",
".modelhub_state/recovery_active_tasks.jsonl": "92a8eebcbc780ccf03bafd37b37759eab6b3b166292552c41f35ecb91e367a0e",
".modelhub_state/recovery_intents.jsonl": "87ed672414ab77f76bc79cb893cd3add13ebecb0cfb55ea133e05ded35b75015",
".modelhub_state/routing_intelligence.json": "4cab060aa87c62b99c0f5f10e414a79361ce90d66fd3ab7f01b38511e88cd04c",
".modelhub_state/submission_exclusions.jsonl": "1e62f6ba5bd2ba5f2f360bc134b44f7b69190230dd0e274919a87a73ea66761c",
".modelhub_state/worker_crashes.jsonl": "21a892d638884250c04f19e07a433baae065285327484e361c9e5067b0bc17dd",
"ledger/submissions.jsonl": "abfab2f3da881ecee3988ff8331be0e15760a3c113c23263b2929fbe88b761d7",
"outcomes/submissions.jsonl": "704ca98d04f8f698d92992ce98fe34015d830bab204ec94e860181aa40c98ff5"
"outcomes/submissions.jsonl": "5ba98f2c7b8dd2872140e8998c3247d163f0d22af33c823bf61e217771d6ad33"
},
"generation": 19498,
"generation": 19499,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-10-02T04:07:28.429470+00:00",
"updatedAt": "2026-10-02T04:10:45.635022+00:00",
"writerId": "a812d0e025c3474eb16b828a4d987334"
}

View File

@@ -233,7 +233,6 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600416+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.045316+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969632", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.599986+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.252209+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969648", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600049+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.237107+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969645", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T11:30:54.600410+00:00", "modelId": "BAAI/RoboBrain2.5-8B-NV", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918210, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918210}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.258565+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4969650", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.599773+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:23.763321+00:00", "targetGpu": "MetaX_c-500", "taskId": "4969808", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671009+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:49.141735+00:00", "targetGpu": "Biren_166m", "taskId": "4970017", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.670603+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:49.147134+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4970014", "taskType": "text-generation", "verifyResult": null}
@@ -723,4 +722,4 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-02T02:41:55.840409+00:00", "modelId": "PleIAs/baguettotron-600m", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "5f9f3c1607c4d592480a2bc6bf4bd3811708695139f6772f4b18a577c41a71ec", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1216600244, "estimatedRequiredGiB": 1.365, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1221756819}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-01T18:36:11.048269+00:00", "targetGpu": "MetaX_c-500", "taskId": "5220158", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-02T03:00:05.603502+00:00", "modelId": "PleIAs/baguettotron-600m", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1216600244, "estimatedRequiredGiB": 1.365, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1221756819}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-01T18:56:27.055637+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5220400", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-02T03:50:13.861293+00:00", "modelId": "PleIAs/Baguettotron-MoE", "modelProfile": {"architectures": ["BaguettotronMoeForCausalLM"], "configFingerprint": "5f9f3c1607c4d592480a2bc6bf4bd3811708695139f6772f4b18a577c41a71ec", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26581256560, "estimatedRequiredGiB": 29.713, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "baguettotron_moe", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:baguettotron_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:moe", "custom_tag:mixtral", "custom_tag:reasoning", "custom_tag:synthetic-data", "custom_tag:custom_code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26586426092}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-01T19:43:04.553246+00:00", "targetGpu": "MetaX_c-500", "taskId": "5221051", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "PleIAs/Baguettotron-MoE", "modelProfile": {"architectures": ["BaguettotronMoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26581256560, "estimatedRequiredGiB": 29.713, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "baguettotron_moe", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:baguettotron_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:moe", "custom_tag:mixtral", "custom_tag:reasoning", "custom_tag:synthetic-data", "custom_tag:custom_code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26586426092}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-01T20:02:02.754254+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5221297", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-02T04:08:31.346005+00:00", "modelId": "PleIAs/Baguettotron-MoE", "modelProfile": {"architectures": ["BaguettotronMoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26581256560, "estimatedRequiredGiB": 29.713, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "baguettotron_moe", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:baguettotron_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:moe", "custom_tag:mixtral", "custom_tag:reasoning", "custom_tag:synthetic-data", "custom_tag:custom_code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26586426092}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-01T20:02:02.754254+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5221297", "taskType": "text-generation", "verifyResult": null}