state: generation 9445 (cycle)

This commit is contained in:
2026-09-18 20:01:26 +00:00
parent e52d9939dc
commit 65422df548
10 changed files with 2013 additions and 2016 deletions

View File

@@ -1743,7 +1743,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-18T19:58:40.016356+00:00",
"generatedAt": "2026-09-18T20:01:26.190666+00:00",
"summary": {
"activeBlockCount": 84,
"byGpuFramework": {

View File

@@ -19,7 +19,7 @@
"10": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 687,
"listingErrors": 688,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0,
"mode": "incremental_decision_only",
"nextAccountIndex": 10,
"nextAccountIndex": 11,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-18T19:58:39.991484+00:00",
"updatedAt": "2026-09-18T20:01:26.166317+00:00",
"version": 1
}

View File

@@ -416,121 +416,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-18T19:56:47.725848+00:00",
"generatedAt": "2026-09-18T19:59:47.978425+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 559.0238095238095,
"backlogHours": 552.3764705882353,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.41955425954988684,
"queueFactor": 1.041444603604236,
"queueWeight": 1.041444603604236,
"recentSuccess": 46,
"recentSuccessRate": 0.18253968253968253,
"recentTerminal": 252,
"recentWilsonLowerBound": 0.13973209561364125,
"qualityFactor": 0.3971246221340684,
"queueFactor": 1.0399104330085065,
"queueWeight": 1.0399104330085065,
"recentSuccess": 47,
"recentSuccessRate": 0.1843137254901961,
"recentTerminal": 255,
"recentWilsonLowerBound": 0.1415305076055906,
"running": 8,
"selectionWeight": 0.43694251952740065,
"selectionWeight": 0.4129740377617786,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 42.0,
"waiting": 23479
"throughputPerHour": 42.5,
"waiting": 23476
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1432.0677966101694,
"backlogHours": 1385.065573770492,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.232922098300023,
"queueFactor": 0.9043908982268876,
"queueWeight": 0.9043908982268876,
"recentSuccess": 45,
"recentSuccessRate": 0.3813559322033898,
"recentTerminal": 118,
"recentWilsonLowerBound": 0.29876863810798276,
"qualityFactor": 2.5,
"queueFactor": 0.9059634161516775,
"queueWeight": 0.9059634161516775,
"recentSuccess": 50,
"recentSuccessRate": 0.4098360655737705,
"recentTerminal": 122,
"recentWilsonLowerBound": 0.32661631886466974,
"running": 8,
"selectionWeight": 2.0194344221522242,
"selectionWeight": 2.264908540379194,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 19.666666666666668,
"waiting": 28164
"throughputPerHour": 20.333333333333332,
"waiting": 28163
},
"Biren_166m": {
"available": true,
"backlogHours": 224.23357664233578,
"backlogHours": 231.02255639097743,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.2709847322388433,
"queueFactor": 1.1943885273573824,
"queueWeight": 1.1943885273573824,
"recentSuccess": 23,
"recentSuccessRate": 0.1678832116788321,
"recentTerminal": 137,
"recentWilsonLowerBound": 0.11455228532881451,
"qualityFactor": 0.23661186605277,
"queueFactor": 1.185176558886276,
"queueWeight": 1.185176558886276,
"recentSuccess": 22,
"recentSuccessRate": 0.16541353383458646,
"recentTerminal": 133,
"recentWilsonLowerBound": 0.11184773748930618,
"running": 8,
"selectionWeight": 0.32366105527508665,
"selectionWeight": 0.2804268372000824,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.833333333333332,
"waiting": 5120
"throughputPerHour": 22.166666666666668,
"waiting": 5121
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1983.5217391304348,
"backlogHours": 1900.75,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 1.9800436964248955,
"queueFactor": 0.8612617800199777,
"queueWeight": 0.8612617800199777,
"recentSuccess": 19,
"recentSuccessRate": 0.41304347826086957,
"recentTerminal": 46,
"recentWilsonLowerBound": 0.2828839329710102,
"qualityFactor": 1.9026529512532413,
"queueFactor": 0.8639576631031007,
"queueWeight": 0.8639576631031007,
"recentSuccess": 20,
"recentSuccessRate": 0.4166666666666667,
"recentTerminal": 48,
"recentWilsonLowerBound": 0.28849459734577015,
"running": 7,
"selectionWeight": 1.7053359585002419,
"selectionWeight": 1.6438115974609682,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 7.666666666666667,
"waiting": 15207
"throughputPerHour": 8.0,
"waiting": 15206
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 527.9433962264151,
"backlogHours": 543.0291262135922,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.6060706436232427,
"queueFactor": 1.0504191132190217,
"queueWeight": 1.0504191132190217,
"recentSuccess": 25,
"recentSuccessRate": 0.2358490566037736,
"recentTerminal": 106,
"recentWilsonLowerBound": 0.16515930334184276,
"qualityFactor": 0.47584888594328273,
"queueFactor": 1.0425760456623157,
"queueWeight": 1.0425760456623157,
"recentSuccess": 23,
"recentSuccessRate": 0.22330097087378642,
"recentTerminal": 103,
"recentWilsonLowerBound": 0.1536565519868537,
"running": 7,
"selectionWeight": 0.6366281880228083,
"selectionWeight": 0.496108649839566,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.666666666666668,
"waiting": 9327
"throughputPerHour": 17.166666666666668,
"waiting": 9322
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 38.8428927680798,
"backlogHours": 39.10552763819096,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -539,108 +539,108 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 13,
"recentSuccessRate": 0.032418952618453865,
"recentTerminal": 401,
"recentWilsonLowerBound": 0.019041812514951725,
"recentSuccess": 14,
"recentSuccessRate": 0.035175879396984924,
"recentTerminal": 398,
"recentWilsonLowerBound": 0.021067003761610307,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 66.83333333333333,
"waiting": 2596
"throughputPerHour": 66.33333333333333,
"waiting": 2594
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 120.04819277108433,
"backlogHours": 120.48387096774192,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.13101238576525534,
"qualityFactor": 0.12165714887607941,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 29,
"recentSuccessRate": 0.11646586345381527,
"recentTerminal": 249,
"recentWilsonLowerBound": 0.0823255146792813,
"recentSuccessRate": 0.11693548387096774,
"recentTerminal": 248,
"recentWilsonLowerBound": 0.0826626888241384,
"running": 3,
"selectionWeight": 0.17031610149483195,
"selectionWeight": 0.15815429353890323,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 41.5,
"waiting": 4982
"throughputPerHour": 41.333333333333336,
"waiting": 4980
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2821.411764705882,
"backlogHours": 2821.235294117647,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 2.5,
"queueFactor": 0.8169222951546015,
"queueWeight": 0.8169222951546015,
"qualityFactor": 2.300700709490534,
"queueFactor": 0.8142641507203228,
"queueWeight": 0.8142641507203228,
"recentSuccess": 16,
"recentSuccessRate": 0.47058823529411764,
"recentTerminal": 34,
"recentWilsonLowerBound": 0.31451251633111366,
"running": 2,
"selectionWeight": 2.0423057378865037,
"selectionWeight": 1.8733781092749535,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 5.666666666666667,
"waiting": 15988
"waiting": 15987
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 600.2222222222222,
"backlogHours": 584.0540540540541,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.580798693767477,
"queueFactor": 1.0303953952874658,
"queueWeight": 1.0303953952874658,
"recentSuccess": 25,
"recentSuccessRate": 0.23148148148148148,
"recentTerminal": 108,
"recentWilsonLowerBound": 0.1619925471777863,
"qualityFactor": 0.45010843438995585,
"queueFactor": 1.031248321130773,
"queueWeight": 1.031248321130773,
"recentSuccess": 24,
"recentSuccessRate": 0.21621621621621623,
"recentTerminal": 111,
"recentWilsonLowerBound": 0.1498210872799431,
"running": 8,
"selectionWeight": 0.5984522996469832,
"selectionWeight": 0.46417356729144266,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.0,
"waiting": 10804
"throughputPerHour": 18.5,
"waiting": 10805
},
"MetaX_c-500": {
"available": true,
"backlogHours": 865.4430379746835,
"backlogHours": 865.367088607595,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.8410220627800471,
"queueFactor": 0.9753600123373738,
"queueWeight": 0.9753600123373738,
"qualityFactor": 0.7739760226140989,
"queueFactor": 0.972190011717225,
"queueWeight": 0.972190011717225,
"recentSuccess": 22,
"recentSuccessRate": 0.27848101265822783,
"recentTerminal": 79,
"recentWilsonLowerBound": 0.19168037554546477,
"running": 4,
"selectionWeight": 0.8202992895291503,
"selectionWeight": 0.752451758494052,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 13.166666666666666,
"waiting": 11395
"waiting": 11394
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 33.58659217877095,
"backlogHours": 33.558213716108455,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
@@ -649,87 +649,87 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 28,
"recentSuccessRate": 0.0074487895716946,
"recentTerminal": 3759,
"recentWilsonLowerBound": 0.005158637460133543,
"recentSuccess": 31,
"recentSuccessRate": 0.008240297713981925,
"recentTerminal": 3762,
"recentWilsonLowerBound": 0.0058113433957103855,
"running": 4,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 626.5,
"waiting": 21042
"throughputPerHour": 627.0,
"waiting": 21041
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 7227.2307692307695,
"backlogHours": 6710.571428571428,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.706622615329211,
"queueFactor": 0.7094224559491921,
"queueWeight": 0.7094224559491921,
"recentSuccess": 5,
"recentSuccessRate": 0.38461538461538464,
"recentTerminal": 13,
"recentWilsonLowerBound": 0.17709446581236818,
"qualityFactor": 0.9842295570167778,
"queueFactor": 0.7150185111788988,
"queueWeight": 0.7150185111788988,
"recentSuccess": 6,
"recentSuccessRate": 0.42857142857142855,
"recentTerminal": 14,
"recentWilsonLowerBound": 0.21380509930400526,
"running": 2,
"selectionWeight": 0.5012939511960901,
"selectionWeight": 0.7037423525164036,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 2.1666666666666665,
"waiting": 15659
"throughputPerHour": 2.3333333333333335,
"waiting": 15658
},
"Vastai_va16": {
"available": true,
"backlogHours": 2144.85,
"backlogHours": 2199.5384615384614,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.14963777764112227,
"queueFactor": 0.8512187492645121,
"queueWeight": 0.8512187492645121,
"qualityFactor": 0.14586850306898946,
"queueFactor": 0.8452427938725839,
"queueWeight": 0.8452427938725839,
"recentSuccess": 7,
"recentSuccessRate": 0.175,
"recentTerminal": 40,
"recentWilsonLowerBound": 0.08745302996883067,
"recentSuccessRate": 0.1794871794871795,
"recentTerminal": 39,
"recentWilsonLowerBound": 0.08977151811469994,
"running": 16,
"selectionWeight": 0.12737448192639728,
"selectionWeight": 0.12329430107204424,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 6.666666666666667,
"waiting": 14299
"throughputPerHour": 6.5,
"waiting": 14297
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 884.4242424242424,
"backlogHours": 850.0194174757281,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 0.7869800764402963,
"queueFactor": 0.9721910620793629,
"queueWeight": 0.9721910620793629,
"recentSuccess": 26,
"recentSuccessRate": 0.26262626262626265,
"recentTerminal": 99,
"recentWilsonLowerBound": 0.18598028163201125,
"qualityFactor": 0.5955011873800976,
"queueFactor": 0.9748030603248123,
"queueWeight": 0.9748030603248123,
"recentSuccess": 25,
"recentSuccessRate": 0.24271844660194175,
"recentTerminal": 103,
"recentWilsonLowerBound": 0.17014922730424603,
"running": 6,
"selectionWeight": 0.7650949963497898,
"selectionWeight": 0.5804963798851787,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 16.5,
"waiting": 14593
"throughputPerHour": 17.166666666666668,
"waiting": 14592
}
},
"queueAttemptedAt": "2026-09-18T19:47:28.014991+00:00",
"queueAttemptedAt": "2026-09-18T19:59:47.978425+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-18T19:47:28.014991+00:00",
"queueUpdatedAt": "2026-09-18T19:59:47.978425+00:00",
"supportedGpus": [
"Vastai_va16",
"Kunlunxin_p-800",

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-18T19:24:36.916552+00:00",
"lastSyncTime": "2026-09-18T19:24:36.881143+00:00",
"generatedAt": "2026-09-18T19:59:40.725193+00:00",
"lastSyncTime": "2026-09-18T19:59:40.687793+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2308,25 +2308,25 @@
},
"Iluvatar_mrv-100|vllm|text-generation": {
"attributableFailureCount": 11,
"decisionFailureRate": 0.7333,
"decisionSuccessRate": 0.2667,
"decisionTotal": 15,
"decisionFailureRate": 0.6875,
"decisionSuccessRate": 0.3125,
"decisionTotal": 16,
"failureBreakdown": {
"ambiguous_runtime": 4,
"framework_architecture_unsupported": 10,
"model_load": 1
},
"failureCount": 15,
"failureRate": 0.7895,
"failureRate": 0.75,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 4,
"successRate": 0.2105,
"successCount": 5,
"successRate": 0.25,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 19,
"total": 20,
"unresolvedFailureCount": 4
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2842,9 +2842,9 @@
},
"vllm": {
"attributableFailureCount": 415,
"decisionFailureRate": 0.8925,
"decisionSuccessRate": 0.1075,
"decisionTotal": 465,
"decisionFailureRate": 0.8906,
"decisionSuccessRate": 0.1094,
"decisionTotal": 466,
"failureBreakdown": {
"ambiguous_runtime": 244,
"backend_operator": 40,
@@ -2858,13 +2858,13 @@
"参数/模板问题": 40
},
"failureCount": 701,
"failureRate": 0.9334,
"failureRate": 0.9322,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 50,
"successRate": 0.0666,
"total": 751,
"successCount": 51,
"successRate": 0.0678,
"total": 752,
"unresolvedFailureCount": 284
},
"vllm-mlu": {
@@ -2977,7 +2977,7 @@
"unresolvedFailureCount": 18
}
},
"generatedAt": "2026-09-18T19:24:36.911249+00:00",
"generatedAt": "2026-09-18T19:59:40.719836+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 58,
@@ -3145,9 +3145,9 @@
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 120,
"decisionFailureRate": 0.8276,
"decisionSuccessRate": 0.1724,
"decisionTotal": 145,
"decisionFailureRate": 0.8219,
"decisionSuccessRate": 0.1781,
"decisionTotal": 146,
"failureBreakdown": {
"ambiguous_runtime": 28,
"framework_architecture_unsupported": 74,
@@ -3159,13 +3159,13 @@
"验证失败": 47
},
"failureCount": 199,
"failureRate": 0.8884,
"failureRate": 0.8844,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 25,
"successRate": 0.1116,
"total": 224,
"successCount": 26,
"successRate": 0.1156,
"total": 225,
"unresolvedFailureCount": 78
},
"Kunlunxin_p-800": {
@@ -5541,23 +5541,23 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.25,
"failureRate": 0.2,
"framework": "vllm",
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 3,
"successRate": 0.75,
"successCount": 4,
"successRate": 0.8,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 4,
"total": 5,
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|vllm|text-generation|rwkv7|none": {
@@ -11523,12 +11523,12 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.25,
"failureRate": 0.2,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3",
@@ -11536,11 +11536,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 3,
"successRate": 0.75,
"successCount": 4,
"successRate": 0.8,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 4,
"total": 5,
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|vllm|text-generation|rwkv7|none|32": {
@@ -14767,13 +14767,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2276,
"totalRecords": 2379,
"terminalRecords": 2277,
"totalRecords": 2380,
"totals": {
"attributableFailureCount": 738,
"decisionFailureRate": 0.833,
"decisionSuccessRate": 0.167,
"decisionTotal": 886,
"decisionFailureRate": 0.832,
"decisionSuccessRate": 0.168,
"decisionTotal": 887,
"failureBreakdown": {
"ambiguous_runtime": 573,
"backend_operator": 55,
@@ -14788,13 +14788,13 @@
"验证失败": 673
},
"failureCount": 2128,
"failureRate": 0.935,
"failureRate": 0.9346,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 11,
"successCount": 148,
"successRate": 0.065,
"total": 2276,
"successCount": 149,
"successRate": 0.0654,
"total": 2277,
"unresolvedFailureCount": 1379
},
"warnings": [
@@ -14834,6 +14834,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2379,
"summarizedRecords": 2380,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff