state: generation 5140 (cycle)

This commit is contained in:
2026-09-10 11:33:42 +00:00
parent fe0ec050fa
commit 930f956fb1
9 changed files with 2803 additions and 3075 deletions

View File

@@ -1313,7 +1313,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T11:30:54.533223+00:00",
"generatedAt": "2026-09-10T11:33:41.933504+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -51,7 +51,7 @@
"4": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 365,
"listingErrors": 366,
"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": 4,
"nextAccountIndex": 5,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-10T11:30:54.505370+00:00",
"updatedAt": "2026-09-10T11:33:41.908860+00:00",
"version": 1
}

View File

@@ -416,29 +416,29 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T11:29:26.246849+00:00",
"generatedAt": "2026-09-10T11:32:01.411784+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 1017.8260869565217,
"backlogHours": 1040.1777777777777,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.3189826023637914,
"queueFactor": 0.9535979537062149,
"queueWeight": 0.9535979537062149,
"recentSuccess": 60,
"recentSuccessRate": 0.43478260869565216,
"recentTerminal": 138,
"recentWilsonLowerBound": 0.3549471151477231,
"qualityFactor": 1.3267203777502505,
"queueFactor": 0.9563537035670682,
"queueWeight": 0.9563537035670682,
"recentSuccess": 58,
"recentSuccessRate": 0.42962962962962964,
"recentTerminal": 135,
"recentWilsonLowerBound": 0.34921160149343466,
"running": 8,
"selectionWeight": 1.2577791105882097,
"selectionWeight": 1.2688139468593518,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 23.0,
"waiting": 23410
"throughputPerHour": 22.5,
"waiting": 23404
},
"Ascend_910-b4": {
"available": true,
@@ -448,15 +448,15 @@
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.7053867327734414,
"queueFactor": 0.9527818712389303,
"queueWeight": 0.9527818712389303,
"recentSuccess": 54,
"recentSuccessRate": 0.33540372670807456,
"qualityFactor": 0.8069852217282076,
"queueFactor": 0.9586538434541438,
"queueWeight": 0.9586538434541438,
"recentSuccess": 56,
"recentSuccessRate": 0.34782608695652173,
"recentTerminal": 161,
"recentWilsonLowerBound": 0.2670624578471647,
"recentWilsonLowerBound": 0.2785774885418679,
"running": 8,
"selectionWeight": 0.6720796911989948,
"selectionWeight": 0.7736194844204407,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 26.833333333333332,
@@ -464,73 +464,73 @@
},
"Biren_166m": {
"available": true,
"backlogHours": 127.4,
"backlogHours": 124.32558139534883,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.22836043043647755,
"qualityFactor": 0.2529414157116665,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 44,
"recentSuccessRate": 0.20952380952380953,
"recentTerminal": 210,
"recentWilsonLowerBound": 0.15994606256192054,
"recentSuccess": 46,
"recentSuccessRate": 0.21395348837209302,
"recentTerminal": 215,
"recentWilsonLowerBound": 0.1644088815320551,
"running": 8,
"selectionWeight": 0.2968685595674208,
"selectionWeight": 0.3288238404251665,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 35.0,
"waiting": 4459
"throughputPerHour": 35.833333333333336,
"waiting": 4455
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 933.4285714285714,
"backlogHours": 965.3863636363636,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.10268776997877094,
"queueFactor": 0.9660601850774305,
"queueWeight": 0.9660601850774305,
"recentSuccess": 16,
"recentSuccessRate": 0.17582417582417584,
"recentTerminal": 91,
"recentWilsonLowerBound": 0.11122434523601707,
"qualityFactor": 0.09652144457198598,
"queueFactor": 0.967118087513467,
"queueWeight": 0.967118087513467,
"recentSuccess": 15,
"recentSuccessRate": 0.17045454545454544,
"recentTerminal": 88,
"recentWilsonLowerBound": 0.10610728809302103,
"running": 7,
"selectionWeight": 0.09920256607088007,
"selectionWeight": 0.09334763487849619,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 15.166666666666666,
"waiting": 14157
"throughputPerHour": 14.666666666666666,
"waiting": 14159
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 477.94594594594594,
"backlogHours": 477.72972972972974,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.32776926649696336,
"queueFactor": 1.0680941336792078,
"queueWeight": 1.0680941336792078,
"qualityFactor": 0.3417224678256897,
"queueFactor": 1.074749716989011,
"queueWeight": 1.074749716989011,
"recentSuccess": 29,
"recentSuccessRate": 0.26126126126126126,
"recentTerminal": 111,
"recentWilsonLowerBound": 0.18850083133789378,
"running": 7,
"selectionWeight": 0.3500884307457435,
"selectionWeight": 0.36726612558444643,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.5,
"waiting": 8842
"waiting": 8838
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 44.41121495327103,
"backlogHours": 44.27329192546584,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -539,197 +539,197 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 22,
"recentSuccessRate": 0.06853582554517133,
"recentTerminal": 321,
"recentWilsonLowerBound": 0.04569203880697953,
"recentSuccess": 23,
"recentSuccessRate": 0.07142857142857142,
"recentTerminal": 322,
"recentWilsonLowerBound": 0.04806469293065581,
"running": 7,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 53.5,
"throughputPerHour": 53.666666666666664,
"waiting": 2376
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 70.88544891640866,
"backlogHours": 70.81114551083591,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.1083125120844518,
"qualityFactor": 0.11292339675855975,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 48,
"recentSuccessRate": 0.14860681114551083,
"recentTerminal": 323,
"recentWilsonLowerBound": 0.11395334754966704,
"running": 2,
"selectionWeight": 0.14080626570978735,
"running": 5,
"selectionWeight": 0.14680041578612768,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 53.833333333333336,
"waiting": 3816
"waiting": 3812
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2018.7391304347825,
"backlogHours": 1895.0204081632655,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.09334523877672281,
"queueFactor": 0.8605068204197565,
"queueWeight": 0.8605068204197565,
"recentSuccess": 9,
"recentSuccessRate": 0.1956521739130435,
"recentTerminal": 46,
"recentWilsonLowerBound": 0.106504904441218,
"qualityFactor": 0.11481542033414766,
"queueFactor": 0.8740627173383672,
"queueWeight": 0.8740627173383672,
"recentSuccess": 10,
"recentSuccessRate": 0.20408163265306123,
"recentTerminal": 49,
"recentWilsonLowerBound": 0.11481727042813812,
"running": 2,
"selectionWeight": 0.0803242146210807,
"selectionWeight": 0.10035587828961191,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 7.666666666666667,
"waiting": 15477
"throughputPerHour": 8.166666666666666,
"waiting": 15476
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 645.7425742574258,
"backlogHours": 645.4455445544555,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.19387470966681433,
"queueFactor": 1.0209569597235155,
"queueWeight": 1.0209569597235155,
"recentSuccess": 22,
"recentSuccessRate": 0.21782178217821782,
"qualityFactor": 0.17818766195037006,
"queueFactor": 1.0273199895070035,
"queueWeight": 1.0273199895070035,
"recentSuccess": 21,
"recentSuccessRate": 0.2079207920792079,
"recentTerminal": 101,
"recentWilsonLowerBound": 0.14847574440775013,
"recentWilsonLowerBound": 0.14020699355070068,
"running": 7,
"selectionWeight": 0.19793773414871002,
"selectionWeight": 0.18305574700513166,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 16.833333333333332,
"waiting": 10870
"waiting": 10865
},
"MetaX_c-500": {
"available": true,
"backlogHours": 519.8636363636364,
"backlogHours": 527.8615384615384,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.3104611669050365,
"queueFactor": 1.0547096779023915,
"queueWeight": 1.0547096779023915,
"recentSuccess": 33,
"recentSuccessRate": 0.25,
"recentTerminal": 132,
"recentWilsonLowerBound": 0.183909324834889,
"running": 4,
"selectionWeight": 0.32744639734761166,
"qualityFactor": 0.30909918551193244,
"queueFactor": 1.0587823107804475,
"queueWeight": 1.0587823107804475,
"recentSuccess": 32,
"recentSuccessRate": 0.24615384615384617,
"recentTerminal": 130,
"recentWilsonLowerBound": 0.18009686195009067,
"running": 2,
"selectionWeight": 0.32726874989667804,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.0,
"throughputPerHour": 21.666666666666668,
"waiting": 11437
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1645.5384615384614,
"backlogHours": 1645.076923076923,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.7399558226605701,
"queueFactor": 0.8872993052506386,
"queueWeight": 0.8872993052506386,
"recentSuccess": 29,
"recentSuccessRate": 0.3717948717948718,
"qualityFactor": 0.701865755246633,
"queueFactor": 0.8928052763606835,
"queueWeight": 0.8928052763606835,
"recentSuccess": 28,
"recentSuccessRate": 0.358974358974359,
"recentTerminal": 78,
"recentWilsonLowerBound": 0.2729339852422717,
"recentWilsonLowerBound": 0.26145402020689096,
"running": 4,
"selectionWeight": 0.6565622873628886,
"selectionWeight": 0.62662944958107,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 13.0,
"waiting": 21392
"waiting": 21386
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 5295.75,
"backlogHours": 5295.0,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.3138153341939451,
"queueFactor": 0.7446071906608079,
"queueWeight": 0.7446071906608079,
"qualityFactor": 0.32717451391462876,
"queueFactor": 0.7492121040342101,
"queueWeight": 0.7492121040342101,
"recentSuccess": 6,
"recentSuccessRate": 0.375,
"recentTerminal": 16,
"recentWilsonLowerBound": 0.18480982554752803,
"running": 2,
"selectionWeight": 0.23366915438043603,
"selectionWeight": 0.24512310595634898,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 2.6666666666666665,
"waiting": 14122
"waiting": 14120
},
"Vastai_va16": {
"available": true,
"backlogHours": 837.25,
"backlogHours": 899.5522388059702,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.3243386512516571,
"queueFactor": 0.9819470588854432,
"queueWeight": 0.9819470588854432,
"recentSuccess": 20,
"recentSuccessRate": 0.2777777777777778,
"recentTerminal": 72,
"recentWilsonLowerBound": 0.18760146005322942,
"qualityFactor": 0.3465287930494029,
"queueFactor": 0.9774188749403991,
"queueWeight": 0.9774188749403991,
"recentSuccess": 19,
"recentSuccessRate": 0.2835820895522388,
"recentTerminal": 67,
"recentWilsonLowerBound": 0.18970136157200854,
"running": 16,
"selectionWeight": 0.31848338467943615,
"selectionWeight": 0.33870378303680176,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.0,
"waiting": 10047
"throughputPerHour": 11.166666666666666,
"waiting": 10045
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 469.02702702702703,
"backlogHours": 468.97297297297297,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 2.5,
"queueFactor": 1.071116394707061,
"queueWeight": 1.071116394707061,
"recentSuccess": 63,
"recentSuccessRate": 0.5675675675675675,
"queueFactor": 1.0777362916281936,
"queueWeight": 1.0777362916281936,
"recentSuccess": 62,
"recentSuccessRate": 0.5585585585585585,
"recentTerminal": 111,
"recentWilsonLowerBound": 0.47466952682168206,
"recentWilsonLowerBound": 0.46575944163399,
"running": 6,
"selectionWeight": 2.6777909867676524,
"selectionWeight": 2.694340729070484,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.5,
"waiting": 8677
"waiting": 8676
}
},
"queueAttemptedAt": "2026-09-10T11:20:29.292294+00:00",
"queueAttemptedAt": "2026-09-10T11:32:01.411784+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-10T11:20:29.292294+00:00",
"queueUpdatedAt": "2026-09-10T11:32:01.411784+00:00",
"supportedGpus": [
"Vastai_va16",
"Iluvatar_mrv-100",

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T11:23:42.435318+00:00",
"lastSyncTime": "2026-09-10T11:23:42.203053+00:00",
"generatedAt": "2026-09-10T11:31:55.552238+00:00",
"lastSyncTime": "2026-09-10T11:31:55.305639+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1474,13 +1474,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 37,
"failureBreakdown": {
"ambiguous_runtime": 30,
"ambiguous_runtime": 31,
"framework_architecture_unsupported": 33,
"memory_capacity": 1,
"repository_structure": 1,
"tokenizer_compatibility": 2
},
"failureCount": 67,
"failureCount": 68,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1490,8 +1490,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 67,
"unresolvedFailureCount": 30
"total": 68,
"unresolvedFailureCount": 31
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 24,
@@ -2321,7 +2321,7 @@
"decisionSuccessRate": 0.0042,
"decisionTotal": 236,
"failureBreakdown": {
"ambiguous_runtime": 162,
"ambiguous_runtime": 163,
"backend_operator": 29,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2332,15 +2332,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 419,
"failureCount": 420,
"failureRate": 0.9976,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 1,
"successRate": 0.0024,
"total": 420,
"unresolvedFailureCount": 183
"total": 421,
"unresolvedFailureCount": 184
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T11:23:42.431392+00:00",
"generatedAt": "2026-09-10T11:31:55.546929+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2474,7 +2474,7 @@
"decisionSuccessRate": 0.05,
"decisionTotal": 40,
"failureBreakdown": {
"ambiguous_runtime": 31,
"ambiguous_runtime": 32,
"framework_architecture_unsupported": 33,
"memory_capacity": 1,
"model_load": 1,
@@ -2483,15 +2483,15 @@
"参数/模板问题": 11,
"验证失败": 175
},
"failureCount": 255,
"failureCount": 256,
"failureRate": 0.9922,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0078,
"total": 257,
"unresolvedFailureCount": 217
"total": 258,
"unresolvedFailureCount": 218
},
"Biren_166m": {
"attributableFailureCount": 25,
@@ -4034,21 +4034,21 @@
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 15,
"framework_architecture_unsupported": 5
"ambiguous_runtime": 16,
"framework_architecture_unsupported": 4
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T10:30:02.547307+00:00",
"lastTerminalAt": "2026-09-10T11:31:55.305639+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4057,7 +4057,7 @@
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 15
"unresolvedFailureCount": 16
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 6,
@@ -4502,29 +4502,6 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|unknown|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-07T22:32:11.428244+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -7025,15 +7002,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1564,
"totalRecords": 1651,
"terminalRecords": 1565,
"totalRecords": 1652,
"totals": {
"attributableFailureCount": 409,
"decisionFailureRate": 0.8891,
"decisionSuccessRate": 0.1109,
"decisionTotal": 460,
"failureBreakdown": {
"ambiguous_runtime": 333,
"ambiguous_runtime": 334,
"backend_operator": 34,
"framework_architecture_unsupported": 271,
"memory_capacity": 11,
@@ -7045,21 +7022,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1513,
"failureCount": 1514,
"failureRate": 0.9674,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 51,
"successRate": 0.0326,
"total": 1564,
"unresolvedFailureCount": 1101
"total": 1565,
"unresolvedFailureCount": 1102
},
"warnings": [
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_mrv-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 Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高≥50%),建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
@@ -7067,7 +7044,7 @@
"GPU hygon_k100-ai 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Biren_166m|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7088,6 +7065,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1651,
"summarizedRecords": 1652,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T11:31:55.305639+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:25:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471913", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T11:14:50.402520+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:09:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4134179", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T11:06:41.315652+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:05:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4134097", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T11:06:41.315686+00:00", "modelId": "nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:01:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457998", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "", "lastSyncTime": "2026-09-07T23:07:55.698411+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T23:07:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4271662", "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", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-07T22:59:07.700197+00:00", "modelId": "nightmedia/Qwen3-4B-Element8-Eva-Heretic-mxfp4-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T22:57:21+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4080072", "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": "", "lastSyncTime": "2026-09-07T22:32:11.428265+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T22:31:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4483787", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-07T22:32:11.428244+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-07T22:25:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4482076", "taskType": "text-generation", "verifyResult": 1}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "e5dbf80b48e7abf383d00721bb031470ae9994eecb3ece5eb1263af92d23d0a4",
".modelhub_state/architecture_history_backfill.json": "7c484f44602fee10ecfa428baa530da78b957af87a09a27add2517c4d159b268",
".modelhub_state/market_intelligence.json": "f07f582efe22077d78b77571f289a95e0087d4368997229a5aecea3770e367f8",
".modelhub_state/official_capabilities.json": "698a921a9239f2dba53559756b93ec8f1ad1de5b843b90cdf719ecf2f70018ac",
".modelhub_state/outcome_checkpoint.json": "8f998d743050b4edd4555160c71c243bbbbf9c0fb85671e1e13fecec16ac1697",
".modelhub_state/architecture_compatibility_blacklist.json": "f7f056717bf68fbc93f976abd4f624da1734b840f9dbde79e4107efcf2cf52af",
".modelhub_state/architecture_history_backfill.json": "6f145c43af606874baaf0af68b0ee8f3fcbcff2cafa2bce43ad182f12c0bf94e",
".modelhub_state/market_intelligence.json": "1e3a90f228795276dd7fddcd052118c37c0ec7dd818ccb08ff2e4fa80c988019",
".modelhub_state/official_capabilities.json": "22f3da9460abf3718ce5e330cc8737650e7890826c506e627f26dabefbcbcdd6",
".modelhub_state/outcome_checkpoint.json": "33a7744fb500a51a0c8f346c2049cbc0df1746e93433ffcfe06e10e16cc0c274",
".modelhub_state/queue_cleanup_latest.json": "b9038630dc67feced29c6931cb43d6d94c28bb175e6dcf80fac9c625a52887d5",
".modelhub_state/recent_outcomes.jsonl": "115b0135e6ba77dd24cf8e1f868c9f8e46be0a9da78839bccb3a188ffb6606a9",
".modelhub_state/recovery_active_tasks.jsonl": "552b108e8fe81dea8ac6768e47a5ad1bbd8a73b8c1ac09dc7bc71e52970dbe9e",
".modelhub_state/recovery_intents.jsonl": "492a7da07934d5eb6f1a6520a7d0fe8664a4a678435cdc3a3af92c2ceadc8cdc",
".modelhub_state/recent_outcomes.jsonl": "2cb2e7472b0438479ea47741a777fc7df816050bf4a9a7ffc011c3936b86388a",
".modelhub_state/recovery_active_tasks.jsonl": "c51700b33973a26163e0510b5d2f13ffa937c5e0dee9a8da4fb8a9e5479f7d19",
".modelhub_state/recovery_intents.jsonl": "1d6f497100c32d3e4ba565f5124bbc4f0bd2d980ce902428ed2a0979e92d5dcd",
".modelhub_state/routing_intelligence.json": "f36cfaf9f9ff191164b0ce0a73a3ce4bbc3a2dc4589f252d583e33b427807fc0",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "8a621da5637d481c7de4b4e3375f2a68cbdabf71fe459244a727034f36ab3eb9",
"outcomes/submissions.jsonl": "eaa6922265ab874d46282c8353419da53665ddca2baca53c5b4240e410666d50"
},
"generation": 5139,
"generation": 5140,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T11:30:54.673784+00:00",
"updatedAt": "2026-09-10T11:33:42.695618+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}