state: generation 4905 (cycle)

This commit is contained in:
2026-09-10 02:25:56 +00:00
parent f8bf5b13aa
commit 4df28ae25d
9 changed files with 2166 additions and 2168 deletions

View File

@@ -1306,7 +1306,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T02:22:36.409402+00:00",
"generatedAt": "2026-09-10T02:25:56.067430+00:00",
"summary": {
"activeBlockCount": 65,
"byGpuFramework": {

View File

@@ -11,7 +11,7 @@
"1": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 349,
"listingErrors": 350,
"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": 1,
"nextAccountIndex": 2,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-10T02:22:36.385431+00:00",
"updatedAt": "2026-09-10T02:25:56.042288+00:00",
"version": 1
}

View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-09-10T02:06:23.007116+00:00",
"communityAttemptedAt": "2026-09-10T02:23:42.128088+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-09-10T02:06:23.007116+00:00",
"communityUpdatedAt": "2026-09-10T02:23:42.128088+00:00",
"frameworkAttemptedAt": "2026-09-10T00:33:23.734278+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -416,121 +416,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T02:20:21.654711+00:00",
"generatedAt": "2026-09-10T02:23:42.128088+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 904.8774193548387,
"backlogHours": 947.5540540540541,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.4426560300241276,
"queueFactor": 0.9607854746128958,
"queueWeight": 0.9607854746128958,
"recentSuccess": 52,
"recentSuccessRate": 0.33548387096774196,
"recentTerminal": 155,
"recentWilsonLowerBound": 0.26592684807262523,
"qualityFactor": 1.34992577652297,
"queueFactor": 0.9545373040686282,
"queueWeight": 0.9545373040686282,
"recentSuccess": 49,
"recentSuccessRate": 0.3310810810810811,
"recentTerminal": 148,
"recentWilsonLowerBound": 0.26037890863761337,
"running": 8,
"selectionWeight": 1.3860829585098875,
"selectionWeight": 1.2885545114149852,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 25.833333333333332,
"waiting": 23376
"throughputPerHour": 24.666666666666668,
"waiting": 23373
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1076.7450980392157,
"backlogHours": 1098.12,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.344106869011053,
"queueFactor": 0.9360476467949449,
"queueWeight": 0.9360476467949449,
"recentSuccess": 50,
"recentSuccessRate": 0.32679738562091504,
"recentTerminal": 153,
"recentWilsonLowerBound": 0.25751021482630554,
"qualityFactor": 1.3089597580366252,
"queueFactor": 0.9336541555575568,
"queueWeight": 0.9336541555575568,
"recentSuccess": 49,
"recentSuccessRate": 0.32666666666666666,
"recentTerminal": 150,
"recentWilsonLowerBound": 0.2567570339087464,
"running": 8,
"selectionWeight": 1.2581480717787172,
"selectionWeight": 1.2221157175485093,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 25.5,
"waiting": 27457
"throughputPerHour": 25.0,
"waiting": 27453
},
"Biren_166m": {
"available": true,
"backlogHours": 152.71764705882353,
"backlogHours": 158.15853658536585,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.45297253003297766,
"queueFactor": 1.2546757601291576,
"queueWeight": 1.2546757601291576,
"recentSuccess": 36,
"recentSuccessRate": 0.21176470588235294,
"recentTerminal": 170,
"recentWilsonLowerBound": 0.15706683435061758,
"qualityFactor": 0.4475661308539564,
"queueFactor": 1.2485893006015176,
"queueWeight": 1.2485893006015176,
"recentSuccess": 35,
"recentSuccessRate": 0.21341463414634146,
"recentTerminal": 164,
"recentWilsonLowerBound": 0.1576423019076134,
"running": 8,
"selectionWeight": 0.5683336534367539,
"selectionWeight": 0.5588262822958687,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 28.333333333333332,
"waiting": 4327
"throughputPerHour": 27.333333333333332,
"waiting": 4323
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1006.3571428571429,
"backlogHours": 994.4470588235295,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.5371669267689904,
"queueFactor": 0.9455882593762263,
"queueWeight": 0.9455882593762263,
"recentSuccess": 21,
"recentSuccessRate": 0.25,
"recentTerminal": 84,
"recentWilsonLowerBound": 0.16972188801500593,
"qualityFactor": 0.5816243784956235,
"queueFactor": 0.9476462635902778,
"queueWeight": 0.9476462635902778,
"recentSuccess": 22,
"recentSuccessRate": 0.25882352941176473,
"recentTerminal": 85,
"recentWilsonLowerBound": 0.1775797328865609,
"running": 7,
"selectionWeight": 0.5079387392779664,
"selectionWeight": 0.5511741690943952,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 14.0,
"waiting": 14089
"throughputPerHour": 14.166666666666666,
"waiting": 14088
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 493.177570093458,
"backlogHours": 522.1782178217823,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.8052875609722555,
"queueFactor": 1.0523601491305072,
"queueWeight": 1.0523601491305072,
"recentSuccess": 30,
"recentSuccessRate": 0.2803738317757009,
"recentTerminal": 107,
"recentWilsonLowerBound": 0.20401679054167657,
"qualityFactor": 0.7498496750465679,
"queueFactor": 1.0437841361519635,
"queueWeight": 1.0437841361519635,
"recentSuccess": 28,
"recentSuccessRate": 0.27722772277227725,
"recentTerminal": 101,
"recentWilsonLowerBound": 0.1993169020819432,
"running": 7,
"selectionWeight": 0.8474525377577052,
"selectionWeight": 0.7826811953123124,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.833333333333332,
"waiting": 8795
"throughputPerHour": 16.833333333333332,
"waiting": 8790
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 50.90391459074733,
"backlogHours": 51.10714285714286,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -540,19 +540,19 @@
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 14,
"recentSuccessRate": 0.0498220640569395,
"recentTerminal": 281,
"recentWilsonLowerBound": 0.029906503727118196,
"running": 4,
"recentSuccessRate": 0.05,
"recentTerminal": 280,
"recentWilsonLowerBound": 0.030014144576117667,
"running": 2,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 46.833333333333336,
"waiting": 2384
"throughputPerHour": 46.666666666666664,
"waiting": 2385
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 84.5111111111111,
"backlogHours": 84.19926199261992,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
@@ -561,104 +561,104 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 11,
"recentSuccessRate": 0.040740740740740744,
"recentTerminal": 270,
"recentWilsonLowerBound": 0.022898555013308324,
"running": 6,
"recentSuccess": 13,
"recentSuccessRate": 0.04797047970479705,
"recentTerminal": 271,
"recentWilsonLowerBound": 0.028245236291175896,
"running": 7,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 45.0,
"throughputPerHour": 45.166666666666664,
"waiting": 3803
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2042.2666666666667,
"backlogHours": 2042.0,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.0703781639091428,
"queueFactor": 0.8503506028782959,
"queueWeight": 0.8503506028782959,
"recentSuccess": 16,
"recentSuccessRate": 0.35555555555555557,
"qualityFactor": 0.873054532038291,
"queueFactor": 0.8506974756322486,
"queueWeight": 0.8506974756322486,
"recentSuccess": 15,
"recentSuccessRate": 0.3333333333333333,
"recentTerminal": 45,
"recentWilsonLowerBound": 0.23218891356904045,
"recentWilsonLowerBound": 0.21358692207276764,
"running": 2,
"selectionWeight": 0.9101967169879029,
"selectionWeight": 0.7427052864942683,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 7.5,
"waiting": 15317
"waiting": 15315
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 607.1214953271028,
"backlogHours": 569.6842105263158,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.2711229861075174,
"queueFactor": 1.020054908173001,
"queueWeight": 1.020054908173001,
"qualityFactor": 0.23024760231833738,
"queueFactor": 1.0302399278759444,
"queueWeight": 1.0302399278759444,
"recentSuccess": 20,
"recentSuccessRate": 0.18691588785046728,
"recentTerminal": 107,
"recentWilsonLowerBound": 0.12438379319362988,
"recentSuccessRate": 0.17543859649122806,
"recentTerminal": 114,
"recentWilsonLowerBound": 0.11653670199867362,
"running": 7,
"selectionWeight": 0.27656033269749347,
"selectionWeight": 0.23721027320605304,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.833333333333332,
"waiting": 10827
"throughputPerHour": 19.0,
"waiting": 10824
},
"MetaX_c-500": {
"available": true,
"backlogHours": 764.4269662921348,
"backlogHours": 747.2967032967033,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.6760231308790667,
"queueFactor": 0.9854043870629302,
"queueWeight": 0.9854043870629302,
"qualityFactor": 0.6296801852436067,
"queueFactor": 0.9891440542325111,
"queueWeight": 0.9891440542325111,
"recentSuccess": 24,
"recentSuccessRate": 0.2696629213483146,
"recentTerminal": 89,
"recentWilsonLowerBound": 0.18841924495236884,
"recentSuccessRate": 0.26373626373626374,
"recentTerminal": 91,
"recentWilsonLowerBound": 0.18410473382523007,
"running": 4,
"selectionWeight": 0.6661561589242498,
"selectionWeight": 0.6228444113017397,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 14.833333333333334,
"waiting": 11339
"throughputPerHour": 15.166666666666666,
"waiting": 11334
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1689.92,
"backlogHours": 1784.957746478873,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.7913142245962601,
"queueFactor": 0.8748527663367222,
"queueWeight": 0.8748527663367222,
"recentSuccess": 22,
"recentSuccessRate": 0.29333333333333333,
"recentTerminal": 75,
"recentWilsonLowerBound": 0.20239997218158162,
"qualityFactor": 0.67778395345575,
"queueFactor": 0.8680391514597264,
"queueWeight": 0.8680391514597264,
"recentSuccess": 20,
"recentSuccessRate": 0.28169014084507044,
"recentTerminal": 71,
"recentWilsonLowerBound": 0.1903694891114979,
"running": 4,
"selectionWeight": 0.6922834384296365,
"selectionWeight": 0.588343007830748,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.5,
"waiting": 21124
"throughputPerHour": 11.833333333333334,
"waiting": 21122
},
"Sunrise_pt-200-x1": {
"available": true,
@@ -668,15 +668,15 @@
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.6478599177729117,
"queueFactor": 0.7385980917507622,
"queueWeight": 0.7385980917507622,
"recentSuccess": 6,
"recentSuccessRate": 0.375,
"qualityFactor": 1.0371839405387653,
"queueFactor": 0.7388849057717721,
"queueWeight": 0.7388849057717721,
"recentSuccess": 7,
"recentSuccessRate": 0.4375,
"recentTerminal": 16,
"recentWilsonLowerBound": 0.18480982554752803,
"recentWilsonLowerBound": 0.2309836333518552,
"running": 2,
"selectionWeight": 0.4785080989888783,
"selectionWeight": 0.7663595581729808,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 2.6666666666666665,
@@ -684,52 +684,52 @@
},
"Vastai_va16": {
"available": true,
"backlogHours": 621.6774193548387,
"backlogHours": 642.4,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 1.3205537490190031,
"queueFactor": 1.0164362080305593,
"queueWeight": 1.0164362080305593,
"recentSuccess": 32,
"recentSuccessRate": 0.34408602150537637,
"recentTerminal": 93,
"recentWilsonLowerBound": 0.25544922494036565,
"qualityFactor": 1.2833091359006765,
"queueFactor": 1.0118419360661415,
"queueWeight": 1.0118419360661415,
"recentSuccess": 31,
"recentSuccessRate": 0.34444444444444444,
"recentTerminal": 90,
"recentWilsonLowerBound": 0.25445765921462965,
"running": 16,
"selectionWeight": 1.3422586451534144,
"selectionWeight": 1.2985060006411075,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 15.5,
"throughputPerHour": 15.0,
"waiting": 9636
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 444.15384615384613,
"backlogHours": 447.82758620689657,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 2.5,
"queueFactor": 1.069017653765618,
"queueWeight": 1.069017653765618,
"queueFactor": 1.068112206713098,
"queueWeight": 1.068112206713098,
"recentSuccess": 50,
"recentSuccessRate": 0.42735042735042733,
"recentTerminal": 117,
"recentWilsonLowerBound": 0.341426544774558,
"recentSuccessRate": 0.43103448275862066,
"recentTerminal": 116,
"recentWilsonLowerBound": 0.3445528576479731,
"running": 6,
"selectionWeight": 2.672544134414045,
"selectionWeight": 2.6702805167827446,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 19.5,
"waiting": 8661
"throughputPerHour": 19.333333333333332,
"waiting": 8658
}
},
"queueAttemptedAt": "2026-09-10T02:12:31.935078+00:00",
"queueAttemptedAt": "2026-09-10T02:23:42.128088+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-10T02:12:31.935078+00:00",
"queueUpdatedAt": "2026-09-10T02:23:42.128088+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": "2026-09-10T02:15:07.319652+00:00",
"lastSyncTime": "2026-09-10T02:15:07.106881+00:00",
"generatedAt": "2026-09-10T02:23:37.333475+00:00",
"lastSyncTime": "2026-09-10T02:23:37.132500+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1786,29 +1786,29 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 64,
"decisionFailureRate": 0.8767,
"decisionSuccessRate": 0.1233,
"decisionTotal": 73,
"attributableFailureCount": 65,
"decisionFailureRate": 0.8784,
"decisionSuccessRate": 0.1216,
"decisionTotal": 74,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 42,
"framework_architecture_unsupported": 43,
"memory_capacity": 1,
"model_load": 21,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 130,
"failureRate": 0.9353,
"failureCount": 131,
"failureRate": 0.9357,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.0647,
"successRate": 0.0643,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 139,
"total": 140,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2284,28 +2284,28 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 116,
"decisionFailureRate": 0.7117,
"decisionSuccessRate": 0.2883,
"decisionTotal": 163,
"attributableFailureCount": 117,
"decisionFailureRate": 0.7134,
"decisionSuccessRate": 0.2866,
"decisionTotal": 164,
"failureBreakdown": {
"ambiguous_runtime": 99,
"backend_operator": 2,
"framework_architecture_unsupported": 83,
"framework_architecture_unsupported": 84,
"memory_capacity": 5,
"model_load": 23,
"tokenizer_compatibility": 3,
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 944,
"failureCount": 945,
"failureRate": 0.9526,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 47,
"successRate": 0.0474,
"total": 991,
"total": 992,
"unresolvedFailureCount": 828
},
"vllm": {
@@ -2436,7 +2436,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T02:15:07.315789+00:00",
"generatedAt": "2026-09-10T02:23:37.327574+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2599,26 +2599,26 @@
"unresolvedFailureCount": 41
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 64,
"decisionFailureRate": 0.8767,
"decisionSuccessRate": 0.1233,
"decisionTotal": 73,
"attributableFailureCount": 65,
"decisionFailureRate": 0.8784,
"decisionSuccessRate": 0.1216,
"decisionTotal": 74,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 42,
"framework_architecture_unsupported": 43,
"memory_capacity": 1,
"model_load": 21,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 130,
"failureRate": 0.9353,
"failureCount": 131,
"failureRate": 0.9357,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.0647,
"total": 139,
"successRate": 0.0643,
"total": 140,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800": {
@@ -4246,7 +4246,7 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 15,
"consecutiveFailures": 5,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8824,
"decisionSuccessRate": 0.1176,
@@ -4260,7 +4260,7 @@
"failureRate": 0.9,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-09T20:45:50.636960+00:00",
"lastTerminalAt": "2026-09-10T02:23:37.132500+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -6765,17 +6765,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1481,
"totalRecords": 1565,
"terminalRecords": 1482,
"totalRecords": 1566,
"totals": {
"attributableFailureCount": 390,
"decisionFailureRate": 0.8904,
"decisionSuccessRate": 0.1096,
"decisionTotal": 438,
"attributableFailureCount": 391,
"decisionFailureRate": 0.8907,
"decisionSuccessRate": 0.1093,
"decisionTotal": 439,
"failureBreakdown": {
"ambiguous_runtime": 274,
"backend_operator": 25,
"framework_architecture_unsupported": 266,
"framework_architecture_unsupported": 267,
"memory_capacity": 11,
"model_load": 45,
"platform_infrastructure": 2,
@@ -6785,21 +6785,21 @@
"参数/模板问题": 94,
"验证失败": 673
},
"failureCount": 1433,
"failureCount": 1434,
"failureRate": 0.9676,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 48,
"successRate": 0.0324,
"total": 1481,
"total": 1482,
"unresolvedFailureCount": 1041
},
"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。",
@@ -6807,7 +6807,7 @@
"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。",
@@ -6828,6 +6828,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1565,
"summarizedRecords": 1566,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-10T02:23:37.132500+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:19:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4483081", "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": "2026-09-10T02:15:07.106855+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:11:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497062", "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": "2026-09-10T01:59:31.241099+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:55:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481728", "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": "2026-09-10T01:59:31.241082+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:53:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481717", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"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": "2026-09-07T05:45:22.903421+00:00", "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T05:43:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4461506", "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": "", "lastSyncTime": "2026-09-07T05:45:22.903457+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T05:33:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080310", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-07T05:31:35.012360+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T05:21:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4459779", "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": "", "lastSyncTime": "2026-09-07T05:18:43.228874+00:00", "modelId": "RedHatAI/DeepSeek-R1-Distill-Qwen-1.5B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T05:13:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080836", "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": "afb934004e5bfeea0cc6630817e205120b674efe2e918ff38c7b8ddf0de5493a",
".modelhub_state/architecture_history_backfill.json": "927265ef17e92feee3c763e59491ced3e5590d4874302b2c45b69d8253486901",
".modelhub_state/market_intelligence.json": "ec36af33a8166dc43331171c6479e3ca31b13288fd14f0dff0b40b720d721e7c",
".modelhub_state/official_capabilities.json": "ed9cc01d69deb9d2737903e7fdb7a8660187bb08a2f91da3cacaa63107fc147e",
".modelhub_state/outcome_checkpoint.json": "26093ea7d69f03e19e96f3706203148445f78056cb0020019def304c07264a9e",
".modelhub_state/architecture_compatibility_blacklist.json": "6ad12d4f975779f0e461530443b23f0465035b55bb254675355f7b6ef1ceea8c",
".modelhub_state/architecture_history_backfill.json": "7cc39ce786a7978008f9efdcada81a6539b420f36f333ec30422729fb1e0fbdb",
".modelhub_state/market_intelligence.json": "bd9ad5760ebef2362a49d37e27343cbe591e890a63a72e7c839afccf916d52e9",
".modelhub_state/official_capabilities.json": "04d75baf0700e21830029e7e3aec5fa707ae272beb792858c3b2928a4d5f63ea",
".modelhub_state/outcome_checkpoint.json": "7eb4683b4257024afbd752749d51fe365b48774a8d3ebfc3543c4ac758a411d5",
".modelhub_state/queue_cleanup_latest.json": "9a11c448074d1c105fe90e48fb81cfc27bce5e7e08d76397232f05c4c9432a32",
".modelhub_state/recent_outcomes.jsonl": "6bbb25cbd2718518c61f90fab5120d729d8808e3d87b6a816ac3518f24ec5766",
".modelhub_state/recovery_active_tasks.jsonl": "dad25eeb514e0146f8cc09e07bf00d1311900070f9ff6f0170ee71a59c3b7ed9",
".modelhub_state/recovery_intents.jsonl": "f4557c81267e8925e2d1d7eb4d8f89021b3b205c56067274fb8a315caf3d0f6f",
".modelhub_state/recent_outcomes.jsonl": "a3620ca09de4595b4e3f27987de44051b34a899cc70747449b591a6841c2dca3",
".modelhub_state/recovery_active_tasks.jsonl": "93d4ab6b3e0a10fd61e44e995add1e7dff947e1603df186f4558de3f27f0b14f",
".modelhub_state/recovery_intents.jsonl": "bde988b2163eea051650f806fc9ad257a97d0cbefdb5499fc96b995a71120743",
".modelhub_state/routing_intelligence.json": "289584603011b6a895f3ab1c0b743c174293ab94ad8d2f1f5a3531e01a72207b",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "d242179d528ce949e36ac1834a20e4f46e6d5194c7a834b19b8e1b58d9a1bea6",
"outcomes/submissions.jsonl": "357d6a5de0d21a39daee132a9bcdb79b003c924c486ab5a4a06fded4f86da82e"
},
"generation": 4904,
"generation": 4905,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T02:22:36.481353+00:00",
"updatedAt": "2026-09-10T02:25:56.713912+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}