state: generation 5995 (cycle)

This commit is contained in:
2026-09-12 03:07:39 +00:00
parent 7b996bd9a6
commit 3a9e29aacb
9 changed files with 2993 additions and 2748 deletions

View File

@@ -1345,7 +1345,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-12T03:04:47.177679+00:00",
"generatedAt": "2026-09-12T03:07:38.738981+00:00",
"summary": {
"activeBlockCount": 68,
"byGpuFramework": {

View File

@@ -59,7 +59,7 @@
"5": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 430,
"listingErrors": 431,
"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": 5,
"nextAccountIndex": 6,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-12T03:04:47.153102+00:00",
"updatedAt": "2026-09-12T03:07:38.713398+00:00",
"version": 1
}

View File

@@ -416,121 +416,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-12T03:03:02.506868+00:00",
"generatedAt": "2026-09-12T03:05:55.166981+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 842.8383233532935,
"backlogHours": 858.0,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.2630800502588289,
"queueFactor": 1.0004019036222853,
"queueWeight": 1.0004019036222853,
"recentSuccess": 55,
"recentSuccessRate": 0.32934131736526945,
"recentTerminal": 167,
"recentWilsonLowerBound": 0.26259971750721955,
"qualityFactor": 1.296547892333578,
"queueFactor": 0.9981198441444624,
"queueWeight": 0.9981198441444624,
"recentSuccess": 54,
"recentSuccessRate": 0.32926829268292684,
"recentTerminal": 164,
"recentWilsonLowerBound": 0.26197101765012754,
"running": 8,
"selectionWeight": 1.263587686706264,
"selectionWeight": 1.2941101802218222,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 27.833333333333332,
"waiting": 23459
"throughputPerHour": 27.333333333333332,
"waiting": 23452
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 956.1279069767442,
"backlogHours": 956.0930232558139,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.8049038659569043,
"queueFactor": 0.9816547027735549,
"queueWeight": 0.9816547027735549,
"recentSuccess": 65,
"recentSuccessRate": 0.37790697674418605,
"qualityFactor": 1.790724679692297,
"queueFactor": 0.982043580199291,
"queueWeight": 0.982043580199291,
"recentSuccess": 64,
"recentSuccessRate": 0.37209302325581395,
"recentTerminal": 172,
"recentWilsonLowerBound": 0.30885834872780116,
"recentWilsonLowerBound": 0.3033882926056711,
"running": 8,
"selectionWeight": 1.7717923680707652,
"selectionWeight": 1.758569675596252,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 28.666666666666668,
"waiting": 27409
"waiting": 27408
},
"Biren_166m": {
"available": true,
"backlogHours": 175.2611464968153,
"backlogHours": 173.1320754716981,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.4882485835861238,
"queueFactor": 1.2661445891511438,
"queueWeight": 1.2661445891511438,
"recentSuccess": 36,
"recentSuccessRate": 0.22929936305732485,
"recentTerminal": 157,
"recentWilsonLowerBound": 0.17047570269344875,
"qualityFactor": 0.602661373696316,
"queueFactor": 1.2689635660549685,
"queueWeight": 1.2689635660549685,
"recentSuccess": 39,
"recentSuccessRate": 0.24528301886792453,
"recentTerminal": 159,
"recentWilsonLowerBound": 0.18493497905616552,
"running": 8,
"selectionWeight": 0.6181933022682806,
"selectionWeight": 0.7647553258892632,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 26.166666666666668,
"waiting": 4586
"throughputPerHour": 26.5,
"waiting": 4588
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1324.9846153846154,
"backlogHours": 1196.3333333333333,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.9924012858018988,
"queueFactor": 0.9347694820399115,
"queueWeight": 0.9347694820399115,
"recentSuccess": 22,
"recentSuccessRate": 0.3384615384615385,
"recentTerminal": 65,
"recentWilsonLowerBound": 0.23533338768646594,
"qualityFactor": 0.9119944777334843,
"queueFactor": 0.9495721150928375,
"queueWeight": 0.9495721150928375,
"recentSuccess": 23,
"recentSuccessRate": 0.3194444444444444,
"recentTerminal": 72,
"recentWilsonLowerBound": 0.2232545704855647,
"running": 7,
"selectionWeight": 0.9276664359047831,
"selectionWeight": 0.8660045251743723,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 10.833333333333334,
"waiting": 14354
"throughputPerHour": 12.0,
"waiting": 14356
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 478.1621621621622,
"backlogHours": 487.1009174311926,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.5036107015095216,
"queueFactor": 1.0891805306872342,
"queueWeight": 1.0891805306872342,
"recentSuccess": 27,
"recentSuccessRate": 0.24324324324324326,
"recentTerminal": 111,
"recentWilsonLowerBound": 0.17289320485810214,
"qualityFactor": 0.5968242681150694,
"queueFactor": 1.0865830878337563,
"queueWeight": 1.0865830878337563,
"recentSuccess": 28,
"recentSuccessRate": 0.25688073394495414,
"recentTerminal": 109,
"recentWilsonLowerBound": 0.18411863732206865,
"running": 7,
"selectionWeight": 0.548522971129911,
"selectionWeight": 0.6484991561425938,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.5,
"waiting": 8846
"throughputPerHour": 18.166666666666668,
"waiting": 8849
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 44.81142857142857,
"backlogHours": 46.029325513196476,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -540,196 +540,196 @@
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 13,
"recentSuccessRate": 0.037142857142857144,
"recentTerminal": 350,
"recentWilsonLowerBound": 0.02183262925617915,
"recentSuccessRate": 0.03812316715542522,
"recentTerminal": 341,
"recentWilsonLowerBound": 0.022412305300455862,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 58.333333333333336,
"waiting": 2614
"throughputPerHour": 56.833333333333336,
"waiting": 2616
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 163.72027972027973,
"backlogHours": 167.14285714285714,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.06901334255468386,
"queueFactor": 1.2791479493556799,
"queueWeight": 1.2791479493556799,
"qualityFactor": 0.07467921542830189,
"queueFactor": 1.2756825357654753,
"queueWeight": 1.2756825357654753,
"recentSuccess": 16,
"recentSuccessRate": 0.11188811188811189,
"recentTerminal": 143,
"recentWilsonLowerBound": 0.07005378612030941,
"running": 9,
"selectionWeight": 0.08827827560700494,
"recentSuccessRate": 0.11428571428571428,
"recentTerminal": 140,
"recentWilsonLowerBound": 0.0715819928363517,
"running": 12,
"selectionWeight": 0.09526697090655235,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 23.833333333333332,
"waiting": 3902
"throughputPerHour": 23.333333333333332,
"waiting": 3900
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2156.5116279069766,
"backlogHours": 2156.3720930232557,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.46947631306872245,
"queueFactor": 0.8689071681566866,
"queueWeight": 0.8689071681566866,
"recentSuccess": 12,
"recentSuccessRate": 0.27906976744186046,
"qualityFactor": 0.3762897730944125,
"queueFactor": 0.8692550609151684,
"queueWeight": 0.8692550609151684,
"recentSuccess": 11,
"recentSuccessRate": 0.2558139534883721,
"recentTerminal": 43,
"recentWilsonLowerBound": 0.16746451821827155,
"recentWilsonLowerBound": 0.14929365877065542,
"running": 2,
"selectionWeight": 0.40793133370518564,
"selectionWeight": 0.32709178963293845,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 7.166666666666667,
"waiting": 15455
"waiting": 15454
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 913.25,
"backlogHours": 939.5142857142857,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.7827143976442126,
"queueFactor": 0.9884340517095083,
"queueWeight": 0.9884340517095083,
"qualityFactor": 0.8621340665418886,
"queueFactor": 0.9846236773103609,
"queueWeight": 0.9846236773103609,
"recentSuccess": 22,
"recentSuccessRate": 0.3055555555555556,
"recentTerminal": 72,
"recentWilsonLowerBound": 0.2112648204592105,
"recentSuccessRate": 0.3142857142857143,
"recentTerminal": 70,
"recentWilsonLowerBound": 0.21762136964668136,
"running": 7,
"selectionWeight": 0.7736615633948363,
"selectionWeight": 0.8488776149330098,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.0,
"waiting": 10959
"throughputPerHour": 11.666666666666666,
"waiting": 10961
},
"MetaX_c-500": {
"available": true,
"backlogHours": 712.5,
"backlogHours": 677.1089108910892,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.7020385449795387,
"queueFactor": 1.0259316318595815,
"queueWeight": 1.0259316318595815,
"recentSuccess": 27,
"recentSuccessRate": 0.28125,
"recentTerminal": 96,
"recentWilsonLowerBound": 0.20107282637501533,
"qualityFactor": 0.710605398261568,
"queueFactor": 1.0342058830208452,
"queueWeight": 1.0342058830208452,
"recentSuccess": 28,
"recentSuccessRate": 0.27722772277227725,
"recentTerminal": 101,
"recentWilsonLowerBound": 0.1993169020819432,
"running": 4,
"selectionWeight": 0.7202435500791843,
"selectionWeight": 0.7349122833884842,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 16.0,
"waiting": 11400
"throughputPerHour": 16.833333333333332,
"waiting": 11398
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 2015.2380952380952,
"backlogHours": 1953.230769230769,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 1.5160212398372566,
"queueFactor": 0.877783061381474,
"queueWeight": 0.877783061381474,
"qualityFactor": 1.4536250179500438,
"queueFactor": 0.882252199440633,
"queueWeight": 0.882252199440633,
"recentSuccess": 25,
"recentSuccessRate": 0.3968253968253968,
"recentTerminal": 63,
"recentWilsonLowerBound": 0.285317281473093,
"recentSuccessRate": 0.38461538461538464,
"recentTerminal": 65,
"recentWilsonLowerBound": 0.27594829385374525,
"running": 4,
"selectionWeight": 1.330737765023685,
"selectionWeight": 1.2824638692483559,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 10.5,
"throughputPerHour": 10.833333333333334,
"waiting": 21160
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 3734.086956521739,
"backlogHours": 3578.75,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.1978247440531085,
"queueFactor": 0.8002183140306344,
"queueWeight": 0.8002183140306344,
"recentSuccess": 10,
"recentSuccessRate": 0.43478260869565216,
"recentTerminal": 23,
"recentWilsonLowerBound": 0.25634368332198654,
"qualityFactor": 0.8104509765165948,
"queueFactor": 0.8056493835625976,
"queueWeight": 0.8056493835625976,
"recentSuccess": 9,
"recentSuccessRate": 0.375,
"recentTerminal": 24,
"recentWilsonLowerBound": 0.21159133433631455,
"running": 2,
"selectionWeight": 0.9585212971903546,
"selectionWeight": 0.6529393296382999,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 3.8333333333333335,
"waiting": 14314
"throughputPerHour": 4.0,
"waiting": 14315
},
"Vastai_va16": {
"available": true,
"backlogHours": 847.36,
"backlogHours": 836.6052631578948,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 2.5,
"queueFactor": 0.9995993309443174,
"queueWeight": 0.9995993309443174,
"queueFactor": 1.0019076540998941,
"queueWeight": 1.0019076540998941,
"recentSuccess": 35,
"recentSuccessRate": 0.4666666666666667,
"recentTerminal": 75,
"recentWilsonLowerBound": 0.35815509458811656,
"recentSuccessRate": 0.4605263157894737,
"recentTerminal": 76,
"recentWilsonLowerBound": 0.3530754655326989,
"running": 16,
"selectionWeight": 2.4989983273607934,
"selectionWeight": 2.5047691352497354,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.5,
"waiting": 10592
"throughputPerHour": 12.666666666666666,
"waiting": 10597
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 585.9101123595506,
"backlogHours": 599.3793103448276,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 1.8007208043622212,
"queueFactor": 1.0564805392076402,
"queueWeight": 1.0564805392076402,
"recentSuccess": 36,
"recentSuccessRate": 0.4044943820224719,
"recentTerminal": 89,
"recentWilsonLowerBound": 0.30853277331729134,
"qualityFactor": 1.8183462874237035,
"queueFactor": 1.0532962091212077,
"queueWeight": 1.0532962091212077,
"recentSuccess": 35,
"recentSuccessRate": 0.40229885057471265,
"recentTerminal": 87,
"recentWilsonLowerBound": 0.3055065555931764,
"running": 6,
"selectionWeight": 1.9024264863550149,
"selectionWeight": 1.9152572514130088,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 14.833333333333334,
"throughputPerHour": 14.5,
"waiting": 8691
}
},
"queueAttemptedAt": "2026-09-12T02:54:17.744485+00:00",
"queueAttemptedAt": "2026-09-12T03:05:55.166981+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-12T02:54:17.744485+00:00",
"queueUpdatedAt": "2026-09-12T03:05:55.166981+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": "2026-09-12T02:56:54.666019+00:00",
"lastSyncTime": "2026-09-12T02:56:54.384007+00:00",
"generatedAt": "2026-09-12T03:05:48.188591+00:00",
"lastSyncTime": "2026-09-12T03:05:47.937930+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1800,18 +1800,18 @@
"unresolvedFailureCount": 4
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 17,
"attributableFailureCount": 18,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 17,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 2,
"framework_architecture_unsupported": 9,
"model_load": 4,
"model_load": 5,
"runtime_memory": 2
},
"failureCount": 24,
"failureCount": 25,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1821,7 +1821,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 24,
"total": 25,
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
@@ -2125,18 +2125,18 @@
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 3,
"attributableFailureCount": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 2,
"tokenizer_compatibility": 3,
"参数/模板问题": 2
},
"failureCount": 7,
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2146,7 +2146,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 7,
"total": 8,
"unresolvedFailureCount": 3
},
"Vastai_va16|unknown|text-generation": {
@@ -2375,30 +2375,30 @@
"unresolvedFailureCount": 862
},
"vllm": {
"attributableFailureCount": 248,
"decisionFailureRate": 0.988,
"decisionSuccessRate": 0.012,
"decisionTotal": 251,
"attributableFailureCount": 250,
"decisionFailureRate": 0.9881,
"decisionSuccessRate": 0.0119,
"decisionTotal": 253,
"failureBreakdown": {
"ambiguous_runtime": 195,
"backend_operator": 33,
"framework_architecture_unsupported": 173,
"memory_capacity": 6,
"model_load": 20,
"model_load": 21,
"platform_infrastructure": 1,
"repository_structure": 5,
"runtime_memory": 6,
"tokenizer_compatibility": 5,
"tokenizer_compatibility": 6,
"参数/模板问题": 24
},
"failureCount": 468,
"failureRate": 0.9936,
"failureCount": 470,
"failureRate": 0.9937,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0064,
"total": 471,
"successRate": 0.0063,
"total": 473,
"unresolvedFailureCount": 219
},
"vllm-mlu": {
@@ -2502,7 +2502,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T02:56:54.660525+00:00",
"generatedAt": "2026-09-12T03:05:48.184736+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2641,27 +2641,27 @@
"unresolvedFailureCount": 27
},
"Iluvatar_bi-150": {
"attributableFailureCount": 22,
"decisionFailureRate": 0.7333,
"decisionSuccessRate": 0.2667,
"decisionTotal": 30,
"attributableFailureCount": 23,
"decisionFailureRate": 0.7419,
"decisionSuccessRate": 0.2581,
"decisionTotal": 31,
"failureBreakdown": {
"ambiguous_runtime": 12,
"backend_operator": 5,
"framework_architecture_unsupported": 10,
"model_load": 5,
"model_load": 6,
"runtime_memory": 2,
"参数/模板问题": 2,
"验证失败": 30
},
"failureCount": 66,
"failureRate": 0.8919,
"failureCount": 67,
"failureRate": 0.8933,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 8,
"successRate": 0.1081,
"total": 74,
"successRate": 0.1067,
"total": 75,
"unresolvedFailureCount": 44
},
"Iluvatar_mrv-100": {
@@ -2760,26 +2760,26 @@
"unresolvedFailureCount": 77
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 45,
"decisionFailureRate": 0.9783,
"decisionSuccessRate": 0.0217,
"decisionTotal": 46,
"attributableFailureCount": 46,
"decisionFailureRate": 0.9787,
"decisionSuccessRate": 0.0213,
"decisionTotal": 47,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 5,
"platform_infrastructure": 3,
"tokenizer_compatibility": 40,
"tokenizer_compatibility": 41,
"参数/模板问题": 9,
"验证失败": 32
},
"failureCount": 90,
"failureRate": 0.989,
"failureCount": 91,
"failureRate": 0.9891,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 1,
"successRate": 0.011,
"total": 91,
"successRate": 0.0109,
"total": 92,
"unresolvedFailureCount": 42
},
"Vastai_va16": {
@@ -4387,23 +4387,23 @@
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 2,
"backend_operator": 1,
"framework_architecture_unsupported": 2,
"model_load": 1
"model_load": 2
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T02:30:20.417896+00:00",
"lastTerminalAt": "2026-09-12T03:05:47.937930+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4411,7 +4411,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 6,
"total": 7,
"unresolvedFailureCount": 2
},
"Iluvatar_mrv-100|unknown|text-generation": {
@@ -4593,18 +4593,18 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 17,
"consecutiveFailures": 17,
"attributableFailureCount": 15,
"consecutiveFailures": 15,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 17,
"decisionTotal": 15,
"failureBreakdown": {
"framework_architecture_unsupported": 2,
"platform_infrastructure": 2,
"tokenizer_compatibility": 15
"tokenizer_compatibility": 13
},
"failureCount": 19,
"failureCount": 17,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-10T11:01:21+00:00",
@@ -4616,26 +4616,26 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 19,
"total": 17,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 1
"tokenizer_compatibility": 2
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": "2026-09-09T17:17:21+00:00",
"lastTerminalAt": "2026-09-11T11:19:08.306651+00:00",
"lastTerminalAt": "2026-09-12T03:05:47.937901+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -4643,7 +4643,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 3,
"total": 4,
"unresolvedFailureCount": 1
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
@@ -7187,40 +7187,41 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1680,
"totalRecords": 1767,
"terminalRecords": 1682,
"totalRecords": 1769,
"totals": {
"attributableFailureCount": 452,
"decisionFailureRate": 0.8898,
"decisionSuccessRate": 0.1102,
"decisionTotal": 508,
"attributableFailureCount": 454,
"decisionFailureRate": 0.8902,
"decisionSuccessRate": 0.1098,
"decisionTotal": 510,
"failureBreakdown": {
"ambiguous_runtime": 394,
"backend_operator": 40,
"framework_architecture_unsupported": 280,
"memory_capacity": 11,
"model_load": 64,
"model_load": 65,
"platform_infrastructure": 4,
"repository_structure": 5,
"runtime_memory": 6,
"tokenizer_compatibility": 46,
"tokenizer_compatibility": 47,
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1624,
"failureCount": 1626,
"failureRate": 0.9667,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 56,
"successRate": 0.0333,
"total": 1680,
"total": 1682,
"unresolvedFailureCount": 1168
},
"warnings": [
"GPU Ascend_910-b3 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 Mthreads_s4000 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 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 Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
@@ -7229,7 +7230,6 @@
"GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-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 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 hygon_k100-ai|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 Ascend_910-b4|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7251,6 +7251,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1767,
"summarizedRecords": 1769,
"version": 1
}

View File

@@ -1,3 +1,5 @@
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T03:05:47.937930+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-Apollo-V0.1-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T03:05:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4080040", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T03:05:47.937901+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:57:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4578245", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T02:56:54.384007+00:00", "modelId": "amd/Qwen2.5-7B-Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:53:23+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079108", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T02:56:54.383989+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:51:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4134178", "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": "2026-09-12T02:48:11.158114+00:00", "modelId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:43:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458009", "taskType": "text-generation", "verifyResult": -1}
@@ -296,5 +298,3 @@
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T13:51:23.322046+00:00", "modelId": "amd/Qwen2.5_3B_Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T13:27:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080032", "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": "2026-09-08T13:16:14.206250+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T12:59:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4133902", "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": "2026-09-08T13:16:14.206275+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T12:57:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4107036", "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": "2026-09-08T12:42:19.103212+00:00", "modelId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T12:21:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4133653", "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": "2026-09-08T12:42:19.103221+00:00", "modelId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T12:19:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4107014", "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": "fef5f8e85141be528ff5282970e2c8ad2113ebe4b8dda3c0d17074cee4d6a22f",
".modelhub_state/architecture_history_backfill.json": "42677c736a4333c0e444e5f30463ebba472d2cbf9971dbcceccd89c126ebbcfe",
".modelhub_state/market_intelligence.json": "546f04cb941e828e4c06064af406988606872df2f81c1835523d5c42ff487710",
".modelhub_state/official_capabilities.json": "9065c6a1480255779e70417f1dd9ae1b1712c5d23e29ccef7dba47f9e986d1b7",
".modelhub_state/outcome_checkpoint.json": "de8419898d771b485c1aeaedd1aa952b409d96ddd876a51daf2d8e645433c46f",
".modelhub_state/architecture_compatibility_blacklist.json": "f2cb48a2f441ea1bdecccff71b9547e92590900f87c8c9402c6c12f9904f57bb",
".modelhub_state/architecture_history_backfill.json": "11aeba87766e74b6622c6c2c1bed2dd52d20c3c3044d8289d9246d1ebe787818",
".modelhub_state/market_intelligence.json": "d735e6a806c5404e04868dad4147f0475c5db7430eed142736ae0224d6a13bb8",
".modelhub_state/official_capabilities.json": "cfc06a47a9965ba84507290c691161d058a31437c563f0da6e97ed1e0bfb954b",
".modelhub_state/outcome_checkpoint.json": "395388841904280539aae77f43ae8066d9adb03f9b1586a0a8fbee34fd61e672",
".modelhub_state/queue_cleanup_latest.json": "dbff8ecbdcba815a2302661742ce4689464c0250a7ef3678d448f0d7a5dc07da",
".modelhub_state/recent_outcomes.jsonl": "fea2c8180e648ab702cfb751b88efcae2b55820fdeb03576bab6e5108dbdc0a3",
".modelhub_state/recovery_active_tasks.jsonl": "dd85494be676f6117957f3ec4e84bf7b558df9553e5945549601a22113cef06b",
".modelhub_state/recovery_intents.jsonl": "cebd8ca56df5eb250c64975557e8591f5e20a5e8483360ade4410f572a5434e9",
".modelhub_state/recent_outcomes.jsonl": "990a39a1e8c54909aad06c81c05ba391c06836f39441ef09339da1eee45a8004",
".modelhub_state/recovery_active_tasks.jsonl": "b5a88cebbb709687f29ea96cc45e984a4ceca733c43519548d555f41eb5a106e",
".modelhub_state/recovery_intents.jsonl": "81c7b9f0ea1be83275cbb33ab367ea7891241ccfe27d2a6922e68fe7100e0221",
".modelhub_state/routing_intelligence.json": "316b7d02e32cf2dd3f7c0ca452f58d571a371863ac4d1c1b5193456035ce3a53",
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
"ledger/submissions.jsonl": "8abcf838f382e71b9140db2901b93972a33b043c4c67a56473d00af9ccd9be3c",
"outcomes/submissions.jsonl": "89e4ed1669c9c8d079363347a986e7e020d5688c4a0a5b51c8c2e756ca106cb7"
},
"generation": 5994,
"generation": 5995,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-12T03:04:47.296322+00:00",
"updatedAt": "2026-09-12T03:07:39.346095+00:00",
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
}