state: generation 4958 (cycle)

This commit is contained in:
2026-09-10 04:56:16 +00:00
parent 6b0ea4aa55
commit aea334157d
9 changed files with 2969 additions and 2858 deletions

View File

@@ -1325,7 +1325,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T04:53:15.462227+00:00",
"generatedAt": "2026-09-10T04:56:15.809722+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -51,7 +51,7 @@
"4": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 353,
"listingErrors": 354,
"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": "2026-09-10T04:53:15.437893+00:00",
"updatedAt": "2026-09-10T04:56:15.781966+00:00",
"version": 1
}

View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-09-10T04:37:22.697573+00:00",
"communityAttemptedAt": "2026-09-10T04:54:24.825776+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-09-10T04:37:22.697573+00:00",
"communityUpdatedAt": "2026-09-10T04:54:24.825776+00:00",
"frameworkAttemptedAt": "2026-09-10T00:33:23.734278+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -416,149 +416,149 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T04:51:12.774430+00:00",
"generatedAt": "2026-09-10T04:54:24.825776+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 972.7083333333334,
"backlogHours": 927.5364238410596,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.4606129262157121,
"queueFactor": 0.948417385981057,
"queueWeight": 0.948417385981057,
"recentSuccess": 49,
"recentSuccessRate": 0.3402777777777778,
"recentTerminal": 144,
"recentWilsonLowerBound": 0.267939727271058,
"qualityFactor": 1.4653622565235713,
"queueFactor": 0.954574102508099,
"queueWeight": 0.954574102508099,
"recentSuccess": 50,
"recentSuccessRate": 0.33112582781456956,
"recentTerminal": 151,
"recentWilsonLowerBound": 0.2610694860590277,
"running": 8,
"selectionWeight": 1.385270693411648,
"selectionWeight": 1.3987968608702308,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 24.0,
"waiting": 23345
"throughputPerHour": 25.166666666666668,
"waiting": 23343
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1126.150684931507,
"backlogHours": 1126.027397260274,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.0722089318711798,
"queueFactor": 0.9278065333388015,
"queueWeight": 0.9278065333388015,
"recentSuccess": 44,
"recentSuccessRate": 0.3013698630136986,
"qualityFactor": 1.2069936386086324,
"queueFactor": 0.9272075305107197,
"queueWeight": 0.9272075305107197,
"recentSuccess": 45,
"recentSuccessRate": 0.3082191780821918,
"recentTerminal": 146,
"recentWilsonLowerBound": 0.23281544289288028,
"recentWilsonLowerBound": 0.23903703655594372,
"running": 8,
"selectionWeight": 0.9948024520942985,
"selectionWeight": 1.1191335909964581,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 24.333333333333332,
"waiting": 27403
"waiting": 27400
},
"Biren_166m": {
"available": true,
"backlogHours": 146.6742857142857,
"backlogHours": 146.77714285714285,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.3640913723360799,
"queueFactor": 1.2596323475988036,
"queueWeight": 1.2596323475988036,
"qualityFactor": 0.38675723090272535,
"queueFactor": 1.2586660825677478,
"queueWeight": 1.2586660825677478,
"recentSuccess": 34,
"recentSuccessRate": 0.19428571428571428,
"recentTerminal": 175,
"recentWilsonLowerBound": 0.14249465932580185,
"running": 8,
"selectionWeight": 0.45862127007616643,
"selectionWeight": 0.4867982087250832,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 29.166666666666668,
"waiting": 4278
"waiting": 4281
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1126.56,
"backlogHours": 1126.64,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.9987864402471202,
"queueFactor": 0.9277559602868054,
"queueWeight": 0.9277559602868054,
"qualityFactor": 1.06096410748398,
"queueFactor": 0.927131888622532,
"queueWeight": 0.927131888622532,
"recentSuccess": 24,
"recentSuccessRate": 0.32,
"recentTerminal": 75,
"recentWilsonLowerBound": 0.22542843754055916,
"running": 7,
"selectionWeight": 0.9266300729929069,
"selectionWeight": 0.9836536567323414,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.5,
"waiting": 14082
"waiting": 14083
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 530.9090909090909,
"backlogHours": 553.0736842105263,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.7237197302984335,
"queueFactor": 1.0385893810188953,
"queueWeight": 1.0385893810188953,
"recentSuccess": 27,
"recentSuccessRate": 0.2727272727272727,
"recentTerminal": 99,
"recentWilsonLowerBound": 0.1947227886340705,
"qualityFactor": 0.6873689344007566,
"queueFactor": 1.0315537081674586,
"queueWeight": 1.0315537081674586,
"recentSuccess": 25,
"recentSuccessRate": 0.2631578947368421,
"recentTerminal": 95,
"recentWilsonLowerBound": 0.18506401390488098,
"running": 7,
"selectionWeight": 0.751647626721812,
"selectionWeight": 0.7090579731602151,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 16.5,
"waiting": 8760
"throughputPerHour": 15.833333333333334,
"waiting": 8757
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 58.9792531120332,
"backlogHours": 60.794871794871796,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 24,
"qualityFactor": 0.06352488226740308,
"qualityFactor": 0.056514184263493784,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 23,
"recentSuccessRate": 0.0954356846473029,
"recentTerminal": 241,
"recentWilsonLowerBound": 0.06443650668106193,
"running": 9,
"selectionWeight": 0.08258234694762401,
"recentSuccess": 21,
"recentSuccessRate": 0.08974358974358974,
"recentTerminal": 234,
"recentWilsonLowerBound": 0.0594463802563413,
"running": 7,
"selectionWeight": 0.07346843954254192,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 40.166666666666664,
"waiting": 2369
"throughputPerHour": 39.0,
"waiting": 2371
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 73.94805194805194,
"backlogHours": 73.98701298701299,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.13647776269360687,
"qualityFactor": 0.14497394222913873,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 38,
@@ -566,170 +566,170 @@
"recentTerminal": 308,
"recentWilsonLowerBound": 0.09122097855217776,
"running": 2,
"selectionWeight": 0.17742109150168894,
"selectionWeight": 0.18846612489788037,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 51.333333333333336,
"waiting": 3796
"waiting": 3798
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2416.7368421052633,
"backlogHours": 2482.0540540540537,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.8930586249801649,
"queueFactor": 0.8273942487056872,
"queueWeight": 0.8273942487056872,
"qualityFactor": 2.14416323352868,
"queueFactor": 0.8235455190199942,
"queueWeight": 0.8235455190199942,
"recentSuccess": 17,
"recentSuccessRate": 0.4473684210526316,
"recentTerminal": 38,
"recentWilsonLowerBound": 0.3014616531155089,
"recentSuccessRate": 0.4594594594594595,
"recentTerminal": 37,
"recentWilsonLowerBound": 0.3103832782845773,
"running": 2,
"selectionWeight": 1.5663058187712848,
"selectionWeight": 1.765816023019966,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 6.333333333333333,
"throughputPerHour": 6.166666666666667,
"waiting": 15306
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 636.0,
"backlogHours": 635.8823529411765,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.439453343468312,
"queueFactor": 1.0108304937428914,
"queueWeight": 1.0108304937428914,
"recentSuccess": 23,
"recentSuccessRate": 0.22549019607843138,
"qualityFactor": 0.41399091833158397,
"queueFactor": 1.0101893320740472,
"queueWeight": 1.0101893320740472,
"recentSuccess": 22,
"recentSuccessRate": 0.21568627450980393,
"recentTerminal": 102,
"recentWilsonLowerBound": 0.1552158384389292,
"recentWilsonLowerBound": 0.14697094402656705,
"running": 7,
"selectionWeight": 0.44421284015503826,
"selectionWeight": 0.4182092092741042,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.0,
"waiting": 10812
"waiting": 10810
},
"MetaX_c-500": {
"available": true,
"backlogHours": 633.5327102803739,
"backlogHours": 639.1132075471697,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.34957296966534684,
"queueFactor": 1.0114200197947993,
"queueWeight": 1.0114200197947993,
"qualityFactor": 0.37933707124241234,
"queueFactor": 1.0094216725576988,
"queueWeight": 1.0094216725576988,
"recentSuccess": 22,
"recentSuccessRate": 0.205607476635514,
"recentTerminal": 107,
"recentWilsonLowerBound": 0.13988321742546095,
"recentSuccessRate": 0.20754716981132076,
"recentTerminal": 106,
"recentWilsonLowerBound": 0.14124543675119416,
"running": 4,
"selectionWeight": 0.35356509989865187,
"selectionWeight": 0.3829110609166548,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.833333333333332,
"waiting": 11298
"throughputPerHour": 17.666666666666668,
"waiting": 11291
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1758.0833333333333,
"backlogHours": 1834.4347826086957,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 1.0980038857856247,
"queueFactor": 0.867842637974155,
"queueWeight": 0.867842637974155,
"recentSuccess": 24,
"qualityFactor": 1.1464342564914651,
"queueFactor": 0.8617552786282141,
"queueWeight": 0.8617552786282141,
"recentSuccess": 23,
"recentSuccessRate": 0.3333333333333333,
"recentTerminal": 72,
"recentWilsonLowerBound": 0.2353448606571184,
"recentTerminal": 69,
"recentWilsonLowerBound": 0.2335089100698828,
"running": 4,
"selectionWeight": 0.9528945887460692,
"selectionWeight": 0.987945772131732,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.0,
"waiting": 21097
"throughputPerHour": 11.5,
"waiting": 21096
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 4178.7,
"backlogHours": 4398.631578947368,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 2.5,
"queueFactor": 0.7621504724775896,
"queueWeight": 0.7621504724775896,
"recentSuccess": 11,
"recentSuccessRate": 0.55,
"recentTerminal": 20,
"recentWilsonLowerBound": 0.34208200830759966,
"qualityFactor": 2.2471777462310714,
"queueFactor": 0.7558082978415763,
"queueWeight": 0.7558082978415763,
"recentSuccess": 10,
"recentSuccessRate": 0.5263157894736842,
"recentTerminal": 19,
"recentWilsonLowerBound": 0.31707482511825114,
"running": 2,
"selectionWeight": 1.905376181193974,
"selectionWeight": 1.698435587326376,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 3.3333333333333335,
"submissionEligible": false,
"throughputPerHour": 3.1666666666666665,
"waiting": 13929
},
"Vastai_va16": {
"available": true,
"backlogHours": 730.7088607594937,
"backlogHours": 721.5749999999999,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 1.476630002718933,
"queueFactor": 0.9900001174063737,
"queueWeight": 0.9900001174063737,
"recentSuccess": 29,
"recentSuccessRate": 0.3670886075949367,
"recentTerminal": 79,
"recentWilsonLowerBound": 0.26927131273817784,
"qualityFactor": 1.385988548353458,
"queueFactor": 0.9912131889956476,
"queueWeight": 0.9912131889956476,
"recentSuccess": 28,
"recentSuccessRate": 0.35,
"recentTerminal": 80,
"recentWilsonLowerBound": 0.2545439440982969,
"running": 16,
"selectionWeight": 1.4618638760575176,
"selectionWeight": 1.3738101289248794,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 13.166666666666666,
"throughputPerHour": 13.333333333333334,
"waiting": 9621
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 529.8367346938776,
"backlogHours": 540.6875,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 2.3893384817249554,
"queueFactor": 1.0389044160734977,
"queueWeight": 1.0389044160734977,
"recentSuccess": 42,
"recentSuccessRate": 0.42857142857142855,
"recentTerminal": 98,
"recentWilsonLowerBound": 0.3351141839487037,
"qualityFactor": 2.5,
"queueFactor": 1.0350643348695037,
"queueWeight": 1.0350643348695037,
"recentSuccess": 41,
"recentSuccessRate": 0.4270833333333333,
"recentTerminal": 96,
"recentWilsonLowerBound": 0.3328192137965024,
"running": 6,
"selectionWeight": 2.4822943001584026,
"selectionWeight": 2.5876608371737593,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 16.333333333333332,
"waiting": 8654
"throughputPerHour": 16.0,
"waiting": 8651
}
},
"queueAttemptedAt": "2026-09-10T04:43:25.935913+00:00",
"queueAttemptedAt": "2026-09-10T04:54:24.825776+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-10T04:43:25.935913+00:00",
"queueUpdatedAt": "2026-09-10T04:54:24.825776+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": "2026-09-10T04:45:49.713641+00:00",
"lastSyncTime": "2026-09-10T04:45:49.293213+00:00",
"generatedAt": "2026-09-10T04:54:16.505309+00:00",
"lastSyncTime": "2026-09-10T04:54:16.213468+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1398,12 +1398,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 26,
"failureBreakdown": {
"ambiguous_runtime": 16,
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 24,
"memory_capacity": 1,
"tokenizer_compatibility": 1
},
"failureCount": 42,
"failureCount": 44,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1413,8 +1413,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 42,
"unresolvedFailureCount": 16
"total": 44,
"unresolvedFailureCount": 18
},
"Ascend_910-b4|llamacpp|text-generation": {
"attributableFailureCount": 1,
@@ -2243,14 +2243,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 9,
"ambiguous_runtime": 10,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"model_load": 3,
"repository_structure": 3,
"runtime_memory": 1
},
"failureCount": 44,
"failureCount": 45,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2260,8 +2260,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 44,
"unresolvedFailureCount": 9
"total": 45,
"unresolvedFailureCount": 10
}
},
"frameworkSummaries": {
@@ -2333,7 +2333,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 230,
"failureBreakdown": {
"ambiguous_runtime": 135,
"ambiguous_runtime": 138,
"backend_operator": 24,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2344,15 +2344,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 387,
"failureCount": 390,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 387,
"unresolvedFailureCount": 156
"total": 390,
"unresolvedFailureCount": 159
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2455,7 +2455,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T04:45:49.709300+00:00",
"generatedAt": "2026-09-10T04:54:16.501434+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2463,22 +2463,22 @@
"decisionSuccessRate": 0.037,
"decisionTotal": 27,
"failureBreakdown": {
"ambiguous_runtime": 16,
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 24,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 8,
"验证失败": 27
},
"failureCount": 77,
"failureRate": 0.9872,
"failureCount": 79,
"failureRate": 0.9875,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0128,
"total": 78,
"unresolvedFailureCount": 51
"successRate": 0.0125,
"total": 80,
"unresolvedFailureCount": 53
},
"Ascend_910-b4": {
"attributableFailureCount": 38,
@@ -2762,7 +2762,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 38,
"failureBreakdown": {
"ambiguous_runtime": 11,
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 30,
"memory_capacity": 1,
"model_load": 3,
@@ -2771,15 +2771,15 @@
"参数/模板问题": 8,
"验证失败": 27
},
"failureCount": 84,
"failureCount": 85,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 84,
"unresolvedFailureCount": 46
"total": 85,
"unresolvedFailureCount": 47
}
},
"observedGpuMemoryGiB": {
@@ -3950,29 +3950,6 @@
}
},
"recentCombinationStats": {
"Ascend_910-b3|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": "2026-09-07T10:17:44.109335+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
@@ -3981,14 +3958,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 3
},
"failureCount": 13,
"failureCount": 15,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T02:32:07.501688+00:00",
"lastTerminalAt": "2026-09-10T04:54:16.213455+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -3996,8 +3973,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 13,
"unresolvedFailureCount": 10
"total": 15,
"unresolvedFailureCount": 12
},
"Ascend_910-b4|llamacpp|text-generation": {
"attributableFailureCount": 1,
@@ -4109,27 +4086,27 @@
"attributableFailureCount": 3,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.6,
"decisionSuccessRate": 0.4,
"decisionTotal": 5,
"decisionFailureRate": 0.75,
"decisionSuccessRate": 0.25,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 10,
"framework_architecture_unsupported": 2,
"tokenizer_compatibility": 1
},
"failureCount": 13,
"failureRate": 0.8667,
"failureRate": 0.9286,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T01:59:31.241099+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.1333,
"successCount": 1,
"successRate": 0.0714,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 15,
"total": 14,
"unresolvedFailureCount": 10
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
@@ -4678,16 +4655,16 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 10,
"failureBreakdown": {
"ambiguous_runtime": 7,
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 8,
"model_load": 1,
"repository_structure": 1
},
"failureCount": 17,
"failureCount": 18,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T04:45:49.293187+00:00",
"lastTerminalAt": "2026-09-10T04:54:16.213427+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4695,8 +4672,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 17,
"unresolvedFailureCount": 7
"total": 18,
"unresolvedFailureCount": 8
}
},
"recentProfileCombinationStats": {
@@ -6905,15 +6882,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1502,
"totalRecords": 1589,
"terminalRecords": 1505,
"totalRecords": 1592,
"totals": {
"attributableFailureCount": 399,
"decisionFailureRate": 0.8906,
"decisionSuccessRate": 0.1094,
"decisionTotal": 448,
"failureBreakdown": {
"ambiguous_runtime": 284,
"ambiguous_runtime": 287,
"backend_operator": 29,
"framework_architecture_unsupported": 270,
"memory_capacity": 11,
@@ -6925,21 +6902,21 @@
"参数/模板问题": 95,
"验证失败": 673
},
"failureCount": 1453,
"failureCount": 1456,
"failureRate": 0.9674,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 49,
"successRate": 0.0326,
"total": 1502,
"unresolvedFailureCount": 1052
"total": 1505,
"unresolvedFailureCount": 1055
},
"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。",
@@ -6947,7 +6924,7 @@
"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。",
@@ -6968,6 +6945,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1589,
"summarizedRecords": 1592,
"version": 1
}

View File

@@ -1,3 +1,6 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T04:54:16.213427+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:51:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493600", "taskType": "text-generation", "verifyResult": -1}
{"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": "2026-09-10T04:54:16.213455+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:51:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505116", "taskType": "text-generation", "verifyResult": -1}
{"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": "2026-09-10T04:54:16.213468+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:49:22+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505115", "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": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T04:45:49.293187+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:43:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493603", "taskType": "text-generation", "verifyResult": -1}
{"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": "2026-09-10T04:27:58.701433+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:25:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471917", "taskType": "text-generation", "verifyResult": -1}
{"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": "2026-09-10T04:27:58.701482+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:23:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471910", "taskType": "text-generation", "verifyResult": -1}
@@ -295,6 +298,3 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-07T10:17:44.109315+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T10:11:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4464041", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-07T10:17:44.109293+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T10:09:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4464043", "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", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-09-07T10:17:44.109327+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T10:05:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4464042", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-07T10:17:44.109335+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-07T09:57:22+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4458964", "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", "failureUnsupportedArchitectures": ["GPTNeoForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-07T09:53:28.210465+00:00", "modelId": "KoboldAI/GPT-Neo-2.7B-Janeway", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T09:45:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079146", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-07T09:29:22.999691+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-07T09:17:22+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4471037", "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": "12cbe8f59d62959e7811034fbbec57fdc3c786748e102b02cd65c38613566ec6",
".modelhub_state/architecture_history_backfill.json": "f99e2a38cde7c3a4f980b27af761c4da0939f9ccf9ff52a212df4fd51938eeb7",
".modelhub_state/market_intelligence.json": "13ef718597e7cf47ef2b3edf8d8d60d5152bed6802f06d7855f412973cfbd6bf",
".modelhub_state/official_capabilities.json": "620debab624233b473f9fef3df4f6affde44fcbe4702f3dc7242bfce32339871",
".modelhub_state/outcome_checkpoint.json": "f123ec16e7df7df588b42b9d139d2ab47d25afbdaaac32795a1042355bdb7837",
".modelhub_state/architecture_compatibility_blacklist.json": "5c1ea077bcbe5fd0b043afb8f368f109f50daff7df71d1b7f1c25d02da911a0e",
".modelhub_state/architecture_history_backfill.json": "7ad71a052c6f10c3a55255b86aa9e2c340d82b278822970cf33e5d9a60dd89c6",
".modelhub_state/market_intelligence.json": "ab294f06de4adce071c45927297ce005853a94ca87b8bfd61210c93813b9f518",
".modelhub_state/official_capabilities.json": "d8d5678e340bddaba798845eacebe53d6505a6a216b5f2d6f0e7d4b4a8537754",
".modelhub_state/outcome_checkpoint.json": "3183debd727a9e378747a368604add80a8cd9b00b21b89fedba50bde13eea8a7",
".modelhub_state/queue_cleanup_latest.json": "b251e2ff52f1e826ed4fc9723e1765d93287b92341cb7f593f01eb5e88982f99",
".modelhub_state/recent_outcomes.jsonl": "e28db23599a9d908223612e0fa980594148a77f1acc6cccec525e210fa3ca35d",
".modelhub_state/recovery_active_tasks.jsonl": "858321c896f1cba09731da900d735027493de2dfa59510ac129d5e2cf2998ee8",
".modelhub_state/recovery_intents.jsonl": "0de1c1f7357a7c01879d8d0c953f1b01f8b0fdd2c3da449e2705b050069518f6",
".modelhub_state/recent_outcomes.jsonl": "32af73424b4be028f2a6e49d00894db9a79745ed8743d28d97eb1e4d68408601",
".modelhub_state/recovery_active_tasks.jsonl": "1f007caa060f597f1fd39cb14f246fd2948692ca1a2c04815a5186d38c50b80c",
".modelhub_state/recovery_intents.jsonl": "a86898483cd659953c7f83db0a151f1fdf4af1b130629ed3f737d88bf5d6051f",
".modelhub_state/routing_intelligence.json": "2c10dfed0a26c6bc51f09f69009667713989adad52ee2398495736003f8b05c0",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "4d2bbfc439a137759b4698122a8725280b082c541629542d0329d6b9040fe6dc",
"outcomes/submissions.jsonl": "e7ef9f0450e529c73e89c5cd1d774421d0e33158d26ca828bacfdf64c7f20d42"
},
"generation": 4957,
"generation": 4958,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T04:53:15.546533+00:00",
"updatedAt": "2026-09-10T04:56:16.961341+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}