state: generation 5508 (cycle)

This commit is contained in:
2026-09-11 03:36:03 +00:00
parent 2abb37c59c
commit 319757bbf0
9 changed files with 3171 additions and 2985 deletions

View File

@@ -1307,7 +1307,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-11T03:32:48.207761+00:00",
"generatedAt": "2026-09-11T03:36:03.035601+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -27,7 +27,7 @@
"11": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 392,
"listingErrors": 393,
"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": 11,
"nextAccountIndex": 0,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-11T03:32:48.183611+00:00",
"updatedAt": "2026-09-11T03:36:03.010783+00:00",
"version": 1
}

View File

@@ -387,298 +387,298 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-11T03:30:43.608458+00:00",
"generatedAt": "2026-09-11T03:33:56.164766+00:00",
"gpuStats": {
"Ascend_910-b4": {
"available": true,
"backlogHours": 1066.5194805194806,
"backlogHours": 1059.5612903225806,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.7350376416305588,
"queueFactor": 0.9282547742018262,
"queueWeight": 0.9282547742018262,
"recentSuccess": 48,
"recentSuccessRate": 0.3116883116883117,
"recentTerminal": 154,
"recentWilsonLowerBound": 0.2438662664082448,
"qualityFactor": 1.897745705469678,
"queueFactor": 0.9252241527764602,
"queueWeight": 0.9252241527764602,
"recentSuccess": 49,
"recentSuccessRate": 0.3161290322580645,
"recentTerminal": 155,
"recentWilsonLowerBound": 0.2481302142025571,
"running": 8,
"selectionWeight": 1.6105569742634436,
"selectionWeight": 1.7558401625283486,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 25.666666666666668,
"waiting": 27374
"throughputPerHour": 25.833333333333332,
"waiting": 27372
},
"Biren_166m": {
"available": true,
"backlogHours": 183.06293706293707,
"backlogHours": 186.9857142857143,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.6597374789519367,
"queueFactor": 1.209128468372544,
"queueWeight": 1.209128468372544,
"recentSuccess": 31,
"recentSuccessRate": 0.21678321678321677,
"recentTerminal": 143,
"recentWilsonLowerBound": 0.15713427867091181,
"qualityFactor": 0.5571992608538506,
"queueFactor": 1.2001750932546231,
"queueWeight": 1.2001750932546231,
"recentSuccess": 28,
"recentSuccessRate": 0.2,
"recentTerminal": 140,
"recentWilsonLowerBound": 0.1421536666143311,
"running": 8,
"selectionWeight": 0.7977073674531188,
"selectionWeight": 0.6687366748566772,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 23.833333333333332,
"throughputPerHour": 23.333333333333332,
"waiting": 4363
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1090.0,
"backlogHours": 1000.2352941176471,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.9264418172711258,
"queueFactor": 0.9252275067617237,
"queueWeight": 0.9252275067617237,
"recentSuccess": 21,
"recentSuccessRate": 0.2692307692307692,
"recentTerminal": 78,
"recentWilsonLowerBound": 0.18335480551618466,
"qualityFactor": 0.9090928933368247,
"queueFactor": 0.9332554777558077,
"queueWeight": 0.9332554777558077,
"recentSuccess": 22,
"recentSuccessRate": 0.25882352941176473,
"recentTerminal": 85,
"recentWilsonLowerBound": 0.1775797328865609,
"running": 7,
"selectionWeight": 0.8571694527535642,
"selectionWeight": 0.8484159224954679,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 13.0,
"throughputPerHour": 14.166666666666666,
"waiting": 14170
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 498.3962264150943,
"backlogHours": 502.9142857142857,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 1.197268159220896,
"queueFactor": 1.0404621801455654,
"queueWeight": 1.0404621801455654,
"qualityFactor": 1.2882601565598908,
"queueFactor": 1.0346459881156673,
"queueWeight": 1.0346459881156673,
"recentSuccess": 30,
"recentSuccessRate": 0.2830188679245283,
"recentTerminal": 106,
"recentWilsonLowerBound": 0.20602338401321438,
"recentSuccessRate": 0.2857142857142857,
"recentTerminal": 105,
"recentWilsonLowerBound": 0.20806999151103064,
"running": 7,
"selectionWeight": 1.2457122391618414,
"selectionWeight": 1.3328932026339524,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.666666666666668,
"waiting": 8805
"throughputPerHour": 17.5,
"waiting": 8801
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 138.41584158415841,
"backlogHours": 132.74285714285713,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 24,
"qualityFactor": 0.05,
"queueFactor": 1.2609116019588222,
"queueWeight": 1.2609116019588222,
"recentSuccess": 8,
"recentSuccessRate": 0.07920792079207921,
"recentTerminal": 101,
"recentWilsonLowerBound": 0.04068048623667316,
"running": 2,
"selectionWeight": 0.06304558009794112,
"queueFactor": 1.2634678626981743,
"queueWeight": 1.2634678626981743,
"recentSuccess": 9,
"recentSuccessRate": 0.08571428571428572,
"recentTerminal": 105,
"recentWilsonLowerBound": 0.045748960070996485,
"running": 0,
"selectionWeight": 0.06317339313490872,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 16.833333333333332,
"waiting": 2330
"throughputPerHour": 17.5,
"waiting": 2323
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 219.5533980582524,
"backlogHours": 203.72972972972974,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.061889402422130035,
"queueFactor": 1.1766071575620591,
"queueWeight": 1.1766071575620591,
"recentSuccess": 10,
"recentSuccessRate": 0.0970873786407767,
"recentTerminal": 103,
"recentWilsonLowerBound": 0.05359319306770389,
"running": 5,
"selectionWeight": 0.07281951386711684,
"qualityFactor": 0.0927794458312044,
"queueFactor": 1.1848345575750066,
"queueWeight": 1.1848345575750066,
"recentSuccess": 12,
"recentSuccessRate": 0.10810810810810811,
"recentTerminal": 111,
"recentWilsonLowerBound": 0.06293144758562783,
"running": 4,
"selectionWeight": 0.10992829365346934,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.166666666666668,
"throughputPerHour": 18.5,
"waiting": 3769
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2279.268292682927,
"backlogHours": 2335.95,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.3229428600804498,
"queueFactor": 0.8283105503555104,
"queueWeight": 0.8283105503555104,
"qualityFactor": 1.476008846229563,
"queueFactor": 0.8217625446462978,
"queueWeight": 0.8217625446462978,
"recentSuccess": 14,
"recentSuccessRate": 0.34146341463414637,
"recentTerminal": 41,
"recentWilsonLowerBound": 0.21558617366643462,
"recentSuccessRate": 0.35,
"recentTerminal": 40,
"recentWilsonLowerBound": 0.22134333171049148,
"running": 2,
"selectionWeight": 1.0958075285221303,
"selectionWeight": 1.212928785398052,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 6.833333333333333,
"waiting": 15575
"throughputPerHour": 6.666666666666667,
"waiting": 15573
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 714.9230769230769,
"backlogHours": 731.1235955056179,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 1.0435722815740367,
"queueFactor": 0.9856520126705572,
"queueWeight": 0.9856520126705572,
"qualityFactor": 1.156265772374164,
"queueFactor": 0.9781765651717929,
"queueWeight": 0.9781765651717929,
"recentSuccess": 25,
"recentSuccessRate": 0.27472527472527475,
"recentTerminal": 91,
"recentWilsonLowerBound": 0.19355049670786545,
"recentSuccessRate": 0.2808988764044944,
"recentTerminal": 89,
"recentWilsonLowerBound": 0.19809358040575942,
"running": 7,
"selectionWeight": 1.0285991197006548,
"selectionWeight": 1.13103208164667,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 15.166666666666666,
"waiting": 10843
"throughputPerHour": 14.833333333333334,
"waiting": 10845
},
"MetaX_c-500": {
"available": true,
"backlogHours": 649.2571428571429,
"backlogHours": 631.1111111111111,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.5331742654935827,
"qualityFactor": 0.6656714501916233,
"queueFactor": 1.0,
"queueWeight": 1.0,
"recentSuccess": 22,
"recentSuccessRate": 0.20952380952380953,
"recentTerminal": 105,
"recentWilsonLowerBound": 0.1426344996383833,
"recentSuccess": 24,
"recentSuccessRate": 0.2222222222222222,
"recentTerminal": 108,
"recentWilsonLowerBound": 0.15412441082279263,
"running": 4,
"selectionWeight": 0.5331742654935827,
"selectionWeight": 0.6656714501916233,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.5,
"waiting": 11362
"throughputPerHour": 18.0,
"waiting": 11360
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 637.74,
"backlogHours": 630.0295566502463,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.05,
"queueFactor": 1.0026883334171017,
"queueWeight": 1.0026883334171017,
"recentSuccess": 11,
"recentSuccessRate": 0.055,
"recentTerminal": 200,
"recentWilsonLowerBound": 0.0309850208013701,
"queueFactor": 1.0002573132157733,
"queueWeight": 1.0002573132157733,
"recentSuccess": 12,
"recentSuccessRate": 0.059113300492610835,
"recentTerminal": 203,
"recentWilsonLowerBound": 0.03413485824824486,
"running": 4,
"selectionWeight": 0.05013441667085509,
"selectionWeight": 0.05001286566078866,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 33.333333333333336,
"waiting": 21258
"throughputPerHour": 33.833333333333336,
"waiting": 21316
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 3177.1111111111113,
"backlogHours": 3299.769230769231,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.3193907999677283,
"queueFactor": 0.7880570342451249,
"queueWeight": 0.7880570342451249,
"recentSuccess": 10,
"recentSuccessRate": 0.37037037037037035,
"recentTerminal": 27,
"recentWilsonLowerBound": 0.21532287067936856,
"qualityFactor": 0.7735214662069869,
"queueFactor": 0.7802671779758309,
"queueWeight": 0.7802671779758309,
"recentSuccess": 8,
"recentSuccessRate": 0.3076923076923077,
"recentTerminal": 26,
"recentWilsonLowerBound": 0.1650112093979267,
"running": 2,
"selectionWeight": 1.0397552008328708,
"selectionWeight": 0.6035534115410527,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 4.5,
"waiting": 14297
"throughputPerHour": 4.333333333333333,
"waiting": 14299
},
"Vastai_va16": {
"available": true,
"backlogHours": 918.9850746268658,
"backlogHours": 905.0294117647059,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.619293450992674,
"queueFactor": 0.9492186045477145,
"queueWeight": 0.9492186045477145,
"qualityFactor": 0.6302748006201606,
"queueFactor": 0.9473631111368773,
"queueWeight": 0.9473631111368773,
"recentSuccess": 16,
"recentSuccessRate": 0.23880597014925373,
"recentTerminal": 67,
"recentWilsonLowerBound": 0.15268010510617858,
"recentSuccessRate": 0.23529411764705882,
"recentTerminal": 68,
"recentWilsonLowerBound": 0.1503436437092872,
"running": 16,
"selectionWeight": 0.5878448653568044,
"selectionWeight": 0.5970990959866904,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 11.166666666666666,
"waiting": 10262
"throughputPerHour": 11.333333333333334,
"waiting": 10257
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 565.4347826086956,
"backlogHours": 571.9120879120879,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 2.5,
"queueFactor": 1.0209515489336232,
"queueWeight": 1.0209515489336232,
"recentSuccess": 35,
"recentSuccessRate": 0.3804347826086957,
"recentTerminal": 92,
"recentWilsonLowerBound": 0.28791001894905327,
"queueFactor": 1.014884179474654,
"queueWeight": 1.014884179474654,
"recentSuccess": 34,
"recentSuccessRate": 0.37362637362637363,
"recentTerminal": 91,
"recentWilsonLowerBound": 0.28124813194188497,
"running": 6,
"selectionWeight": 2.552378872334058,
"selectionWeight": 2.537210448686635,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 15.333333333333334,
"waiting": 8670
"throughputPerHour": 15.166666666666666,
"waiting": 8674
}
},
"queueAttemptedAt": "2026-09-11T03:22:03.418295+00:00",
"queueAttemptedAt": "2026-09-11T03:33:56.164766+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-11T03:22:03.418295+00:00",
"queueUpdatedAt": "2026-09-11T03:33:56.164766+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": "2026-09-11T03:25:07.038041+00:00",
"lastSyncTime": "2026-09-11T03:25:05.807699+00:00",
"generatedAt": "2026-09-11T03:33:49.103183+00:00",
"lastSyncTime": "2026-09-11T03:33:48.898214+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1541,24 +1541,24 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 32,
"ambiguous_runtime": 33,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 91,
"failureRate": 0.9785,
"failureCount": 92,
"failureRate": 0.9787,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0215,
"successRate": 0.0213,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 93,
"unresolvedFailureCount": 71
"total": 94,
"unresolvedFailureCount": 72
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 7,
@@ -2293,7 +2293,7 @@
"decisionSuccessRate": 0.2667,
"decisionTotal": 180,
"failureBreakdown": {
"ambiguous_runtime": 127,
"ambiguous_runtime": 128,
"backend_operator": 4,
"framework_architecture_unsupported": 89,
"memory_capacity": 5,
@@ -2303,15 +2303,15 @@
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 989,
"failureRate": 0.9537,
"failureCount": 990,
"failureRate": 0.9538,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.0463,
"total": 1037,
"unresolvedFailureCount": 856
"successRate": 0.0462,
"total": 1038,
"unresolvedFailureCount": 857
},
"vllm": {
"attributableFailureCount": 240,
@@ -2441,7 +2441,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-11T03:25:07.033553+00:00",
"generatedAt": "2026-09-11T03:33:49.099427+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2521,21 +2521,21 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 32,
"ambiguous_runtime": 33,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 91,
"failureRate": 0.9785,
"failureCount": 92,
"failureRate": 0.9787,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0215,
"total": 93,
"unresolvedFailureCount": 71
"successRate": 0.0213,
"total": 94,
"unresolvedFailureCount": 72
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 17,
@@ -4145,7 +4145,7 @@
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-11T03:25:05.807699+00:00",
"lastTerminalAt": "2026-09-11T03:33:48.898214+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4183,17 +4183,16 @@
"unresolvedFailureCount": 14
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 0,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"参数/模板问题": 3
},
"failureCount": 4,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4205,7 +4204,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 4,
"total": 3,
"unresolvedFailureCount": 3
},
"Iluvatar_bi-100|transformers|text-generation": {
@@ -4599,31 +4598,6 @@
}
},
"recentProfileCombinationStats": {
"Cambricon_mlu-370-x8|vllm|text-generation|qwen3_5_moe|eschamoe": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-08T15:50:00.101653+00:00",
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "eschamoe",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -6962,15 +6936,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1644,
"totalRecords": 1731,
"terminalRecords": 1645,
"totalRecords": 1732,
"totals": {
"attributableFailureCount": 427,
"decisionFailureRate": 0.8896,
"decisionSuccessRate": 0.1104,
"decisionTotal": 480,
"failureBreakdown": {
"ambiguous_runtime": 389,
"ambiguous_runtime": 390,
"backend_operator": 40,
"framework_architecture_unsupported": 273,
"memory_capacity": 11,
@@ -6982,30 +6956,31 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1591,
"failureCount": 1592,
"failureRate": 0.9678,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 53,
"successRate": 0.0322,
"total": 1644,
"unresolvedFailureCount": 1160
"total": 1645,
"unresolvedFailureCount": 1161
},
"warnings": [
"GPU Ascend_910-b3 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 Iluvatar_mrv-100 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 MetaX_c-500 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 Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 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 Iluvatar_bi-150 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 Cambricon_mlu-370-x8 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 Ascend_910-b4 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-x4|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 Mthreads_s4000|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 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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7020,11 +6995,10 @@
"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 Iluvatar_bi-150|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 Vastai_va16|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 Cambricon_mlu-370-x4|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 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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1731,
"summarizedRecords": 1732,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"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": "2026-09-11T03:33:48.898214+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T03:29:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497066", "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": "2026-09-11T03:25:05.807699+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T03:23:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497054", "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": "2026-09-10T23:52:39.100972+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T23:51:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477786", "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": "2026-09-10T23:36:16.447910+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T23:33:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497061", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831495+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.934706+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712836", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831446+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.928754+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712837", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831476+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.927161+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712835", "taskType": "text-generation", "verifyResult": null}
{"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": "vllm", "lastSyncTime": "2026-09-08T15:50:00.101653+00:00", "modelId": "EschaLabs/Qwen3.6-35B-A3B-Escha-W2", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12296952480, "estimatedRequiredGiB": 13.771, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 12322205679, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7300654928, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:mlx", "library:safetensors", "task:text-generation", "custom_tag:mixture-of-experts", "custom_tag:moe", "custom_tag:qwen3", "custom_tag:2-bit", "custom_tag:quantization", "custom_tag:eschamoe", "custom_tag:sglang", "custom_tag:zml", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:metal", "custom_tag:code", "custom_tag:reasoning", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "eschamoe", "repositoryOnDiskBytes": 12322205679}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:11.886266+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712834", "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": "9ea0aecc104d25c26562f8714d6143ef2d640189410f830b4ffa724bdf816679",
".modelhub_state/architecture_history_backfill.json": "fba1b49acdaf439fb285c26b4ce35c35659b8f1412a54073706d7eb4119da93a",
".modelhub_state/market_intelligence.json": "67237f587591120a59c807fbba60292b1c7a01fbb6612c03b2b7444325032cce",
".modelhub_state/official_capabilities.json": "7eb57a939777d3f2c6354c3327fa709e91650666f2638b540e8bf8b637271115",
".modelhub_state/outcome_checkpoint.json": "f4a510ed675007ae3f63721d3ce3b6ae107e5469fe337fef6ca5d949bdd41e68",
".modelhub_state/architecture_compatibility_blacklist.json": "ea6959dc07da836a91b89e2564ec2778802fd8d5d16a9a26741bc8331cbea8d5",
".modelhub_state/architecture_history_backfill.json": "6b545c4f9109e97c9d8c4257a2443f79cf7b54e619317ab7812b880ed53196b5",
".modelhub_state/market_intelligence.json": "fa24174e98f90f78fbda742ea49811eea28dfeb2d0716454030b78b1484c19d4",
".modelhub_state/official_capabilities.json": "e0e62b1c08442b47d9756b9e2c4f6817c103f667600b80baa3c70ef3d322440e",
".modelhub_state/outcome_checkpoint.json": "f79b0cf8c8d78cb276a7074d4430aa3bb8d5a6e9e047a99be83b7839affea55d",
".modelhub_state/queue_cleanup_latest.json": "757bb52cd4c1e398d565b25c01e1a394e97727dc87500e4184be2784f229ae2a",
".modelhub_state/recent_outcomes.jsonl": "3db8cbb1a7cc73b42ed867fa670224e1a04c08716d86a1fa5744f1d052aa19c9",
".modelhub_state/recovery_active_tasks.jsonl": "4141fca5495c02458c74fa42d477757b4c9a2cf0da09777e2eb00d673c7b43bb",
".modelhub_state/recovery_intents.jsonl": "9d8998c0091e8676ffb78f90d15dbb2009beb0a5bbc7233a6cc727aba736b3a8",
".modelhub_state/recent_outcomes.jsonl": "cd38593344e217489915142ed481535713d3230c773d364e965c12e8bf6e84a9",
".modelhub_state/recovery_active_tasks.jsonl": "38e865a276b0d1c79191a6b10686a866e18dc70465c6383134b17802cb1304d4",
".modelhub_state/recovery_intents.jsonl": "aa880a2a65829d1d72265ff02f92fb19991f836a30273dd9415ef60e61731024",
".modelhub_state/routing_intelligence.json": "a7d892e1ccda118f72a13ee212ed5aad3be9d65cdbf4c8218d696761745235b0",
".modelhub_state/submission_exclusions.jsonl": "a07e1a02840754257cdff556f0bbb75a93364d6fc493705741531a86b71b768e",
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
"ledger/submissions.jsonl": "369d50ba323fae299168a3afc0597ce8bc04a737b67af19154a569c0c08db4aa",
"outcomes/submissions.jsonl": "c1c3d0d4da05824c9f827503db934bd7ce488d83abf9ec539b0907e9b7086f77"
},
"generation": 5507,
"generation": 5508,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-11T03:32:48.278884+00:00",
"updatedAt": "2026-09-11T03:36:03.617050+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42"
}