state: generation 11385 (cycle)

This commit is contained in:
2026-09-21 10:05:25 +00:00
parent 479efbb6c6
commit 68bb2c1ec1
9 changed files with 2114 additions and 2090 deletions

View File

@@ -2652,7 +2652,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-21T10:01:40.238300+00:00",
"generatedAt": "2026-09-21T10:05:14.085772+00:00",
"summary": {
"activeBlockCount": 133,
"byGpuFramework": {

View File

@@ -434,121 +434,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-21T10:04:10.177617+00:00",
"generatedAt": "2026-09-21T10:05:23.787223+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 957.4459459459459,
"backlogHours": 964.1632653061224,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.025666568543973,
"queueFactor": 0.9910022665434337,
"queueWeight": 0.9910022665434337,
"recentSuccess": 43,
"recentSuccessRate": 0.2905405405405405,
"recentTerminal": 148,
"recentWilsonLowerBound": 0.22343062480550951,
"qualityFactor": 1.0255872330871003,
"queueFactor": 0.9917622177216276,
"queueWeight": 0.9917622177216276,
"recentSuccess": 44,
"recentSuccessRate": 0.29931972789115646,
"recentTerminal": 147,
"recentWilsonLowerBound": 0.23116798348527112,
"running": 8,
"selectionWeight": 1.0164378941449033,
"selectionWeight": 1.0171386687534505,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 24.666666666666668,
"waiting": 23617
"throughputPerHour": 24.5,
"waiting": 23622
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1348.3809523809523,
"backlogHours": 1327.3125,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.3958982963647815,
"queueFactor": 0.9413906837949334,
"queueWeight": 0.9413906837949334,
"recentSuccess": 42,
"recentSuccessRate": 0.3333333333333333,
"recentTerminal": 126,
"recentWilsonLowerBound": 0.2570292256450892,
"qualityFactor": 1.1000772511413817,
"queueFactor": 0.945331585464432,
"queueWeight": 0.945331585464432,
"recentSuccess": 40,
"recentSuccessRate": 0.3125,
"recentTerminal": 128,
"recentWilsonLowerBound": 0.23865407613652956,
"running": 8,
"selectionWeight": 1.3140856517230242,
"selectionWeight": 1.0399377719548364,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 21.0,
"throughputPerHour": 21.333333333333332,
"waiting": 28316
},
"Biren_166m": {
"available": true,
"backlogHours": 177.06896551724137,
"backlogHours": 185.06586826347305,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.2322354188631864,
"queueFactor": 1.2764988266904402,
"queueWeight": 1.2764988266904402,
"qualityFactor": 0.2363224153649593,
"queueFactor": 1.2703728310316402,
"queueWeight": 1.2703728310316402,
"recentSuccess": 28,
"recentSuccessRate": 0.16091954022988506,
"recentTerminal": 174,
"recentWilsonLowerBound": 0.11374322651966227,
"recentSuccessRate": 0.16766467065868262,
"recentTerminal": 167,
"recentWilsonLowerBound": 0.11862320234962478,
"running": 8,
"selectionWeight": 0.29644823969482037,
"selectionWeight": 0.3002175758434185,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 29.0,
"waiting": 5135
"throughputPerHour": 27.833333333333332,
"waiting": 5151
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1475.2131147540983,
"backlogHours": 1430.095238095238,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.7649849450853935,
"queueFactor": 0.9287815352262515,
"queueWeight": 0.9287815352262515,
"recentSuccess": 18,
"recentSuccessRate": 0.29508196721311475,
"recentTerminal": 61,
"recentWilsonLowerBound": 0.19554865403985322,
"qualityFactor": 0.8821324804294756,
"queueFactor": 0.9348144186887947,
"queueWeight": 0.9348144186887947,
"recentSuccess": 20,
"recentSuccessRate": 0.31746031746031744,
"recentTerminal": 63,
"recentWilsonLowerBound": 0.21586527168091207,
"running": 7,
"selectionWeight": 0.7105038917213815,
"selectionWeight": 0.8246301618991847,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 10.166666666666666,
"waiting": 14998
"throughputPerHour": 10.5,
"waiting": 15016
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 457.6859504132231,
"backlogHours": 454.91803278688525,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.2141250978866827,
"queueFactor": 1.1070230158743228,
"queueWeight": 1.1070230158743228,
"qualityFactor": 0.1950037950183471,
"queueFactor": 1.1100439485577436,
"queueWeight": 1.1100439485577436,
"recentSuccess": 20,
"recentSuccessRate": 0.1652892561983471,
"recentTerminal": 121,
"recentWilsonLowerBound": 0.10962203759241998,
"recentSuccessRate": 0.16393442622950818,
"recentTerminal": 122,
"recentWilsonLowerBound": 0.10870072431592571,
"running": 7,
"selectionWeight": 0.2370414116369001,
"selectionWeight": 0.21646278260591087,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 20.166666666666668,
"waiting": 9230
"throughputPerHour": 20.333333333333332,
"waiting": 9250
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 39.10569105691057,
"backlogHours": 37.336787564766844,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -557,197 +557,197 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 24,
"recentSuccessRate": 0.06504065040650407,
"recentTerminal": 369,
"recentWilsonLowerBound": 0.044092991505070275,
"recentSuccess": 22,
"recentSuccessRate": 0.05699481865284974,
"recentTerminal": 386,
"recentWilsonLowerBound": 0.03793620535056797,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 61.5,
"waiting": 2405
"throughputPerHour": 64.33333333333333,
"waiting": 2402
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 106.80866425992781,
"backlogHours": 100.23050847457628,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.1936779334589081,
"qualityFactor": 0.13633432948524812,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 39,
"recentSuccessRate": 0.1407942238267148,
"recentTerminal": 277,
"recentWilsonLowerBound": 0.10473344792429565,
"running": 7,
"selectionWeight": 0.25178131349658056,
"recentSuccess": 37,
"recentSuccessRate": 0.12542372881355932,
"recentTerminal": 295,
"recentWilsonLowerBound": 0.09238019524417321,
"running": 8,
"selectionWeight": 0.17723462833082257,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 46.166666666666664,
"waiting": 4931
"throughputPerHour": 49.166666666666664,
"waiting": 4928
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 3841.4399999999996,
"backlogHours": 4364.727272727273,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 2.5,
"queueFactor": 0.8045771219807961,
"queueWeight": 0.8045771219807961,
"recentSuccess": 13,
"recentSuccessRate": 0.52,
"recentTerminal": 25,
"recentWilsonLowerBound": 0.3349821795314731,
"queueFactor": 0.7907452278423037,
"queueWeight": 0.7907452278423037,
"recentSuccess": 12,
"recentSuccessRate": 0.5454545454545454,
"recentTerminal": 22,
"recentWilsonLowerBound": 0.3465947328904156,
"running": 2,
"selectionWeight": 2.01144280495199,
"selectionWeight": 1.9768630696057592,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 4.166666666666667,
"waiting": 16006
"throughputPerHour": 3.6666666666666665,
"waiting": 16004
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 594.5607476635514,
"backlogHours": 579.0,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.4127304604676082,
"queueFactor": 1.0644183485182297,
"queueWeight": 1.0644183485182297,
"recentSuccess": 23,
"recentSuccessRate": 0.21495327102803738,
"recentTerminal": 107,
"recentWilsonLowerBound": 0.14772120660505175,
"qualityFactor": 0.4498586899253121,
"queueFactor": 1.0706027680107695,
"queueWeight": 1.0706027680107695,
"recentSuccess": 25,
"recentSuccessRate": 0.22727272727272727,
"recentTerminal": 110,
"recentWilsonLowerBound": 0.15894521607203976,
"running": 8,
"selectionWeight": 0.43931787511410003,
"selectionWeight": 0.4816199586477376,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.833333333333332,
"waiting": 10603
"throughputPerHour": 18.333333333333332,
"waiting": 10615
},
"MetaX_c-500": {
"available": true,
"backlogHours": 684.375,
"backlogHours": 684.125,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.5284246032567707,
"queueFactor": 1.0421918364275486,
"queueWeight": 1.0421918364275486,
"recentSuccess": 23,
"recentSuccessRate": 0.23958333333333334,
"qualityFactor": 0.5499209007051823,
"queueFactor": 1.0441426297529484,
"queueWeight": 1.0441426297529484,
"recentSuccess": 24,
"recentSuccessRate": 0.25,
"recentTerminal": 96,
"recentWilsonLowerBound": 0.16528105536529172,
"recentWilsonLowerBound": 0.17413849417796742,
"running": 4,
"selectionWeight": 0.5507198076816726,
"selectionWeight": 0.574195855418419,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 16.0,
"waiting": 10950
"waiting": 10946
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 2007.0461538461536,
"backlogHours": 1976.5454545454545,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 2.223347318928749,
"queueFactor": 0.886866363402042,
"queueWeight": 0.886866363402042,
"qualityFactor": 1.9896056161874065,
"queueFactor": 0.8905209183965654,
"queueWeight": 0.8905209183965654,
"recentSuccess": 28,
"recentSuccessRate": 0.4307692307692308,
"recentTerminal": 65,
"recentWilsonLowerBound": 0.31759267537345776,
"recentSuccessRate": 0.42424242424242425,
"recentTerminal": 66,
"recentWilsonLowerBound": 0.31242322955377905,
"running": 4,
"selectionWeight": 1.9718119513180197,
"selectionWeight": 1.7717854205741737,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 10.833333333333334,
"waiting": 21743
"throughputPerHour": 11.0,
"waiting": 21742
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 5234.333333333333,
"backlogHours": 5234.0,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.262887733112932,
"queueFactor": 0.7680908314669678,
"queueWeight": 0.7680908314669678,
"qualityFactor": 1.1716669634159769,
"queueFactor": 0.7694937357765416,
"queueWeight": 0.7694937357765416,
"recentSuccess": 8,
"recentSuccessRate": 0.4444444444444444,
"recentTerminal": 18,
"recentWilsonLowerBound": 0.24559231101389123,
"running": 2,
"selectionWeight": 0.970012488976146,
"selectionWeight": 0.9015903887649165,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 3.0,
"waiting": 15703
"waiting": 15702
},
"Vastai_va16": {
"available": true,
"backlogHours": 1573.418181818182,
"backlogHours": 1699.4117647058824,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.06339684947274064,
"queueFactor": 0.9198460818773394,
"queueWeight": 0.9198460818773394,
"recentSuccess": 7,
"recentSuccessRate": 0.12727272727272726,
"recentTerminal": 55,
"recentWilsonLowerBound": 0.06304130417480196,
"qualityFactor": 0.10402027436196304,
"queueFactor": 0.9109307305557416,
"queueWeight": 0.9109307305557416,
"recentSuccess": 8,
"recentSuccessRate": 0.1568627450980392,
"recentTerminal": 51,
"recentWilsonLowerBound": 0.08169125888021325,
"running": 16,
"selectionWeight": 0.05831534359086795,
"selectionWeight": 0.09475526451715166,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 9.166666666666666,
"waiting": 14423
"throughputPerHour": 8.5,
"waiting": 14445
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 845.4690265486727,
"backlogHours": 860.7027027027027,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 0.8083612858986949,
"queueFactor": 1.0096646057989307,
"queueWeight": 1.0096646057989307,
"qualityFactor": 0.7812802606287282,
"queueFactor": 1.0087932588693656,
"queueWeight": 1.0087932588693656,
"recentSuccess": 31,
"recentSuccessRate": 0.2743362831858407,
"recentTerminal": 113,
"recentWilsonLowerBound": 0.2005129306491566,
"recentSuccessRate": 0.27927927927927926,
"recentTerminal": 111,
"recentWilsonLowerBound": 0.20427535700815577,
"running": 6,
"selectionWeight": 0.8161737790700225,
"selectionWeight": 0.788150260209962,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.833333333333332,
"throughputPerHour": 18.5,
"waiting": 15923
}
},
"queueAttemptedAt": "2026-09-21T09:54:22.177158+00:00",
"queueAttemptedAt": "2026-09-21T10:05:23.787223+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-21T09:54:22.177158+00:00",
"queueUpdatedAt": "2026-09-21T10:05:23.787223+00:00",
"supportedGpus": [
"Vastai_va16",
"Kunlunxin_p-800",

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-09-21T10:04:10.177617+00:00",
"catalogUpdatedAt": "2026-09-21T10:05:23.787223+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-09-21T10:04:10.177617+00:00",
"generatedAt": "2026-09-21T10:05:23.787223+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6520,6 +6520,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-09-21T10:04:10.177617+00:00",
"taskTreeUpdatedAt": "2026-09-21T10:05:23.787223+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T10:01:40.168106+00:00",
"lastSyncTime": "2026-09-21T10:01:37.498157+00:00",
"generatedAt": "2026-09-21T10:05:14.010504+00:00",
"lastSyncTime": "2026-09-21T10:05:11.455599+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2961,11 +2961,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 21,
"failureBreakdown": {
"ambiguous_runtime": 30,
"ambiguous_runtime": 31,
"framework_architecture_unsupported": 21,
"platform_infrastructure": 1
},
"failureCount": 52,
"failureCount": 53,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
@@ -2975,8 +2975,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 52,
"unresolvedFailureCount": 30
"total": 53,
"unresolvedFailureCount": 31
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 201,
@@ -5446,7 +5446,7 @@
"decisionSuccessRate": 0.0317,
"decisionTotal": 63,
"failureBreakdown": {
"ambiguous_runtime": 52,
"ambiguous_runtime": 53,
"context_length": 1,
"framework_architecture_unsupported": 56,
"memory_capacity": 1,
@@ -5455,18 +5455,18 @@
"tokenizer_compatibility": 1,
"参数/模板问题": 19
},
"failureCount": 133,
"failureRate": 0.9852,
"failureCount": 134,
"failureRate": 0.9853,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 2,
"successRate": 0.0148,
"total": 135,
"unresolvedFailureCount": 71
"successRate": 0.0147,
"total": 136,
"unresolvedFailureCount": 72
}
},
"generatedAt": "2026-09-21T10:01:40.113915+00:00",
"generatedAt": "2026-09-21T10:05:13.998246+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 91,
@@ -5500,7 +5500,7 @@
"decisionSuccessRate": 0.164,
"decisionTotal": 378,
"failureBreakdown": {
"ambiguous_runtime": 162,
"ambiguous_runtime": 163,
"context_length": 1,
"framework_architecture_unsupported": 175,
"memory_capacity": 18,
@@ -5512,15 +5512,15 @@
"日志缺失": 14,
"验证失败": 175
},
"failureCount": 931,
"failureCount": 932,
"failureRate": 0.9376,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 62,
"successRate": 0.0624,
"total": 993,
"unresolvedFailureCount": 613
"total": 994,
"unresolvedFailureCount": 614
},
"Biren_166m": {
"attributableFailureCount": 182,
@@ -7008,9 +7008,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "phi3",
@@ -7022,8 +7022,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen2|compressed-tensors": {
"attributableFailureCount": 0,
@@ -15427,12 +15427,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 7,
"ambiguous_runtime": 6,
"context_length": 1,
"framework_architecture_unsupported": 1,
"参数/模板问题": 4
},
"failureCount": 13,
"failureCount": 12,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
@@ -15444,8 +15444,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 13,
"unresolvedFailureCount": 11
"total": 12,
"unresolvedFailureCount": 10
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 1,
@@ -15506,9 +15506,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1,
"platform_infrastructure": 1
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": "2026-09-20T03:41:42.246689+00:00",
@@ -15520,8 +15521,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
"total": 2,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 2,
@@ -16305,31 +16306,6 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-21T04:15:31.153931+00:00",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mpt|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -16431,6 +16407,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-21T10:05:11.455599+00:00",
"modelType": "phi3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen2|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -21365,6 +21366,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 31,
"modelType": "phi3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -33470,15 +33495,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16208,
"totalRecords": 16391,
"terminalRecords": 16209,
"totalRecords": 16392,
"totals": {
"attributableFailureCount": 5864,
"decisionFailureRate": 0.8615,
"decisionSuccessRate": 0.1385,
"decisionTotal": 6807,
"failureBreakdown": {
"ambiguous_runtime": 3910,
"ambiguous_runtime": 3911,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
@@ -33494,31 +33519,31 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15265,
"failureCount": 15266,
"failureRate": 0.9418,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 924,
"successCount": 943,
"successRate": 0.0582,
"total": 16208,
"unresolvedFailureCount": 8477
"total": 16209,
"unresolvedFailureCount": 8478
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Kunlunxin_p-800 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 Biren_166m 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_bi-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 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 Cambricon_mlu-370-x4 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-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 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。",
"组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Sunrise_pt-200-x1|vllm_fix_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 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -33558,6 +33583,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16391,
"summarizedRecords": 16392,
"version": 1
}

View File

@@ -266,6 +266,7 @@
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T01:08:25.664296+00:00", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-20T03:25:32.245630+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969647", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T02:15:17.867315+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-20T03:25:31.995522+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969637", "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", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T08:25:31.485651+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430847031, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430847031}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:25:31.991647+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969636", "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_tokenizer_patch", "lastSyncTime": "2026-09-21T10:05:11.455599+00:00", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2263018168, "estimatedRequiredGiB": 2.532, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 2265562651, "modelscopeLicense": "llama2", "modelscopeParams": 3821079552, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2265562651}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:25:24.247231+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969623", "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": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:42:10.765050+00:00", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463599, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463599}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:25:24.240446+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969618", "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": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:42:10.765072+00:00", "modelId": "OpenBMB/BitCPM-CANN-8B", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16370604914, "estimatedRequiredGiB": 18.305, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm", "modelscopeFileSize": 16378634956, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm", "library:pytorch", "library:transformer", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16378634956}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:25:24.238793+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969621", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T01:08:25.664243+00:00", "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-20T03:24:23.636965+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969578", "taskType": "text-generation", "verifyResult": null}
@@ -297,4 +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", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T22:43:47.754995+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21930054875, "estimatedRequiredGiB": 24.532, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21950415614, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6024588416, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21950415614}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:18.238662+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969344", "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_tokenizer_patch", "lastSyncTime": "2026-09-21T05:07:16.468537+00:00", "modelId": "IntervitensInc/kek_mk3", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3289069288, "estimatedRequiredGiB": 3.683, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 3295875324, "modelscopeLicense": null, "modelscopeParams": 1644515328, "modelscopeTags": ["model_type:stablelm", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3295875324}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:18.153275+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969341", "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_tokenizer_patch", "lastSyncTime": "2026-09-20T22:43:47.754892+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248516007, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248516007}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:18.150831+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969343", "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_tokenizer_patch", "lastSyncTime": "2026-09-21T04:15:31.153931+00:00", "modelId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6711252896, "estimatedRequiredGiB": 7.503, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 6713123803, "modelscopeLicense": "mit", "modelscopeParams": 3355609600, "modelscopeTags": ["license:mit", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6713123803}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:18.145895+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969340", "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