state: generation 5242 (cycle)

This commit is contained in:
2026-09-10 15:50:09 +00:00
parent ac49c9c2f7
commit d7a1963c8f
9 changed files with 2349 additions and 2349 deletions

View File

@@ -1311,7 +1311,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T15:48:13.786319+00:00",
"generatedAt": "2026-09-10T15:50:08.273850+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -27,7 +27,7 @@
"11": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 372,
"listingErrors": 373,
"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": "2026-09-10T15:48:13.761788+00:00",
"updatedAt": "2026-09-10T15:50:08.250135+00:00",
"version": 1
}

View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-09-10T15:32:30.904683+00:00",
"communityAttemptedAt": "2026-09-10T15:48:18.068558+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-09-10T15:32:30.904683+00:00",
"communityUpdatedAt": "2026-09-10T15:48:18.068558+00:00",
"frameworkAttemptedAt": "2026-09-10T15:27:32.924657+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -416,121 +416,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T15:46:34.191476+00:00",
"generatedAt": "2026-09-10T15:48:18.068558+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 1052.5263157894735,
"backlogHours": 1044.761194029851,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.4959487127459472,
"queueFactor": 0.950827479451698,
"queueWeight": 0.950827479451698,
"recentSuccess": 55,
"recentSuccessRate": 0.41353383458646614,
"recentTerminal": 133,
"recentWilsonLowerBound": 0.33341222192525477,
"qualityFactor": 1.5105741149813945,
"queueFactor": 0.9578714420980382,
"queueWeight": 0.9578714420980382,
"recentSuccess": 56,
"recentSuccessRate": 0.417910447761194,
"recentTerminal": 134,
"recentWilsonLowerBound": 0.33782807660784847,
"running": 8,
"selectionWeight": 1.422389143929241,
"selectionWeight": 1.446935805913196,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.166666666666668,
"waiting": 23331
"throughputPerHour": 22.333333333333332,
"waiting": 23333
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1002.7682926829269,
"backlogHours": 967.3411764705883,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.1030093912341048,
"queueFactor": 0.9577597462033183,
"queueWeight": 0.9577597462033183,
"recentSuccess": 59,
"recentSuccessRate": 0.3597560975609756,
"recentTerminal": 164,
"recentWilsonLowerBound": 0.2902873490000026,
"qualityFactor": 1.1769251419314453,
"queueFactor": 0.9689978851457486,
"queueWeight": 0.9689978851457486,
"recentSuccess": 63,
"recentSuccessRate": 0.37058823529411766,
"recentTerminal": 170,
"recentWilsonLowerBound": 0.30159636659650746,
"running": 8,
"selectionWeight": 1.0564179946082528,
"selectionWeight": 1.1404379735064305,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 27.333333333333332,
"waiting": 27409
"throughputPerHour": 28.333333333333332,
"waiting": 27408
},
"Biren_166m": {
"available": true,
"backlogHours": 132.8140703517588,
"backlogHours": 132.57,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.26274861339635686,
"queueFactor": 1.2970301036893808,
"queueWeight": 1.2970301036893808,
"recentSuccess": 40,
"recentSuccessRate": 0.20100502512562815,
"recentTerminal": 199,
"recentWilsonLowerBound": 0.15122676607480934,
"qualityFactor": 0.23875019247501558,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 39,
"recentSuccessRate": 0.195,
"recentTerminal": 200,
"recentWilsonLowerBound": 0.1460544156450576,
"running": 8,
"selectionWeight": 0.34079286127771774,
"selectionWeight": 0.31037525021752027,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 33.166666666666664,
"waiting": 4405
"throughputPerHour": 33.333333333333336,
"waiting": 4419
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1059.1499999999999,
"backlogHours": 1021.2289156626506,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.12326334086102188,
"queueFactor": 0.9499331606699173,
"queueWeight": 0.9499331606699173,
"recentSuccess": 14,
"recentSuccessRate": 0.175,
"recentTerminal": 80,
"recentWilsonLowerBound": 0.10720538981609888,
"qualityFactor": 0.1349527910746232,
"queueFactor": 0.9611503200987329,
"queueWeight": 0.9611503200987329,
"recentSuccess": 15,
"recentSuccessRate": 0.18072289156626506,
"recentTerminal": 83,
"recentWilsonLowerBound": 0.1126926689223679,
"running": 7,
"selectionWeight": 0.11709193497884388,
"selectionWeight": 0.12970991833959153,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 13.333333333333334,
"waiting": 14122
"throughputPerHour": 13.833333333333334,
"waiting": 14127
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 405.9230769230769,
"backlogHours": 396.9924812030075,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.38589654486084696,
"queueFactor": 1.0969077572115458,
"queueWeight": 1.0969077572115458,
"recentSuccess": 32,
"recentSuccessRate": 0.24615384615384617,
"recentTerminal": 130,
"recentWilsonLowerBound": 0.18009686195009067,
"qualityFactor": 0.42138232782885615,
"queueFactor": 1.1074966931731056,
"queueWeight": 1.1074966931731056,
"recentSuccess": 34,
"recentSuccessRate": 0.2556390977443609,
"recentTerminal": 133,
"recentWilsonLowerBound": 0.18908882696541707,
"running": 7,
"selectionWeight": 0.4232929135389963,
"selectionWeight": 0.4666795346320437,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 21.666666666666668,
"waiting": 8795
"throughputPerHour": 22.166666666666668,
"waiting": 8800
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 72.70408163265307,
"backlogHours": 74.25,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -540,196 +540,196 @@
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 15,
"recentSuccessRate": 0.07653061224489796,
"recentTerminal": 196,
"recentWilsonLowerBound": 0.046923968553331995,
"recentSuccessRate": 0.078125,
"recentTerminal": 192,
"recentWilsonLowerBound": 0.04791348285135001,
"running": 1,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 32.666666666666664,
"waiting": 2375
"throughputPerHour": 32.0,
"waiting": 2376
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 131.9655172413793,
"backlogHours": 138.36144578313252,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.08331423831369847,
"queueFactor": 1.2982777058387625,
"queueWeight": 1.2982777058387625,
"recentSuccess": 23,
"recentSuccessRate": 0.13218390804597702,
"recentTerminal": 174,
"recentWilsonLowerBound": 0.08972051418842682,
"qualityFactor": 0.08063910327167675,
"queueFactor": 1.2972017224722014,
"queueWeight": 1.2972017224722014,
"recentSuccess": 22,
"recentSuccessRate": 0.13253012048192772,
"recentTerminal": 166,
"recentWilsonLowerBound": 0.0891749459521856,
"running": 1,
"selectionWeight": 0.10816501818161238,
"selectionWeight": 0.10460518366263281,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 29.0,
"waiting": 3827
"throughputPerHour": 27.666666666666668,
"waiting": 3828
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 1973.2340425531916,
"backlogHours": 1974.2553191489362,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.33710417600401693,
"queueFactor": 0.8652864026625077,
"queueWeight": 0.8652864026625077,
"qualityFactor": 0.33068779929555303,
"queueFactor": 0.8706613840552417,
"queueWeight": 0.8706613840552417,
"recentSuccess": 13,
"recentSuccessRate": 0.2765957446808511,
"recentTerminal": 47,
"recentWilsonLowerBound": 0.16936405991152934,
"running": 2,
"selectionWeight": 0.29169165977702466,
"selectionWeight": 0.2879170970248482,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 7.833333333333333,
"waiting": 15457
"waiting": 15465
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 656.9090909090909,
"backlogHours": 677.5625,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.3728006188353344,
"queueFactor": 1.0204949930699954,
"queueWeight": 1.0204949930699954,
"qualityFactor": 0.3923786979135713,
"queueFactor": 1.0221564562706613,
"queueWeight": 1.0221564562706613,
"recentSuccess": 25,
"recentSuccessRate": 0.25252525252525254,
"recentTerminal": 99,
"recentWilsonLowerBound": 0.17729258424187705,
"recentSuccessRate": 0.2604166666666667,
"recentTerminal": 96,
"recentWilsonLowerBound": 0.18305777843717666,
"running": 7,
"selectionWeight": 0.3804411649348545,
"selectionWeight": 0.40107241937543237,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 16.5,
"waiting": 10839
"throughputPerHour": 16.0,
"waiting": 10841
},
"MetaX_c-500": {
"available": true,
"backlogHours": 555.6585365853658,
"backlogHours": 551.0806451612902,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.4026505132042215,
"queueFactor": 1.0464427427637062,
"queueWeight": 1.0464427427637062,
"recentSuccess": 31,
"recentSuccessRate": 0.25203252032520324,
"recentTerminal": 123,
"recentWilsonLowerBound": 0.18360980012600733,
"qualityFactor": 0.35560024512156896,
"queueFactor": 1.0543322881367032,
"queueWeight": 1.0543322881367032,
"recentSuccess": 30,
"recentSuccessRate": 0.24193548387096775,
"recentTerminal": 124,
"recentWilsonLowerBound": 0.17504889877225968,
"running": 4,
"selectionWeight": 0.42135070741263947,
"selectionWeight": 0.3749208201009963,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 20.5,
"waiting": 11391
"throughputPerHour": 20.666666666666668,
"waiting": 11389
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1878.441176470588,
"backlogHours": 1936.3636363636363,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.9878212979600234,
"queueFactor": 0.8716999661281176,
"queueWeight": 0.8716999661281176,
"recentSuccess": 26,
"recentSuccessRate": 0.38235294117647056,
"recentTerminal": 68,
"recentWilsonLowerBound": 0.2760927529710457,
"qualityFactor": 0.933854915847343,
"queueFactor": 0.8731960101634612,
"queueWeight": 0.8731960101634612,
"recentSuccess": 25,
"recentSuccessRate": 0.3787878787878788,
"recentTerminal": 66,
"recentWilsonLowerBound": 0.271492715804161,
"running": 4,
"selectionWeight": 0.8610837919723856,
"selectionWeight": 0.8154383865894347,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 11.333333333333334,
"waiting": 21289
"throughputPerHour": 11.0,
"waiting": 21300
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 3852.0,
"backlogHours": 3853.909090909091,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.9343788600784148,
"queueFactor": 0.7826790826031609,
"queueWeight": 0.7826790826031609,
"qualityFactor": 0.9165940707419076,
"queueFactor": 0.787543516499178,
"queueWeight": 0.787543516499178,
"recentSuccess": 10,
"recentSuccessRate": 0.45454545454545453,
"recentTerminal": 22,
"recentWilsonLowerBound": 0.26920014432004846,
"running": 2,
"selectionWeight": 0.7313187890099608,
"selectionWeight": 0.7218577176743782,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 3.6666666666666665,
"waiting": 14124
"waiting": 14131
},
"Vastai_va16": {
"available": true,
"backlogHours": 847.1830985915493,
"backlogHours": 890.735294117647,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.6394477119029198,
"queueFactor": 0.9822908002037513,
"queueWeight": 0.9822908002037513,
"qualityFactor": 0.6934668090196909,
"queueFactor": 0.9810643199042673,
"queueWeight": 0.9810643199042673,
"recentSuccess": 23,
"recentSuccessRate": 0.323943661971831,
"recentTerminal": 71,
"recentWilsonLowerBound": 0.22657056384385282,
"recentSuccessRate": 0.3382352941176471,
"recentTerminal": 68,
"recentWilsonLowerBound": 0.23714091243789054,
"running": 16,
"selectionWeight": 0.6281236046135769,
"selectionWeight": 0.6803355433670856,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 11.833333333333334,
"waiting": 10025
"throughputPerHour": 11.333333333333334,
"waiting": 10095
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 476.2568807339449,
"backlogHours": 489.90566037735846,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 2.5,
"queueFactor": 1.0709285079589086,
"queueWeight": 1.0709285079589086,
"recentSuccess": 56,
"recentSuccessRate": 0.5137614678899083,
"recentTerminal": 109,
"recentWilsonLowerBound": 0.4210714006745304,
"queueFactor": 1.0731067132760987,
"queueWeight": 1.0731067132760987,
"recentSuccess": 55,
"recentSuccessRate": 0.5188679245283019,
"recentTerminal": 106,
"recentWilsonLowerBound": 0.4247656250772565,
"running": 6,
"selectionWeight": 2.6773212698972717,
"selectionWeight": 2.682766783190247,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.166666666666668,
"waiting": 8652
"throughputPerHour": 17.666666666666668,
"waiting": 8655
}
},
"queueAttemptedAt": "2026-09-10T15:37:46.140578+00:00",
"queueAttemptedAt": "2026-09-10T15:48:18.068558+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-10T15:37:46.140578+00:00",
"queueUpdatedAt": "2026-09-10T15:48:18.068558+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": "2026-09-10T15:27:10.017950+00:00",
"lastSyncTime": "2026-09-10T15:27:09.820580+00:00",
"generatedAt": "2026-09-10T15:48:18.040272+00:00",
"lastSyncTime": "2026-09-10T15:48:17.745945+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1472,13 +1472,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 37,
"failureBreakdown": {
"ambiguous_runtime": 31,
"ambiguous_runtime": 33,
"framework_architecture_unsupported": 33,
"memory_capacity": 1,
"repository_structure": 1,
"tokenizer_compatibility": 2
},
"failureCount": 68,
"failureCount": 70,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1488,8 +1488,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 68,
"unresolvedFailureCount": 31
"total": 70,
"unresolvedFailureCount": 33
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 26,
@@ -2321,7 +2321,7 @@
"decisionSuccessRate": 0.0083,
"decisionTotal": 241,
"failureBreakdown": {
"ambiguous_runtime": 172,
"ambiguous_runtime": 174,
"backend_operator": 32,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2332,15 +2332,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 24
},
"failureCount": 436,
"failureRate": 0.9954,
"failureCount": 438,
"failureRate": 0.9955,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 2,
"successRate": 0.0046,
"total": 438,
"unresolvedFailureCount": 196
"successRate": 0.0045,
"total": 440,
"unresolvedFailureCount": 198
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T15:27:10.014184+00:00",
"generatedAt": "2026-09-10T15:48:18.035267+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2474,7 +2474,7 @@
"decisionSuccessRate": 0.05,
"decisionTotal": 40,
"failureBreakdown": {
"ambiguous_runtime": 32,
"ambiguous_runtime": 34,
"framework_architecture_unsupported": 33,
"memory_capacity": 1,
"model_load": 1,
@@ -2483,15 +2483,15 @@
"参数/模板问题": 11,
"验证失败": 175
},
"failureCount": 256,
"failureRate": 0.9922,
"failureCount": 258,
"failureRate": 0.9923,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0078,
"total": 258,
"unresolvedFailureCount": 218
"successRate": 0.0077,
"total": 260,
"unresolvedFailureCount": 220
},
"Biren_166m": {
"attributableFailureCount": 27,
@@ -4033,21 +4033,21 @@
"unresolvedFailureCount": 19
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 16,
"framework_architecture_unsupported": 4
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 2
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T11:31:55.305639+00:00",
"lastTerminalAt": "2026-09-10T15:48:17.745912+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4056,23 +4056,23 @@
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 16
"unresolvedFailureCount": 18
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 7,
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 8,
"decisionFailureRate": 0.8571,
"decisionSuccessRate": 0.1429,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 10,
"backend_operator": 4,
"framework_architecture_unsupported": 2,
"framework_architecture_unsupported": 1,
"model_load": 1
},
"failureCount": 17,
"failureRate": 0.9444,
"failureCount": 16,
"failureRate": 0.9412,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T13:55:40.785120+00:00",
@@ -4080,10 +4080,10 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0556,
"successRate": 0.0588,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 18,
"total": 17,
"unresolvedFailureCount": 10
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -7121,15 +7121,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1600,
"totalRecords": 1687,
"terminalRecords": 1602,
"totalRecords": 1689,
"totals": {
"attributableFailureCount": 419,
"decisionFailureRate": 0.8896,
"decisionSuccessRate": 0.1104,
"decisionTotal": 471,
"failureBreakdown": {
"ambiguous_runtime": 355,
"ambiguous_runtime": 357,
"backend_operator": 39,
"framework_architecture_unsupported": 272,
"memory_capacity": 11,
@@ -7141,31 +7141,30 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1548,
"failureCount": 1550,
"failureRate": 0.9675,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 52,
"successRate": 0.0325,
"total": 1600,
"unresolvedFailureCount": 1126
"total": 1602,
"unresolvedFailureCount": 1128
},
"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 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 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。",
@@ -7180,10 +7179,11 @@
"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": 1687,
"summarizedRecords": 1689,
"version": 1
}

View File

@@ -1,3 +1,5 @@
{"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": "2026-09-10T15:48:17.745912+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T15:43:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471922", "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": "2026-09-10T15:48:17.745945+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T15:43:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471921", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T13:55:40.785120+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T13:47:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610380", "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": "2026-09-10T13:30:05.632388+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T13:23:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496944", "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": "2026-09-10T13:23:06.708419+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T13:19:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496965", "taskType": "text-generation", "verifyResult": -1}
@@ -296,5 +298,3 @@
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-09-08T03:52:50.094582+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T03:33:22+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4478318", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-08T03:17:11.503480+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T03:15:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4482682", "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": "2026-09-08T03:17:11.503517+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T03:11:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4487542", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T03:17:11.503505+00:00", "modelId": "nightmedia/Qwen3-4B-Element8-Eva-Heretic-mxfp4-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T03:05:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079944", "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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-08T03:04:50.903963+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T03:01:23+00:00", "targetGpu": "Biren_166m", "taskId": "4610405", "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": "3ccfda1540a111ffe21ebf89d30d747c8ab224dc4040b382739c0b6fd1b99a4d",
".modelhub_state/architecture_history_backfill.json": "977532e88b873ec90bc38c808ed0d9069591a6a299400e57fe2156b0b4be1641",
".modelhub_state/market_intelligence.json": "109bb30544d81e0e7cf274973150cdc6d2595a7ded9f199146ee4ba4170d959b",
".modelhub_state/official_capabilities.json": "ed0930445d8c8f67339e6fef6ef023d3fea0f946ed4f683e375003b84433da8c",
".modelhub_state/outcome_checkpoint.json": "58029266bb92b932d377336c9fccb3b6ebe1a82cdd97af970a66ed989f9c8b82",
".modelhub_state/architecture_compatibility_blacklist.json": "06ea17c6c75b7e0ae49c79b821a6ba89452f010580e1c261356930be2f488421",
".modelhub_state/architecture_history_backfill.json": "fd80af1f7e15e1f5551c74976c9e9af62f71626b2a69396771d64c25ceaa49db",
".modelhub_state/market_intelligence.json": "d10e05aabaa3882dba969c036522166ec20c106b0628037874d1743b87a57094",
".modelhub_state/official_capabilities.json": "a573d6a5a5daf19434b517f1ae7ebfc0bb077561420a0517d7584c7954347fef",
".modelhub_state/outcome_checkpoint.json": "ca8829a87164af09127727f6dfb8984cd62c7f3aa4237736893f7009a6070187",
".modelhub_state/queue_cleanup_latest.json": "c4c0c2f745124fbabf68b2aa082c5aeee0f45dbb41d40369e8064e674a33adbe",
".modelhub_state/recent_outcomes.jsonl": "9e9cb1dd0f2d6f58384a1234e9beec7ab6c7ae3a92d636f21215b319e8b90f3a",
".modelhub_state/recovery_active_tasks.jsonl": "25236c152f1a4887cf064f250d81b7dab44b49a12cb9cba7373f50851d92188e",
".modelhub_state/recovery_intents.jsonl": "05539d773a62a7e745988b4abfa5db0421acce80c3b952a9531eb7180bc0b7c1",
".modelhub_state/recent_outcomes.jsonl": "2d9c6f0ff443f4eee5090318f02dcc2cc42792959df656ead9cafc98c5ebaf0d",
".modelhub_state/recovery_active_tasks.jsonl": "93c1ac093940dcf307c3e07beadf0c6531631bf3a534b33cb591b2ed9ae2ac31",
".modelhub_state/recovery_intents.jsonl": "e144dc1d248e807589d01635285b3974678fe0d958233e5f0df726a824030793",
".modelhub_state/routing_intelligence.json": "07412703d74f144906be81443e9a62c63c16be09020d45073f303d32bb738925",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
"ledger/submissions.jsonl": "f33b133e8b25d698947530491a83aadf25705b3248f050bf303ed51744c603b5",
"outcomes/submissions.jsonl": "77be1a4fc6a7c7b12ea68a3994f9f2730126081209a2fe599940d37f0cbdba1c"
},
"generation": 5241,
"generation": 5242,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T15:48:15.042026+00:00",
"updatedAt": "2026-09-10T15:50:09.220526+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42"
}