state: generation 6099 (cycle)

This commit is contained in:
2026-09-12 07:46:34 +00:00
parent 9799a210c0
commit 2aa388e3e4
9 changed files with 2377 additions and 2377 deletions

View File

@@ -1364,7 +1364,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-12T07:43:40.171344+00:00",
"generatedAt": "2026-09-12T07:46:34.130895+00:00",
"summary": {
"activeBlockCount": 69,
"byGpuFramework": {

View File

@@ -59,7 +59,7 @@
"5": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 438,
"listingErrors": 439,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0,
"mode": "incremental_decision_only",
"nextAccountIndex": 5,
"nextAccountIndex": 6,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-12T07:43:40.148056+00:00",
"updatedAt": "2026-09-12T07:46:34.103106+00:00",
"version": 1
}

View File

@@ -416,121 +416,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-12T07:41:46.392005+00:00",
"generatedAt": "2026-09-12T07:44:48.714690+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 900.9230769230769,
"backlogHours": 889.367088607595,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.8915034260303232,
"queueFactor": 0.9899371017057625,
"queueWeight": 0.9899371017057625,
"recentSuccess": 54,
"recentSuccessRate": 0.34615384615384615,
"recentTerminal": 156,
"recentWilsonLowerBound": 0.27600507509161326,
"running": 8,
"selectionWeight": 0.8825323177252158,
"qualityFactor": 0.9898523314737215,
"queueFactor": 0.9937717867629584,
"queueWeight": 0.9937717867629584,
"recentSuccess": 56,
"recentSuccessRate": 0.35443037974683544,
"recentTerminal": 158,
"recentWilsonLowerBound": 0.28410808213585914,
"running": 10,
"selectionWeight": 0.9836873200801204,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 26.0,
"waiting": 23424
"throughputPerHour": 26.333333333333332,
"waiting": 23420
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1021.4906832298137,
"backlogHours": 1041.0,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.8689794500818647,
"queueFactor": 0.971461506476151,
"queueWeight": 0.971461506476151,
"recentSuccess": 55,
"recentSuccessRate": 0.3416149068322981,
"recentTerminal": 161,
"recentWilsonLowerBound": 0.2728132581070264,
"qualityFactor": 0.7792542066681183,
"queueFactor": 0.9705797178306391,
"queueWeight": 0.9705797178306391,
"recentSuccess": 51,
"recentSuccessRate": 0.3227848101265823,
"recentTerminal": 158,
"recentWilsonLowerBound": 0.2548357131436929,
"running": 8,
"selectionWeight": 0.8441800856733456,
"selectionWeight": 0.7563283280262808,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 26.833333333333332,
"waiting": 27410
"throughputPerHour": 26.333333333333332,
"waiting": 27413
},
"Biren_166m": {
"available": true,
"backlogHours": 158.94797687861274,
"backlogHours": 159.87209302325581,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.23041349517100687,
"queueFactor": 1.2841699629708436,
"queueWeight": 1.2841699629708436,
"recentSuccess": 35,
"recentSuccessRate": 0.2023121387283237,
"recentTerminal": 173,
"recentWilsonLowerBound": 0.14921733969871423,
"running": 8,
"selectionWeight": 0.29589008956173457,
"qualityFactor": 0.2809873760641823,
"queueFactor": 1.2855320894027866,
"queueWeight": 1.2855320894027866,
"recentSuccess": 37,
"recentSuccessRate": 0.21511627906976744,
"recentTerminal": 172,
"recentWilsonLowerBound": 0.16028767638500904,
"running": 9,
"selectionWeight": 0.3612182886475948,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 28.833333333333332,
"throughputPerHour": 28.666666666666668,
"waiting": 4583
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1077.75,
"backlogHours": 1051.3902439024391,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.26001895663934654,
"queueFactor": 0.9636804605921052,
"queueWeight": 0.9636804605921052,
"recentSuccess": 19,
"recentSuccessRate": 0.2375,
"recentTerminal": 80,
"recentWilsonLowerBound": 0.15764551183088746,
"running": 7,
"selectionWeight": 0.2505751878968841,
"qualityFactor": 0.29470208746560983,
"queueFactor": 0.9691348915214029,
"queueWeight": 0.9691348915214029,
"recentSuccess": 20,
"recentSuccessRate": 0.24390243902439024,
"recentTerminal": 82,
"recentWilsonLowerBound": 0.1637976208028234,
"running": 8,
"selectionWeight": 0.28560607556711476,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 13.333333333333334,
"waiting": 14370
"throughputPerHour": 13.666666666666666,
"waiting": 14369
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 418.2047244094488,
"backlogHours": 438.94214876033055,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.5006824908525629,
"queueFactor": 1.1107144397786952,
"queueWeight": 1.1107144397786952,
"recentSuccess": 36,
"recentSuccessRate": 0.28346456692913385,
"recentTerminal": 127,
"recentWilsonLowerBound": 0.21233709936296657,
"qualityFactor": 0.5016236040593347,
"queueFactor": 1.1048103351234893,
"queueWeight": 1.1048103351234893,
"recentSuccess": 34,
"recentSuccessRate": 0.2809917355371901,
"recentTerminal": 121,
"recentWilsonLowerBound": 0.2085956290113622,
"running": 7,
"selectionWeight": 0.5561152723343061,
"selectionWeight": 0.5541989421066461,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 21.166666666666668,
"throughputPerHour": 20.166666666666668,
"waiting": 8852
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 44.26315789473684,
"backlogHours": 43.042735042735046,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -539,197 +539,197 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 11,
"recentSuccessRate": 0.03216374269005848,
"recentTerminal": 342,
"recentWilsonLowerBound": 0.01805272147959169,
"recentSuccess": 12,
"recentSuccessRate": 0.03418803418803419,
"recentTerminal": 351,
"recentWilsonLowerBound": 0.019663050672568818,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 57.0,
"waiting": 2523
"throughputPerHour": 58.5,
"waiting": 2518
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 78.5050505050505,
"backlogHours": 65.71267605633803,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.21674310397682828,
"qualityFactor": 0.14455270381840615,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 55,
"recentSuccessRate": 0.18518518518518517,
"recentTerminal": 297,
"recentWilsonLowerBound": 0.14512604946176072,
"running": 4,
"selectionWeight": 0.28176603516987675,
"recentSuccess": 54,
"recentSuccessRate": 0.15211267605633802,
"recentTerminal": 355,
"recentWilsonLowerBound": 0.11849247596716095,
"running": 1,
"selectionWeight": 0.187918514963928,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 49.5,
"waiting": 3886
"throughputPerHour": 59.166666666666664,
"waiting": 3888
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2652.514285714286,
"backlogHours": 2509.297297297297,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.48005439005441686,
"queueFactor": 0.8419030801075725,
"queueWeight": 0.8419030801075725,
"qualityFactor": 0.4390166277184363,
"queueFactor": 0.8505816382485641,
"queueWeight": 0.8505816382485641,
"recentSuccess": 12,
"recentSuccessRate": 0.34285714285714286,
"recentTerminal": 35,
"recentWilsonLowerBound": 0.20831495282688925,
"recentSuccessRate": 0.32432432432432434,
"recentTerminal": 37,
"recentWilsonLowerBound": 0.1963307782081548,
"running": 2,
"selectionWeight": 0.4041592696059756,
"selectionWeight": 0.3734194824231075,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 5.833333333333333,
"waiting": 15473
"throughputPerHour": 6.166666666666667,
"waiting": 15474
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 833.2405063291139,
"backlogHours": 854.6493506493506,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.26760814876377,
"queueFactor": 1.0016020436748048,
"queueWeight": 1.0016020436748048,
"qualityFactor": 0.2956602730762017,
"queueFactor": 0.9997251690161039,
"queueWeight": 0.9997251690161039,
"recentSuccess": 19,
"recentSuccessRate": 0.24050632911392406,
"recentTerminal": 79,
"recentWilsonLowerBound": 0.15972056887933211,
"recentSuccessRate": 0.24675324675324675,
"recentTerminal": 77,
"recentWilsonLowerBound": 0.1640394822845753,
"running": 7,
"selectionWeight": 0.2680368687058232,
"selectionWeight": 0.29557901647245316,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 13.166666666666666,
"waiting": 10971
"throughputPerHour": 12.833333333333334,
"waiting": 10968
},
"MetaX_c-500": {
"available": true,
"backlogHours": 656.7692307692308,
"backlogHours": 696.795918367347,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.44726062077430856,
"queueFactor": 1.03800354901774,
"queueWeight": 1.03800354901774,
"qualityFactor": 0.5341062374795755,
"queueFactor": 1.0308203446505737,
"queueWeight": 1.0308203446505737,
"recentSuccess": 29,
"recentSuccessRate": 0.27884615384615385,
"recentTerminal": 104,
"recentWilsonLowerBound": 0.20172158008187036,
"running": 4,
"selectionWeight": 0.4642581116996098,
"recentSuccessRate": 0.29591836734693877,
"recentTerminal": 98,
"recentWilsonLowerBound": 0.21463049371609197,
"running": 5,
"selectionWeight": 0.5505675757987172,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.333333333333332,
"waiting": 11384
"throughputPerHour": 16.333333333333332,
"waiting": 11381
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 2123.3,
"backlogHours": 2159.7966101694915,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 2.5,
"queueFactor": 0.8704805148627496,
"queueWeight": 0.8704805148627496,
"recentSuccess": 34,
"recentSuccessRate": 0.5666666666666667,
"recentTerminal": 60,
"recentWilsonLowerBound": 0.4410321465469486,
"queueFactor": 0.8699351776068366,
"queueWeight": 0.8699351776068366,
"recentSuccess": 33,
"recentSuccessRate": 0.559322033898305,
"recentTerminal": 59,
"recentWilsonLowerBound": 0.43289130270422654,
"running": 4,
"selectionWeight": 2.176201287156874,
"selectionWeight": 2.1748379440170913,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 10.0,
"waiting": 21233
"throughputPerHour": 9.833333333333334,
"waiting": 21238
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 2609.6363636363635,
"backlogHours": 2692.125,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.11030473581380777,
"queueFactor": 0.8439636832459588,
"queueWeight": 0.8439636832459588,
"qualityFactor": 0.12331800736432094,
"queueFactor": 0.8416558335956469,
"queueWeight": 0.8416558335956469,
"recentSuccess": 7,
"recentSuccessRate": 0.21212121212121213,
"recentTerminal": 33,
"recentWilsonLowerBound": 0.10675886566436177,
"recentSuccessRate": 0.21875,
"recentTerminal": 32,
"recentWilsonLowerBound": 0.11023696931531854,
"running": 2,
"selectionWeight": 0.09309319111689364,
"selectionWeight": 0.10379132028557167,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 5.5,
"waiting": 14353
"throughputPerHour": 5.333333333333333,
"waiting": 14358
},
"Vastai_va16": {
"available": true,
"backlogHours": 851.12,
"backlogHours": 851.52,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 1.7057970750510343,
"queueFactor": 0.9984173945701551,
"queueWeight": 0.9984173945701551,
"recentSuccess": 36,
"recentSuccessRate": 0.48,
"qualityFactor": 1.647642587018629,
"queueFactor": 1.0002754112859538,
"queueWeight": 1.0002754112859538,
"recentSuccess": 35,
"recentSuccessRate": 0.4666666666666667,
"recentTerminal": 75,
"recentWilsonLowerBound": 0.37068921756788065,
"recentWilsonLowerBound": 0.35815509458811656,
"running": 16,
"selectionWeight": 1.703097471337845,
"selectionWeight": 1.648096366382312,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.5,
"waiting": 10639
"waiting": 10644
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 635.4216867469879,
"backlogHours": 615.0697674418604,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 2.1542033925668194,
"queueFactor": 1.0431612670177985,
"queueWeight": 1.0431612670177985,
"qualityFactor": 2.062061056528722,
"queueFactor": 1.0502922574626528,
"queueWeight": 1.0502922574626528,
"recentSuccess": 43,
"recentSuccessRate": 0.5180722891566265,
"recentTerminal": 83,
"recentWilsonLowerBound": 0.41217569697662826,
"recentSuccessRate": 0.5,
"recentTerminal": 86,
"recentWilsonLowerBound": 0.39660790465524204,
"running": 6,
"selectionWeight": 2.247181540404043,
"selectionWeight": 2.165766762087374,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 13.833333333333334,
"waiting": 8790
"throughputPerHour": 14.333333333333334,
"waiting": 8816
}
},
"queueAttemptedAt": "2026-09-12T07:32:44.113975+00:00",
"queueAttemptedAt": "2026-09-12T07:44:48.714690+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-12T07:32:44.113975+00:00",
"queueUpdatedAt": "2026-09-12T07:44:48.714690+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": "2026-09-12T07:35:30.629329+00:00",
"lastSyncTime": "2026-09-12T07:35:30.412992+00:00",
"generatedAt": "2026-09-12T07:44:41.124320+00:00",
"lastSyncTime": "2026-09-12T07:44:40.913717+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1545,30 +1545,30 @@
"unresolvedFailureCount": 34
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 26,
"decisionFailureRate": 0.963,
"decisionSuccessRate": 0.037,
"decisionTotal": 27,
"attributableFailureCount": 27,
"decisionFailureRate": 0.9643,
"decisionSuccessRate": 0.0357,
"decisionTotal": 28,
"failureBreakdown": {
"ambiguous_runtime": 26,
"backend_operator": 4,
"framework_architecture_unsupported": 18,
"framework_architecture_unsupported": 19,
"memory_capacity": 1,
"model_load": 2,
"tokenizer_compatibility": 1,
"验证失败": 27
},
"failureCount": 79,
"failureRate": 0.9875,
"failureCount": 80,
"failureRate": 0.9877,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0125,
"successRate": 0.0123,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 80,
"total": 81,
"unresolvedFailureCount": 53
},
"Biren_166m|vllm|text-generation": {
@@ -2370,14 +2370,14 @@
"unresolvedFailureCount": 7
},
"unknown": {
"attributableFailureCount": 142,
"decisionFailureRate": 0.7358,
"decisionSuccessRate": 0.2642,
"decisionTotal": 193,
"attributableFailureCount": 143,
"decisionFailureRate": 0.7371,
"decisionSuccessRate": 0.2629,
"decisionTotal": 194,
"failureBreakdown": {
"ambiguous_runtime": 130,
"backend_operator": 4,
"framework_architecture_unsupported": 90,
"framework_architecture_unsupported": 91,
"memory_capacity": 5,
"model_load": 40,
"platform_infrastructure": 1,
@@ -2385,14 +2385,14 @@
"参数/模板问题": 59,
"验证失败": 673
},
"failureCount": 1005,
"failureRate": 0.9517,
"failureCount": 1006,
"failureRate": 0.9518,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 51,
"successRate": 0.0483,
"total": 1056,
"successRate": 0.0482,
"total": 1057,
"unresolvedFailureCount": 862
},
"vllm": {
@@ -2524,7 +2524,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T07:35:30.625131+00:00",
"generatedAt": "2026-09-12T07:44:41.120022+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2575,27 +2575,27 @@
"unresolvedFailureCount": 222
},
"Biren_166m": {
"attributableFailureCount": 27,
"decisionFailureRate": 0.9643,
"decisionSuccessRate": 0.0357,
"decisionTotal": 28,
"attributableFailureCount": 28,
"decisionFailureRate": 0.9655,
"decisionSuccessRate": 0.0345,
"decisionTotal": 29,
"failureBreakdown": {
"ambiguous_runtime": 26,
"backend_operator": 4,
"framework_architecture_unsupported": 18,
"framework_architecture_unsupported": 19,
"memory_capacity": 1,
"model_load": 3,
"tokenizer_compatibility": 1,
"验证失败": 27
},
"failureCount": 80,
"failureRate": 0.9877,
"failureCount": 81,
"failureRate": 0.9878,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0123,
"total": 81,
"successRate": 0.0122,
"total": 82,
"unresolvedFailureCount": 53
},
"Cambricon_mlu-370-x4": {
@@ -4305,23 +4305,23 @@
"unresolvedFailureCount": 18
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 9,
"backend_operator": 4,
"framework_architecture_unsupported": 1,
"framework_architecture_unsupported": 2,
"model_load": 1
},
"failureCount": 15,
"failureCount": 16,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T13:55:40.785120+00:00",
"lastTerminalAt": "2026-09-12T07:44:40.913717+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4329,7 +4329,7 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 15,
"total": 16,
"unresolvedFailureCount": 9
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -7185,17 +7185,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1697,
"totalRecords": 1784,
"terminalRecords": 1698,
"totalRecords": 1785,
"totals": {
"attributableFailureCount": 466,
"decisionFailureRate": 0.8927,
"decisionSuccessRate": 0.1073,
"decisionTotal": 522,
"attributableFailureCount": 467,
"decisionFailureRate": 0.8929,
"decisionSuccessRate": 0.1071,
"decisionTotal": 523,
"failureBreakdown": {
"ambiguous_runtime": 397,
"backend_operator": 41,
"framework_architecture_unsupported": 285,
"framework_architecture_unsupported": 286,
"memory_capacity": 11,
"model_load": 68,
"platform_infrastructure": 4,
@@ -7205,20 +7205,21 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1641,
"failureCount": 1642,
"failureRate": 0.967,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 56,
"successRate": 0.033,
"total": 1697,
"total": 1698,
"unresolvedFailureCount": 1171
},
"warnings": [
"GPU Ascend_910-b3 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
@@ -7227,7 +7228,6 @@
"GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 hygon_k100-ai|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b4|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7249,6 +7249,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1784,
"summarizedRecords": 1785,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"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", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "", "lastSyncTime": "2026-09-12T07:44:40.913717+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T07:39:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610364", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-12T07:35:30.412992+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T07:33:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4547660", "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": "2026-09-12T06:59:46.603354+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Lite-Preview-Distill-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T06:55:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079259", "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": "2026-09-12T06:34:23.913239+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-2507-Gemini-3-Pro-Preview-High-Reasoning-Distill-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T06:29:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079116", "taskType": "text-generation", "verifyResult": -1}
@@ -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", "framework": "vllm", "lastSyncTime": "2026-09-08T17:33:37.506924+00:00", "modelId": "amd/Phi-3.5-mini-instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T17:25:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079902", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T17:33:37.506936+00:00", "modelId": "amd/Phi-4-mini-instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T17:25:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079101", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T17:15:48.506951+00:00", "modelId": "amd/Phi-4-mini-instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T17:15:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4080076", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T16:13:44.313888+00:00", "modelId": "amd/Phi-4-mini-instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T16:07:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080088", "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": "9498ba87e64ea5dd42a60bb039d9361a4fefa83c0bb2eedc2bd0124f32fb4967",
".modelhub_state/architecture_history_backfill.json": "bb1bfc7ccdb1a22e9f82508c68335a188c69c5ea058d4491e354bf9e400415ff",
".modelhub_state/market_intelligence.json": "9e829fe3111b60a588b3fbaea7529bc960f8fe7bc9913155ae9a9d9aa00496c3",
".modelhub_state/official_capabilities.json": "ceb9d6571ac69299e76840001f37f630ef5ba636bde55d90e86013d34efd9f68",
".modelhub_state/outcome_checkpoint.json": "54e92ba38e7a37f0e921c0c3aba4fa915c38f95fe46f7f43b64d95043ae26f61",
".modelhub_state/architecture_compatibility_blacklist.json": "36317aebf9cff4a1dca16fa91cfa24ba1ef0737d9b0210fd5d67a218d6fd4153",
".modelhub_state/architecture_history_backfill.json": "dcbd219f9322affe461987325156c94ccf857ef70f4445ee049326313c5b9de9",
".modelhub_state/market_intelligence.json": "890b18e307eff173bc276ef20a5197f382bb008f48f41e63ae6df0799cd583f1",
".modelhub_state/official_capabilities.json": "4e1d78612a58da852601c0866883f3e83c8b33ac84362f36063587dab0a4214b",
".modelhub_state/outcome_checkpoint.json": "58120d7a2d7f554080f2a652045ef3450521d93c37a5553c8e8a6543a6318680",
".modelhub_state/queue_cleanup_latest.json": "90e4dcfb9592532e113083f4f6101f91569aa480a0f7e2747a042a0aba314e96",
".modelhub_state/recent_outcomes.jsonl": "670bc5419d24a2357be52a61a6f872e44886f55cb4a01e794c1b8aa699541fe5",
".modelhub_state/recovery_active_tasks.jsonl": "811e7cee7df63391b241f2bdfb643924f3682885998bc0b64fb177ded63b65df",
".modelhub_state/recovery_intents.jsonl": "262062234d5d43365494e5322cf66b6c2aaed151744362c2e7f98c8daf34f798",
".modelhub_state/recent_outcomes.jsonl": "f3cc5d8f9057e0a9d8465ae9c98a3e559877190100f5af0bb2557b81f37f95fd",
".modelhub_state/recovery_active_tasks.jsonl": "1efd27af1c118e4773905165b83ac6d7dd383cfc45654b897a03c5b35e92899e",
".modelhub_state/recovery_intents.jsonl": "42c58612391fac99f8adf3308ad1fe48b439015f4a20f4de0128cb77b163380c",
".modelhub_state/routing_intelligence.json": "2855b5a64db2097d238c63bc8e3c9527429b37e5743e8c4067b04a47b96bf6d5",
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
"ledger/submissions.jsonl": "fce27fb2f360720694402834960f8bd72b07cc9cdb7df41af2ff877c48deb61a",
"outcomes/submissions.jsonl": "c1fb4ffb5f8805609635341d14f8a0d312d7065898c795a6d23cb2b73c0d9814"
},
"generation": 6098,
"generation": 6099,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-12T07:43:40.260183+00:00",
"updatedAt": "2026-09-12T07:46:34.873914+00:00",
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
}