state: generation 6643 (cycle)

This commit is contained in:
2026-09-13 09:42:21 +00:00
parent ba0a8c956b
commit 873b76ca87
9 changed files with 2184 additions and 2182 deletions

View File

@@ -1323,17 +1323,19 @@
"architectures": [
"spark2_5forcausallm"
],
"evidenceCount": 1,
"expiresAt": "2026-10-12T10:55:22+00:00",
"evidenceCount": 2,
"expiresAt": "2026-10-13T09:33:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-12T10:55:22+00:00",
"latestFailureAt": "2026-09-13T09:33:21+00:00",
"latestSuccessfulAt": null,
"matchType": "architectures",
"modelType": null,
"sourceModelIds": [
"XHToken/Spark-X2.5-1.7B",
"XHToken/Spark-X2.5-4B"
],
"sourceTaskIds": [
"4557415",
"4554931"
],
"targetGpu": "Vastai_va16",
@@ -1473,7 +1475,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-13T09:39:22.596416+00:00",
"generatedAt": "2026-09-13T09:42:20.048448+00:00",
"summary": {
"activeBlockCount": 74,
"byGpuFramework": {

View File

@@ -59,7 +59,7 @@
"5": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 481,
"listingErrors": 482,
"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": "2026-09-13T09:39:22.573274+00:00",
"updatedAt": "2026-09-13T09:42:20.025387+00:00",
"version": 1
}

View File

@@ -416,121 +416,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-13T09:37:29.958482+00:00",
"generatedAt": "2026-09-13T09:40:34.607667+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 1045.7014925373135,
"backlogHours": 1053.7894736842104,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.1139452217765893,
"queueFactor": 0.979465828273807,
"queueWeight": 0.979465828273807,
"qualityFactor": 2.0908241940973498,
"queueFactor": 0.9828265669283466,
"queueWeight": 0.9828265669283466,
"recentSuccess": 49,
"recentSuccessRate": 0.3656716417910448,
"recentTerminal": 134,
"recentWilsonLowerBound": 0.2889258915556576,
"running": 9,
"selectionWeight": 2.070537107572864,
"recentSuccessRate": 0.3684210526315789,
"recentTerminal": 133,
"recentWilsonLowerBound": 0.2912079039326208,
"running": 8,
"selectionWeight": 2.054917564735425,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.333333333333332,
"waiting": 23354
"throughputPerHour": 22.166666666666668,
"waiting": 23359
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1200.9635036496352,
"backlogHours": 1175.5285714285715,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.4585029851746647,
"queueFactor": 0.9593365180168295,
"queueWeight": 0.9593365180168295,
"recentSuccess": 53,
"recentSuccessRate": 0.38686131386861317,
"recentTerminal": 137,
"recentWilsonLowerBound": 0.3094526414865042,
"running": 10,
"selectionWeight": 2.358531693331444,
"qualityFactor": 2.5,
"queueFactor": 0.9668408410404088,
"queueWeight": 0.9668408410404088,
"recentSuccess": 55,
"recentSuccessRate": 0.39285714285714285,
"recentTerminal": 140,
"recentWilsonLowerBound": 0.3158538021545772,
"running": 8,
"selectionWeight": 2.4171021026010218,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.833333333333332,
"waiting": 27422
"throughputPerHour": 23.333333333333332,
"waiting": 27429
},
"Biren_166m": {
"available": true,
"backlogHours": 152.93333333333334,
"backlogHours": 156.47727272727272,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.48599927281944877,
"qualityFactor": 0.5718312882140526,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 36,
"recentSuccessRate": 0.2,
"recentTerminal": 180,
"recentWilsonLowerBound": 0.14810790208917995,
"running": 9,
"selectionWeight": 0.6317990546652834,
"recentSuccess": 38,
"recentSuccessRate": 0.2159090909090909,
"recentTerminal": 176,
"recentWilsonLowerBound": 0.1615368169280793,
"running": 8,
"selectionWeight": 0.7433806746782684,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 30.0,
"waiting": 4588
"throughputPerHour": 29.333333333333332,
"waiting": 4590
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1069.9024390243903,
"backlogHours": 1083.6296296296296,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.4540962804457446,
"queueFactor": 0.9761101334851875,
"queueWeight": 0.9761101334851875,
"recentSuccess": 18,
"recentSuccessRate": 0.21951219512195122,
"recentTerminal": 82,
"recentWilsonLowerBound": 0.1436067129787513,
"qualityFactor": 0.387636195665024,
"queueFactor": 0.9787185847287733,
"queueWeight": 0.9787185847287733,
"recentSuccess": 17,
"recentSuccessRate": 0.20987654320987653,
"recentTerminal": 81,
"recentWilsonLowerBound": 0.1353706249001661,
"running": 7,
"selectionWeight": 0.4432479809210229,
"selectionWeight": 0.3793867488109181,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 13.666666666666666,
"waiting": 14622
"throughputPerHour": 13.5,
"waiting": 14629
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 398.64179104477614,
"backlogHours": 384.2589928057554,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.2576372712308628,
"queueFactor": 1.1319129385841924,
"queueWeight": 1.1319129385841924,
"recentSuccess": 22,
"recentSuccessRate": 0.16417910447761194,
"recentTerminal": 134,
"recentWilsonLowerBound": 0.11099240521268962,
"qualityFactor": 0.2911763823713282,
"queueFactor": 1.1433951872101595,
"queueWeight": 1.1433951872101595,
"recentSuccess": 24,
"recentSuccessRate": 0.17266187050359713,
"recentTerminal": 139,
"recentWilsonLowerBound": 0.11886086838811098,
"running": 7,
"selectionWeight": 0.29162296076773847,
"selectionWeight": 0.3329296742326418,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.333333333333332,
"waiting": 8903
"throughputPerHour": 23.166666666666668,
"waiting": 8902
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 38.0545905707196,
"backlogHours": 39.16836734693878,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -539,197 +539,197 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 21,
"recentSuccessRate": 0.052109181141439205,
"recentTerminal": 403,
"recentWilsonLowerBound": 0.034331864965854955,
"recentSuccess": 19,
"recentSuccessRate": 0.04846938775510204,
"recentTerminal": 392,
"recentWilsonLowerBound": 0.031246049236934997,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 67.16666666666667,
"waiting": 2556
"throughputPerHour": 65.33333333333333,
"waiting": 2559
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 87.62105263157895,
"backlogHours": 87.57894736842105,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.25721888862951714,
"qualityFactor": 0.25004024350319004,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 42,
"recentSuccessRate": 0.14736842105263157,
"recentTerminal": 285,
"recentWilsonLowerBound": 0.11091044030216608,
"running": 3,
"selectionWeight": 0.3343845552183723,
"running": 5,
"selectionWeight": 0.32505231655414707,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 47.5,
"waiting": 4162
"waiting": 4160
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2761.235294117647,
"backlogHours": 2760.176470588235,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.1020010934048483,
"queueFactor": 0.8467104809152709,
"queueWeight": 0.8467104809152709,
"qualityFactor": 1.0712456740788119,
"queueFactor": 0.8506471248581964,
"queueWeight": 0.8506471248581964,
"recentSuccess": 12,
"recentSuccessRate": 0.35294117647058826,
"recentTerminal": 34,
"recentWilsonLowerBound": 0.2148771489529607,
"running": 2,
"selectionWeight": 0.9330758757659735,
"selectionWeight": 0.9112520526719219,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 5.666666666666667,
"waiting": 15647
"waiting": 15641
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 775.5348837209302,
"backlogHours": 823.925925925926,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.9970860703257117,
"queueFactor": 1.0243780110333651,
"queueWeight": 1.0243780110333651,
"qualityFactor": 1.1128452573976175,
"queueFactor": 1.0197805876156778,
"queueWeight": 1.0197805876156778,
"recentSuccess": 25,
"recentSuccessRate": 0.29069767441860467,
"recentTerminal": 86,
"recentWilsonLowerBound": 0.20532437829302616,
"recentSuccessRate": 0.30864197530864196,
"recentTerminal": 81,
"recentWilsonLowerBound": 0.2186306293369854,
"running": 7,
"selectionWeight": 1.0213930455493265,
"selectionWeight": 1.1348579905142626,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 14.333333333333334,
"waiting": 11116
"throughputPerHour": 13.5,
"waiting": 11123
},
"MetaX_c-500": {
"available": true,
"backlogHours": 736.5806451612904,
"backlogHours": 736.9677419354839,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.8330090119239464,
"queueFactor": 1.032327276638415,
"queueWeight": 1.032327276638415,
"qualityFactor": 0.8097608122466377,
"queueFactor": 1.0369855245966724,
"queueWeight": 1.0369855245966724,
"recentSuccess": 25,
"recentSuccessRate": 0.26881720430107525,
"recentTerminal": 93,
"recentWilsonLowerBound": 0.18921182161860808,
"running": 6,
"selectionWeight": 0.8599379246947045,
"running": 4,
"selectionWeight": 0.8397102406854071,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 15.5,
"waiting": 11417
"waiting": 11423
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 2247.3103448275865,
"backlogHours": 2247.9310344827586,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 2.5,
"queueFactor": 0.8732749256114725,
"queueWeight": 0.8732749256114725,
"qualityFactor": 2.430228246800074,
"queueFactor": 0.8772482658776884,
"queueWeight": 0.8772482658776884,
"recentSuccess": 25,
"recentSuccessRate": 0.43103448275862066,
"recentTerminal": 58,
"recentWilsonLowerBound": 0.3118160080083492,
"running": 4,
"selectionWeight": 2.183187314028681,
"selectionWeight": 2.1319135151923403,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 9.666666666666666,
"waiting": 21724
"waiting": 21730
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 3654.25,
"backlogHours": 3654.5,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.7438313553551519,
"queueFactor": 0.8118591873578813,
"queueWeight": 0.8118591873578813,
"recentSuccess": 8,
"recentSuccessRate": 0.3333333333333333,
"qualityFactor": 1.0355376620082566,
"queueFactor": 0.8155785044861604,
"queueWeight": 0.8155785044861604,
"recentSuccess": 9,
"recentSuccessRate": 0.375,
"recentTerminal": 24,
"recentWilsonLowerBound": 0.17971978688379645,
"recentWilsonLowerBound": 0.21159133433631455,
"running": 2,
"selectionWeight": 0.603886319689945,
"selectionWeight": 0.844562257719789,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 4.0,
"waiting": 14617
"waiting": 14618
},
"Vastai_va16": {
"available": true,
"backlogHours": 1144.258064516129,
"backlogHours": 1145.8064516129032,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.4263566828923155,
"queueFactor": 0.9663219636149533,
"queueWeight": 0.9663219636149533,
"recentSuccess": 14,
"recentSuccessRate": 0.22580645161290322,
"qualityFactor": 0.5034991857031401,
"queueFactor": 0.9705619839109918,
"queueWeight": 0.9705619839109918,
"recentSuccess": 15,
"recentSuccessRate": 0.24193548387096775,
"recentTerminal": 62,
"recentWilsonLowerBound": 0.13955057139297952,
"running": 17,
"selectionWeight": 0.41199782701286025,
"recentWilsonLowerBound": 0.1524576368094854,
"running": 16,
"selectionWeight": 0.48867716857360854,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 10.333333333333334,
"waiting": 11824
"waiting": 11840
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 683.7575757575758,
"backlogHours": 706.3125,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 1.3951876370120064,
"queueFactor": 1.0439149696666226,
"queueWeight": 1.0439149696666226,
"qualityFactor": 1.4561916870297145,
"queueFactor": 1.043615286868718,
"queueWeight": 1.043615286868718,
"recentSuccess": 32,
"recentSuccessRate": 0.32323232323232326,
"recentTerminal": 99,
"recentWilsonLowerBound": 0.23919862826396276,
"running": 7,
"selectionWeight": 1.4564572597706356,
"recentSuccessRate": 0.3333333333333333,
"recentTerminal": 96,
"recentWilsonLowerBound": 0.24705550523810998,
"running": 6,
"selectionWeight": 1.519703905195358,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 16.5,
"waiting": 11282
"throughputPerHour": 16.0,
"waiting": 11301
}
},
"queueAttemptedAt": "2026-09-13T09:28:55.064795+00:00",
"queueAttemptedAt": "2026-09-13T09:40:34.607667+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-13T09:28:55.064795+00:00",
"queueUpdatedAt": "2026-09-13T09:40:34.607667+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": "2026-09-13T08:31:13.164252+00:00",
"lastSyncTime": "2026-09-13T08:31:12.943798+00:00",
"generatedAt": "2026-09-13T09:40:23.888574+00:00",
"lastSyncTime": "2026-09-13T09:40:23.641563+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1327,17 +1327,19 @@
"architectures": [
"spark2_5forcausallm"
],
"evidenceCount": 1,
"expiresAt": "2026-10-12T10:55:22+00:00",
"evidenceCount": 2,
"expiresAt": "2026-10-13T09:33:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-12T10:55:22+00:00",
"latestFailureAt": "2026-09-13T09:33:21+00:00",
"latestSuccessfulAt": null,
"matchType": "architectures",
"modelType": null,
"sourceModelIds": [
"XHToken/Spark-X2.5-1.7B",
"XHToken/Spark-X2.5-4B"
],
"sourceTaskIds": [
"4557415",
"4554931"
],
"targetGpu": "Vastai_va16",
@@ -2328,17 +2330,17 @@
"unresolvedFailureCount": 2
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 48,
"attributableFailureCount": 49,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 48,
"decisionTotal": 49,
"failureBreakdown": {
"ambiguous_runtime": 61,
"framework_architecture_unsupported": 42,
"framework_architecture_unsupported": 43,
"memory_capacity": 1,
"model_load": 5
},
"failureCount": 109,
"failureCount": 110,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2348,7 +2350,7 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 109,
"total": 110,
"unresolvedFailureCount": 61
},
"hygon_k100-ai|llamacpp|text-generation": {
@@ -2508,14 +2510,14 @@
"unresolvedFailureCount": 875
},
"vllm": {
"attributableFailureCount": 295,
"decisionFailureRate": 0.9899,
"decisionSuccessRate": 0.0101,
"decisionTotal": 298,
"attributableFailureCount": 296,
"decisionFailureRate": 0.99,
"decisionSuccessRate": 0.01,
"decisionTotal": 299,
"failureBreakdown": {
"ambiguous_runtime": 201,
"backend_operator": 34,
"framework_architecture_unsupported": 208,
"framework_architecture_unsupported": 209,
"memory_capacity": 6,
"model_load": 26,
"platform_infrastructure": 1,
@@ -2524,14 +2526,14 @@
"tokenizer_compatibility": 7,
"参数/模板问题": 24
},
"failureCount": 521,
"failureCount": 522,
"failureRate": 0.9943,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0057,
"total": 524,
"total": 525,
"unresolvedFailureCount": 225
},
"vllm-mlu": {
@@ -2636,7 +2638,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-13T08:31:13.160082+00:00",
"generatedAt": "2026-09-13T09:40:23.884789+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 31,
@@ -2920,26 +2922,26 @@
"unresolvedFailureCount": 43
},
"Vastai_va16": {
"attributableFailureCount": 51,
"decisionFailureRate": 0.7969,
"decisionSuccessRate": 0.2031,
"decisionTotal": 64,
"attributableFailureCount": 52,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 65,
"failureBreakdown": {
"ambiguous_runtime": 63,
"framework_architecture_unsupported": 44,
"framework_architecture_unsupported": 45,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 13,
"验证失败": 130
},
"failureCount": 257,
"failureRate": 0.9519,
"failureCount": 258,
"failureRate": 0.952,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.0481,
"total": 270,
"successRate": 0.048,
"total": 271,
"unresolvedFailureCount": 206
},
"hygon_k100-ai": {
@@ -5000,21 +5002,21 @@
"unresolvedFailureCount": 1
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 16,
"framework_architecture_unsupported": 4
"ambiguous_runtime": 15,
"framework_architecture_unsupported": 5
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-13T08:31:12.943798+00:00",
"lastTerminalAt": "2026-09-13T09:40:23.641563+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -5023,7 +5025,7 @@
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 16
"unresolvedFailureCount": 15
},
"hygon_k100-ai|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -7481,17 +7483,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1769,
"totalRecords": 1856,
"terminalRecords": 1770,
"totalRecords": 1857,
"totals": {
"attributableFailureCount": 515,
"decisionFailureRate": 0.8972,
"decisionSuccessRate": 0.1028,
"decisionTotal": 574,
"attributableFailureCount": 516,
"decisionFailureRate": 0.8974,
"decisionSuccessRate": 0.1026,
"decisionTotal": 575,
"failureBreakdown": {
"ambiguous_runtime": 415,
"backend_operator": 43,
"framework_architecture_unsupported": 324,
"framework_architecture_unsupported": 325,
"memory_capacity": 11,
"model_load": 73,
"platform_infrastructure": 4,
@@ -7501,20 +7503,21 @@
"参数/模板问题": 103,
"验证失败": 673
},
"failureCount": 1710,
"failureRate": 0.9666,
"failureCount": 1711,
"failureRate": 0.9667,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 59,
"successRate": 0.0334,
"total": 1769,
"successRate": 0.0333,
"total": 1770,
"unresolvedFailureCount": 1191
},
"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。",
@@ -7523,7 +7526,6 @@
"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。",
@@ -7546,6 +7548,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1856,
"summarizedRecords": 1857,
"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", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-13T09:40:23.641563+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T09:33:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4557415", "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": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-13T08:31:12.943798+00:00", "modelId": "RWKV/RWKV7-2.9B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T08:23:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4609080", "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", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "", "lastSyncTime": "2026-09-13T06:31:13.105179+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T06:27:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610370", "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": "2026-09-13T05:58:35.516166+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T05:53:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4558021", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T16:44:50.902809+00:00", "modelId": "OpenBMB/BitCPM-CANN-8B", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16370604914, "estimatedRequiredGiB": 18.305, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm", "modelscopeFileSize": 16378634920, "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": "2026-09-09T12:30:12.314907+00:00", "targetGpu": "Vastai_va16", "taskId": "4740401", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-09T12:08:11.431365+00:00", "modelId": "neuralmagic/starcoder2-3b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T12:07:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080603", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-09T11:43:37.216601+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-09T11:43:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4460828", "taskType": "text-generation", "verifyResult": 1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-09T11:43:37.216624+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-09T11:41:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4460430", "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": "9fb62762fb42cce6081bebde080c4c99d9209d1469088ad35c4b2a3f132d3b02",
".modelhub_state/architecture_history_backfill.json": "2eed09834eecc94da6bc725d17f9babab67ad0ae381b2b754b67deeaff6d40e4",
".modelhub_state/market_intelligence.json": "a89860de30858fff811b1699dbe4e456a885e9e940f3a7c74a9fc669c9335392",
".modelhub_state/official_capabilities.json": "7de30b88629a90b7caaa4428c2e8d51db476d3caaa1e6ee79748477ca759cd79",
".modelhub_state/outcome_checkpoint.json": "a6ff44834e4288cc4f5a9348f67330f858499aa58939bced4a5662f75fe5816b",
".modelhub_state/architecture_compatibility_blacklist.json": "9ff13f2193a5577193f230f4c3900464463f3be3e8bb5b34ed7ab596c4526a06",
".modelhub_state/architecture_history_backfill.json": "6cec6326f5446aa3b6d0bb363e7a5bcd23df475fd9b863d77e7f63ddb905367d",
".modelhub_state/market_intelligence.json": "65ed943c66013588d5a48d9f72a6f79305176222700795db5415ba513f5f1fe4",
".modelhub_state/official_capabilities.json": "c7a66b066d6ca288d535a427156de31b7ce6faa4564081e8aa20ac2a303b04f4",
".modelhub_state/outcome_checkpoint.json": "96405d855a2a95a4d84eb43cca03b3e2bea042142ef1c8da6829d6598a85dbe4",
".modelhub_state/queue_cleanup_latest.json": "ead6d4dadaa1cc97a064674e6cd6e82e9bc551fa8eef7e0d699d7fc494f51834",
".modelhub_state/recent_outcomes.jsonl": "570acc6faa28525e6b155425e48ac9197ab5d43f5107182c148edf0086c4ed87",
".modelhub_state/recovery_active_tasks.jsonl": "c374fdce3d56a0cb631936aae4397399c35872fcc74ccdb640293b289a0fccc1",
".modelhub_state/recovery_intents.jsonl": "2abcff028e99dbb813faced1af55a810696a952010413d363606528ad0325c96",
".modelhub_state/recent_outcomes.jsonl": "93e80e0dfefc0d7c521a75d2eae3a6d22cfcb3033462a2e0b28a22629a4be629",
".modelhub_state/recovery_active_tasks.jsonl": "bd78dfac310af82ed93399652c1be1a7b9cf57774e7cfdeba4fe54e16d83671a",
".modelhub_state/recovery_intents.jsonl": "9a01cbbf81c831fd15b8c5185546231188eeb4721d4258336dbbd0cddd5d951a",
".modelhub_state/routing_intelligence.json": "8bbc9c8a0b34a70e0b79e5c4089e16cf94def46a7292fb8d7d5c9890b2433a99",
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
"ledger/submissions.jsonl": "1a43aba60f5a20c4003652cc68d94d682c68a27eb62b4140cbdbf822a121d016",
"outcomes/submissions.jsonl": "b41282e90b445956e11184fac94c9cc3e805749e8e9eb05ae4ff79d53e15a030"
},
"generation": 6642,
"generation": 6643,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-13T09:39:22.666357+00:00",
"updatedAt": "2026-09-13T09:42:21.056357+00:00",
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
}