state: generation 6338 (cycle)

This commit is contained in:
2026-09-12 19:26:28 +00:00
parent 9bd6228930
commit b76b7bcac8
9 changed files with 2206 additions and 2203 deletions

View File

@@ -161,17 +161,19 @@
"ascend_910-b3|vllm|text-generation|model_type:rwkv7": {
"architectureSignature": "model_type:rwkv7",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-09T18:31:21+00:00",
"evidenceCount": 2,
"expiresAt": "2026-10-12T19:13:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-09T18:31:21+00:00",
"latestFailureAt": "2026-09-12T19:13:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "rwkv7",
"sourceModelIds": [
"RWKV/RWKV7-2.9B-20260805",
"RWKV/RWKV7-1.5B-20260805"
],
"sourceTaskIds": [
"4583368",
"4579389"
],
"targetGpu": "Ascend_910-b3",
@@ -1427,7 +1429,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-12T19:22:44.542949+00:00",
"generatedAt": "2026-09-12T19:26:27.478643+00:00",
"summary": {
"activeBlockCount": 72,
"byGpuFramework": {

View File

@@ -35,7 +35,7 @@
"2": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 457,
"listingErrors": 458,
"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": 2,
"nextAccountIndex": 3,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-12T19:22:44.517205+00:00",
"updatedAt": "2026-09-12T19:26:27.455128+00:00",
"version": 1
}

View File

@@ -416,121 +416,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-12T19:20:47.840514+00:00",
"generatedAt": "2026-09-12T19:23:53.051554+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 978.8811188811189,
"backlogHours": 978.6293706293707,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.2814100297653126,
"queueFactor": 1.0022525213422586,
"queueWeight": 1.0022525213422586,
"recentSuccess": 50,
"recentSuccessRate": 0.34965034965034963,
"qualityFactor": 1.27738335392764,
"queueFactor": 1.003471960975336,
"queueWeight": 1.003471960975336,
"recentSuccess": 49,
"recentSuccessRate": 0.34265734265734266,
"recentTerminal": 143,
"recentWilsonLowerBound": 0.2763537399903497,
"recentWilsonLowerBound": 0.2698994070063999,
"running": 8,
"selectionWeight": 1.2842964332055433,
"selectionWeight": 1.2818183790830207,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 23.833333333333332,
"waiting": 23330
"waiting": 23324
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1263.5076923076922,
"backlogHours": 1263.6,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.9477692742505772,
"queueFactor": 0.9646060171245319,
"queueWeight": 0.9646060171245319,
"recentSuccess": 54,
"recentSuccessRate": 0.4153846153846154,
"qualityFactor": 2.351006221737035,
"queueFactor": 0.9657318087505898,
"queueWeight": 0.9657318087505898,
"recentSuccess": 57,
"recentSuccessRate": 0.43846153846153846,
"recentTerminal": 130,
"recentWilsonLowerBound": 0.3342905969843901,
"running": 10,
"selectionWeight": 1.8788299619123894,
"recentWilsonLowerBound": 0.3561441424577135,
"running": 8,
"selectionWeight": 2.2704414909019968,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 21.666666666666668,
"waiting": 27376
"waiting": 27378
},
"Biren_166m": {
"available": true,
"backlogHours": 183.18120805369128,
"backlogHours": 185.59183673469389,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.33714325755640845,
"queueFactor": 1.2887079640317558,
"queueWeight": 1.2887079640317558,
"qualityFactor": 0.3650220381247947,
"queueFactor": 1.287698376972757,
"queueWeight": 1.287698376972757,
"recentSuccess": 31,
"recentSuccessRate": 0.2080536912751678,
"recentTerminal": 149,
"recentWilsonLowerBound": 0.15062130950665817,
"recentSuccessRate": 0.2108843537414966,
"recentTerminal": 147,
"recentWilsonLowerBound": 0.1527313597425877,
"running": 8,
"selectionWeight": 0.434479201032553,
"selectionWeight": 0.470038286052586,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 24.833333333333332,
"waiting": 4549
"throughputPerHour": 24.5,
"waiting": 4547
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1443.9,
"backlogHours": 1468.3728813559321,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.4475790910767181,
"queueFactor": 0.9454881340058545,
"queueWeight": 0.9454881340058545,
"qualityFactor": 0.4885458232884035,
"queueFactor": 0.9442185439924863,
"queueWeight": 0.9442185439924863,
"recentSuccess": 16,
"recentSuccessRate": 0.26666666666666666,
"recentTerminal": 60,
"recentWilsonLowerBound": 0.17132496487078855,
"running": 8,
"selectionWeight": 0.42318071964216264,
"recentSuccessRate": 0.2711864406779661,
"recentTerminal": 59,
"recentWilsonLowerBound": 0.17436824992508337,
"running": 7,
"selectionWeight": 0.4612940259389869,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 10.0,
"throughputPerHour": 9.833333333333334,
"waiting": 14439
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 455.5344827586207,
"backlogHours": 451.5897435897436,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.647973735074233,
"queueFactor": 1.1241090948962436,
"queueWeight": 1.1241090948962436,
"qualityFactor": 0.6671735588306151,
"queueFactor": 1.1269025673538315,
"queueWeight": 1.1269025673538315,
"recentSuccess": 32,
"recentSuccessRate": 0.27586206896551724,
"recentTerminal": 116,
"recentWilsonLowerBound": 0.2027031395742815,
"running": 8,
"selectionWeight": 0.7283931688508343,
"recentSuccessRate": 0.27350427350427353,
"recentTerminal": 117,
"recentWilsonLowerBound": 0.2009012531479607,
"running": 7,
"selectionWeight": 0.7518395963168127,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 19.333333333333332,
"waiting": 8807
"throughputPerHour": 19.5,
"waiting": 8806
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 44.19512195121951,
"backlogHours": 41.91304347826087,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -540,196 +540,196 @@
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 16,
"recentSuccessRate": 0.04878048780487805,
"recentTerminal": 328,
"recentWilsonLowerBound": 0.03024589060163344,
"running": 26,
"recentSuccessRate": 0.0463768115942029,
"recentTerminal": 345,
"recentWilsonLowerBound": 0.02874508204823863,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 54.666666666666664,
"waiting": 2416
"throughputPerHour": 57.5,
"waiting": 2410
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 105.62114537444933,
"backlogHours": 101.69491525423729,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.08236263216353167,
"qualityFactor": 0.06415197735670991,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 26,
"recentSuccessRate": 0.1145374449339207,
"recentTerminal": 227,
"recentWilsonLowerBound": 0.07937181295688597,
"running": 9,
"selectionWeight": 0.10707142181259117,
"recentSuccess": 24,
"recentSuccessRate": 0.1016949152542373,
"recentTerminal": 236,
"recentWilsonLowerBound": 0.06929419232185546,
"running": 5,
"selectionWeight": 0.08339757056372289,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 37.833333333333336,
"waiting": 3996
"throughputPerHour": 39.333333333333336,
"waiting": 4000
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2518.5405405405404,
"backlogHours": 2588.0,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.153579150191713,
"queueFactor": 0.8697897958379429,
"queueWeight": 0.8697897958379429,
"recentSuccess": 15,
"recentSuccessRate": 0.40540540540540543,
"recentTerminal": 37,
"recentWilsonLowerBound": 0.2634629583994014,
"running": 3,
"selectionWeight": 1.0033713735281578,
"qualityFactor": 1.0589595057900854,
"queueFactor": 0.8672680312855909,
"queueWeight": 0.8672680312855909,
"recentSuccess": 14,
"recentSuccessRate": 0.3888888888888889,
"recentTerminal": 36,
"recentWilsonLowerBound": 0.24784655417822946,
"running": 2,
"selectionWeight": 0.9184017257977296,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 6.166666666666667,
"waiting": 15531
"throughputPerHour": 6.0,
"waiting": 15528
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 1083.737704918033,
"backlogHours": 1101.6,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.5987216809791078,
"queueFactor": 0.9870701593441116,
"queueWeight": 0.9870701593441116,
"recentSuccess": 18,
"recentSuccessRate": 0.29508196721311475,
"recentTerminal": 61,
"recentWilsonLowerBound": 0.19554865403985322,
"qualityFactor": 0.4699833134199839,
"queueFactor": 0.9858126566972174,
"queueWeight": 0.9858126566972174,
"recentSuccess": 16,
"recentSuccessRate": 0.26666666666666666,
"recentTerminal": 60,
"recentWilsonLowerBound": 0.17132496487078855,
"running": 7,
"selectionWeight": 0.5909803050468223,
"selectionWeight": 0.4633154988059153,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 10.166666666666666,
"waiting": 11018
"throughputPerHour": 10.0,
"waiting": 11016
},
"MetaX_c-500": {
"available": true,
"backlogHours": 909.12,
"backlogHours": 885.3506493506493,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.49750633743828904,
"queueFactor": 1.0134293281770905,
"queueWeight": 1.0134293281770905,
"recentSuccess": 20,
"recentSuccessRate": 0.26666666666666666,
"recentTerminal": 75,
"recentWilsonLowerBound": 0.1797617929648875,
"qualityFactor": 0.6382450158469157,
"queueFactor": 1.018663352562484,
"queueWeight": 1.018663352562484,
"recentSuccess": 22,
"recentSuccessRate": 0.2857142857142857,
"recentTerminal": 77,
"recentWilsonLowerBound": 0.1968937869371719,
"running": 4,
"selectionWeight": 0.5041875133139302,
"selectionWeight": 0.6501568075989149,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.5,
"waiting": 11364
"throughputPerHour": 12.833333333333334,
"waiting": 11362
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 2180.64406779661,
"backlogHours": 2010.28125,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 1.9828113017031037,
"queueFactor": 0.8887895353835682,
"queueWeight": 0.8887895353835682,
"recentSuccess": 27,
"recentSuccessRate": 0.4576271186440678,
"recentTerminal": 59,
"recentWilsonLowerBound": 0.33701102140242434,
"running": 5,
"selectionWeight": 1.7623019355939895,
"qualityFactor": 1.8955691993764572,
"queueFactor": 0.9007607533873497,
"queueWeight": 0.9007607533873497,
"recentSuccess": 28,
"recentSuccessRate": 0.4375,
"recentTerminal": 64,
"recentWilsonLowerBound": 0.32293817065427327,
"running": 4,
"selectionWeight": 1.707454340128193,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 9.833333333333334,
"throughputPerHour": 10.666666666666666,
"waiting": 21443
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 3092.3571428571427,
"backlogHours": 2985.9310344827586,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.49488395852864964,
"queueFactor": 0.8434186563941293,
"queueWeight": 0.8434186563941293,
"qualityFactor": 0.4786523619609337,
"queueFactor": 0.8488598898595312,
"queueWeight": 0.8488598898595312,
"recentSuccess": 9,
"recentSuccessRate": 0.32142857142857145,
"recentTerminal": 28,
"recentWilsonLowerBound": 0.1793304754342074,
"recentSuccessRate": 0.3103448275862069,
"recentTerminal": 29,
"recentWilsonLowerBound": 0.17275424489768068,
"running": 2,
"selectionWeight": 0.41739436337324165,
"selectionWeight": 0.4063087912551626,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 4.666666666666667,
"waiting": 14431
"throughputPerHour": 4.833333333333333,
"waiting": 14432
},
"Vastai_va16": {
"available": true,
"backlogHours": 1008.46875,
"backlogHours": 1024.3809523809523,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.4570440127681632,
"queueFactor": 0.9977857184181627,
"queueWeight": 0.9977857184181627,
"recentSuccess": 17,
"recentSuccessRate": 0.265625,
"recentTerminal": 64,
"recentWilsonLowerBound": 0.1729623856953776,
"qualityFactor": 0.42008077017686674,
"queueFactor": 0.9966180639683474,
"queueWeight": 0.9966180639683474,
"recentSuccess": 16,
"recentSuccessRate": 0.25396825396825395,
"recentTerminal": 63,
"recentWilsonLowerBound": 0.1628027458309815,
"running": 16,
"selectionWeight": 0.4560319886286016,
"selectionWeight": 0.4186600838840012,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 10.666666666666666,
"waiting": 10757
"throughputPerHour": 10.5,
"waiting": 10756
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 652.2558139534883,
"backlogHours": 676.0481927710844,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 2.5,
"queueFactor": 1.065182337223001,
"queueWeight": 1.065182337223001,
"recentSuccess": 41,
"recentSuccessRate": 0.47674418604651164,
"recentTerminal": 86,
"recentWilsonLowerBound": 0.37445361147407896,
"queueFactor": 1.0607213988977988,
"queueWeight": 1.0607213988977988,
"recentSuccess": 39,
"recentSuccessRate": 0.46987951807228917,
"recentTerminal": 83,
"recentWilsonLowerBound": 0.36623168109196985,
"running": 6,
"selectionWeight": 2.662955843057502,
"selectionWeight": 2.6518034972444973,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 14.333333333333334,
"waiting": 9349
"throughputPerHour": 13.833333333333334,
"waiting": 9352
}
},
"queueAttemptedAt": "2026-09-12T19:11:08.187363+00:00",
"queueAttemptedAt": "2026-09-12T19:23:53.051554+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-12T19:11:08.187363+00:00",
"queueUpdatedAt": "2026-09-12T19:23:53.051554+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": "2026-09-12T18:59:53.566932+00:00",
"lastSyncTime": "2026-09-12T18:59:53.316571+00:00",
"generatedAt": "2026-09-12T19:23:45.508363+00:00",
"lastSyncTime": "2026-09-12T19:23:45.302791+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -165,17 +165,19 @@
"ascend_910-b3|vllm|text-generation|model_type:rwkv7": {
"architectureSignature": "model_type:rwkv7",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-09T18:31:21+00:00",
"evidenceCount": 2,
"expiresAt": "2026-10-12T19:13:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-09T18:31:21+00:00",
"latestFailureAt": "2026-09-12T19:13:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "rwkv7",
"sourceModelIds": [
"RWKV/RWKV7-2.9B-20260805",
"RWKV/RWKV7-1.5B-20260805"
],
"sourceTaskIds": [
"4583368",
"4579389"
],
"targetGpu": "Ascend_910-b3",
@@ -1495,17 +1497,17 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 29,
"attributableFailureCount": 30,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 29,
"decisionTotal": 30,
"failureBreakdown": {
"ambiguous_runtime": 28,
"framework_architecture_unsupported": 27,
"framework_architecture_unsupported": 28,
"memory_capacity": 1,
"tokenizer_compatibility": 1
},
"failureCount": 57,
"failureCount": 58,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1515,7 +1517,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 57,
"total": 58,
"unresolvedFailureCount": 28
},
"Ascend_910-b4|llamacpp|text-generation": {
@@ -2461,14 +2463,14 @@
"unresolvedFailureCount": 866
},
"vllm": {
"attributableFailureCount": 281,
"decisionFailureRate": 0.9894,
"decisionSuccessRate": 0.0106,
"decisionTotal": 284,
"attributableFailureCount": 282,
"decisionFailureRate": 0.9895,
"decisionSuccessRate": 0.0105,
"decisionTotal": 285,
"failureBreakdown": {
"ambiguous_runtime": 200,
"backend_operator": 34,
"framework_architecture_unsupported": 195,
"framework_architecture_unsupported": 196,
"memory_capacity": 6,
"model_load": 26,
"platform_infrastructure": 1,
@@ -2477,14 +2479,14 @@
"tokenizer_compatibility": 6,
"参数/模板问题": 24
},
"failureCount": 506,
"failureCount": 507,
"failureRate": 0.9941,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0059,
"total": 509,
"total": 510,
"unresolvedFailureCount": 224
},
"vllm-mlu": {
@@ -2589,29 +2591,29 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T18:59:53.563039+00:00",
"generatedAt": "2026-09-12T19:23:45.503104+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 29,
"decisionFailureRate": 0.9667,
"decisionSuccessRate": 0.0333,
"decisionTotal": 30,
"attributableFailureCount": 30,
"decisionFailureRate": 0.9677,
"decisionSuccessRate": 0.0323,
"decisionTotal": 31,
"failureBreakdown": {
"ambiguous_runtime": 28,
"framework_architecture_unsupported": 27,
"framework_architecture_unsupported": 28,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 8,
"验证失败": 27
},
"failureCount": 92,
"failureRate": 0.9892,
"failureCount": 93,
"failureRate": 0.9894,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0108,
"total": 93,
"successRate": 0.0106,
"total": 94,
"unresolvedFailureCount": 63
},
"Ascend_910-b4": {
@@ -4364,21 +4366,21 @@
},
"recentCombinationStats": {
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 3
"ambiguous_runtime": 16,
"framework_architecture_unsupported": 4
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T18:59:53.316516+00:00",
"lastTerminalAt": "2026-09-12T19:23:45.302791+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4387,7 +4389,7 @@
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 17
"unresolvedFailureCount": 16
},
"Ascend_910-b4|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4658,9 +4660,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 11
"ambiguous_runtime": 10
},
"failureCount": 11,
"failureCount": 10,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -4672,8 +4674,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 11,
"unresolvedFailureCount": 11
"total": 10,
"unresolvedFailureCount": 10
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 6,
@@ -5096,9 +5098,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-09T16:50:57.939999+00:00",
@@ -5111,8 +5113,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|zaya|none": {
"attributableFailureCount": 0,
@@ -7369,17 +7371,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1734,
"totalRecords": 1821,
"terminalRecords": 1735,
"totalRecords": 1822,
"totals": {
"attributableFailureCount": 494,
"decisionFailureRate": 0.8966,
"decisionSuccessRate": 0.1034,
"decisionTotal": 551,
"attributableFailureCount": 495,
"decisionFailureRate": 0.8967,
"decisionSuccessRate": 0.1033,
"decisionTotal": 552,
"failureBreakdown": {
"ambiguous_runtime": 405,
"backend_operator": 42,
"framework_architecture_unsupported": 307,
"framework_architecture_unsupported": 308,
"memory_capacity": 11,
"model_load": 72,
"platform_infrastructure": 4,
@@ -7389,21 +7391,20 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1677,
"failureCount": 1678,
"failureRate": 0.9671,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 57,
"successRate": 0.0329,
"total": 1734,
"total": 1735,
"unresolvedFailureCount": 1179
},
"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。",
@@ -7412,6 +7413,7 @@
"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。",
@@ -7434,6 +7436,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1821,
"summarizedRecords": 1822,
"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", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-12T19:23:45.302791+00:00", "modelId": "RWKV/RWKV7-2.9B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T19:13:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4583368", "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", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-12T18:59:53.316516+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T18:53:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4549470", "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": "2026-09-12T17:16:49.913530+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T17:15:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4543650", "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": "2026-09-12T17:06:34.916681+00:00", "modelId": "amd/Qwen2-7B-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T16:57:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079249", "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": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T11:30:49.443166+00:00", "modelId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3SmallForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8630134648, "estimatedRequiredGiB": 9.647, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3small", "modelscopeFileSize": 8632060880, "modelscopeLicense": "mit", "modelscopeParams": 7803314176, "modelscopeTags": ["license:mit", "model_type:phi3small", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8632060880}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.888188+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729519", "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": "2026-09-10T02:58:51.546388+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293356304, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295851911, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295851911}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.847566+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729520", "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": "2026-09-09T14:21:21.949411+00:00", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4020365960, "estimatedRequiredGiB": 4.496, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4022810352, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4022810352}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.843439+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729517", "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": "2026-09-09T14:24:47.907622+00:00", "modelId": "RedHatAI/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7855165704, "estimatedRequiredGiB": 8.783, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7858540940, "modelscopeLicense": "other", "modelscopeParams": 7400416256, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-07T06:07:37.712079+00:00", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 7858540940}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.841387+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729516", "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": "14871d999fa596519a1bf4572b3dca6adaffe5f7d6931fd4fca46f233af2878b",
".modelhub_state/architecture_history_backfill.json": "4cb14c27a1a2e9f925db36c645c7995b59894b4a4df9261319d5ab4da74ad58b",
".modelhub_state/market_intelligence.json": "520fbe028cf37aea8f3ef7caadce94bb95c677ca661c22f5b13c597a130d787b",
".modelhub_state/official_capabilities.json": "3ac7fd4f0453c507d26cca7ad0b0567abdf7d6abbe933d3db09481ce3044350a",
".modelhub_state/outcome_checkpoint.json": "844817e021a11d003b1c6bf2075a968bffdea02bbf91d2ba43ea8e0ec897380e",
".modelhub_state/architecture_compatibility_blacklist.json": "cbd4a70fbf4a05c92aeadaf8e9797a9476eca0948164c1b9f1c726dabdf90b55",
".modelhub_state/architecture_history_backfill.json": "8075e3c2f764798300189fd693aafe4fbe533959eb7f4909acb4c49b7fa015a0",
".modelhub_state/market_intelligence.json": "124de8fdbb90ad58db91653ef151bf87226e4ae60bc26fbb476b281b555cedcc",
".modelhub_state/official_capabilities.json": "c12cefc19c750c0e003d58f3244975704decee9b62e2aebf192f71471ad69749",
".modelhub_state/outcome_checkpoint.json": "1bef1ad52b293c45e2cff91f1c8a161bc57c57d326b2e02403cb92818daf7082",
".modelhub_state/queue_cleanup_latest.json": "6e13d9db1daf048f4029a2d84ef15f8fcc26ad0dfa4a2deea5f40c92de0af1f3",
".modelhub_state/recent_outcomes.jsonl": "8700b4b73aac2619ea8092ab07f4561a8675c7e73466883ba9f929d6a6acd71c",
".modelhub_state/recovery_active_tasks.jsonl": "e0afcd1ea3334df6c73547e11eae2d8abdf2a2d676d2f756bd324b42827bc1bb",
".modelhub_state/recovery_intents.jsonl": "00cb8d2beacbbf4bfb0541ec3505d87c79baf8b56d143267531e199fac86aa86",
".modelhub_state/recent_outcomes.jsonl": "91dc4faf524f29fac02399df5721cf003a46b32a0d5f4720cd5507a90ca7754e",
".modelhub_state/recovery_active_tasks.jsonl": "ce6f5cac435d07471927e895621b51e684e16eaebf32aafbb3e3465b0204c7cb",
".modelhub_state/recovery_intents.jsonl": "abdc159c0976806f8d2b870b9171e584dc18421e65565d15155b9c4163e00b27",
".modelhub_state/routing_intelligence.json": "cdd3341d66484775862c4a1f5c766a7fc0200b1a3a204a76975162502e1d3457",
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
"ledger/submissions.jsonl": "828c7254d2bda84e29c1ccc3489b033f26de0fa8f8ae7cf4e571de42b1210714",
"outcomes/submissions.jsonl": "330f4925bfdc6851862a37bcf16ba89cafeb5e0ec5028e9aac675e630a66f055"
},
"generation": 6337,
"generation": 6338,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-12T19:22:44.643121+00:00",
"updatedAt": "2026-09-12T19:26:28.105278+00:00",
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
}