state: generation 5332 (intent)

This commit is contained in:
2026-09-10 19:50:30 +00:00
parent 2303f48519
commit 1018664029
7 changed files with 1408 additions and 1311 deletions

View File

@@ -397,7 +397,7 @@
"cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:qwen3_5_mtp": {
"architectureSignature": "model_type:qwen3_5_mtp",
"architectures": [],
"evidenceCount": 2,
"evidenceCount": 1,
"expiresAt": "2026-10-08T06:46:11.587867+00:00",
"framework": "vllm-mlu",
"latestFailureAt": "2026-09-08T06:46:11.587867+00:00",
@@ -405,12 +405,10 @@
"matchType": "model_type",
"modelType": "qwen3_5_mtp",
"sourceModelIds": [
"mlx-community/Qwen3.8-27B-MTP-nvfp4",
"mlx-community/Qwen3.8-27B-MTP-mxfp4"
"mlx-community/Qwen3.8-27B-MTP-nvfp4"
],
"sourceTaskIds": [
"4712816",
"4712822"
"4712816"
],
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation"
@@ -1311,7 +1309,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T19:47:09.322933+00:00",
"generatedAt": "2026-09-10T19:48:10.317843+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -416,121 +416,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T19:44:28.197468+00:00",
"generatedAt": "2026-09-10T19:48:15.537232+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 1114.2857142857142,
"backlogHours": 1055.548872180451,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.5785634952557193,
"queueFactor": 0.9625690074056412,
"queueWeight": 0.9625690074056412,
"recentSuccess": 52,
"recentSuccessRate": 0.4126984126984127,
"recentTerminal": 126,
"recentWilsonLowerBound": 0.3305590263103976,
"qualityFactor": 1.6247953993626276,
"queueFactor": 0.9709329414076598,
"queueWeight": 0.9709329414076598,
"recentSuccess": 53,
"recentSuccessRate": 0.39849624060150374,
"recentTerminal": 133,
"recentWilsonLowerBound": 0.3192652583897698,
"running": 8,
"selectionWeight": 1.5194762967550772,
"selectionWeight": 1.5775673762887894,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 21.0,
"waiting": 23400
"throughputPerHour": 22.166666666666668,
"waiting": 23398
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1160.7042253521126,
"backlogHours": 1152.3776223776224,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.0818279096799492,
"queueFactor": 0.9566941620905063,
"queueWeight": 0.9566941620905063,
"recentSuccess": 50,
"recentSuccessRate": 0.352112676056338,
"recentTerminal": 142,
"recentWilsonLowerBound": 0.2783917433242715,
"qualityFactor": 1.244533971363667,
"queueFactor": 0.9582344169253308,
"queueWeight": 0.9582344169253308,
"recentSuccess": 51,
"recentSuccessRate": 0.35664335664335667,
"recentTerminal": 143,
"recentWilsonLowerBound": 0.28282576415035254,
"running": 8,
"selectionWeight": 1.034978445577383,
"selectionWeight": 1.1925552843934297,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 23.666666666666668,
"waiting": 27470
"throughputPerHour": 23.833333333333332,
"waiting": 27465
},
"Biren_166m": {
"available": true,
"backlogHours": 148.6304347826087,
"backlogHours": 151.66666666666666,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.09869003197168076,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 25,
"recentSuccessRate": 0.1358695652173913,
"recentTerminal": 184,
"recentWilsonLowerBound": 0.09375218533785815,
"qualityFactor": 0.08192042840244705,
"queueFactor": 1.298905233110771,
"queueWeight": 1.298905233110771,
"recentSuccess": 22,
"recentSuccessRate": 0.12222222222222222,
"recentTerminal": 180,
"recentWilsonLowerBound": 0.08211480209844403,
"running": 8,
"selectionWeight": 0.128297041563185,
"selectionWeight": 0.10640687315061473,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 30.666666666666668,
"waiting": 4558
"throughputPerHour": 30.0,
"waiting": 4550
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1039.7560975609756,
"backlogHours": 1107.1948051948052,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.15206168774136353,
"queueFactor": 0.9726165097461745,
"queueWeight": 0.9726165097461745,
"recentSuccess": 15,
"recentSuccessRate": 0.18292682926829268,
"recentTerminal": 82,
"recentWilsonLowerBound": 0.1141092170763672,
"qualityFactor": 0.1606084692626208,
"queueFactor": 0.9640007724188163,
"queueWeight": 0.9640007724188163,
"recentSuccess": 14,
"recentSuccessRate": 0.18181818181818182,
"recentTerminal": 77,
"recentWilsonLowerBound": 0.1115115201004776,
"running": 7,
"selectionWeight": 0.14789770799711766,
"selectionWeight": 0.15482668842617017,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 13.666666666666666,
"waiting": 14210
"throughputPerHour": 12.833333333333334,
"waiting": 14209
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 422.95238095238096,
"backlogHours": 436.72131147540983,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.5638783469236829,
"queueFactor": 1.1131088546596164,
"queueWeight": 1.1131088546596164,
"recentSuccess": 35,
"recentSuccessRate": 0.2777777777777778,
"recentTerminal": 126,
"recentWilsonLowerBound": 0.20702956384009177,
"qualityFactor": 0.7262419411908285,
"queueFactor": 1.1083586882251188,
"queueWeight": 1.1083586882251188,
"recentSuccess": 36,
"recentSuccessRate": 0.29508196721311475,
"recentTerminal": 122,
"recentWilsonLowerBound": 0.22140591975625476,
"running": 7,
"selectionWeight": 0.6276579809115784,
"selectionWeight": 0.8049365652723306,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 21.0,
"waiting": 8882
"throughputPerHour": 20.333333333333332,
"waiting": 8880
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 96.40816326530613,
"backlogHours": 96.44897959183673,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -539,20 +539,20 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 9,
"recentSuccessRate": 0.061224489795918366,
"recentSuccess": 10,
"recentSuccessRate": 0.06802721088435375,
"recentTerminal": 147,
"recentWilsonLowerBound": 0.032541132146123544,
"running": 4,
"recentWilsonLowerBound": 0.03736716429228684,
"running": 2,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 24.5,
"waiting": 2362
"waiting": 2363
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 115.02512562814071,
"backlogHours": 114.05999999999999,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
@@ -561,175 +561,175 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 15,
"recentSuccessRate": 0.07537688442211055,
"recentTerminal": 199,
"recentWilsonLowerBound": 0.04620825117869708,
"running": 8,
"recentSuccess": 17,
"recentSuccessRate": 0.085,
"recentTerminal": 200,
"recentWilsonLowerBound": 0.05374529946985246,
"running": 2,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 33.166666666666664,
"waiting": 3815
"submissionEligible": true,
"throughputPerHour": 33.333333333333336,
"waiting": 3802
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2675.3142857142857,
"backlogHours": 2925.9375,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.7220550851213057,
"queueFactor": 0.8440635329574684,
"queueWeight": 0.8440635329574684,
"qualityFactor": 0.992613384058803,
"queueFactor": 0.8332421503791794,
"queueWeight": 0.8332421503791794,
"recentSuccess": 13,
"recentSuccessRate": 0.37142857142857144,
"recentTerminal": 35,
"recentWilsonLowerBound": 0.2316560736889106,
"recentSuccessRate": 0.40625,
"recentTerminal": 32,
"recentWilsonLowerBound": 0.25519402480313796,
"running": 2,
"selectionWeight": 0.6094603661373948,
"selectionWeight": 0.8270873106283112,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 5.833333333333333,
"waiting": 15606
"throughputPerHour": 5.333333333333333,
"waiting": 15605
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 688.3578947368421,
"backlogHours": 687.978947368421,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.35187579462649826,
"queueFactor": 1.0346875275454828,
"queueWeight": 1.0346875275454828,
"recentSuccess": 23,
"recentSuccessRate": 0.24210526315789474,
"qualityFactor": 0.3466515075456514,
"queueFactor": 1.0353202666077699,
"queueWeight": 1.0353202666077699,
"recentSuccess": 22,
"recentSuccessRate": 0.23157894736842105,
"recentTerminal": 95,
"recentWilsonLowerBound": 0.16708723217598367,
"recentWilsonLowerBound": 0.15819566451338007,
"running": 7,
"selectionWeight": 0.36408149594519357,
"selectionWeight": 0.3588953312121491,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 15.833333333333334,
"waiting": 10899
"waiting": 10893
},
"MetaX_c-500": {
"available": true,
"backlogHours": 557.4634146341464,
"backlogHours": 566.6776859504132,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.2446076506508317,
"queueFactor": 1.0679450400409427,
"queueWeight": 1.0679450400409427,
"recentSuccess": 25,
"recentSuccessRate": 0.2032520325203252,
"recentTerminal": 123,
"recentWilsonLowerBound": 0.1416321145776123,
"qualityFactor": 0.3463291204828412,
"queueFactor": 1.0658855412541401,
"queueWeight": 1.0658855412541401,
"recentSuccess": 27,
"recentSuccessRate": 0.2231404958677686,
"recentTerminal": 121,
"recentWilsonLowerBound": 0.1581287736809404,
"running": 4,
"selectionWeight": 0.2612275272686234,
"selectionWeight": 0.3691472020379235,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 20.5,
"throughputPerHour": 20.166666666666668,
"waiting": 11428
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1274.6732673267327,
"backlogHours": 1202.8598130841121,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.15709177320179288,
"queueFactor": 0.94334711798404,
"queueWeight": 0.94334711798404,
"recentSuccess": 18,
"recentSuccessRate": 0.1782178217821782,
"recentTerminal": 101,
"recentWilsonLowerBound": 0.1158097450050057,
"qualityFactor": 0.177604921452416,
"queueFactor": 0.9520916042501633,
"queueWeight": 0.9520916042501633,
"recentSuccess": 19,
"recentSuccessRate": 0.17757009345794392,
"recentTerminal": 107,
"recentWilsonLowerBound": 0.11672859553461687,
"running": 4,
"selectionWeight": 0.14819207150891375,
"selectionWeight": 0.16909615458835497,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 16.833333333333332,
"waiting": 21457
"throughputPerHour": 17.833333333333332,
"waiting": 21451
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 3431.04,
"backlogHours": 3574.0,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 2.5,
"queueFactor": 0.8131440555592307,
"queueWeight": 0.8131440555592307,
"recentSuccess": 15,
"recentSuccessRate": 0.6,
"recentTerminal": 25,
"recentWilsonLowerBound": 0.4073912778512734,
"queueFactor": 0.808607575212013,
"queueWeight": 0.808607575212013,
"recentSuccess": 14,
"recentSuccessRate": 0.5833333333333334,
"recentTerminal": 24,
"recentWilsonLowerBound": 0.3883433764938864,
"running": 2,
"selectionWeight": 2.032860138898077,
"selectionWeight": 2.0215189380300327,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 4.166666666666667,
"throughputPerHour": 4.0,
"waiting": 14296
},
"Vastai_va16": {
"available": true,
"backlogHours": 1064.2758620689656,
"backlogHours": 1046.2372881355932,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.9758050136470664,
"queueFactor": 0.9692219181484393,
"queueWeight": 0.9692219181484393,
"recentSuccess": 22,
"recentSuccessRate": 0.3793103448275862,
"recentTerminal": 58,
"recentWilsonLowerBound": 0.26564088902603683,
"qualityFactor": 0.9158899000357565,
"queueFactor": 0.9722242707364858,
"queueWeight": 0.9722242707364858,
"recentSuccess": 21,
"recentSuccessRate": 0.3559322033898305,
"recentTerminal": 59,
"recentWilsonLowerBound": 0.24603115869434763,
"running": 16,
"selectionWeight": 0.9457716070658737,
"selectionWeight": 0.8904503901371763,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 9.666666666666666,
"throughputPerHour": 9.833333333333334,
"waiting": 10288
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 535.979381443299,
"backlogHours": 553.0851063829788,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 1.9982087873518384,
"queueFactor": 1.0742593595028294,
"queueWeight": 1.0742593595028294,
"recentSuccess": 45,
"recentSuccessRate": 0.4639175257731959,
"recentTerminal": 97,
"recentWilsonLowerBound": 0.36794664127193955,
"qualityFactor": 2.1210913200275106,
"queueFactor": 1.0697743811248126,
"queueWeight": 1.0697743811248126,
"recentSuccess": 43,
"recentSuccessRate": 0.4574468085106383,
"recentTerminal": 94,
"recentWilsonLowerBound": 0.36038786252396654,
"running": 6,
"selectionWeight": 2.146594492053511,
"selectionWeight": 2.269089154191642,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 16.166666666666668,
"throughputPerHour": 15.666666666666666,
"waiting": 8665
}
},
"queueAttemptedAt": "2026-09-10T19:34:54.306456+00:00",
"queueAttemptedAt": "2026-09-10T19:48:15.537232+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-10T19:34:54.306456+00:00",
"queueUpdatedAt": "2026-09-10T19:48:15.537232+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": "2026-09-10T19:38:05.803026+00:00",
"lastSyncTime": "2026-09-10T19:38:05.602511+00:00",
"generatedAt": "2026-09-10T19:48:10.294794+00:00",
"lastSyncTime": "2026-09-10T19:48:09.995356+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -401,7 +401,7 @@
"cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:qwen3_5_mtp": {
"architectureSignature": "model_type:qwen3_5_mtp",
"architectures": [],
"evidenceCount": 2,
"evidenceCount": 1,
"expiresAt": "2026-10-08T06:46:11.587867+00:00",
"framework": "vllm-mlu",
"latestFailureAt": "2026-09-08T06:46:11.587867+00:00",
@@ -409,12 +409,10 @@
"matchType": "model_type",
"modelType": "qwen3_5_mtp",
"sourceModelIds": [
"mlx-community/Qwen3.8-27B-MTP-nvfp4",
"mlx-community/Qwen3.8-27B-MTP-mxfp4"
"mlx-community/Qwen3.8-27B-MTP-nvfp4"
],
"sourceTaskIds": [
"4712816",
"4712822"
"4712816"
],
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation"
@@ -2144,12 +2142,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 57,
"ambiguous_runtime": 58,
"framework_architecture_unsupported": 38,
"memory_capacity": 1,
"model_load": 5
},
"failureCount": 101,
"failureCount": 102,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2159,8 +2157,8 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 101,
"unresolvedFailureCount": 57
"total": 102,
"unresolvedFailureCount": 58
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -2323,7 +2321,7 @@
"decisionSuccessRate": 0.0083,
"decisionTotal": 242,
"failureBreakdown": {
"ambiguous_runtime": 184,
"ambiguous_runtime": 185,
"backend_operator": 33,
"framework_architecture_unsupported": 169,
"memory_capacity": 6,
@@ -2334,15 +2332,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 24
},
"failureCount": 449,
"failureCount": 450,
"failureRate": 0.9956,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 2,
"successRate": 0.0044,
"total": 451,
"unresolvedFailureCount": 208
"total": 452,
"unresolvedFailureCount": 209
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2445,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T19:38:05.798763+00:00",
"generatedAt": "2026-09-10T19:48:10.290792+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2731,22 +2729,22 @@
"decisionSuccessRate": 0.2167,
"decisionTotal": 60,
"failureBreakdown": {
"ambiguous_runtime": 59,
"ambiguous_runtime": 60,
"framework_architecture_unsupported": 40,
"memory_capacity": 1,
"model_load": 6,
"参数/模板问题": 13,
"验证失败": 130
},
"failureCount": 249,
"failureRate": 0.9504,
"failureCount": 250,
"failureRate": 0.9506,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.0496,
"total": 262,
"unresolvedFailureCount": 202
"successRate": 0.0494,
"total": 263,
"unresolvedFailureCount": 203
},
"hygon_k100-ai": {
"attributableFailureCount": 39,
@@ -4165,18 +4163,18 @@
"unresolvedFailureCount": 14
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 3,
"framework_architecture_unsupported": 3,
"framework_architecture_unsupported": 2,
"参数/模板问题": 1
},
"failureCount": 7,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastPlatformFailureAt": null,
@@ -4188,7 +4186,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 7,
"total": 6,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
@@ -4541,7 +4539,7 @@
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T16:05:31.804365+00:00",
"lastTerminalAt": "2026-09-10T19:48:09.995356+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4659,15 +4657,15 @@
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_mtp|none": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-09-08T18:40:55.416623+00:00",
@@ -4680,7 +4678,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 2,
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm|text-generation|qwen3_5_moe|eschamoe": {
@@ -7022,15 +7020,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1627,
"totalRecords": 1714,
"terminalRecords": 1628,
"totalRecords": 1715,
"totals": {
"attributableFailureCount": 425,
"decisionFailureRate": 0.891,
"decisionSuccessRate": 0.109,
"decisionTotal": 477,
"failureBreakdown": {
"ambiguous_runtime": 375,
"ambiguous_runtime": 376,
"backend_operator": 40,
"framework_architecture_unsupported": 273,
"memory_capacity": 11,
@@ -7042,30 +7040,31 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1575,
"failureRate": 0.968,
"failureCount": 1576,
"failureRate": 0.9681,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 52,
"successRate": 0.032,
"total": 1627,
"unresolvedFailureCount": 1146
"successRate": 0.0319,
"total": 1628,
"unresolvedFailureCount": 1147
},
"warnings": [
"GPU Ascend_910-b3 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 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 Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。",
"组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Mthreads_s4000|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7080,11 +7079,10 @@
"组合 hygon_k100-ai|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-150|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Vastai_va16|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1714,
"summarizedRecords": 1715,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T19:48:09.995356+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:45:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477833", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_mtp"], "framework": "", "lastSyncTime": "2026-09-10T19:38:05.602511+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-8bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:37:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332704", "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": "2026-09-10T19:27:42.923434+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:25:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523215", "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": "2026-09-10T19:17:56.906562+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:09:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523222", "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-mlu", "lastSyncTime": "2026-09-09T01:56:43.203825+00:00", "modelId": "RedHatAI/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615358, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615358}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:11.593738+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712817", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T04:17:40.427917+00:00", "modelId": "RWKV/RWKV7-7.2B-20260805", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.589203+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712819", "taskType": "text-generation", "verifyResult": null}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_mtp"], "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T18:40:55.416623+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-nvfp4", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 238933307, "estimatedRequiredGiB": 0.297, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_mtp", "modelscopeFileSize": 265664321, "modelscopeLicense": "apache-2.0", "modelscopeParams": 106194432, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_mtp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-vlm", "custom_tag:qwen3_5_mtp", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:qwen", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:nvfp4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 265664321}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:11.587867+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712816", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_mtp"], "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T23:49:45.832679+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-mxfp4", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 225662258, "estimatedRequiredGiB": 0.282, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_mtp", "modelscopeFileSize": 252393272, "modelscopeLicense": "apache-2.0", "modelscopeParams": 79652352, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_mtp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-vlm", "custom_tag:qwen3_5_mtp", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:qwen", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:mxfp4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 252393272}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:11.586261+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712822", "taskType": "text-generation", "verifyResult": -1}

View File

@@ -653,6 +653,7 @@
{"batchId": "c880d7cf224c45b98c145549709dc34e", "completedAt": "2026-09-10T17:52:13.814201+00:00", "configFingerprint": "34532436dbc855d32b74faf635c17eb60fc9f7a7dc8d2b76403af96f7424ebf3", "configSource": "modelhub_live", "createdAt": "2026-09-10T17:52:06.627408+00:00", "framework": "llamacpp", "intentId": "93776e1aa6634b3d8e8149734e3ac9a7", "lastModified": "2026-08-24T12:58:44+00:00", "modelAddress": "https://modelscope.cn/models/guaidao2/LFM2.5-2.6B-For-CTF", "reason": null, "reconciledAt": "2026-09-10T19:40:09.754816+00:00", "repoId": "guaidao2/LFM2.5-2.6B-For-CTF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "4764441", "taskType": "text-generation"}
{"batchId": "816d6004b62a4761ae3c03a2cc2b60fc", "completedAt": "2026-09-10T18:09:29.180907+00:00", "configFingerprint": "1bb1691a97b5ca0ea0c7ced63e4ad26ae05d4e6853c41103188e78e754faa6b2", "configSource": "modelhub_live", "createdAt": "2026-09-10T18:09:16.635733+00:00", "framework": "llamacpp", "intentId": "ed832d0ea0bf44979fe822c3e68b66cb", "lastModified": "2026-08-24T12:58:44+00:00", "modelAddress": "https://modelscope.cn/models/guaidao2/LFM2.5-2.6B-For-CTF", "reason": null, "reconciledAt": "2026-09-10T19:40:09.754296+00:00", "repoId": "guaidao2/LFM2.5-2.6B-For-CTF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4764783", "taskType": "text-generation"}
{"batchId": "b4ac4e477f634c77b8ffb19dc474c5f0", "completedAt": "2026-09-10T18:25:47.382708+00:00", "configFingerprint": "5f5faa291a86bf437595530575b613347621c9e314bbff70f201eec1d3f4e9bd", "configSource": "modelhub_live", "createdAt": "2026-09-10T18:25:39.599830+00:00", "framework": "llamacpp", "intentId": "bb5ab6fe9c87440cb3aa316daba6943f", "lastModified": "2026-08-24T12:58:44+00:00", "modelAddress": "https://modelscope.cn/models/guaidao2/LFM2.5-2.6B-For-CTF", "reason": null, "reconciledAt": "2026-09-10T19:40:09.755849+00:00", "repoId": "guaidao2/LFM2.5-2.6B-For-CTF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "4765091", "taskType": "text-generation"}
{"batchId": "cee895a0ef20468dbab7790293418812", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-10T19:50:30.663170+00:00", "framework": "vllm", "intentId": "ad0a4cb1e6d64ae59352d1a20465000f", "lastModified": "2026-09-10T14:58:25+00:00", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3", "repoId": "webAI-Official/TwIL-LM3", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"}
{"batchId": "93abbd86b4564ff2b94a94e46d15997c", "completedAt": "2026-09-10T02:01:15.152981+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-10T02:01:07.997982+00:00", "framework": "vllm", "intentId": "f62de0b86d234667845793d4dabba8be", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Iluvatar_mrv-100", "taskId": null, "taskType": "text-generation"}
{"batchId": "60b640169cee4eb6aeaf36aa752d68d4", "completedAt": "2026-09-09T21:08:33.584377+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-09T21:08:21.304731+00:00", "framework": "vllm_fix_tokenizer", "intentId": "31500eb429ef4b3cbc844e4096a6b5f6", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "395e59f0f1df48fcb2e0269b69d9bce5", "completedAt": "2026-09-09T16:24:21.684805+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-09T16:24:14.160686+00:00", "framework": "vllm", "intentId": "e2523fa4e63645688fd5e7c0c7c1a5d5", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "uniqueness_rejected", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}

View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "fe74d25e3d5391f15fc17d39430ffdf7de2e3a6d2409a19f6c41ee22bee8a39d",
".modelhub_state/architecture_compatibility_blacklist.json": "aee56b359965792708af7603d25376cbbb2893d289458678de2e104f0b7371ba",
".modelhub_state/architecture_history_backfill.json": "dcf7bd2edf02eb300e8d9d8c6a99e7f7b68c67a19dc1aa06001b95dbfb7700d3",
".modelhub_state/market_intelligence.json": "838b939f39e600bd7275c8cad81191b198ecb794d143f5f499f35bc697929144",
".modelhub_state/official_capabilities.json": "0bc9c05fce265cb8948a4add7144d1785cd54e8e8a3b8ebb29f116da6ed0ff56",
".modelhub_state/outcome_checkpoint.json": "88430152ff98138b7888e1c11ccefb688db72a7638bdf9c1cde52aa208fdfc1b",
".modelhub_state/market_intelligence.json": "c8e9699850ea34497f49351a67fa71004817b01c39f92ffcdc19e1ec86b851bb",
".modelhub_state/official_capabilities.json": "6d93bf51863f14516913da7344c46b093554ea7e65cdb0ae99a45a4642a49f95",
".modelhub_state/outcome_checkpoint.json": "e3cc11c7b5bd493198a0cf07cf68829a57a6b59822f64bc50b7170af0df0fc41",
".modelhub_state/queue_cleanup_latest.json": "c4c0c2f745124fbabf68b2aa082c5aeee0f45dbb41d40369e8064e674a33adbe",
".modelhub_state/recent_outcomes.jsonl": "18cca6e68b2debcaaf1300a8f56cc81bf83c5aac5f0a5ec6de306f37b9978c5f",
".modelhub_state/recent_outcomes.jsonl": "e6fe1b7782ab31a174f8f4376604b7c9183fa77c195694c2800b7217efb9c2de",
".modelhub_state/recovery_active_tasks.jsonl": "8e55c188d6d9b626863015ba9999e20671134e3a98795026a83e71e9b66035d0",
".modelhub_state/recovery_intents.jsonl": "13817573f8a507dd357fdf40a0ec06aeb0582ac258f42a6e8f212171d138cdf6",
".modelhub_state/recovery_intents.jsonl": "ebe098cff905872717ef717670e6e38fc449f7fcf7f424c8c3ace1b3219d57be",
".modelhub_state/routing_intelligence.json": "7e77ebd4538eae240305b9b7218df18db6f864488fe914a9ce22b09526e6df6c",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
"ledger/submissions.jsonl": "666d3d2a6579643ce987f9dc944f3169c02e619fe50a5b6144105e85857aa8c5",
"outcomes/submissions.jsonl": "328b6e09b9ffd31462af8316c4ab7811046b316a1a9404ff8de3ff4fb90aff41"
},
"generation": 5331,
"phase": "cycle",
"generation": 5332,
"phase": "intent",
"schemaVersion": 1,
"updatedAt": "2026-09-10T19:47:09.388675+00:00",
"updatedAt": "2026-09-10T19:50:30.732607+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42"
}