state: generation 11120 (cycle)

This commit is contained in:
2026-09-21 02:58:45 +00:00
parent f5bf4460d3
commit 9a965e3eb0
10 changed files with 2040 additions and 2042 deletions

View File

@@ -2414,7 +2414,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-21T02:55:04.571357+00:00",
"generatedAt": "2026-09-21T02:58:32.985009+00:00",
"summary": {
"activeBlockCount": 119,
"byGpuFramework": {

View File

@@ -425,121 +425,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-21T02:57:29.347945+00:00",
"generatedAt": "2026-09-21T02:58:43.321969+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 819.6627906976744,
"backlogHours": 819.4186046511628,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.8055526293279949,
"queueFactor": 0.9778683038087814,
"queueWeight": 0.9778683038087814,
"recentSuccess": 39,
"recentSuccessRate": 0.22674418604651161,
"qualityFactor": 0.7179320696110454,
"queueFactor": 0.9778693250472548,
"queueWeight": 0.9778693250472548,
"recentSuccess": 38,
"recentSuccessRate": 0.22093023255813954,
"recentTerminal": 172,
"recentWilsonLowerBound": 0.17053610472369476,
"recentWilsonLowerBound": 0.1654034598109465,
"running": 8,
"selectionWeight": 0.7877243832696704,
"selectionWeight": 0.7020437483403317,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 28.666666666666668,
"waiting": 23497
"waiting": 23490
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1148.8378378378377,
"backlogHours": 1148.5945945945946,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.5,
"queueFactor": 0.9295801529942901,
"queueWeight": 0.9295801529942901,
"recentSuccess": 53,
"recentSuccessRate": 0.3581081081081081,
"queueFactor": 0.9295691040474398,
"queueWeight": 0.9295691040474398,
"recentSuccess": 54,
"recentSuccessRate": 0.36486486486486486,
"recentTerminal": 148,
"recentWilsonLowerBound": 0.2853531972897633,
"recentWilsonLowerBound": 0.2916373002819259,
"running": 8,
"selectionWeight": 2.3239503824857253,
"selectionWeight": 2.323922760118599,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 24.666666666666668,
"waiting": 28338
"waiting": 28332
},
"Biren_166m": {
"available": true,
"backlogHours": 143.91346153846155,
"backlogHours": 143.2248803827751,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.6739671547435999,
"queueFactor": 1.2694349159977378,
"queueWeight": 1.2694349159977378,
"qualityFactor": 0.6355132349431445,
"queueFactor": 1.270293060812849,
"queueWeight": 1.270293060812849,
"recentSuccess": 43,
"recentSuccessRate": 0.20673076923076922,
"recentTerminal": 208,
"recentWilsonLowerBound": 0.1572568005334758,
"recentSuccessRate": 0.20574162679425836,
"recentTerminal": 209,
"recentWilsonLowerBound": 0.156484897123764,
"running": 8,
"selectionWeight": 0.8555574384671761,
"selectionWeight": 0.8072880524030023,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 34.666666666666664,
"throughputPerHour": 34.833333333333336,
"waiting": 4989
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1309.2173913043478,
"backlogHours": 1328.5588235294117,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.6991068028923648,
"queueFactor": 0.9115361306816657,
"queueWeight": 0.9115361306816657,
"qualityFactor": 0.6890858601676707,
"queueFactor": 0.9094934541994483,
"queueWeight": 0.9094934541994483,
"recentSuccess": 17,
"recentSuccessRate": 0.2463768115942029,
"recentTerminal": 69,
"recentWilsonLowerBound": 0.1598964745113261,
"recentSuccessRate": 0.25,
"recentTerminal": 68,
"recentWilsonLowerBound": 0.16234881695499528,
"running": 7,
"selectionWeight": 0.6372611100417361,
"selectionWeight": 0.6267190792038928,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 11.5,
"waiting": 15056
"throughputPerHour": 11.333333333333334,
"waiting": 15057
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 412.0444444444444,
"backlogHours": 415.02985074626866,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.4336588315093327,
"queueFactor": 1.08413669153229,
"queueWeight": 1.08413669153229,
"qualityFactor": 0.42037223414062097,
"queueFactor": 1.0829160632506116,
"queueWeight": 1.0829160632506116,
"recentSuccess": 25,
"recentSuccessRate": 0.18518518518518517,
"recentTerminal": 135,
"recentWilsonLowerBound": 0.12869695822609414,
"recentSuccessRate": 0.1865671641791045,
"recentTerminal": 134,
"recentWilsonLowerBound": 0.1296838224720284,
"running": 7,
"selectionWeight": 0.4701454508462868,
"selectionWeight": 0.4552278448954256,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.5,
"waiting": 9271
"throughputPerHour": 22.333333333333332,
"waiting": 9269
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 46.76190476190476,
"backlogHours": 47.70873786407767,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -548,197 +548,197 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 7,
"recentSuccessRate": 0.022222222222222223,
"recentTerminal": 315,
"recentWilsonLowerBound": 0.010805109085923924,
"recentSuccess": 6,
"recentSuccessRate": 0.019417475728155338,
"recentTerminal": 309,
"recentWilsonLowerBound": 0.008928721406924705,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 52.5,
"waiting": 2455
"throughputPerHour": 51.5,
"waiting": 2457
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 150.9795918367347,
"backlogHours": 150.243654822335,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.15019440103125106,
"queueFactor": 1.260340567218354,
"queueWeight": 1.260340567218354,
"recentSuccess": 23,
"recentSuccessRate": 0.11734693877551021,
"recentTerminal": 196,
"recentWilsonLowerBound": 0.07947904176250928,
"running": 6,
"selectionWeight": 0.1892960965887479,
"qualityFactor": 0.1585346901501332,
"queueFactor": 1.2612096207441725,
"queueWeight": 1.2612096207441725,
"recentSuccess": 24,
"recentSuccessRate": 0.1218274111675127,
"recentTerminal": 197,
"recentWilsonLowerBound": 0.0832494527329842,
"running": 7,
"selectionWeight": 0.1999454764390444,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 32.666666666666664,
"waiting": 4932
"throughputPerHour": 32.833333333333336,
"waiting": 4933
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 3025.3125,
"backlogHours": 3227.0,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.9019136532088223,
"queueFactor": 0.8039149703954984,
"queueWeight": 0.8039149703954984,
"recentSuccess": 10,
"recentSuccessRate": 0.3125,
"recentTerminal": 32,
"recentWilsonLowerBound": 0.17952352116618736,
"qualityFactor": 0.7298470900129251,
"queueFactor": 0.7961352459138944,
"queueWeight": 0.7961352459138944,
"recentSuccess": 9,
"recentSuccessRate": 0.3,
"recentTerminal": 30,
"recentWilsonLowerBound": 0.16664562643958936,
"running": 2,
"selectionWeight": 0.7250618878186662,
"selectionWeight": 0.5810569924869804,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 5.333333333333333,
"throughputPerHour": 5.0,
"waiting": 16135
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 592.4444444444445,
"backlogHours": 592.2777777777778,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.7194275246464042,
"queueFactor": 1.0266644112004508,
"queueWeight": 1.0266644112004508,
"qualityFactor": 0.6857634461365623,
"queueFactor": 1.0266629277988235,
"queueWeight": 1.0266629277988235,
"recentSuccess": 25,
"recentSuccessRate": 0.23148148148148148,
"recentTerminal": 108,
"recentWilsonLowerBound": 0.1619925471777863,
"running": 8,
"selectionWeight": 0.7386106359924984,
"selectionWeight": 0.7040479073879738,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.0,
"waiting": 10664
"waiting": 10661
},
"MetaX_c-500": {
"available": true,
"backlogHours": 571.396551724138,
"backlogHours": 576.0521739130435,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.5481587264665204,
"queueFactor": 1.0322502817975603,
"queueWeight": 1.0322502817975603,
"recentSuccess": 24,
"recentSuccessRate": 0.20689655172413793,
"recentTerminal": 116,
"recentWilsonLowerBound": 0.14316009603424576,
"qualityFactor": 0.47530730968866597,
"queueFactor": 1.0309495726355582,
"queueWeight": 1.0309495726355582,
"recentSuccess": 23,
"recentSuccessRate": 0.2,
"recentTerminal": 115,
"recentWilsonLowerBound": 0.1371296827840679,
"running": 4,
"selectionWeight": 0.5658369998648575,
"selectionWeight": 0.49001786779408707,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 19.333333333333332,
"waiting": 11047
"throughputPerHour": 19.166666666666668,
"waiting": 11041
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1550.7142857142858,
"backlogHours": 1514.3720930232557,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 1.2794138714372014,
"queueFactor": 0.8886809778251732,
"queueWeight": 0.8886809778251732,
"recentSuccess": 25,
"recentSuccessRate": 0.2976190476190476,
"recentTerminal": 84,
"recentWilsonLowerBound": 0.2104467918626258,
"qualityFactor": 1.2840319040486128,
"queueFactor": 0.8918089083739755,
"queueWeight": 0.8918089083739755,
"recentSuccess": 26,
"recentSuccessRate": 0.3023255813953488,
"recentTerminal": 86,
"recentWilsonLowerBound": 0.21543382392193752,
"running": 4,
"selectionWeight": 1.1369907703119027,
"selectionWeight": 1.1451110906669506,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 14.0,
"waiting": 21710
"throughputPerHour": 14.333333333333334,
"waiting": 21706
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 1811.5384615384617,
"backlogHours": 1922.5714285714287,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.15268695985706304,
"queueFactor": 0.8681974751442203,
"queueWeight": 0.8681974751442203,
"qualityFactor": 0.16650290574589705,
"queueFactor": 0.8604473934701,
"queueWeight": 0.8604473934701,
"recentSuccess": 8,
"recentSuccessRate": 0.15384615384615385,
"recentTerminal": 52,
"recentWilsonLowerBound": 0.08007589590882648,
"recentSuccessRate": 0.16326530612244897,
"recentTerminal": 49,
"recentWilsonLowerBound": 0.08512596988208977,
"running": 2,
"selectionWeight": 0.13256243303534906,
"selectionWeight": 0.14326699125425485,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 8.666666666666666,
"waiting": 15700
"throughputPerHour": 8.166666666666666,
"waiting": 15701
},
"Vastai_va16": {
"available": true,
"backlogHours": 1203.6666666666667,
"backlogHours": 1220.7042253521126,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.05,
"queueFactor": 0.9231020540117282,
"queueWeight": 0.9231020540117282,
"queueFactor": 0.9211177022285634,
"queueWeight": 0.9211177022285634,
"recentSuccess": 6,
"recentSuccessRate": 0.08333333333333333,
"recentTerminal": 72,
"recentWilsonLowerBound": 0.03875189713049035,
"recentSuccessRate": 0.08450704225352113,
"recentTerminal": 71,
"recentWilsonLowerBound": 0.039305972354112026,
"running": 16,
"selectionWeight": 0.04615510270058641,
"selectionWeight": 0.04605588511142817,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 12.0,
"waiting": 14444
"throughputPerHour": 11.833333333333334,
"waiting": 14445
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 325.3061224489796,
"backlogHours": 316.6092715231788,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 0.05401870294154659,
"queueFactor": 1.1232639395330322,
"queueWeight": 1.1232639395330322,
"qualityFactor": 0.05,
"queueFactor": 1.1277897720528962,
"queueWeight": 1.1277897720528962,
"recentSuccess": 22,
"recentSuccessRate": 0.07482993197278912,
"recentTerminal": 294,
"recentWilsonLowerBound": 0.04993265127097582,
"recentSuccessRate": 0.0728476821192053,
"recentTerminal": 302,
"recentWilsonLowerBound": 0.04859629433610135,
"running": 6,
"selectionWeight": 0.060677261074586215,
"selectionWeight": 0.05638948860264481,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 49.0,
"waiting": 15940
"throughputPerHour": 50.333333333333336,
"waiting": 15936
}
},
"queueAttemptedAt": "2026-09-21T02:48:17.967660+00:00",
"queueAttemptedAt": "2026-09-21T02:58:43.321969+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-21T02:48:17.967660+00:00",
"queueUpdatedAt": "2026-09-21T02:58:43.321969+00:00",
"supportedGpus": [
"Vastai_va16",
"Kunlunxin_p-800",

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-09-21T02:57:29.347945+00:00",
"catalogUpdatedAt": "2026-09-21T02:58:43.321969+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-09-21T02:57:29.347945+00:00",
"generatedAt": "2026-09-21T02:58:43.321969+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6341,6 +6341,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-09-21T02:57:29.347945+00:00",
"taskTreeUpdatedAt": "2026-09-21T02:58:43.321969+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T02:55:04.508310+00:00",
"lastSyncTime": "2026-09-21T02:55:04.446781+00:00",
"generatedAt": "2026-09-21T02:58:32.920784+00:00",
"lastSyncTime": "2026-09-21T02:58:30.354826+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2744,7 +2744,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 199,
"failureBreakdown": {
"ambiguous_runtime": 103,
"ambiguous_runtime": 104,
"context_length": 1,
"framework_architecture_unsupported": 153,
"memory_capacity": 9,
@@ -2752,7 +2752,7 @@
"repository_structure": 27,
"tokenizer_compatibility": 9
},
"failureCount": 303,
"failureCount": 304,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2762,8 +2762,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 303,
"unresolvedFailureCount": 103
"total": 304,
"unresolvedFailureCount": 104
},
"Biren_166m|unknown|feature_emb": {
"attributableFailureCount": 0,
@@ -4219,7 +4219,7 @@
"decisionSuccessRate": 0.0372,
"decisionTotal": 646,
"failureBreakdown": {
"ambiguous_runtime": 128,
"ambiguous_runtime": 129,
"architecture_compatibility": 20,
"backend_operator": 43,
"context_length": 46,
@@ -4232,7 +4232,7 @@
"tokenizer_compatibility": 78,
"参数/模板问题": 9
},
"failureCount": 762,
"failureCount": 763,
"failureRate": 0.9695,
"framework": "vllm",
"pendingCount": 0,
@@ -4242,8 +4242,8 @@
"successRate": 0.0305,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 786,
"unresolvedFailureCount": 137
"total": 787,
"unresolvedFailureCount": 138
},
"MetaX_c-500|vllm|unknown": {
"attributableFailureCount": 1,
@@ -5034,7 +5034,7 @@
"decisionSuccessRate": 0.0231,
"decisionTotal": 3588,
"failureBreakdown": {
"ambiguous_runtime": 1457,
"ambiguous_runtime": 1459,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
@@ -5048,15 +5048,15 @@
"tokenizer_compatibility": 410,
"参数/模板问题": 41
},
"failureCount": 5867,
"failureCount": 5869,
"failureRate": 0.9861,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 864,
"successCount": 83,
"successRate": 0.0139,
"total": 5950,
"unresolvedFailureCount": 1498
"total": 5952,
"unresolvedFailureCount": 1500
},
"vllm-customized": {
"attributableFailureCount": 2,
@@ -5194,7 +5194,7 @@
"unresolvedFailureCount": 58
}
},
"generatedAt": "2026-09-21T02:55:04.498715+00:00",
"generatedAt": "2026-09-21T02:58:32.910619+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 90,
@@ -5227,7 +5227,7 @@
"decisionSuccessRate": 0.1671,
"decisionTotal": 371,
"failureBreakdown": {
"ambiguous_runtime": 156,
"ambiguous_runtime": 157,
"context_length": 1,
"framework_architecture_unsupported": 169,
"memory_capacity": 18,
@@ -5239,15 +5239,15 @@
"日志缺失": 14,
"验证失败": 175
},
"failureCount": 909,
"failureRate": 0.9361,
"failureCount": 910,
"failureRate": 0.9362,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 62,
"successRate": 0.0639,
"total": 971,
"unresolvedFailureCount": 599
"successRate": 0.0638,
"total": 972,
"unresolvedFailureCount": 600
},
"Biren_166m": {
"attributableFailureCount": 179,
@@ -5465,7 +5465,7 @@
"decisionSuccessRate": 0.1808,
"decisionTotal": 802,
"failureBreakdown": {
"ambiguous_runtime": 300,
"ambiguous_runtime": 301,
"architecture_compatibility": 21,
"backend_operator": 43,
"context_length": 59,
@@ -5480,15 +5480,15 @@
"日志缺失": 15,
"验证失败": 48
},
"failureCount": 1423,
"failureRate": 0.9075,
"failureCount": 1424,
"failureRate": 0.9076,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 5,
"successCount": 145,
"successRate": 0.0925,
"total": 1568,
"unresolvedFailureCount": 761
"successRate": 0.0924,
"total": 1569,
"unresolvedFailureCount": 762
},
"Mthreads_s4000": {
"attributableFailureCount": 71,
@@ -13787,14 +13787,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 2,
"ambiguous_runtime": 3,
"framework_architecture_unsupported": 1
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T00:42:10.765065+00:00",
"lastTerminalAt": "2026-09-21T02:58:30.354798+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -13802,8 +13802,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 2
"total": 4,
"unresolvedFailureCount": 3
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 5,
@@ -14152,26 +14152,26 @@
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.5,
"decisionSuccessRate": 0.5,
"decisionTotal": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 1
},
"failureCount": 2,
"failureRate": 0.6667,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-18T11:36:11.987002+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.3333,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 3,
"total": 2,
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|vllm|text-generation": {
@@ -14207,9 +14207,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5
"ambiguous_runtime": 4
},
"failureCount": 5,
"failureCount": 4,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
@@ -14221,8 +14221,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 5
"total": 4,
"unresolvedFailureCount": 4
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 0,
@@ -14332,17 +14332,17 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 4,
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 1,
"model_load": 1,
"runtime_memory": 2,
"tokenizer_compatibility": 1
},
"failureCount": 9,
"failureCount": 10,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T02:38:57.372787+00:00",
"lastTerminalAt": "2026-09-21T02:58:30.354826+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -14350,8 +14350,8 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 9,
"unresolvedFailureCount": 4
"total": 10,
"unresolvedFailureCount": 5
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 7,
@@ -29931,15 +29931,15 @@
"unresolvedFailureCount": 1
}
},
"terminalRecords": 16057,
"totalRecords": 16224,
"terminalRecords": 16059,
"totalRecords": 16226,
"totals": {
"attributableFailureCount": 5830,
"decisionFailureRate": 0.8617,
"decisionSuccessRate": 0.1383,
"decisionTotal": 6766,
"failureBreakdown": {
"ambiguous_runtime": 3836,
"ambiguous_runtime": 3838,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
@@ -29955,31 +29955,31 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 15121,
"failureCount": 15123,
"failureRate": 0.9417,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 936,
"successRate": 0.0583,
"total": 16057,
"unresolvedFailureCount": 8369
"total": 16059,
"unresolvedFailureCount": 8371
},
"warnings": [
"GPU Iluvatar_mrv-100 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 Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Kunlunxin_p-800 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 Biren_166m 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_bi-100 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 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 Cambricon_mlu-370-x4 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU hygon_k100-ai 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 MetaX_c-500 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。",
"组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Sunrise_pt-200-x1|vllm_fix_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 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -30016,6 +30016,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16224,
"summarizedRecords": 16226,
"version": 1
}

View File

@@ -1,3 +1,5 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T02:58:30.354798+00:00", "modelId": "tencent-community/WeDLM-7B-Instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:57:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079148", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T02:58:30.354826+00:00", "modelId": "tencent-community/WeDLM-7B-Instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:57:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4080024", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446730+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:08+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4860052", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446754+00:00", "modelId": "Edge0/Edge0-35B-A3B-preview", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:08+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4849007", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446763+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:08+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4860051", "taskType": "text-generation", "verifyResult": null}
@@ -296,5 +298,3 @@
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-17T03:22:03.500197+00:00", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T03:21:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4610340", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-17T03:13:03.854062+00:00", "modelId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T03:09:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4460612", "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": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-17T03:13:03.854075+00:00", "modelId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T03:05:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4458152", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-17T02:54:53.830188+00:00", "modelId": "pfnet/plamo-3-nict-8b-base", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T02:53:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4460545", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-17T02:37:21.545556+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-17T02:29:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4610409", "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