state: generation 21520 (cycle)

This commit is contained in:
2026-10-06 19:38:43 +00:00
parent 6c162e8843
commit 4d1be2d328
10 changed files with 1998 additions and 2002 deletions

View File

@@ -2777,7 +2777,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-10-06T19:27:03.366397+00:00",
"generatedAt": "2026-10-06T19:35:17.200993+00:00",
"summary": {
"activeBlockCount": 140,
"byGpuFramework": {

View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-10-06T19:20:35.083844+00:00",
"communityAttemptedAt": "2026-10-06T19:36:49.678214+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-10-06T19:20:35.083844+00:00",
"communityUpdatedAt": "2026-10-06T19:36:49.678214+00:00",
"frameworkAttemptedAt": "2026-10-06T14:47:12.986887+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -434,121 +434,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-06T19:34:13.758416+00:00",
"generatedAt": "2026-10-06T19:36:49.678214+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 1112.255033557047,
"backlogHours": 1127.3469387755101,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.822261201328149,
"queueFactor": 0.9978427409877711,
"queueWeight": 0.9978427409877711,
"qualityFactor": 0.7742063360942855,
"queueFactor": 0.9987442975634993,
"queueWeight": 0.9987442975634993,
"recentSuccess": 43,
"recentSuccessRate": 0.28859060402684567,
"recentTerminal": 149,
"recentWilsonLowerBound": 0.22187300471396995,
"recentSuccessRate": 0.2925170068027211,
"recentTerminal": 147,
"recentWilsonLowerBound": 0.22501034967520298,
"running": 8,
"selectionWeight": 0.8204873709411776,
"selectionWeight": 0.7732341633116976,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 24.833333333333332,
"waiting": 27621
"throughputPerHour": 24.5,
"waiting": 27620
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1379.3129770992366,
"backlogHours": 1434.047619047619,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.5,
"queueFactor": 0.966147280903986,
"queueWeight": 0.966147280903986,
"queueFactor": 0.9633373863752328,
"queueWeight": 0.9633373863752328,
"recentSuccess": 59,
"recentSuccessRate": 0.45038167938931295,
"recentTerminal": 131,
"recentWilsonLowerBound": 0.36780548101323723,
"running": 10,
"selectionWeight": 2.415368202259965,
"recentSuccessRate": 0.46825396825396826,
"recentTerminal": 126,
"recentWilsonLowerBound": 0.38335752175424204,
"running": 8,
"selectionWeight": 2.4083434659380822,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 21.833333333333332,
"throughputPerHour": 21.0,
"waiting": 30115
},
"Biren_166m": {
"available": true,
"backlogHours": 127.38461538461539,
"backlogHours": 132.48,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.43319921589308924,
"qualityFactor": 0.3620643319868545,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 45,
"recentSuccessRate": 0.21634615384615385,
"recentTerminal": 208,
"recentWilsonLowerBound": 0.1658037706036833,
"recentSuccess": 42,
"recentSuccessRate": 0.21,
"recentTerminal": 200,
"recentWilsonLowerBound": 0.1592832952786342,
"running": 8,
"selectionWeight": 0.563158980661016,
"selectionWeight": 0.4706836315829109,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 34.666666666666664,
"throughputPerHour": 33.333333333333336,
"waiting": 4416
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1430.6666666666667,
"backlogHours": 1471.457142857143,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.25589699890807416,
"queueFactor": 0.9608641509070607,
"queueWeight": 0.9608641509070607,
"recentSuccess": 15,
"recentSuccessRate": 0.20833333333333334,
"recentTerminal": 72,
"recentWilsonLowerBound": 0.1305194089904011,
"running": 8,
"selectionWeight": 0.24588225257547172,
"qualityFactor": 0.29839942094096134,
"queueFactor": 0.9596233536563841,
"queueWeight": 0.9596233536563841,
"recentSuccess": 16,
"recentSuccessRate": 0.22857142857142856,
"recentTerminal": 70,
"recentWilsonLowerBound": 0.14587940188627677,
"running": 7,
"selectionWeight": 0.28635105305248837,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.0,
"waiting": 17168
"throughputPerHour": 11.666666666666666,
"waiting": 17167
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 405.40425531914894,
"backlogHours": 408.3,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.506392859552754,
"queueFactor": 1.1609393018819343,
"queueWeight": 1.1609393018819343,
"recentSuccess": 34,
"recentSuccessRate": 0.24113475177304963,
"recentTerminal": 141,
"recentWilsonLowerBound": 0.1779969432886709,
"qualityFactor": 0.5455356093579545,
"queueFactor": 1.1630972909208526,
"queueWeight": 1.1630972909208526,
"recentSuccess": 36,
"recentSuccessRate": 0.2571428571428571,
"recentTerminal": 140,
"recentWilsonLowerBound": 0.19190942531957864,
"running": 7,
"selectionWeight": 0.5878913728471706,
"selectionWeight": 0.6345109893450934,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 23.5,
"throughputPerHour": 23.333333333333332,
"waiting": 9527
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 46.49315068493151,
"backlogHours": 46.71925754060325,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -557,148 +557,148 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 16,
"recentSuccessRate": 0.0365296803652968,
"recentTerminal": 438,
"recentWilsonLowerBound": 0.022608176941540287,
"recentSuccess": 13,
"recentSuccessRate": 0.030162412993039442,
"recentTerminal": 431,
"recentWilsonLowerBound": 0.01771014787160388,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 73.0,
"waiting": 3394
"throughputPerHour": 71.83333333333333,
"waiting": 3356
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 188.89756097560976,
"backlogHours": 186.17391304347825,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.15680641666983475,
"qualityFactor": 0.12815897995229963,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 30,
"recentSuccessRate": 0.14634146341463414,
"recentTerminal": 205,
"recentWilsonLowerBound": 0.1044702565533821,
"recentSuccess": 29,
"recentSuccessRate": 0.14009661835748793,
"recentTerminal": 207,
"recentWilsonLowerBound": 0.09934672373950382,
"running": 3,
"selectionWeight": 0.20384834167078517,
"selectionWeight": 0.16660667393798953,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 34.166666666666664,
"waiting": 6454
"throughputPerHour": 34.5,
"waiting": 6423
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2462.0526315789475,
"backlogHours": 2462.2105263157896,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.7448510715765768,
"queueFactor": 0.8857234833998042,
"queueWeight": 0.8857234833998042,
"qualityFactor": 0.6799871478070678,
"queueFactor": 0.8883092278160539,
"queueWeight": 0.8883092278160539,
"recentSuccess": 13,
"recentSuccessRate": 0.34210526315789475,
"recentTerminal": 38,
"recentWilsonLowerBound": 0.21212220026458956,
"running": 2,
"selectionWeight": 0.6597320857308825,
"selectionWeight": 0.6040388581933374,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 6.333333333333333,
"waiting": 15593
"waiting": 15594
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 459.8048780487805,
"backlogHours": 455.8548387096774,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.19172014566092024,
"queueFactor": 1.1392176977939916,
"queueWeight": 1.1392176977939916,
"recentSuccess": 21,
"recentSuccessRate": 0.17073170731707318,
"recentTerminal": 123,
"recentWilsonLowerBound": 0.1144659352748107,
"running": 9,
"selectionWeight": 0.2184109829605623,
"qualityFactor": 0.19483805345967845,
"queueFactor": 1.1440340900629702,
"queueWeight": 1.1440340900629702,
"recentSuccess": 22,
"recentSuccessRate": 0.1774193548387097,
"recentTerminal": 124,
"recentWilsonLowerBound": 0.12018398862314911,
"running": 8,
"selectionWeight": 0.22290137519938358,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 20.5,
"waiting": 9426
"throughputPerHour": 20.666666666666668,
"waiting": 9421
},
"MetaX_c-500": {
"available": true,
"backlogHours": 831.15,
"backlogHours": 831.0749999999999,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 1.4623541854207023,
"queueFactor": 1.0424154699695,
"queueWeight": 1.0424154699695,
"recentSuccess": 31,
"recentSuccessRate": 0.3875,
"qualityFactor": 1.5785515642913073,
"queueFactor": 1.0454828628380173,
"queueWeight": 1.0454828628380173,
"recentSuccess": 33,
"recentSuccessRate": 0.4125,
"recentTerminal": 80,
"recentWilsonLowerBound": 0.2882439968827771,
"running": 5,
"selectionWeight": 1.5243806254571868,
"recentWilsonLowerBound": 0.31105686511513087,
"running": 4,
"selectionWeight": 1.6503486085727064,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 13.333333333333334,
"waiting": 11082
"waiting": 11081
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1180.6486486486488,
"backlogHours": 1191.4363636363637,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.8749761148541934,
"queueFactor": 0.9889507362657926,
"queueWeight": 0.9889507362657926,
"qualityFactor": 0.8155802166577754,
"queueFactor": 0.9904950819709447,
"queueWeight": 0.9904950819709447,
"recentSuccess": 34,
"recentSuccessRate": 0.3063063063063063,
"recentTerminal": 111,
"recentWilsonLowerBound": 0.22822909598063226,
"running": 5,
"selectionWeight": 0.8653082730000372,
"recentSuccessRate": 0.3090909090909091,
"recentTerminal": 110,
"recentWilsonLowerBound": 0.23039855434915507,
"running": 4,
"selectionWeight": 0.807828193552324,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.5,
"waiting": 21842
"throughputPerHour": 18.333333333333332,
"waiting": 21843
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 2087.877551020408,
"backlogHours": 2176.851063829787,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.1930171308080899,
"queueFactor": 0.907897887475803,
"queueWeight": 0.907897887475803,
"qualityFactor": 0.19381169367550305,
"queueFactor": 0.904875112637795,
"queueWeight": 0.904875112637795,
"recentSuccess": 10,
"recentSuccessRate": 0.20408163265306123,
"recentTerminal": 49,
"recentWilsonLowerBound": 0.11481727042813812,
"recentSuccessRate": 0.2127659574468085,
"recentTerminal": 47,
"recentWilsonLowerBound": 0.11989580124247318,
"running": 2,
"selectionWeight": 0.17523984530730558,
"selectionWeight": 0.17537537814514265,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 8.166666666666666,
"waiting": 17051
"throughputPerHour": 7.833333333333333,
"waiting": 17052
},
"Vastai_va16": {
"available": true,
@@ -709,14 +709,14 @@
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.05,
"queueFactor": 0.9428842081913421,
"queueWeight": 0.9428842081913421,
"queueFactor": 0.9456459217534472,
"queueWeight": 0.9456459217534472,
"recentSuccess": 2,
"recentSuccessRate": 0.031746031746031744,
"recentTerminal": 63,
"recentWilsonLowerBound": 0.008749344040296984,
"running": 16,
"selectionWeight": 0.04714421040956711,
"selectionWeight": 0.047282296087672364,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 10.5,
@@ -724,30 +724,30 @@
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 1080.457627118644,
"backlogHours": 1108.5391304347825,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 0.8205621587423922,
"queueFactor": 1.00219353845393,
"queueWeight": 1.00219353845393,
"recentSuccess": 35,
"recentSuccessRate": 0.2966101694915254,
"recentTerminal": 118,
"recentWilsonLowerBound": 0.22166449745305886,
"running": 7,
"selectionWeight": 0.8223620933914335,
"qualityFactor": 0.8557783083798159,
"queueFactor": 1.0012679087208847,
"queueWeight": 1.0012679087208847,
"recentSuccess": 36,
"recentSuccessRate": 0.3130434782608696,
"recentTerminal": 115,
"recentWilsonLowerBound": 0.2354926144761668,
"running": 6,
"selectionWeight": 0.8568633571601546,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 19.666666666666668,
"waiting": 21249
"throughputPerHour": 19.166666666666668,
"waiting": 21247
}
},
"queueAttemptedAt": "2026-10-06T19:25:58.170644+00:00",
"queueAttemptedAt": "2026-10-06T19:36:49.678214+00:00",
"queueError": null,
"queueUpdatedAt": "2026-10-06T19:25:58.170644+00:00",
"queueUpdatedAt": "2026-10-06T19:36:49.678214+00:00",
"supportedGpus": [
"Vastai_va16",
"Cambricon_mlu-370-x4",

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-10-06T19:34:13.758416+00:00",
"catalogUpdatedAt": "2026-10-06T19:36:49.678214+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-10-06T19:34:13.758416+00:00",
"generatedAt": "2026-10-06T19:36:49.678214+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6643,6 +6643,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-10-06T19:34:13.758416+00:00",
"taskTreeUpdatedAt": "2026-10-06T19:36:49.678214+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-06T19:00:42.555850+00:00",
"lastSyncTime": "2026-10-06T19:00:42.266417+00:00",
"generatedAt": "2026-10-06T19:35:17.107434+00:00",
"lastSyncTime": "2026-10-06T19:35:16.862376+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3217,10 +3217,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 124,
"ambiguous_runtime": 125,
"memory_capacity": 1
},
"failureCount": 125,
"failureCount": 126,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -3230,8 +3230,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 125,
"unresolvedFailureCount": 124
"total": 126,
"unresolvedFailureCount": 125
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 50,
@@ -5608,7 +5608,7 @@
"decisionSuccessRate": 0.0281,
"decisionTotal": 178,
"failureBreakdown": {
"ambiguous_runtime": 357,
"ambiguous_runtime": 358,
"backend_operator": 9,
"framework_architecture_unsupported": 47,
"memory_capacity": 10,
@@ -5617,15 +5617,15 @@
"tokenizer_compatibility": 95,
"参数/模板问题": 13
},
"failureCount": 568,
"failureCount": 569,
"failureRate": 0.9913,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 25,
"successCount": 5,
"successRate": 0.0087,
"total": 573,
"unresolvedFailureCount": 370
"total": 574,
"unresolvedFailureCount": 371
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 150,
@@ -5656,7 +5656,7 @@
"unresolvedFailureCount": 235
}
},
"generatedAt": "2026-10-06T19:00:42.537107+00:00",
"generatedAt": "2026-10-06T19:35:17.090433+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 119,
@@ -5719,7 +5719,7 @@
"decisionSuccessRate": 0.1147,
"decisionTotal": 218,
"failureBreakdown": {
"ambiguous_runtime": 268,
"ambiguous_runtime": 269,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 125,
@@ -5733,15 +5733,15 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 766,
"failureCount": 767,
"failureRate": 0.9684,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.0316,
"total": 791,
"unresolvedFailureCount": 571
"total": 792,
"unresolvedFailureCount": 572
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 759,
@@ -9575,9 +9575,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 14
"ambiguous_runtime": 15
},
"failureCount": 14,
"failureCount": 15,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5",
@@ -9589,8 +9589,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 14,
"unresolvedFailureCount": 14
"total": 15,
"unresolvedFailureCount": 15
},
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_vl|none": {
"attributableFailureCount": 0,
@@ -25019,9 +25019,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 11
"ambiguous_runtime": 12
},
"failureCount": 11,
"failureCount": 12,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -25033,8 +25033,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 11,
"unresolvedFailureCount": 11
"total": 12,
"unresolvedFailureCount": 12
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -26273,9 +26273,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
"ambiguous_runtime": 4
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-22T16:15:27.384896+00:00",
@@ -26288,8 +26288,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
"total": 4,
"unresolvedFailureCount": 4
},
"Biren_166m|vllm_fix_tokenizer|text-generation|smollm3|none": {
"attributableFailureCount": 0,
@@ -34722,9 +34722,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 7
"ambiguous_runtime": 8
},
"failureCount": 7,
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
@@ -34737,8 +34737,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 7
"total": 8,
"unresolvedFailureCount": 8
},
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|none|35": {
"attributableFailureCount": 0,
@@ -57546,15 +57546,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17342,
"totalRecords": 17566,
"terminalRecords": 17343,
"totalRecords": 17567,
"totals": {
"attributableFailureCount": 6235,
"decisionFailureRate": 0.8644,
"decisionSuccessRate": 0.1356,
"decisionTotal": 7213,
"failureBreakdown": {
"ambiguous_runtime": 4549,
"ambiguous_runtime": 4550,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 129,
@@ -57570,15 +57570,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16364,
"failureCount": 16365,
"failureRate": 0.9436,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 952,
"successCount": 978,
"successRate": 0.0564,
"total": 17342,
"unresolvedFailureCount": 9177
"total": 17343,
"unresolvedFailureCount": 9178
},
"warnings": [
"GPU MetaX_c-500 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -57587,14 +57587,14 @@
"GPU hygon_k100-ai 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 Ascend_910-b3 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 Iluvatar_mrv-100 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 Cambricon_mlu-370-x8 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-b4 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-100 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 Mthreads_s4000 本地统计失败率偏高(≥50%),建议重点关注。",
"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 Ascend_910-b3|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_mrv-100|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -57638,6 +57638,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17566,
"summarizedRecords": 17567,
"version": 1
}

View File

@@ -254,6 +254,7 @@
{"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_tokenizer_patch", "lastSyncTime": "2026-09-29T16:17:37.246200+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093197700, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093197700}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:29:25.979829+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997053", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-30T05:01:54.142796+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:29:25.977872+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997055", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-23T18:18:45.361433+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T08:17:20.243727+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4996859", "taskType": "text-generation", "verifyResult": null}
{"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": "2026-10-06T19:35:16.862376+00:00", "modelId": "blue2star/Qwen-Image-2.1-PE-T2I-ComfyUI", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29306922460, "estimatedRequiredGiB": 32.775, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29326950127, "modelscopeLicense": "other", "modelscopeParams": 18821595084, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:prompt-rewriting", "custom_tag:text-to-image"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29326950127}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:17:20.209866+00:00", "targetGpu": "Biren_166m", "taskId": "4996857", "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-customized", "lastSyncTime": "2026-09-22T08:29:00.965161+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:11:51.336512+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4996820", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-23T15:01:41.955014+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8239718268, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8239718268}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:09:36.692226+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4996782", "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", "lastSyncTime": "2026-09-26T21:44:28.758500+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093204103, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm", "custom_tag:quantized", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093204103}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:07:48.338371+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4996781", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-21T04:36:00.569175+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T04:35:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4576912", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569197+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:31:57+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969802", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569297+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:31:57+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969335", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569333+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:31:57+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969619", "taskType": "text-generation", "verifyResult": null}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff