state: generation 7086 (cycle)

This commit is contained in:
2026-09-14 08:31:47 +00:00
parent a9c3e19946
commit 3e176c67b6
10 changed files with 2331 additions and 2214 deletions

View File

@@ -1498,7 +1498,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-14T08:28:31.506869+00:00",
"generatedAt": "2026-09-14T08:31:46.239256+00:00",
"summary": {
"activeBlockCount": 75,
"byGpuFramework": {

View File

@@ -11,7 +11,7 @@
"1": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 515,
"listingErrors": 516,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0,
"mode": "incremental_decision_only",
"nextAccountIndex": 1,
"nextAccountIndex": 2,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-14T08:28:31.481012+00:00",
"updatedAt": "2026-09-14T08:31:46.214734+00:00",
"version": 1
}

View File

@@ -416,121 +416,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-14T08:26:41.589727+00:00",
"generatedAt": "2026-09-14T08:29:44.219271+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 949.3783783783783,
"backlogHours": 942.8456375838927,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.518541178161229,
"queueFactor": 0.9889458774025638,
"queueWeight": 0.9889458774025638,
"recentSuccess": 62,
"recentSuccessRate": 0.4189189189189189,
"recentTerminal": 148,
"recentWilsonLowerBound": 0.34246617038461147,
"qualityFactor": 1.8379510301922395,
"queueFactor": 0.988605262563196,
"queueWeight": 0.988605262563196,
"recentSuccess": 63,
"recentSuccessRate": 0.4228187919463087,
"recentTerminal": 149,
"recentWilsonLowerBound": 0.3464154337700474,
"running": 8,
"selectionWeight": 1.5017550378085796,
"selectionWeight": 1.8170080607814956,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 24.666666666666668,
"waiting": 23418
"throughputPerHour": 24.833333333333332,
"waiting": 23414
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1554.2803738317757,
"backlogHours": 1539.6666666666667,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.5,
"queueFactor": 0.9184574058937285,
"queueWeight": 0.9184574058937285,
"recentSuccess": 56,
"recentSuccessRate": 0.5233644859813084,
"recentTerminal": 107,
"recentWilsonLowerBound": 0.4295689431021738,
"queueFactor": 0.9184912032330096,
"queueWeight": 0.9184912032330096,
"recentSuccess": 53,
"recentSuccessRate": 0.49074074074074076,
"recentTerminal": 108,
"recentWilsonLowerBound": 0.398407280234078,
"running": 8,
"selectionWeight": 2.296143514734321,
"selectionWeight": 2.296228008082524,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.833333333333332,
"waiting": 27718
"throughputPerHour": 18.0,
"waiting": 27714
},
"Biren_166m": {
"available": true,
"backlogHours": 149.17460317460316,
"backlogHours": 151.61290322580646,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.111582148266448,
"qualityFactor": 0.12402502338754626,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 28,
"recentSuccessRate": 0.14814814814814814,
"recentTerminal": 189,
"recentWilsonLowerBound": 0.10452966572796771,
"recentSuccess": 27,
"recentSuccessRate": 0.14516129032258066,
"recentTerminal": 186,
"recentWilsonLowerBound": 0.10171950180324031,
"running": 2,
"selectionWeight": 0.1450567927463824,
"selectionWeight": 0.16123253040381014,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 31.5,
"waiting": 4699
"throughputPerHour": 31.0,
"waiting": 4700
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1170.857142857143,
"backlogHours": 1141.139240506329,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.507200096282347,
"queueFactor": 0.958325045443387,
"queueWeight": 0.958325045443387,
"qualityFactor": 0.5642122679600595,
"queueFactor": 0.9607009306448449,
"queueWeight": 0.9607009306448449,
"recentSuccess": 23,
"recentSuccessRate": 0.2987012987012987,
"recentTerminal": 77,
"recentWilsonLowerBound": 0.2080375145120104,
"recentSuccessRate": 0.2911392405063291,
"recentTerminal": 79,
"recentWilsonLowerBound": 0.2025185332205674,
"running": 7,
"selectionWeight": 0.48606255531867043,
"selectionWeight": 0.5420392509104678,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.833333333333334,
"waiting": 15026
"throughputPerHour": 13.166666666666666,
"waiting": 15025
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 500.5321100917431,
"backlogHours": 505.22222222222223,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.3181464972120201,
"queueFactor": 1.0886132934434891,
"queueWeight": 1.0886132934434891,
"qualityFactor": 0.38344761540067024,
"queueFactor": 1.0855920160506738,
"queueWeight": 1.0855920160506738,
"recentSuccess": 26,
"recentSuccessRate": 0.23853211009174313,
"recentTerminal": 109,
"recentWilsonLowerBound": 0.16829549205620983,
"recentSuccessRate": 0.24074074074074073,
"recentTerminal": 108,
"recentWilsonLowerBound": 0.16991077352557898,
"running": 7,
"selectionWeight": 0.346338506127487,
"selectionWeight": 0.416267669852637,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.166666666666668,
"waiting": 9093
"throughputPerHour": 18.0,
"waiting": 9094
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 52.01298701298701,
"backlogHours": 50.0625,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -540,196 +540,196 @@
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 13,
"recentSuccessRate": 0.04220779220779221,
"recentTerminal": 308,
"recentWilsonLowerBound": 0.02482956319203055,
"recentSuccessRate": 0.040625,
"recentTerminal": 320,
"recentWilsonLowerBound": 0.02389250371261424,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 51.333333333333336,
"throughputPerHour": 53.333333333333336,
"waiting": 2670
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 146.1942857142857,
"backlogHours": 143.69662921348313,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.760662612209962,
"qualityFactor": 0.824100046243901,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 55,
"recentSuccessRate": 0.3142857142857143,
"recentTerminal": 175,
"recentWilsonLowerBound": 0.2501194406850868,
"running": 6,
"selectionWeight": 0.9888613958729506,
"recentSuccess": 54,
"recentSuccessRate": 0.30337078651685395,
"recentTerminal": 178,
"recentWilsonLowerBound": 0.24057722254988562,
"running": 4,
"selectionWeight": 1.0713300601170712,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 29.166666666666668,
"waiting": 4264
"throughputPerHour": 29.666666666666668,
"waiting": 4263
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2336.85,
"backlogHours": 2280.146341463415,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.0144571226214179,
"queueFactor": 0.8639603255042868,
"queueWeight": 0.8639603255042868,
"qualityFactor": 1.1287988159605913,
"queueFactor": 0.8659535544454422,
"queueWeight": 0.8659535544454422,
"recentSuccess": 17,
"recentSuccessRate": 0.425,
"recentTerminal": 40,
"recentWilsonLowerBound": 0.2850916852481588,
"recentSuccessRate": 0.4146341463414634,
"recentTerminal": 41,
"recentWilsonLowerBound": 0.2775633082533015,
"running": 2,
"selectionWeight": 0.8764507058701424,
"selectionWeight": 0.9774873469348806,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 6.666666666666667,
"waiting": 15579
"throughputPerHour": 6.833333333333333,
"waiting": 15581
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 813.7590361445783,
"backlogHours": 804.1428571428571,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.6581511469958199,
"queueFactor": 1.0120781555507812,
"queueWeight": 1.0120781555507812,
"qualityFactor": 0.7555100310596299,
"queueFactor": 1.0124859983489767,
"queueWeight": 1.0124859983489767,
"recentSuccess": 27,
"recentSuccessRate": 0.3253012048192771,
"recentTerminal": 83,
"recentWilsonLowerBound": 0.23419186209445625,
"recentSuccessRate": 0.32142857142857145,
"recentTerminal": 84,
"recentWilsonLowerBound": 0.23125977350162447,
"running": 7,
"selectionWeight": 0.6661003989251605,
"selectionWeight": 0.7649433280600757,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 13.833333333333334,
"waiting": 11257
"throughputPerHour": 14.0,
"waiting": 11258
},
"MetaX_c-500": {
"available": true,
"backlogHours": 729.6631578947369,
"backlogHours": 700.1818181818181,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.6970545191385844,
"queueFactor": 1.028774194767134,
"queueWeight": 1.028774194767134,
"qualityFactor": 0.7479607118910048,
"queueFactor": 1.0337306256192873,
"queueWeight": 1.0337306256192873,
"recentSuccess": 31,
"recentSuccessRate": 0.3263157894736842,
"recentTerminal": 95,
"recentWilsonLowerBound": 0.24038572025731433,
"recentSuccessRate": 0.31313131313131315,
"recentTerminal": 99,
"recentWilsonLowerBound": 0.23020651977353204,
"running": 4,
"selectionWeight": 0.717111701635589,
"selectionWeight": 0.7731898946417358,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 15.833333333333334,
"throughputPerHour": 16.5,
"waiting": 11553
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 2114.25,
"backlogHours": 2147.904761904762,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 1.9202155699014916,
"queueFactor": 0.8770310596514,
"queueWeight": 0.8770310596514,
"recentSuccess": 32,
"recentSuccessRate": 0.5,
"recentTerminal": 64,
"recentWilsonLowerBound": 0.3810188849321495,
"qualityFactor": 2.1583585607464966,
"queueFactor": 0.8737491258269602,
"queueWeight": 0.8737491258269602,
"recentSuccess": 31,
"recentSuccessRate": 0.49206349206349204,
"recentTerminal": 63,
"recentWilsonLowerBound": 0.3726660281435346,
"running": 4,
"selectionWeight": 1.6840886960298223,
"selectionWeight": 1.8858639056733872,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 10.666666666666666,
"waiting": 22552
"throughputPerHour": 10.5,
"waiting": 22553
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 3044.4827586206898,
"backlogHours": 3678.5,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.23619658114752884,
"queueFactor": 0.8303503958273946,
"queueWeight": 0.8303503958273946,
"recentSuccess": 8,
"recentSuccessRate": 0.27586206896551724,
"recentTerminal": 29,
"recentWilsonLowerBound": 0.1469858133850274,
"qualityFactor": 0.17838377220845048,
"queueFactor": 0.8060062200410748,
"queueWeight": 0.8060062200410748,
"recentSuccess": 6,
"recentSuccessRate": 0.25,
"recentTerminal": 24,
"recentWilsonLowerBound": 0.11999203479342334,
"running": 2,
"selectionWeight": 0.1961259246489279,
"selectionWeight": 0.1437784299544013,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 4.833333333333333,
"waiting": 14715
"throughputPerHour": 4.0,
"waiting": 14714
},
"Vastai_va16": {
"available": true,
"backlogHours": 1411.9245283018868,
"backlogHours": 1438.846153846154,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.19443583973879877,
"queueFactor": 0.9317871188800116,
"queueWeight": 0.9317871188800116,
"qualityFactor": 0.23971016443212614,
"queueFactor": 0.9278694018866794,
"queueWeight": 0.9278694018866794,
"recentSuccess": 12,
"recentSuccessRate": 0.22641509433962265,
"recentTerminal": 53,
"recentWilsonLowerBound": 0.13454499977265524,
"recentSuccessRate": 0.23076923076923078,
"recentTerminal": 52,
"recentWilsonLowerBound": 0.13724127341871611,
"running": 16,
"selectionWeight": 0.18117281091723098,
"selectionWeight": 0.22241972689779446,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 8.833333333333334,
"waiting": 12472
"throughputPerHour": 8.666666666666666,
"waiting": 12470
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 583.4634146341464,
"backlogHours": 569.6666666666666,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 0.2943553141957113,
"queueFactor": 1.0638646549889366,
"queueWeight": 1.0638646549889366,
"recentSuccess": 28,
"recentSuccessRate": 0.22764227642276422,
"recentTerminal": 123,
"recentWilsonLowerBound": 0.16245354051668648,
"qualityFactor": 0.3947749468470906,
"queueFactor": 1.066217695867679,
"queueWeight": 1.066217695867679,
"recentSuccess": 30,
"recentSuccessRate": 0.23809523809523808,
"recentTerminal": 126,
"recentWilsonLowerBound": 0.17217416354451306,
"running": 6,
"selectionWeight": 0.31315421478098043,
"selectionWeight": 0.42091603421359036,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 20.5,
"waiting": 11961
"throughputPerHour": 21.0,
"waiting": 11963
}
},
"queueAttemptedAt": "2026-09-14T08:17:35.448359+00:00",
"queueAttemptedAt": "2026-09-14T08:29:44.219271+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-14T08:17:35.448359+00:00",
"queueUpdatedAt": "2026-09-14T08:29:44.219271+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": "2026-09-14T07:52:31.153148+00:00",
"lastSyncTime": "2026-09-14T07:52:30.913060+00:00",
"generatedAt": "2026-09-14T08:29:32.873595+00:00",
"lastSyncTime": "2026-09-14T08:29:32.453371+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1679,31 +1679,31 @@
"unresolvedFailureCount": 35
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 31,
"decisionFailureRate": 0.9688,
"decisionSuccessRate": 0.0312,
"decisionTotal": 32,
"attributableFailureCount": 32,
"decisionFailureRate": 0.9697,
"decisionSuccessRate": 0.0303,
"decisionTotal": 33,
"failureBreakdown": {
"ambiguous_runtime": 29,
"ambiguous_runtime": 30,
"backend_operator": 4,
"framework_architecture_unsupported": 23,
"framework_architecture_unsupported": 24,
"memory_capacity": 1,
"model_load": 2,
"tokenizer_compatibility": 1,
"验证失败": 27
},
"failureCount": 87,
"failureRate": 0.9886,
"failureCount": 89,
"failureRate": 0.9889,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0114,
"successRate": 0.0111,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 88,
"unresolvedFailureCount": 56
"total": 90,
"unresolvedFailureCount": 57
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 4,
@@ -1779,16 +1779,17 @@
"unresolvedFailureCount": 47
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 7,
"attributableFailureCount": 8,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 20,
"framework_architecture_unsupported": 7,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 30,
"failureCount": 31,
"failureRate": 1.0,
"framework": "vllm-mlu",
"pendingCount": 0,
@@ -1798,7 +1799,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 30,
"total": 31,
"unresolvedFailureCount": 23
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
@@ -1931,28 +1932,28 @@
"unresolvedFailureCount": 32
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 8,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 10,
"attributableFailureCount": 9,
"decisionFailureRate": 0.8182,
"decisionSuccessRate": 0.1818,
"decisionTotal": 11,
"failureBreakdown": {
"ambiguous_runtime": 6,
"backend_operator": 3,
"framework_architecture_unsupported": 3,
"model_load": 1,
"runtime_memory": 1
"runtime_memory": 2
},
"failureCount": 14,
"failureRate": 0.875,
"failureCount": 15,
"failureRate": 0.8824,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.125,
"successRate": 0.1176,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 16,
"total": 17,
"unresolvedFailureCount": 6
},
"Iluvatar_bi-150|vllm|text-generation": {
@@ -2080,10 +2081,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 35,
"ambiguous_runtime": 36,
"参数/模板问题": 1
},
"failureCount": 36,
"failureCount": 37,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2093,8 +2094,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 36,
"unresolvedFailureCount": 36
"total": 37,
"unresolvedFailureCount": 37
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2510,14 +2511,14 @@
"unresolvedFailureCount": 8
},
"unknown": {
"attributableFailureCount": 159,
"decisionFailureRate": 0.7465,
"decisionSuccessRate": 0.2535,
"decisionTotal": 213,
"attributableFailureCount": 160,
"decisionFailureRate": 0.7477,
"decisionSuccessRate": 0.2523,
"decisionTotal": 214,
"failureBreakdown": {
"ambiguous_runtime": 147,
"ambiguous_runtime": 148,
"backend_operator": 4,
"framework_architecture_unsupported": 102,
"framework_architecture_unsupported": 103,
"memory_capacity": 5,
"model_load": 45,
"platform_infrastructure": 1,
@@ -2525,15 +2526,15 @@
"参数/模板问题": 61,
"验证失败": 673
},
"failureCount": 1041,
"failureRate": 0.9507,
"failureCount": 1043,
"failureRate": 0.9508,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 54,
"successRate": 0.0493,
"total": 1095,
"unresolvedFailureCount": 881
"successRate": 0.0492,
"total": 1097,
"unresolvedFailureCount": 882
},
"vllm": {
"attributableFailureCount": 310,
@@ -2563,23 +2564,24 @@
"unresolvedFailureCount": 234
},
"vllm-mlu": {
"attributableFailureCount": 7,
"attributableFailureCount": 8,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 20,
"framework_architecture_unsupported": 7,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 30,
"failureCount": 31,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 30,
"total": 31,
"unresolvedFailureCount": 23
},
"vllm-patch-tokenizer": {
@@ -2602,25 +2604,25 @@
"unresolvedFailureCount": 8
},
"vllm_0_17_0_corex_4_4_0": {
"attributableFailureCount": 8,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 10,
"attributableFailureCount": 9,
"decisionFailureRate": 0.8182,
"decisionSuccessRate": 0.1818,
"decisionTotal": 11,
"failureBreakdown": {
"ambiguous_runtime": 6,
"backend_operator": 3,
"framework_architecture_unsupported": 3,
"model_load": 1,
"runtime_memory": 1
"runtime_memory": 2
},
"failureCount": 14,
"failureRate": 0.875,
"failureCount": 15,
"failureRate": 0.8824,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.125,
"total": 16,
"successRate": 0.1176,
"total": 17,
"unresolvedFailureCount": 6
},
"vllm_fix_tokenizer": {
@@ -2629,7 +2631,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 53,
"failureBreakdown": {
"ambiguous_runtime": 37,
"ambiguous_runtime": 38,
"backend_operator": 2,
"framework_architecture_unsupported": 8,
"model_load": 1,
@@ -2637,15 +2639,15 @@
"tokenizer_compatibility": 42,
"参数/模板问题": 7
},
"failureCount": 101,
"failureCount": 102,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 0,
"successRate": 0.0,
"total": 101,
"unresolvedFailureCount": 44
"total": 102,
"unresolvedFailureCount": 45
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 0,
@@ -2666,7 +2668,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-14T07:52:31.148510+00:00",
"generatedAt": "2026-09-14T08:29:32.865753+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 33,
@@ -2717,28 +2719,28 @@
"unresolvedFailureCount": 223
},
"Biren_166m": {
"attributableFailureCount": 35,
"decisionFailureRate": 0.9722,
"decisionSuccessRate": 0.0278,
"decisionTotal": 36,
"attributableFailureCount": 36,
"decisionFailureRate": 0.973,
"decisionSuccessRate": 0.027,
"decisionTotal": 37,
"failureBreakdown": {
"ambiguous_runtime": 29,
"ambiguous_runtime": 30,
"backend_operator": 4,
"framework_architecture_unsupported": 26,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"model_load": 3,
"tokenizer_compatibility": 1,
"验证失败": 27
},
"failureCount": 91,
"failureRate": 0.9891,
"failureCount": 93,
"failureRate": 0.9894,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0109,
"total": 92,
"unresolvedFailureCount": 56
"successRate": 0.0106,
"total": 94,
"unresolvedFailureCount": 57
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 22,
@@ -2763,26 +2765,26 @@
"unresolvedFailureCount": 75
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 18,
"decisionFailureRate": 0.9,
"decisionSuccessRate": 0.1,
"decisionTotal": 20,
"attributableFailureCount": 19,
"decisionFailureRate": 0.9048,
"decisionSuccessRate": 0.0952,
"decisionTotal": 21,
"failureBreakdown": {
"ambiguous_runtime": 40,
"framework_architecture_unsupported": 16,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 18,
"验证失败": 22
},
"failureCount": 98,
"failureRate": 0.98,
"failureCount": 99,
"failureRate": 0.9802,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.02,
"total": 100,
"successRate": 0.0198,
"total": 101,
"unresolvedFailureCount": 80
},
"Iluvatar_bi-100": {
@@ -2805,28 +2807,28 @@
"unresolvedFailureCount": 29
},
"Iluvatar_bi-150": {
"attributableFailureCount": 35,
"decisionFailureRate": 0.814,
"decisionSuccessRate": 0.186,
"decisionTotal": 43,
"attributableFailureCount": 36,
"decisionFailureRate": 0.8182,
"decisionSuccessRate": 0.1818,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 14,
"backend_operator": 6,
"framework_architecture_unsupported": 17,
"model_load": 8,
"repository_structure": 1,
"runtime_memory": 3,
"runtime_memory": 4,
"参数/模板问题": 2,
"验证失败": 30
},
"failureCount": 81,
"failureRate": 0.9101,
"failureCount": 82,
"failureRate": 0.9111,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 8,
"successRate": 0.0899,
"total": 89,
"successRate": 0.0889,
"total": 90,
"unresolvedFailureCount": 46
},
"Iluvatar_mrv-100": {
@@ -2859,20 +2861,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 74,
"ambiguous_runtime": 75,
"memory_capacity": 1,
"参数/模板问题": 1,
"验证失败": 23
},
"failureCount": 99,
"failureCount": 100,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 99,
"unresolvedFailureCount": 98
"total": 100,
"unresolvedFailureCount": 99
},
"MetaX_c-500": {
"attributableFailureCount": 55,
@@ -3338,6 +3340,29 @@
"total": 2,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"tokenizer_compatibility": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|rwkv7|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -3566,6 +3591,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"runtime_memory": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|gptq": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -3917,9 +3965,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3",
@@ -3931,8 +3979,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|rwkv7|none": {
"attributableFailureCount": 0,
@@ -4865,23 +4913,23 @@
"unresolvedFailureCount": 11
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 8,
"consecutiveFailures": 8,
"attributableFailureCount": 9,
"consecutiveFailures": 9,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 8,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 9,
"ambiguous_runtime": 10,
"backend_operator": 2,
"framework_architecture_unsupported": 5,
"framework_architecture_unsupported": 6,
"model_load": 1
},
"failureCount": 17,
"failureCount": 19,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-14T04:51:03.045568+00:00",
"lastTerminalAt": "2026-09-14T08:29:32.453358+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4889,8 +4937,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 17,
"unresolvedFailureCount": 9
"total": 19,
"unresolvedFailureCount": 10
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 2,
@@ -5850,6 +5898,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3|none|24": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"tokenizer_compatibility": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 24,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|rwkv7|none|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -6206,6 +6278,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|compressed-tensors|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"runtime_memory": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|gptq|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -6758,6 +6854,30 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none|24": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 24,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -8029,35 +8149,35 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1817,
"totalRecords": 1910,
"terminalRecords": 1822,
"totalRecords": 1915,
"totals": {
"attributableFailureCount": 544,
"decisionFailureRate": 0.9022,
"decisionSuccessRate": 0.0978,
"decisionTotal": 603,
"attributableFailureCount": 547,
"decisionFailureRate": 0.9026,
"decisionSuccessRate": 0.0974,
"decisionTotal": 606,
"failureBreakdown": {
"ambiguous_runtime": 426,
"ambiguous_runtime": 428,
"backend_operator": 43,
"framework_architecture_unsupported": 346,
"framework_architecture_unsupported": 347,
"memory_capacity": 12,
"model_load": 76,
"platform_infrastructure": 6,
"repository_structure": 8,
"runtime_memory": 7,
"tokenizer_compatibility": 52,
"runtime_memory": 8,
"tokenizer_compatibility": 53,
"参数/模板问题": 109,
"验证失败": 673
},
"failureCount": 1758,
"failureRate": 0.9675,
"failureCount": 1763,
"failureRate": 0.9676,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 6,
"successCount": 59,
"successRate": 0.0325,
"total": 1817,
"unresolvedFailureCount": 1208
"successRate": 0.0324,
"total": 1822,
"unresolvedFailureCount": 1210
},
"warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
@@ -8095,6 +8215,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1910,
"summarizedRecords": 1915,
"version": 1
}

View File

@@ -1,3 +1,5 @@
{"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": "2026-09-14T08:29:32.453358+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T08:17:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610363", "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_moe"], "framework": "", "lastSyncTime": "2026-09-14T08:29:32.453304+00:00", "modelId": "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T08:15:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610382", "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": "2026-09-14T07:52:30.913030+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T07:49:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4584855", "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": "2026-09-14T07:52:30.913060+00:00", "modelId": "RedHatAI/gemma-2-2b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T07:45:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523320", "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": ["gpt_oss"], "framework": "", "lastSyncTime": "2026-09-14T07:31:50.924203+00:00", "modelId": "siliconflow/gpt-oss-20b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T07:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4585970", "taskType": "text-generation", "verifyResult": -1}
@@ -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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_mtp"], "framework": "", "lastSyncTime": "2026-09-09T20:34:13.525512+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-nvfp4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T20:25:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332982", "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": "2026-09-09T20:34:13.525546+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T20:25:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505092", "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": "2026-09-09T20:23:37.101867+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T20:21:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505089", "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": "2026-09-09T20:23:37.101902+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T20:21:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523211", "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": "2026-09-09T20:23:37.101893+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T20:19:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4458013", "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