state: generation 4917 (cycle)

This commit is contained in:
2026-09-10 03:01:00 +00:00
parent b36d182f22
commit 337c98d989
10 changed files with 2349 additions and 2327 deletions

View File

@@ -1306,7 +1306,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T02:57:50.726964+00:00",
"generatedAt": "2026-09-10T03:00:59.860168+00:00",
"summary": {
"activeBlockCount": 65,
"byGpuFramework": {

View File

@@ -11,7 +11,7 @@
"1": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 350,
"listingErrors": 351,
"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": "2026-09-10T02:57:50.703173+00:00",
"updatedAt": "2026-09-10T03:00:59.827923+00:00",
"version": 1
}

View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-09-10T02:40:54.299569+00:00",
"communityAttemptedAt": "2026-09-10T02:58:57.076173+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-09-10T02:40:54.299569+00:00",
"communityUpdatedAt": "2026-09-10T02:58:57.076173+00:00",
"frameworkAttemptedAt": "2026-09-10T00:33:23.734278+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -416,121 +416,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T02:55:46.198620+00:00",
"generatedAt": "2026-09-10T02:58:57.076173+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 941.1543624161075,
"backlogHours": 941.1946308724832,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.2118780416972095,
"queueFactor": 0.9496968332308842,
"queueWeight": 0.9496968332308842,
"recentSuccess": 48,
"recentSuccessRate": 0.3221476510067114,
"qualityFactor": 1.3031037687617446,
"queueFactor": 0.9496287800905773,
"queueWeight": 0.9496287800905773,
"recentSuccess": 50,
"recentSuccessRate": 0.33557046979865773,
"recentTerminal": 149,
"recentWilsonLowerBound": 0.2523981353536608,
"recentWilsonLowerBound": 0.26472902222515887,
"running": 8,
"selectionWeight": 1.1509167384618852,
"selectionWeight": 1.2374648422606491,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 24.833333333333332,
"waiting": 23372
"waiting": 23373
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1069.1298701298701,
"backlogHours": 1062.0387096774193,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.4487463473781894,
"queueFactor": 0.9317074095279081,
"queueWeight": 0.9317074095279081,
"qualityFactor": 1.381904302313493,
"queueFactor": 0.9325770688213993,
"queueWeight": 0.9325770688213993,
"recentSuccess": 53,
"recentSuccessRate": 0.34415584415584416,
"recentTerminal": 154,
"recentWilsonLowerBound": 0.27373391810581155,
"recentSuccessRate": 0.3419354838709677,
"recentTerminal": 155,
"recentWilsonLowerBound": 0.2718892242755767,
"running": 8,
"selectionWeight": 1.3498077063787517,
"selectionWeight": 1.2887322636431982,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 25.666666666666668,
"waiting": 27441
"throughputPerHour": 25.833333333333332,
"waiting": 27436
},
"Biren_166m": {
"available": true,
"backlogHours": 154.10714285714286,
"backlogHours": 155.81927710843374,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.4707447869436355,
"queueFactor": 1.2458355045243885,
"queueWeight": 1.2458355045243885,
"qualityFactor": 0.46828900000926316,
"queueFactor": 1.2436913292886456,
"queueWeight": 1.2436913292886456,
"recentSuccess": 37,
"recentSuccessRate": 0.22023809523809523,
"recentTerminal": 168,
"recentWilsonLowerBound": 0.16421635802623955,
"recentSuccessRate": 0.22289156626506024,
"recentTerminal": 166,
"recentWilsonLowerBound": 0.1662539567085869,
"running": 8,
"selectionWeight": 0.5864705691441499,
"selectionWeight": 0.582406968912771,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 28.0,
"waiting": 4315
"throughputPerHour": 27.666666666666668,
"waiting": 4311
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1056.075,
"backlogHours": 1126.56,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.6426519684011479,
"queueFactor": 0.9334260231872538,
"queueWeight": 0.9334260231872538,
"qualityFactor": 0.7219025322124107,
"queueFactor": 0.924363174260655,
"queueWeight": 0.924363174260655,
"recentSuccess": 22,
"recentSuccessRate": 0.275,
"recentTerminal": 80,
"recentWilsonLowerBound": 0.18917622847735993,
"recentSuccessRate": 0.29333333333333333,
"recentTerminal": 75,
"recentWilsonLowerBound": 0.20239997218158162,
"running": 7,
"selectionWeight": 0.5998680711581441,
"selectionWeight": 0.6673001161826687,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 13.333333333333334,
"waiting": 14081
"throughputPerHour": 12.5,
"waiting": 14082
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 506.76923076923083,
"backlogHours": 521.4059405940594,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.8099713497029161,
"queueFactor": 1.0421076477070614,
"queueWeight": 1.0421076477070614,
"recentSuccess": 30,
"recentSuccessRate": 0.28846153846153844,
"recentTerminal": 104,
"recentWilsonLowerBound": 0.21015782725460305,
"qualityFactor": 0.9150868182582381,
"queueFactor": 1.037598626241995,
"queueWeight": 1.037598626241995,
"recentSuccess": 31,
"recentSuccessRate": 0.3069306930693069,
"recentTerminal": 101,
"recentWilsonLowerBound": 0.22543494459305355,
"running": 7,
"selectionWeight": 0.8440773379490195,
"selectionWeight": 0.949492825516906,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.333333333333332,
"waiting": 8784
"throughputPerHour": 16.833333333333332,
"waiting": 8777
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 60.278481012658226,
"backlogHours": 59.77405857740585,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -540,19 +540,19 @@
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 16,
"recentSuccessRate": 0.06751054852320675,
"recentTerminal": 237,
"recentWilsonLowerBound": 0.041978621921925606,
"running": 0,
"recentSuccessRate": 0.06694560669456066,
"recentTerminal": 239,
"recentWilsonLowerBound": 0.041623741065227725,
"running": 1,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 39.5,
"throughputPerHour": 39.833333333333336,
"waiting": 2381
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 99.48471615720524,
"backlogHours": 96.50847457627118,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
@@ -561,104 +561,104 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 16,
"recentSuccessRate": 0.06986899563318777,
"recentTerminal": 229,
"recentWilsonLowerBound": 0.04346080725852322,
"running": 2,
"recentSuccess": 18,
"recentSuccessRate": 0.07627118644067797,
"recentTerminal": 236,
"recentWilsonLowerBound": 0.0487865940329056,
"running": 5,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 38.166666666666664,
"waiting": 3797
"throughputPerHour": 39.333333333333336,
"waiting": 3796
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 1997.086956521739,
"backlogHours": 1954.340425531915,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.7973057017748473,
"queueFactor": 0.8483490395810963,
"queueWeight": 0.8483490395810963,
"recentSuccess": 15,
"recentSuccessRate": 0.32608695652173914,
"recentTerminal": 46,
"recentWilsonLowerBound": 0.20865764564493355,
"qualityFactor": 0.8818242600853943,
"queueFactor": 0.8510513246009626,
"queueWeight": 0.8510513246009626,
"recentSuccess": 16,
"recentSuccessRate": 0.3404255319148936,
"recentTerminal": 47,
"recentWilsonLowerBound": 0.2216726071376219,
"running": 2,
"selectionWeight": 0.6763935263532237,
"selectionWeight": 0.7504777046109385,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 7.666666666666667,
"waiting": 15311
"throughputPerHour": 7.833333333333333,
"waiting": 15309
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 579.6964285714286,
"backlogHours": 584.7567567567568,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.17285011000392872,
"queueFactor": 1.0213016300808366,
"queueWeight": 1.0213016300808366,
"qualityFactor": 0.17076710307093768,
"queueFactor": 1.0199044742735504,
"queueWeight": 1.0199044742735504,
"recentSuccess": 18,
"recentSuccessRate": 0.16071428571428573,
"recentTerminal": 112,
"recentWilsonLowerBound": 0.10414453380551848,
"recentSuccessRate": 0.16216216216216217,
"recentTerminal": 111,
"recentWilsonLowerBound": 0.10510689256844917,
"running": 7,
"selectionWeight": 0.17653209910666434,
"selectionWeight": 0.1741661324807819,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.666666666666668,
"waiting": 10821
"throughputPerHour": 18.5,
"waiting": 10818
},
"MetaX_c-500": {
"available": true,
"backlogHours": 738.4565217391304,
"backlogHours": 738.0,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.6590591640884362,
"queueFactor": 0.9848846737388366,
"queueWeight": 0.9848846737388366,
"qualityFactor": 0.6380733086675484,
"queueFactor": 0.9849117759346465,
"queueWeight": 0.9849117759346465,
"recentSuccess": 25,
"recentSuccessRate": 0.2717391304347826,
"recentTerminal": 92,
"recentWilsonLowerBound": 0.19135648353357726,
"running": 4,
"selectionWeight": 0.6490972697978299,
"selectionWeight": 0.628445915616251,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 15.333333333333334,
"waiting": 11323
"waiting": 11316
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1667.2894736842106,
"backlogHours": 1666.9736842105265,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.7232101218181328,
"queueFactor": 0.8716305981847972,
"queueWeight": 0.8716305981847972,
"qualityFactor": 0.7001815624984393,
"queueFactor": 0.871598497149158,
"queueWeight": 0.871598497149158,
"recentSuccess": 22,
"recentSuccessRate": 0.2894736842105263,
"recentTerminal": 76,
"recentWilsonLowerBound": 0.19960875564331393,
"running": 4,
"selectionWeight": 0.6303720710936391,
"running": 5,
"selectionWeight": 0.610277197605189,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.666666666666666,
"waiting": 21119
"waiting": 21115
},
"Sunrise_pt-200-x1": {
"available": true,
@@ -668,15 +668,15 @@
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.6104702850978171,
"queueFactor": 0.7344148298411828,
"queueWeight": 0.7344148298411828,
"qualityFactor": 0.5910316036563256,
"queueFactor": 0.7343669163292347,
"queueWeight": 0.7343669163292347,
"recentSuccess": 6,
"recentSuccessRate": 0.375,
"recentTerminal": 16,
"recentWilsonLowerBound": 0.18480982554752803,
"running": 2,
"selectionWeight": 0.44833843055321165,
"selectionWeight": 0.43403405623021823,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 2.6666666666666665,
@@ -684,52 +684,52 @@
},
"Vastai_va16": {
"available": true,
"backlogHours": 595.8556701030927,
"backlogHours": 595.7319587628865,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 1.325693620082914,
"queueFactor": 1.017098367697002,
"queueWeight": 1.017098367697002,
"qualityFactor": 1.283480695721361,
"queueFactor": 1.0170636889549367,
"queueWeight": 1.0170636889549367,
"recentSuccess": 34,
"recentSuccessRate": 0.35051546391752575,
"recentTerminal": 97,
"recentWilsonLowerBound": 0.26290948573797346,
"running": 16,
"selectionWeight": 1.3483608170526613,
"selectionWeight": 1.305381611092816,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 16.166666666666668,
"waiting": 9633
"waiting": 9631
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 476.14678899082566,
"backlogHours": 471.70909090909095,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 2.5,
"queueFactor": 1.0518964509046012,
"queueWeight": 1.0518964509046012,
"recentSuccess": 48,
"recentSuccessRate": 0.44036697247706424,
"recentTerminal": 109,
"recentWilsonLowerBound": 0.3507777944894326,
"queueFactor": 1.0533062166118052,
"queueWeight": 1.0533062166118052,
"recentSuccess": 49,
"recentSuccessRate": 0.44545454545454544,
"recentTerminal": 110,
"recentWilsonLowerBound": 0.3559755711590631,
"running": 6,
"selectionWeight": 2.6297411272615028,
"selectionWeight": 2.633265541529513,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.166666666666668,
"waiting": 8650
"throughputPerHour": 18.333333333333332,
"waiting": 8648
}
},
"queueAttemptedAt": "2026-09-10T02:47:27.736389+00:00",
"queueAttemptedAt": "2026-09-10T02:58:57.076173+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-10T02:47:27.736389+00:00",
"queueUpdatedAt": "2026-09-10T02:58:57.076173+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": "2026-09-10T02:50:12.530651+00:00",
"lastSyncTime": "2026-09-10T02:50:12.317776+00:00",
"generatedAt": "2026-09-10T02:58:51.739711+00:00",
"lastSyncTime": "2026-09-10T02:58:51.546388+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1861,10 +1861,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 21,
"ambiguous_runtime": 22,
"参数/模板问题": 1
},
"failureCount": 22,
"failureCount": 23,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -1874,8 +1874,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 22,
"unresolvedFailureCount": 22
"total": 23,
"unresolvedFailureCount": 23
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2400,22 +2400,22 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 22,
"ambiguous_runtime": 23,
"framework_architecture_unsupported": 4,
"model_load": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 27,
"参数/模板问题": 7
},
"failureCount": 62,
"failureCount": 63,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 62,
"unresolvedFailureCount": 29
"total": 63,
"unresolvedFailureCount": 30
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 0,
@@ -2436,7 +2436,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T02:50:12.526687+00:00",
"generatedAt": "2026-09-10T02:58:51.735217+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2627,20 +2627,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 53,
"ambiguous_runtime": 54,
"memory_capacity": 1,
"参数/模板问题": 1,
"验证失败": 23
},
"failureCount": 78,
"failureCount": 79,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 78,
"unresolvedFailureCount": 77
"total": 79,
"unresolvedFailureCount": 78
},
"MetaX_c-500": {
"attributableFailureCount": 38,
@@ -3291,9 +3291,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "phi3",
@@ -3305,8 +3305,8 @@
"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|qwen3_5_moe|none": {
"attributableFailureCount": 0,
@@ -3939,10 +3939,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 11,
"ambiguous_runtime": 10,
"framework_architecture_unsupported": 3
},
"failureCount": 14,
"failureCount": 13,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -3954,8 +3954,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 14,
"unresolvedFailureCount": 11
"total": 13,
"unresolvedFailureCount": 10
},
"Ascend_910-b4|llamacpp|text-generation": {
"attributableFailureCount": 1,
@@ -4303,9 +4303,9 @@
"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,
@@ -4317,8 +4317,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 11,
"unresolvedFailureCount": 11
"total": 12,
"unresolvedFailureCount": 12
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4987,12 +4987,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-09T14:21:21.949411+00:00",
"lastTerminalAt": "2026-09-10T02:58:51.546388+00:00",
"modelType": "phi3",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -5002,8 +5002,8 @@
"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|qwen3_5_moe|none": {
"attributableFailureCount": 0,
@@ -5899,6 +5899,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3|compressed-tensors|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
"modelType": "phi3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|36": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -6764,15 +6788,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1490,
"totalRecords": 1574,
"terminalRecords": 1491,
"totalRecords": 1575,
"totals": {
"attributableFailureCount": 394,
"decisionFailureRate": 0.8894,
"decisionSuccessRate": 0.1106,
"decisionTotal": 443,
"failureBreakdown": {
"ambiguous_runtime": 278,
"ambiguous_runtime": 279,
"backend_operator": 25,
"framework_architecture_unsupported": 269,
"memory_capacity": 11,
@@ -6784,21 +6808,21 @@
"参数/模板问题": 94,
"验证失败": 673
},
"failureCount": 1441,
"failureCount": 1442,
"failureRate": 0.9671,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 49,
"successRate": 0.0329,
"total": 1490,
"unresolvedFailureCount": 1045
"total": 1491,
"unresolvedFailureCount": 1046
},
"warnings": [
"GPU Cambricon_mlu-370-x8 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 Iluvatar_mrv-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 Iluvatar_bi-150 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 Vastai_va16 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。",
@@ -6806,7 +6830,7 @@
"GPU hygon_k100-ai 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Biren_166m|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -6827,6 +6851,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1574,
"summarizedRecords": 1575,
"version": 1
}

View File

@@ -95,6 +95,7 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T20:13:30.044094+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-nvfp4", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 238933307, "estimatedRequiredGiB": 0.297, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_mtp", "modelscopeFileSize": 265664321, "modelscopeLicense": "apache-2.0", "modelscopeParams": 106194432, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_mtp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-vlm", "custom_tag:qwen3_5_mtp", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:qwen", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:nvfp4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 265664321}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.985375+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729522", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T16:50:57.939999+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-07T06:07:37.712079+00:00", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 17788663591}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.889698+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729518", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T11:30:49.443166+00:00", "modelId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3SmallForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8630134648, "estimatedRequiredGiB": 9.647, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3small", "modelscopeFileSize": 8632060880, "modelscopeLicense": "mit", "modelscopeParams": 7803314176, "modelscopeTags": ["license:mit", "model_type:phi3small", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8632060880}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.888188+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729519", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T02:58:51.546388+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293356304, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295851911, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295851911}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.847566+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729520", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T14:21:21.949411+00:00", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4020365960, "estimatedRequiredGiB": 4.496, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4022810352, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4022810352}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.843439+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729517", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T14:24:47.907622+00:00", "modelId": "RedHatAI/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7855165704, "estimatedRequiredGiB": 8.783, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7858540940, "modelscopeLicense": "other", "modelscopeParams": 7400416256, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-07T06:07:37.712079+00:00", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 7858540940}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.841387+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729516", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T14:00:25.508497+00:00", "modelId": "FlagRelease/Qwen3.5-35B-A3B-hygon-FlagOS", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 71903878016, "estimatedRequiredGiB": 80.385, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 71927003441, "modelscopeLicense": null, "modelscopeParams": 35951822704, "modelscopeTags": ["model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 71927003441}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.829157+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729513", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-07T08:32:22.399402+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T08:09:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4083445", "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": "2026-09-07T08:04:59.604222+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T07:55:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4464045", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-07T07:41:41.205199+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T07:33:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4459518", "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": "2026-09-07T07:41:41.205155+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T07:25:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4461223", "taskType": "text-generation", "verifyResult": -1}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "042655838b1f2bb91d6e8cafa462975ea3ce917af7191b5f33f621bc6ec26ea1",
".modelhub_state/architecture_history_backfill.json": "e8a3d6d8915adb2cc316d42ec764e35f15cd0b6e768981b584eb920e0f352aab",
".modelhub_state/market_intelligence.json": "7d16cb5bcf96bc5d240bf5c943b4ec09e18c2e06480b5db75ac816995e805be0",
".modelhub_state/official_capabilities.json": "7881a011157ee39342a45966df800a9c090b632ca7f5ab4ed4b24110176ca6ce",
".modelhub_state/outcome_checkpoint.json": "53509b2d33fefbdbfe56392f582c2983abf0c282535c6ce09f7b6c19fa9fc167",
".modelhub_state/architecture_compatibility_blacklist.json": "f0714997655a368009ea0f7983db1feecc20a0a2ef216f3697729b9a58c359e2",
".modelhub_state/architecture_history_backfill.json": "b9deacada33eab9b2804aab407a2ef7969032136d9ab64ecb63235143e1e2be0",
".modelhub_state/market_intelligence.json": "b5bf111ee6cb53a162ca1307521989626fa36cfebb6b0835541ff7f69f88a13d",
".modelhub_state/official_capabilities.json": "03733fd5fe913a2e020a555e4e9308a5079e08422d7ec8f09415cdc5def888b5",
".modelhub_state/outcome_checkpoint.json": "a98031182101634b188a4062876a59cd736063d6439726061c1aa9d1d1a49a2e",
".modelhub_state/queue_cleanup_latest.json": "1ff9cf1dcc1b2c2557b532394e1e76da55fa710317d6832581664c56c6ecc7b3",
".modelhub_state/recent_outcomes.jsonl": "fe1ad7982be490a4b6861efe900a7d2823ce6b804550372dc799712794aa2fc8",
".modelhub_state/recovery_active_tasks.jsonl": "7b54a6eda8bb505b3ff58f8b327f24ddd02508a4d8469010e12343fef594bfc4",
".modelhub_state/recovery_intents.jsonl": "93ea7698c3fef30a3e86945873f7f0d7e10b3b0b014ef865aa7960a858cf8e1f",
".modelhub_state/recent_outcomes.jsonl": "da87468be4ce603c73643d396ababb0efbfdc2c7827ed09fbedd200012c6de95",
".modelhub_state/recovery_active_tasks.jsonl": "467227aaffc82ba67427427452952faaa6a5a1bbad7cf52229560569ec185970",
".modelhub_state/recovery_intents.jsonl": "6aa19446d0c6e71b5152f403a6c6fae23f8ced3b47e2849865e20bfffd4b3629",
".modelhub_state/routing_intelligence.json": "289584603011b6a895f3ab1c0b743c174293ab94ad8d2f1f5a3531e01a72207b",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "d242179d528ce949e36ac1834a20e4f46e6d5194c7a834b19b8e1b58d9a1bea6",
"outcomes/submissions.jsonl": "aa4777b88adb640cc19bee1b1611d6a4701b470fc709ec54f48c2db876528cb5"
"outcomes/submissions.jsonl": "2f50352a9f7c248dfd39475d1755157e32f5d2294929f486f9db9d335e5599cd"
},
"generation": 4916,
"generation": 4917,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T02:57:50.822524+00:00",
"updatedAt": "2026-09-10T03:01:00.885949+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}

View File

@@ -409,7 +409,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504652+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31263441624, "estimatedRequiredGiB": 34.958, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 31280205657, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 30554505408, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_moe", "library:safetensors", "library:other", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 31280205657}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:51.785155+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729509", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504544+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612468, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-07T06:07:37.712079+00:00", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 17788612468}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:51.818347+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729510", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504496+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:51.831733+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729515", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504620+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293356304, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295851911, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295851911}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:51.847566+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729520", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504512+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293335560, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295942065, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295942065}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:51.830682+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729514", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504565+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4385544296, "estimatedRequiredGiB": 4.926, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 4407367933, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4407367933}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:51.824770+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729512", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504647+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998647728, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020563851, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 12020563851}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:51.913002+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729521", "taskType": "text-generation", "verifyResult": null}