state: generation 7016 (cycle)

This commit is contained in:
2026-09-14 03:40:25 +00:00
parent 7208ddbe79
commit 6f97b0e764
9 changed files with 2250 additions and 2236 deletions

View File

@@ -1498,7 +1498,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-14T03:37:14.702620+00:00", "generatedAt": "2026-09-14T03:40:24.090272+00:00",
"summary": { "summary": {
"activeBlockCount": 75, "activeBlockCount": 75,
"byGpuFramework": { "byGpuFramework": {

View File

@@ -75,7 +75,7 @@
"7": { "7": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 510, "listingErrors": 511,
"nextPage": 1, "nextPage": 1,
"recordsScanned": 0, "recordsScanned": 0,
"uniqueRecords": 0 "uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00", "cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0, "failureLogsInspected": 0,
"mode": "incremental_decision_only", "mode": "incremental_decision_only",
"nextAccountIndex": 7, "nextAccountIndex": 8,
"recordsScanned": 0, "recordsScanned": 0,
"seenTaskIds": [], "seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00", "startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0, "terminalRecords": 0,
"uniqueRecords": 0, "uniqueRecords": 0,
"updatedAt": "2026-09-14T03:37:14.676873+00:00", "updatedAt": "2026-09-14T03:40:24.065966+00:00",
"version": 1 "version": 1
} }

View File

@@ -1,8 +1,8 @@
{ {
"communityAttemptedAt": "2026-09-14T03:22:50.989709+00:00", "communityAttemptedAt": "2026-09-14T03:38:21.550349+00:00",
"communityError": null, "communityError": null,
"communitySample": {}, "communitySample": {},
"communityUpdatedAt": "2026-09-14T03:22:50.989709+00:00", "communityUpdatedAt": "2026-09-14T03:38:21.550349+00:00",
"frameworkAttemptedAt": "2026-09-14T02:52:06.573026+00:00", "frameworkAttemptedAt": "2026-09-14T02:52:06.573026+00:00",
"frameworkError": null, "frameworkError": null,
"frameworkStats": { "frameworkStats": {
@@ -416,121 +416,121 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-14T03:35:10.874187+00:00", "generatedAt": "2026-09-14T03:38:21.550349+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 947.4729729729729, "backlogHours": 928.6490066225165,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Ascend_910-b3", "gpu": "Ascend_910-b3",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 1.8582198000728707, "qualityFactor": 1.9076171714563221,
"queueFactor": 0.9925391638419214, "queueFactor": 0.9880723452605392,
"queueWeight": 0.9925391638419214, "queueWeight": 0.9880723452605392,
"recentSuccess": 51, "recentSuccess": 53,
"recentSuccessRate": 0.34459459459459457, "recentSuccessRate": 0.3509933774834437,
"recentTerminal": 148, "recentTerminal": 151,
"recentWilsonLowerBound": 0.2728332041114695, "recentWilsonLowerBound": 0.27942214983028035,
"running": 8, "running": 8,
"selectionWeight": 1.8443559265988294, "selectionWeight": 1.8848637724601245,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 24.666666666666668, "throughputPerHour": 25.166666666666668,
"waiting": 23371 "waiting": 23371
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1247.8195488721803, "backlogHours": 1257.2272727272727,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Ascend_910-b4", "gpu": "Ascend_910-b4",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 2.5, "qualityFactor": 2.239718898873953,
"queueFactor": 0.9523792158341162, "queueFactor": 0.9441791698135321,
"queueWeight": 0.9523792158341162, "queueWeight": 0.9441791698135321,
"recentSuccess": 52, "recentSuccess": 50,
"recentSuccessRate": 0.39097744360902253, "recentSuccessRate": 0.3787878787878788,
"recentTerminal": 133, "recentTerminal": 132,
"recentWilsonLowerBound": 0.3122210568041714, "recentWilsonLowerBound": 0.30056865609414096,
"running": 8, "running": 8,
"selectionWeight": 2.3809480395852907, "selectionWeight": 2.114695930554487,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 22.166666666666668, "throughputPerHour": 22.0,
"waiting": 27660 "waiting": 27659
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 141.93939393939394, "backlogHours": 143.26530612244898,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Biren_166m", "gpu": "Biren_166m",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 0.24309400416069143, "qualityFactor": 0.22164365537999456,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 30, "recentSuccess": 29,
"recentSuccessRate": 0.15151515151515152, "recentSuccessRate": 0.14795918367346939,
"recentTerminal": 198, "recentTerminal": 196,
"recentWilsonLowerBound": 0.10823976564597644, "recentWilsonLowerBound": 0.10503533186445975,
"running": 8, "running": 8,
"selectionWeight": 0.31602220540889886, "selectionWeight": 0.2881367519939929,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 33.0, "throughputPerHour": 32.666666666666664,
"waiting": 4684 "waiting": 4680
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1152.7692307692307, "backlogHours": 1110.0740740740741,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Cambricon_mlu-370-x4", "gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 7, "maxConcurrentTasks": 7,
"qualityFactor": 0.775115184807309, "qualityFactor": 0.6923619759894433,
"queueFactor": 0.9637653772104294, "queueFactor": 0.9619747881066026,
"queueWeight": 0.9637653772104294, "queueWeight": 0.9619747881066026,
"recentSuccess": 21, "recentSuccess": 21,
"recentSuccessRate": 0.2692307692307692, "recentSuccessRate": 0.25925925925925924,
"recentTerminal": 78, "recentTerminal": 81,
"recentWilsonLowerBound": 0.18335480551618466, "recentWilsonLowerBound": 0.17627430254837975,
"running": 7, "running": 7,
"selectionWeight": 0.7470291784673478, "selectionWeight": 0.6660347651455134,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 13.0, "throughputPerHour": 13.5,
"waiting": 14986 "waiting": 14986
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 541.4851485148515, "backlogHours": 552.4242424242424,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Cambricon_mlu-370-x8", "gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 7, "maxConcurrentTasks": 7,
"qualityFactor": 0.3761966244723344, "qualityFactor": 0.2874874566989013,
"queueFactor": 1.0794305229072312, "queueFactor": 1.0681335947601487,
"queueWeight": 1.0794305229072312, "queueWeight": 1.0681335947601487,
"recentSuccess": 20, "recentSuccess": 18,
"recentSuccessRate": 0.19801980198019803, "recentSuccessRate": 0.18181818181818182,
"recentTerminal": 101, "recentTerminal": 99,
"recentWilsonLowerBound": 0.13200401398360054, "recentWilsonLowerBound": 0.11821769885745202,
"running": 7, "running": 7,
"selectionWeight": 0.40607811907010716, "selectionWeight": 0.30707501057225,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 16.833333333333332, "throughputPerHour": 16.5,
"waiting": 9115 "waiting": 9115
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 53.56849315068494, "backlogHours": 52.6510067114094,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -540,196 +540,196 @@
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 4, "recentSuccess": 4,
"recentSuccessRate": 0.0136986301369863, "recentSuccessRate": 0.013422818791946308,
"recentTerminal": 292, "recentTerminal": 298,
"recentWilsonLowerBound": 0.005339594255973408, "recentWilsonLowerBound": 0.005231836788119275,
"running": 24, "running": 24,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 48.666666666666664, "throughputPerHour": 49.666666666666664,
"waiting": 2607 "waiting": 2615
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 272.64516129032256, "backlogHours": 263.875,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-150", "gpu": "Iluvatar_bi-150",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 50, "maxConcurrentTasks": 50,
"qualityFactor": 0.3400717030620776, "qualityFactor": 0.3574811736491776,
"queueFactor": 1.196445739817255, "queueFactor": 1.1933195261920682,
"queueWeight": 1.196445739817255, "queueWeight": 1.1933195261920682,
"recentSuccess": 18, "recentSuccess": 19,
"recentSuccessRate": 0.1935483870967742, "recentSuccessRate": 0.19791666666666666,
"recentTerminal": 93, "recentTerminal": 96,
"recentWilsonLowerBound": 0.1260833866437487, "recentWilsonLowerBound": 0.13052631601888467,
"running": 5, "running": 15,
"selectionWeight": 0.4068773403610213, "selectionWeight": 0.426589264761621,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 15.5, "throughputPerHour": 16.0,
"waiting": 4226 "waiting": 4222
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2027.7391304347825, "backlogHours": 2120.0454545454545,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_mrv-100", "gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 0.6841502159942696, "qualityFactor": 0.7388021441261722,
"queueFactor": 0.8854842982481015, "queueFactor": 0.8730009334787356,
"queueWeight": 0.8854842982481015, "queueWeight": 0.8730009334787356,
"recentSuccess": 13, "recentSuccess": 13,
"recentSuccessRate": 0.2826086956521739, "recentSuccessRate": 0.29545454545454547,
"recentTerminal": 46, "recentTerminal": 44,
"recentWilsonLowerBound": 0.1732404154491407, "recentWilsonLowerBound": 0.18155360887243294,
"running": 2, "running": 2,
"selectionWeight": 0.6058042739059729, "selectionWeight": 0.6449749614782397,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 7.666666666666667, "throughputPerHour": 7.333333333333333,
"waiting": 15546 "waiting": 15547
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 855.1898734177215, "backlogHours": 785.860465116279,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Kunlunxin_p-800", "gpu": "Kunlunxin_p-800",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 7, "maxConcurrentTasks": 7,
"qualityFactor": 0.5721594277293567, "qualityFactor": 0.6850829845102037,
"queueFactor": 1.007913574732105, "queueFactor": 1.0131288155970897,
"queueWeight": 1.007913574732105, "queueWeight": 1.0131288155970897,
"recentSuccess": 19, "recentSuccess": 22,
"recentSuccessRate": 0.24050632911392406, "recentSuccessRate": 0.2558139534883721,
"recentTerminal": 79, "recentTerminal": 86,
"recentWilsonLowerBound": 0.15972056887933211, "recentWilsonLowerBound": 0.1754295012969836,
"running": 7, "running": 7,
"selectionWeight": 0.5766872541193714, "selectionWeight": 0.6940773126825419,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 13.166666666666666, "throughputPerHour": 14.333333333333334,
"waiting": 11260 "waiting": 11264
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 735.0, "backlogHours": 712.3917525773195,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "MetaX_c-500", "gpu": "MetaX_c-500",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 4, "maxConcurrentTasks": 4,
"qualityFactor": 1.441272169414847, "qualityFactor": 1.5414363198834193,
"queueFactor": 1.0310733834918453, "queueFactor": 1.0281551412032093,
"queueWeight": 1.0310733834918453, "queueWeight": 1.0281551412032093,
"recentSuccess": 31, "recentSuccess": 33,
"recentSuccessRate": 0.32978723404255317, "recentSuccessRate": 0.3402061855670103,
"recentTerminal": 94, "recentTerminal": 97,
"recentWilsonLowerBound": 0.24307351447114595, "recentWilsonLowerBound": 0.25362119291999513,
"running": 4, "running": 4,
"selectionWeight": 1.4860573722511983, "selectionWeight": 1.5848356771254923,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 15.666666666666666, "throughputPerHour": 16.166666666666668,
"waiting": 11515 "waiting": 11517
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 2044.3636363636363, "backlogHours": 1984.2352941176468,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Mthreads_s4000", "gpu": "Mthreads_s4000",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 4, "maxConcurrentTasks": 4,
"qualityFactor": 2.045862545518635, "qualityFactor": 2.5,
"queueFactor": 0.8844004496459942, "queueFactor": 0.8817135366378127,
"queueWeight": 0.8844004496459942, "queueWeight": 0.8817135366378127,
"recentSuccess": 26, "recentSuccess": 29,
"recentSuccessRate": 0.3939393939393939, "recentSuccessRate": 0.4264705882352941,
"recentTerminal": 66, "recentTerminal": 68,
"recentWilsonLowerBound": 0.2850282099029192, "recentWilsonLowerBound": 0.31597057562082875,
"running": 4, "running": 4,
"selectionWeight": 1.8093617551705787, "selectionWeight": 2.2042838415945316,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 11.0, "throughputPerHour": 11.333333333333334,
"waiting": 22488 "waiting": 22488
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 3249.3333333333335, "backlogHours": 3250.4444444444443,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Sunrise_pt-200-x1", "gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 1.1038791909916121, "qualityFactor": 1.4303707033377098,
"queueFactor": 0.8250182146536964, "queueFactor": 0.8187947923266466,
"queueWeight": 0.8250182146536964, "queueWeight": 0.8187947923266466,
"recentSuccess": 10, "recentSuccess": 11,
"recentSuccessRate": 0.37037037037037035, "recentSuccessRate": 0.4074074074074074,
"recentTerminal": 27, "recentTerminal": 27,
"recentWilsonLowerBound": 0.21532287067936856, "recentWilsonLowerBound": 0.24514513372857347,
"running": 2, "running": 2,
"selectionWeight": 0.9107204393452666, "selectionWeight": 1.1711800829895196,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 4.5, "throughputPerHour": 4.5,
"waiting": 14622 "waiting": 14627
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 1109.4626865671642, "backlogHours": 1077.4782608695652,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Vastai_va16", "gpu": "Vastai_va16",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 16, "maxConcurrentTasks": 16,
"qualityFactor": 0.9624505350619168, "qualityFactor": 1.001674753248378,
"queueFactor": 0.9693168710354231, "queueFactor": 0.9662849301013177,
"queueWeight": 0.9693168710354231, "queueWeight": 0.9662849301013177,
"recentSuccess": 20, "recentSuccess": 21,
"recentSuccessRate": 0.29850746268656714, "recentSuccessRate": 0.30434782608695654,
"recentTerminal": 67, "recentTerminal": 69,
"recentWilsonLowerBound": 0.20231361154976887, "recentWilsonLowerBound": 0.2084947626304856,
"running": 16, "running": 16,
"selectionWeight": 0.9329195411725859, "selectionWeight": 0.9679032189268636,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 11.166666666666666, "throughputPerHour": 11.5,
"waiting": 12389 "waiting": 12391
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 587.9504132231405, "backlogHours": 573.4354838709677,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "hygon_k100-ai", "gpu": "hygon_k100-ai",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 6, "maxConcurrentTasks": 6,
"qualityFactor": 1.0294248325609419, "qualityFactor": 0.9480997881442561,
"queueFactor": 1.0661825539319174, "queueFactor": 1.062169433664257,
"queueWeight": 1.0661825539319174, "queueWeight": 1.062169433664257,
"recentSuccess": 34, "recentSuccess": 34,
"recentSuccessRate": 0.2809917355371901, "recentSuccessRate": 0.27419354838709675,
"recentTerminal": 121, "recentTerminal": 124,
"recentWilsonLowerBound": 0.2085956290113622, "recentWilsonLowerBound": 0.2033498857097495,
"running": 6, "running": 6,
"selectionWeight": 1.0975547970607615, "selectionWeight": 1.0070426150303866,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 20.166666666666668, "throughputPerHour": 20.666666666666668,
"waiting": 11857 "waiting": 11851
} }
}, },
"queueAttemptedAt": "2026-09-14T03:26:26.523286+00:00", "queueAttemptedAt": "2026-09-14T03:38:21.550349+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-09-14T03:26:26.523286+00:00", "queueUpdatedAt": "2026-09-14T03:38:21.550349+00:00",
"supportedGpus": [ "supportedGpus": [
"Vastai_va16", "Vastai_va16",
"Iluvatar_mrv-100", "Iluvatar_mrv-100",

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-14T03:29:33.257959+00:00", "generatedAt": "2026-09-14T03:38:15.698828+00:00",
"lastSyncTime": "2026-09-14T03:29:33.013591+00:00", "lastSyncTime": "2026-09-14T03:38:15.505403+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -2036,11 +2036,11 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 1, "decisionTotal": 1,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 38, "ambiguous_runtime": 39,
"memory_capacity": 1, "memory_capacity": 1,
"验证失败": 22 "验证失败": 22
}, },
"failureCount": 61, "failureCount": 62,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "unknown", "framework": "unknown",
"pendingCount": 0, "pendingCount": 0,
@@ -2050,8 +2050,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Kunlunxin_p-800", "targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation", "taskType": "text-generation",
"total": 61, "total": 62,
"unresolvedFailureCount": 60 "unresolvedFailureCount": 61
}, },
"Kunlunxin_p-800|unknown|visual-multi-modal": { "Kunlunxin_p-800|unknown|visual-multi-modal": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -2515,7 +2515,7 @@
"decisionSuccessRate": 0.2571, "decisionSuccessRate": 0.2571,
"decisionTotal": 210, "decisionTotal": 210,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 145, "ambiguous_runtime": 146,
"backend_operator": 4, "backend_operator": 4,
"framework_architecture_unsupported": 100, "framework_architecture_unsupported": 100,
"memory_capacity": 5, "memory_capacity": 5,
@@ -2525,15 +2525,15 @@
"参数/模板问题": 61, "参数/模板问题": 61,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1036, "failureCount": 1037,
"failureRate": 0.9505, "failureRate": 0.9505,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 54, "successCount": 54,
"successRate": 0.0495, "successRate": 0.0495,
"total": 1090, "total": 1091,
"unresolvedFailureCount": 879 "unresolvedFailureCount": 880
}, },
"vllm": { "vllm": {
"attributableFailureCount": 306, "attributableFailureCount": 306,
@@ -2666,7 +2666,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-14T03:29:33.252471+00:00", "generatedAt": "2026-09-14T03:38:15.693992+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 32, "attributableFailureCount": 32,
@@ -2859,20 +2859,20 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 1, "decisionTotal": 1,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 73, "ambiguous_runtime": 74,
"memory_capacity": 1, "memory_capacity": 1,
"参数/模板问题": 1, "参数/模板问题": 1,
"验证失败": 23 "验证失败": 23
}, },
"failureCount": 98, "failureCount": 99,
"failureRate": 1.0, "failureRate": 1.0,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 0, "successCount": 0,
"successRate": 0.0, "successRate": 0.0,
"total": 98, "total": 99,
"unresolvedFailureCount": 97 "unresolvedFailureCount": 98
}, },
"MetaX_c-500": { "MetaX_c-500": {
"attributableFailureCount": 54, "attributableFailureCount": 54,
@@ -4966,13 +4966,13 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 9 "ambiguous_runtime": 10
}, },
"failureCount": 9, "failureCount": 10,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-13T13:43:30.144198+00:00", "lastTerminalAt": "2026-09-14T03:38:15.505403+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -4980,8 +4980,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Kunlunxin_p-800", "targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation", "taskType": "text-generation",
"total": 9, "total": 10,
"unresolvedFailureCount": 9 "unresolvedFailureCount": 10
}, },
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": { "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -7841,15 +7841,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1798, "terminalRecords": 1799,
"totalRecords": 1891, "totalRecords": 1892,
"totals": { "totals": {
"attributableFailureCount": 537, "attributableFailureCount": 537,
"decisionFailureRate": 0.901, "decisionFailureRate": 0.901,
"decisionSuccessRate": 0.099, "decisionSuccessRate": 0.099,
"decisionTotal": 596, "decisionTotal": 596,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 420, "ambiguous_runtime": 421,
"backend_operator": 43, "backend_operator": 43,
"framework_architecture_unsupported": 340, "framework_architecture_unsupported": 340,
"memory_capacity": 12, "memory_capacity": 12,
@@ -7861,15 +7861,15 @@
"参数/模板问题": 103, "参数/模板问题": 103,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1739, "failureCount": 1740,
"failureRate": 0.9672, "failureRate": 0.9672,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 6, "platformFailureCount": 6,
"successCount": 59, "successCount": 59,
"successRate": 0.0328, "successRate": 0.0328,
"total": 1798, "total": 1799,
"unresolvedFailureCount": 1196 "unresolvedFailureCount": 1197
}, },
"warnings": [ "warnings": [
"GPU Iluvatar_mrv-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。",
@@ -7907,6 +7907,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 1891, "summarizedRecords": 1892,
"version": 1 "version": 1
} }

View File

@@ -1,3 +1,4 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-14T03:38:15.505403+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T03:35:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4596909", "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": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-14T02:51:59.045472+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T02:47:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4493314", "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": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-14T02:51:59.045472+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T02:47:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4493314", "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": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-14T02:14:40.319417+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T02:13:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4582655", "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": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-14T02:14:40.319417+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T02:13:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4582655", "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_moe"], "framework": "vllm", "lastSyncTime": "2026-09-14T00:51:56.404636+00:00", "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T00:43:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4490280", "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_moe"], "framework": "vllm", "lastSyncTime": "2026-09-14T00:51:56.404636+00:00", "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T00:43:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4490280", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T19:18:48.711721+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T19:17:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4458012", "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": "2026-09-09T19:18:48.711721+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T19:17:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4458012", "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": "2026-09-09T19:18:48.711664+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T19:11:22+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4477955", "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": "2026-09-09T19:18:48.711664+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T19:11:22+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4477955", "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": "2026-09-09T19:08:24.911910+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T19:05:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493488", "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": "2026-09-09T19:08:24.911910+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T19:05:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493488", "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": "2026-09-09T19:08:24.911937+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T19:01:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493487", "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", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "a04cd3fc58264e236e81c0f9da0625c47f774c1d1ea2e36a613f59f85d9410da", ".modelhub_state/architecture_compatibility_blacklist.json": "7615de70d15abd1941c270018bd74b8ee2134d3ce1833fdb0fccf9728c2148ad",
".modelhub_state/architecture_history_backfill.json": "48452642f76c3138c2b7ab1833f4faeba67dfec3604e40836bd279bb8d3c460e", ".modelhub_state/architecture_history_backfill.json": "d7e2c3550cd5621733a126cf11f4116bb40cb286695cce2ddfb65ed9de7a9a20",
".modelhub_state/market_intelligence.json": "7bf29f7336571590817698ee0e03a10606814daed4d770834aa4d57e84913b67", ".modelhub_state/market_intelligence.json": "a791d731b54169e864dec8eb0676cabc98349e0ad48fd740fca2182f4c5097c3",
".modelhub_state/official_capabilities.json": "b45b36fdb844a992fdd49e2c661529bcf1e0038bcf3e37f8016b84316361e161", ".modelhub_state/official_capabilities.json": "d433cb57d7cd930ef5928a5869bf695555534e269ae864baaf2b51c299c2ff8b",
".modelhub_state/outcome_checkpoint.json": "52f0bb512df73e0ec147f970cdf57aff16fd08bf077854e3b1ced6c9aba6012f", ".modelhub_state/outcome_checkpoint.json": "0f2eb46203e0b54d280558069da0392b11423e2fb3a716badc6c8e09274dd02f",
".modelhub_state/queue_cleanup_latest.json": "0ca25e7a552999a61b0e5c18fc5c08134dd7fe9caf89eaa601a60afcccac2b45", ".modelhub_state/queue_cleanup_latest.json": "0ca25e7a552999a61b0e5c18fc5c08134dd7fe9caf89eaa601a60afcccac2b45",
".modelhub_state/recent_outcomes.jsonl": "7963e18e944f8b195b19aec867f24aff3e730537582f1557454178f485b0163d", ".modelhub_state/recent_outcomes.jsonl": "fea567b565535c5f8546761205ad7ae5b5d5e063ded4aa2ab73e404f37ff0343",
".modelhub_state/recovery_active_tasks.jsonl": "39ccd333ef906ed5a2bda9a91480a005c713ae16af3053a81503bfdbebcfe6a9", ".modelhub_state/recovery_active_tasks.jsonl": "9f51b5e65e57fc830ba254b1560974601860e3d5cdadab07b4f2695b150ab242",
".modelhub_state/recovery_intents.jsonl": "10767b75ceadeadb89ca4688fba628c289ca2fe2eb25b41f77a25e4a308c7cc3", ".modelhub_state/recovery_intents.jsonl": "ac68c35b91185ff4ecfebbf0dcf5db0dd77971d62037da348074f4a47e243f2a",
".modelhub_state/routing_intelligence.json": "f57ee2e18ed0ace5dc075009569f92659c48337959476d9eab19e2dfed2e4296", ".modelhub_state/routing_intelligence.json": "f57ee2e18ed0ace5dc075009569f92659c48337959476d9eab19e2dfed2e4296",
".modelhub_state/submission_exclusions.jsonl": "75ddc8b4d313a8cecec2f373afc57298143d78e0eb907ca44f420d7bf9c55263", ".modelhub_state/submission_exclusions.jsonl": "75ddc8b4d313a8cecec2f373afc57298143d78e0eb907ca44f420d7bf9c55263",
".modelhub_state/worker_crashes.jsonl": "53505d335313446ff7094bcb58658b561de55799302fa7bfb49e418e414eebad", ".modelhub_state/worker_crashes.jsonl": "53505d335313446ff7094bcb58658b561de55799302fa7bfb49e418e414eebad",
"ledger/submissions.jsonl": "b94d9a7a630c5df675e6f5ac76acb16374279d00120dfa6fb3f00067b347dd5e", "ledger/submissions.jsonl": "b94d9a7a630c5df675e6f5ac76acb16374279d00120dfa6fb3f00067b347dd5e",
"outcomes/submissions.jsonl": "082373f875671f458c422a15e87c665b36bb8b0521f498626dd354523b7f72aa" "outcomes/submissions.jsonl": "082373f875671f458c422a15e87c665b36bb8b0521f498626dd354523b7f72aa"
}, },
"generation": 7015, "generation": 7016,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-14T03:37:14.782845+00:00", "updatedAt": "2026-09-14T03:40:25.069851+00:00",
"writerId": "69701e73196b4ac2b3fad0f412335168" "writerId": "69701e73196b4ac2b3fad0f412335168"
} }