state: generation 7692 (cycle)

This commit is contained in:
2026-09-15 13:09:41 +00:00
parent 33f5e33d2b
commit 9c926cc99d
9 changed files with 2234 additions and 2224 deletions

View File

@@ -1616,7 +1616,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-15T13:06:17.845880+00:00", "generatedAt": "2026-09-15T13:09:40.533790+00:00",
"summary": { "summary": {
"activeBlockCount": 79, "activeBlockCount": 79,
"byGpuFramework": { "byGpuFramework": {

View File

@@ -83,7 +83,7 @@
"8": { "8": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 559, "listingErrors": 560,
"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": 8, "nextAccountIndex": 9,
"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": "2026-09-15T13:06:17.820823+00:00", "updatedAt": "2026-09-15T13:09:40.504251+00:00",
"version": 1 "version": 1
} }

View File

@@ -416,121 +416,121 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-15T13:04:40.915726+00:00", "generatedAt": "2026-09-15T13:07:30.105713+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 1010.1428571428572, "backlogHours": 968.5890410958905,
"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": 1.0439194919989685, "qualityFactor": 1.1259010681489614,
"queueFactor": 1.0089736714919753, "queueFactor": 1.009143737733071,
"queueWeight": 1.0089736714919753, "queueWeight": 1.009143737733071,
"recentSuccess": 42, "recentSuccess": 44,
"recentSuccessRate": 0.3, "recentSuccessRate": 0.3013698630136986,
"recentTerminal": 140, "recentTerminal": 146,
"recentWilsonLowerBound": 0.23026125017102184, "recentWilsonLowerBound": 0.23281544289288028,
"running": 8, "running": 8,
"selectionWeight": 1.053287282584237, "selectionWeight": 1.1361960122295,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 23.333333333333332, "throughputPerHour": 24.333333333333332,
"waiting": 23570 "waiting": 23569
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1134.1216216216217, "backlogHours": 1089.7792207792206,
"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": 2.5,
"queueFactor": 0.9916040886457553, "queueFactor": 0.9914554028334973,
"queueWeight": 0.9916040886457553, "queueWeight": 0.9914554028334973,
"recentSuccess": 62, "recentSuccess": 63,
"recentSuccessRate": 0.4189189189189189, "recentSuccessRate": 0.4090909090909091,
"recentTerminal": 148, "recentTerminal": 154,
"recentWilsonLowerBound": 0.34246617038461147, "recentWilsonLowerBound": 0.33456800777135237,
"running": 8, "running": 8,
"selectionWeight": 2.4790102216143883, "selectionWeight": 2.478638507083743,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 24.666666666666668, "throughputPerHour": 25.666666666666668,
"waiting": 27975 "waiting": 27971
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 1150.5, "backlogHours": 1110.8275862068965,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Biren_166m", "gpu": "Biren_166m",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 0.42190416869445085, "qualityFactor": 0.16952735054287074,
"queueFactor": 0.9894737105874707, "queueFactor": 0.9886144721008003,
"queueWeight": 0.9894737105874707, "queueWeight": 0.9886144721008003,
"recentSuccess": 8, "recentSuccess": 6,
"recentSuccessRate": 0.2857142857142857, "recentSuccessRate": 0.20689655172413793,
"recentTerminal": 28, "recentTerminal": 29,
"recentWilsonLowerBound": 0.15253815848329966, "recentWilsonLowerBound": 0.09845936515585209,
"running": 2, "running": 2,
"selectionWeight": 0.4174630833104205, "selectionWeight": 0.16759719216358748,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 4.666666666666667, "throughputPerHour": 4.833333333333333,
"waiting": 5369 "waiting": 5369
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1535.8, "backlogHours": 1439.8125,
"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": 0.18777277493663685, "qualityFactor": 0.17073063478749684,
"queueFactor": 0.9475170942285459, "queueFactor": 0.9508851635000757,
"queueWeight": 0.9475170942285459, "queueWeight": 0.9508851635000757,
"recentSuccess": 11, "recentSuccess": 11,
"recentSuccessRate": 0.18333333333333332, "recentSuccessRate": 0.171875,
"recentTerminal": 60, "recentTerminal": 64,
"recentWilsonLowerBound": 0.10557689037136128, "recentWilsonLowerBound": 0.09877641267316228,
"running": 7, "running": 7,
"selectionWeight": 0.17791791408319288, "selectionWeight": 0.16234522757438064,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.0, "throughputPerHour": 10.666666666666666,
"waiting": 15358 "waiting": 15358
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 683.1325301204819, "backlogHours": 651.6551724137931,
"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": 0.7024650038775676, "qualityFactor": 0.6637175000289377,
"queueFactor": 1.0699451350023566, "queueFactor": 1.0709551538307607,
"queueWeight": 1.0699451350023566, "queueWeight": 1.0709551538307607,
"recentSuccess": 23, "recentSuccess": 23,
"recentSuccessRate": 0.27710843373493976, "recentSuccessRate": 0.26436781609195403,
"recentTerminal": 83, "recentTerminal": 87,
"recentWilsonLowerBound": 0.1923179435941366, "recentWilsonLowerBound": 0.18309896615432047,
"running": 7, "running": 7,
"selectionWeight": 0.751599013408215, "selectionWeight": 0.7108116773436589,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 13.833333333333334, "throughputPerHour": 14.5,
"waiting": 9450 "waiting": 9449
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 48.725075528700906, "backlogHours": 50.373831775700936,
"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": 23, "recentSuccess": 23,
"recentSuccessRate": 0.06948640483383686, "recentSuccessRate": 0.07165109034267912,
"recentTerminal": 331, "recentTerminal": 321,
"recentWilsonLowerBound": 0.04674513127653245, "recentWilsonLowerBound": 0.048215924926894964,
"running": 24, "running": 24,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 55.166666666666664, "throughputPerHour": 53.5,
"waiting": 2688 "waiting": 2695
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 149.51999999999998, "backlogHours": 151.98837209302326,
"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": 0.8846046209237829, "qualityFactor": 0.8684780098096496,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 48, "recentSuccess": 46,
"recentSuccessRate": 0.2742857142857143, "recentSuccessRate": 0.26744186046511625,
"recentTerminal": 175, "recentTerminal": 172,
"recentWilsonLowerBound": 0.21356542670728645, "recentWilsonLowerBound": 0.20690247751944094,
"running": 10, "running": 10,
"selectionWeight": 1.1499860072009178, "selectionWeight": 1.1290214127525446,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 29.166666666666668, "throughputPerHour": 28.666666666666668,
"waiting": 4361 "waiting": 4357
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2120.266666666667, "backlogHours": 2074.173913043478,
"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": 0.8848005108022945, "qualityFactor": 0.884768744276299,
"queueFactor": 0.9027732467302113, "queueFactor": 0.9002169522414161,
"queueWeight": 0.9027732467302113, "queueWeight": 0.9002169522414161,
"recentSuccess": 15, "recentSuccess": 15,
"recentSuccessRate": 0.3333333333333333, "recentSuccessRate": 0.32608695652173914,
"recentTerminal": 45, "recentTerminal": 46,
"recentWilsonLowerBound": 0.21358692207276764, "recentWilsonLowerBound": 0.20865764564493355,
"running": 2, "running": 2,
"selectionWeight": 0.7987742298455368, "selectionWeight": 0.7964838224108748,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 7.5, "throughputPerHour": 7.666666666666667,
"waiting": 15902 "waiting": 15902
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 775.1333333333333, "backlogHours": 766.4175824175825,
"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": 0.39897331210968023, "qualityFactor": 0.4095465997221106,
"queueFactor": 1.0498585545190458, "queueFactor": 1.0452114129772874,
"queueWeight": 1.0498585545190458, "queueWeight": 1.0452114129772874,
"recentSuccess": 20, "recentSuccess": 20,
"recentSuccessRate": 0.2222222222222222, "recentSuccessRate": 0.21978021978021978,
"recentTerminal": 90, "recentTerminal": 91,
"recentWilsonLowerBound": 0.14871223281666784, "recentWilsonLowerBound": 0.14702013817844428,
"running": 7, "running": 7,
"selectionWeight": 0.41886554474314497, "selectionWeight": 0.42806278017559074,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 15.0, "throughputPerHour": 15.166666666666666,
"waiting": 11627 "waiting": 11624
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 831.529411764706, "backlogHours": 851.5662650602409,
"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": 0.6650697456050697, "qualityFactor": 0.6553242726185926,
"queueFactor": 1.0388566186883612, "queueFactor": 1.0288242562229404,
"queueWeight": 1.0388566186883612, "queueWeight": 1.0288242562229404,
"recentSuccess": 23, "recentSuccess": 22,
"recentSuccessRate": 0.27058823529411763, "recentSuccessRate": 0.26506024096385544,
"recentTerminal": 85, "recentTerminal": 83,
"recentWilsonLowerBound": 0.18759486332171668, "recentWilsonLowerBound": 0.18204284443216528,
"running": 4, "running": 4,
"selectionWeight": 0.6909121071112113, "selectionWeight": 0.674213507361663,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 14.166666666666666, "throughputPerHour": 13.833333333333334,
"waiting": 11780 "waiting": 11780
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 1674.9285714285713, "backlogHours": 1655.2235294117647,
"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": 1.8045400608136632, "qualityFactor": 2.0009212630410973,
"queueFactor": 0.9352717350774298, "queueFactor": 0.9312053543748348,
"queueWeight": 0.9352717350774298, "queueWeight": 0.9312053543748348,
"recentSuccess": 33, "recentSuccess": 34,
"recentSuccessRate": 0.39285714285714285, "recentSuccessRate": 0.4,
"recentTerminal": 84, "recentTerminal": 85,
"recentWilsonLowerBound": 0.2953018006281275, "recentWilsonLowerBound": 0.30236068121692405,
"running": 4, "running": 4,
"selectionWeight": 1.6877353136939255, "selectionWeight": 1.863268593826327,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 14.0, "throughputPerHour": 14.166666666666666,
"waiting": 23449 "waiting": 23449
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 4580.4, "backlogHours": 4580.099999999999,
"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": 1.8586587516583883, "qualityFactor": 1.9565585487371604,
"queueFactor": 0.8042697648317377, "queueFactor": 0.7993605628006016,
"queueWeight": 0.8042697648317377, "queueWeight": 0.7993605628006016,
"recentSuccess": 10, "recentSuccess": 10,
"recentSuccessRate": 0.5, "recentSuccessRate": 0.5,
"recentTerminal": 20, "recentTerminal": 20,
"recentWilsonLowerBound": 0.2992949144298199, "recentWilsonLowerBound": 0.2992949144298199,
"running": 2, "running": 2,
"selectionWeight": 1.4948630370987432, "selectionWeight": 1.5639957426708648,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 3.3333333333333335, "throughputPerHour": 3.3333333333333335,
"waiting": 15268 "waiting": 15267
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 1403.3454545454547, "backlogHours": 1456.3018867924527,
"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": 0.29408434334603034, "qualityFactor": 0.33696356407240113,
"queueFactor": 0.9604230278552641, "queueFactor": 0.949262337505635,
"queueWeight": 0.9604230278552641, "queueWeight": 0.949262337505635,
"recentSuccess": 12, "recentSuccess": 12,
"recentSuccessRate": 0.21818181818181817, "recentSuccessRate": 0.22641509433962265,
"recentTerminal": 55, "recentTerminal": 53,
"recentWilsonLowerBound": 0.12945897827653216, "recentWilsonLowerBound": 0.13454499977265524,
"running": 16, "running": 16,
"selectionWeight": 0.28244537548122156, "selectionWeight": 0.31986682048559734,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 9.166666666666666, "throughputPerHour": 8.833333333333334,
"waiting": 12864 "waiting": 12864
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 715.7777777777778, "backlogHours": 736.1142857142858,
"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": 1.176968153126549, "qualityFactor": 1.2248072181998866,
"queueFactor": 1.0624794079387407, "queueFactor": 1.0515554419370408,
"queueWeight": 1.0624794079387407, "queueWeight": 1.0515554419370408,
"recentSuccess": 35, "recentSuccess": 34,
"recentSuccessRate": 0.32407407407407407, "recentSuccessRate": 0.3238095238095238,
"recentTerminal": 108, "recentTerminal": 105,
"recentWilsonLowerBound": 0.24316531824673593, "recentWilsonLowerBound": 0.24189861275835717,
"running": 6, "running": 6,
"selectionWeight": 1.250504426496649, "selectionWeight": 1.2879526956218592,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 18.0, "throughputPerHour": 17.5,
"waiting": 12884 "waiting": 12882
} }
}, },
"queueAttemptedAt": "2026-09-15T12:55:43.099935+00:00", "queueAttemptedAt": "2026-09-15T13:07:30.105713+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-09-15T12:55:43.099935+00:00", "queueUpdatedAt": "2026-09-15T13:07:30.105713+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": "2026-09-15T12:23:08.264840+00:00", "generatedAt": "2026-09-15T13:07:18.884376+00:00",
"lastSyncTime": "2026-09-15T12:23:08.015674+00:00", "lastSyncTime": "2026-09-15T13:07:18.613629+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -1820,31 +1820,31 @@
"unresolvedFailureCount": 39 "unresolvedFailureCount": 39
}, },
"Biren_166m|unknown|text-generation": { "Biren_166m|unknown|text-generation": {
"attributableFailureCount": 32, "attributableFailureCount": 33,
"decisionFailureRate": 0.9412, "decisionFailureRate": 0.9429,
"decisionSuccessRate": 0.0588, "decisionSuccessRate": 0.0571,
"decisionTotal": 34, "decisionTotal": 35,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 31, "ambiguous_runtime": 31,
"backend_operator": 4, "backend_operator": 4,
"framework_architecture_unsupported": 24, "framework_architecture_unsupported": 24,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 2, "model_load": 3,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"参数/模板问题": 1, "参数/模板问题": 1,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 91, "failureCount": 92,
"failureRate": 0.9785, "failureRate": 0.9787,
"framework": "unknown", "framework": "unknown",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 2, "successCount": 2,
"successRate": 0.0215, "successRate": 0.0213,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 93, "total": 94,
"unresolvedFailureCount": 59 "unresolvedFailureCount": 59
}, },
"Biren_166m|vllm|text-generation": { "Biren_166m|vllm|text-generation": {
@@ -2657,29 +2657,29 @@
"unresolvedFailureCount": 8 "unresolvedFailureCount": 8
}, },
"unknown": { "unknown": {
"attributableFailureCount": 171, "attributableFailureCount": 172,
"decisionFailureRate": 0.7467, "decisionFailureRate": 0.7478,
"decisionSuccessRate": 0.2533, "decisionSuccessRate": 0.2522,
"decisionTotal": 229, "decisionTotal": 230,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 156, "ambiguous_runtime": 156,
"backend_operator": 4, "backend_operator": 4,
"framework_architecture_unsupported": 112, "framework_architecture_unsupported": 112,
"memory_capacity": 5, "memory_capacity": 5,
"model_load": 45, "model_load": 46,
"platform_infrastructure": 1, "platform_infrastructure": 1,
"tokenizer_compatibility": 5, "tokenizer_compatibility": 5,
"参数/模板问题": 66, "参数/模板问题": 66,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1067, "failureCount": 1068,
"failureRate": 0.9484, "failureRate": 0.9485,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 58, "successCount": 58,
"successRate": 0.0516, "successRate": 0.0515,
"total": 1125, "total": 1126,
"unresolvedFailureCount": 895 "unresolvedFailureCount": 895
}, },
"vllm": { "vllm": {
@@ -2816,7 +2816,7 @@
"unresolvedFailureCount": 2 "unresolvedFailureCount": 2
} }
}, },
"generatedAt": "2026-09-15T12:23:08.259159+00:00", "generatedAt": "2026-09-15T13:07:18.878835+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 43, "attributableFailureCount": 43,
@@ -2867,28 +2867,28 @@
"unresolvedFailureCount": 227 "unresolvedFailureCount": 227
}, },
"Biren_166m": { "Biren_166m": {
"attributableFailureCount": 39, "attributableFailureCount": 40,
"decisionFailureRate": 0.9286, "decisionFailureRate": 0.9302,
"decisionSuccessRate": 0.0714, "decisionSuccessRate": 0.0698,
"decisionTotal": 42, "decisionTotal": 43,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 31, "ambiguous_runtime": 31,
"backend_operator": 4, "backend_operator": 4,
"framework_architecture_unsupported": 30, "framework_architecture_unsupported": 30,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 3, "model_load": 4,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"参数/模板问题": 1, "参数/模板问题": 1,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 98, "failureCount": 99,
"failureRate": 0.9703, "failureRate": 0.9706,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 3, "successCount": 3,
"successRate": 0.0297, "successRate": 0.0294,
"total": 101, "total": 102,
"unresolvedFailureCount": 59 "unresolvedFailureCount": 59
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
@@ -5730,31 +5730,32 @@
"unresolvedFailureCount": 6 "unresolvedFailureCount": 6
}, },
"Biren_166m|unknown|text-generation": { "Biren_166m|unknown|text-generation": {
"attributableFailureCount": 8, "attributableFailureCount": 9,
"consecutiveFailures": 0, "consecutiveFailures": 1,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8889, "decisionFailureRate": 0.9,
"decisionSuccessRate": 0.1111, "decisionSuccessRate": 0.1,
"decisionTotal": 9, "decisionTotal": 10,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 7, "ambiguous_runtime": 7,
"backend_operator": 2, "backend_operator": 2,
"framework_architecture_unsupported": 6, "framework_architecture_unsupported": 6,
"model_load": 1,
"参数/模板问题": 1 "参数/模板问题": 1
}, },
"failureCount": 16, "failureCount": 17,
"failureRate": 0.9412, "failureRate": 0.9444,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-14T18:50:27.851828+00:00", "lastTerminalAt": "2026-09-15T13:07:18.613629+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 1, "successCount": 1,
"successRate": 0.0588, "successRate": 0.0556,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 17, "total": 18,
"unresolvedFailureCount": 8 "unresolvedFailureCount": 8
}, },
"Cambricon_mlu-370-x4|unknown|text-generation": { "Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -9775,19 +9776,19 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1926, "terminalRecords": 1927,
"totalRecords": 2020, "totalRecords": 2021,
"totals": { "totals": {
"attributableFailureCount": 600, "attributableFailureCount": 601,
"decisionFailureRate": 0.8969, "decisionFailureRate": 0.897,
"decisionSuccessRate": 0.1031, "decisionSuccessRate": 0.103,
"decisionTotal": 669, "decisionTotal": 670,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 461, "ambiguous_runtime": 461,
"backend_operator": 44, "backend_operator": 44,
"framework_architecture_unsupported": 393, "framework_architecture_unsupported": 393,
"memory_capacity": 12, "memory_capacity": 12,
"model_load": 78, "model_load": 79,
"platform_infrastructure": 7, "platform_infrastructure": 7,
"repository_structure": 8, "repository_structure": 8,
"runtime_memory": 9, "runtime_memory": 9,
@@ -9795,14 +9796,14 @@
"参数/模板问题": 116, "参数/模板问题": 116,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1857, "failureCount": 1858,
"failureRate": 0.9642, "failureRate": 0.9642,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 7, "platformFailureCount": 7,
"successCount": 69, "successCount": 69,
"successRate": 0.0358, "successRate": 0.0358,
"total": 1926, "total": 1927,
"unresolvedFailureCount": 1250 "unresolvedFailureCount": 1250
}, },
"warnings": [ "warnings": [
@@ -9842,6 +9843,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 2020, "summarizedRecords": 2021,
"version": 1 "version": 1
} }

View File

@@ -1,3 +1,4 @@
{"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": "2026-09-15T13:07:18.613629+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T13:05:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610406", "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": "2026-09-15T12:05:21.552265+00:00", "modelId": "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T11:59:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4588155", "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": "2026-09-15T12:05:21.552265+00:00", "modelId": "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T11:59:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4588155", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-15T11:19:29.645035+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T11:11:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4590790", "taskType": "text-generation", "verifyResult": -1} {"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-15T11:19:29.645035+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T11:11:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4590790", "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": "2026-09-15T10:50:55.652660+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T10:49:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4609103", "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": "2026-09-15T10:50:55.652660+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T10:49:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4609103", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T07:53:10.699377+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T07:51:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481723", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T07:53:10.699377+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T07:51:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481723", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T07:53:10.699435+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T07:51:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481716", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T07:53:10.699435+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T07:51:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481716", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T07:53:10.699425+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T07:47:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481724", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T07:53:10.699425+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T07:47:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481724", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T07:29:02.941680+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T07:23:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496943", "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": "ccdfa88f65753ef9af9b01e033145abb01ccc99e461e7f81fc00abeedb6f2ce3", ".modelhub_state/architecture_compatibility_blacklist.json": "bf10a08b370eeacb0ba4cf50e783a90d881ec65bd3f032603e5a7732ac4a15e1",
".modelhub_state/architecture_history_backfill.json": "fa1856f13329a77bdb994c4e33878419de7dee39524360ebebdb3608bd974c56", ".modelhub_state/architecture_history_backfill.json": "c17599bd1edbd4dcf195f321426101117600a5a1bcd7728d9cba97ad1a1c89ae",
".modelhub_state/market_intelligence.json": "f0301808c655e39dcb80ba85df5d0be365e92dab83f2b3e746d8788eb7c68496", ".modelhub_state/market_intelligence.json": "4d8a3914ca4f520b8aaf7bd44b8f684fb338571bef0938ac04ad83bd96e2a0ff",
".modelhub_state/official_capabilities.json": "e44495adf5ff1f9b4e3cd7fd7618af8f6f496ec4804203144198c0374d76923d", ".modelhub_state/official_capabilities.json": "6bc9b9d5913616003bc05509b076f193c691202a870a0ad9f0ffc61b8f5812db",
".modelhub_state/outcome_checkpoint.json": "2ea53af7454247482f95c283e4e232279b98a8f489361a51450f515e4e25a95b", ".modelhub_state/outcome_checkpoint.json": "de13411cf2c2929536cf871c958134fc2b6a0eb29cb78d4682249ddc3afe0394",
".modelhub_state/queue_cleanup_latest.json": "8b5a109f802adbb3f6d71b840ee3c5b08dc5ec52695df88bb268acf7d6c01583", ".modelhub_state/queue_cleanup_latest.json": "8b5a109f802adbb3f6d71b840ee3c5b08dc5ec52695df88bb268acf7d6c01583",
".modelhub_state/recent_outcomes.jsonl": "a0c0dd110c1638c66c25f2de47b9ea3daa184485b0433df0d88505e37d21707d", ".modelhub_state/recent_outcomes.jsonl": "6a22282ad815592b26af94e944c10e486f467a1d673bd15d6afef044d6c5eace",
".modelhub_state/recovery_active_tasks.jsonl": "f784b6b14f04b9763145bbbbbf089d13b1344ce4c6372fa4d341389088387bed", ".modelhub_state/recovery_active_tasks.jsonl": "bf4b8fc7577f49534a6bbfb13114e920df278d5c4f3f11aa3e204e6c7f8ae625",
".modelhub_state/recovery_intents.jsonl": "bda2580b5c23f00bc9639d7bafc89f322d375a957ebd4375c7283316341f4c03", ".modelhub_state/recovery_intents.jsonl": "919ec51c70c956ac55d433c9ebb1d1cf4c406769e9b4f527b99bf5b2ab20eb9a",
".modelhub_state/routing_intelligence.json": "5c8070320d5755aaf914efa600b2d376703dd44fa4a64fb6e2078f23011d8cb3", ".modelhub_state/routing_intelligence.json": "5c8070320d5755aaf914efa600b2d376703dd44fa4a64fb6e2078f23011d8cb3",
".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552", ".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983", ".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
"ledger/submissions.jsonl": "ac8aa72c28eb11f8c2ceb74c1aa900e711f5d12175589bd7b3292bbe3bf359b5", "ledger/submissions.jsonl": "ac8aa72c28eb11f8c2ceb74c1aa900e711f5d12175589bd7b3292bbe3bf359b5",
"outcomes/submissions.jsonl": "26fb36360b61389d0b426f6ae52aaadaddee0cb8c6948c1519567ec72cf041e9" "outcomes/submissions.jsonl": "26fb36360b61389d0b426f6ae52aaadaddee0cb8c6948c1519567ec72cf041e9"
}, },
"generation": 7691, "generation": 7692,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-15T13:06:17.945962+00:00", "updatedAt": "2026-09-15T13:09:41.182760+00:00",
"writerId": "07a76ec4a8bc45bc8c08d7549ca0fd6c" "writerId": "07a76ec4a8bc45bc8c08d7549ca0fd6c"
} }