CoolBoy/submmit
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

state: generation 8647 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-17 09:13:21 +00:00
parent e03d91e88f
commit ac54deb27c
9 changed files with 2133 additions and 2063 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -1741,7 +1741,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-17T09:09:59.825652+00:00", "generatedAt": "2026-09-17T09:13:20.595943+00:00",
"summary": { "summary": {
"activeBlockCount": 84, "activeBlockCount": 84,
"byGpuFramework": { "byGpuFramework": {

6
.modelhub_state/architecture_history_backfill.json
View File

@@ -19,7 +19,7 @@
"10": { "10": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 632, "listingErrors": 633,
"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": 10, "nextAccountIndex": 11,
"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": "2026-09-17T09:09:59.801570+00:00", "updatedAt": "2026-09-17T09:13:20.569229+00:00",
"version": 1 "version": 1
} }

274
.modelhub_state/market_intelligence.json
View File

@@ -416,121 +416,121 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-17T09:08:01.235465+00:00", "generatedAt": "2026-09-17T09:11:08.851921+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 1107.8139534883721, "backlogHours": 1201.2100840336136,
"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": 1.3035915520631596, "qualityFactor": 1.2202114217481967,
"queueFactor": 0.988270720010001, "queueFactor": 0.979439131135625,
"queueWeight": 0.988270720010001, "queueWeight": 0.979439131135625,
"recentSuccess": 42, "recentSuccess": 39,
"recentSuccessRate": 0.32558139534883723, "recentSuccessRate": 0.3277310924369748,
"recentTerminal": 129, "recentTerminal": 119,
"recentWilsonLowerBound": 0.25077958524200566, "recentWilsonLowerBound": 0.2499369805737803,
"running": 9, "running": 9,
"selectionWeight": 1.2883013617564134, "selectionWeight": 1.1951228147188195,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 21.5, "throughputPerHour": 19.833333333333332,
"waiting": 23818 "waiting": 23824
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1496.7610619469028, "backlogHours": 1537.8545454545456,
"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": 2.3732281515364226, "qualityFactor": 2.006203404503589,
"queueFactor": 0.9446546825644213, "queueFactor": 0.9438065945998133,
"queueWeight": 0.9446546825644213, "queueWeight": 0.9438065945998133,
"recentSuccess": 47, "recentSuccess": 44,
"recentSuccessRate": 0.415929203539823, "recentSuccessRate": 0.4,
"recentTerminal": 113, "recentTerminal": 110,
"recentWilsonLowerBound": 0.32927895669940405, "recentWilsonLowerBound": 0.31331775680061763,
"running": 8, "running": 9,
"selectionWeight": 2.2418810861425875, "selectionWeight": 1.893468003279084,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 18.833333333333332, "throughputPerHour": 18.333333333333332,
"waiting": 28189 "waiting": 28194
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 190.0, "backlogHours": 188.86046511627907,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Biren_166m", "gpu": "Biren_166m",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 5, "maxConcurrentTasks": 5,
"qualityFactor": 0.3663697094824243, "qualityFactor": 0.3409665041339533,
"queueFactor": 1.2874575339792815, "queueFactor": 1.2927041361810736,
"queueWeight": 1.2874575339792815, "queueWeight": 1.2927041361810736,
"recentSuccess": 33, "recentSuccess": 33,
"recentSuccessRate": 0.19298245614035087, "recentSuccessRate": 0.19186046511627908,
"recentTerminal": 171, "recentTerminal": 172,
"recentWilsonLowerBound": 0.14084347623053362, "recentWilsonLowerBound": 0.14000323744713258,
"running": 6, "running": 6,
"selectionWeight": 0.4716854426949478, "selectionWeight": 0.44076881019316255,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 28.5, "throughputPerHour": 28.666666666666668,
"waiting": 5415 "waiting": 5414
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1240.135135135135, "backlogHours": 1176.5384615384614,
"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": 0.29112914446510496, "qualityFactor": 0.2435613009217304,
"queueFactor": 0.9716852300431394, "queueFactor": 0.9824928019426701,
"queueWeight": 0.9716852300431394, "queueWeight": 0.9824928019426701,
"recentSuccess": 15, "recentSuccess": 15,
"recentSuccessRate": 0.20270270270270271, "recentSuccessRate": 0.19230769230769232,
"recentTerminal": 74, "recentTerminal": 78,
"recentWilsonLowerBound": 0.1268696381027667, "recentWilsonLowerBound": 0.12015101048823743,
"running": 7, "running": 7,
"selectionWeight": 0.28288588971183787, "selectionWeight": 0.23929722498739273,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 12.333333333333334, "throughputPerHour": 13.0,
"waiting": 15295 "waiting": 15295
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 602.0210526315789, "backlogHours": 614.7096774193549,
"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": 0.416959355193707, "qualityFactor": 0.41272089345544083,
"queueFactor": 1.0829395162722584, "queueFactor": 1.0829783859731013,
"queueWeight": 1.0829395162722584, "queueWeight": 1.0829783859731013,
"recentSuccess": 21, "recentSuccess": 21,
"recentSuccessRate": 0.22105263157894736, "recentSuccessRate": 0.22580645161290322,
"recentTerminal": 95, "recentTerminal": 93,
"recentWilsonLowerBound": 0.14937242983925722, "recentWilsonLowerBound": 0.15270042020646624,
"running": 8, "running": 7,
"selectionWeight": 0.45154176241866584, "selectionWeight": 0.4469678070517496,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 15.833333333333334, "throughputPerHour": 15.5,
"waiting": 9532 "waiting": 9528
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 29.017142857142858, "backlogHours": 30.047337278106507,
"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": 16, "recentSuccess": 16,
"recentSuccessRate": 0.030476190476190476, "recentSuccessRate": 0.03155818540433925,
"recentTerminal": 525, "recentTerminal": 507,
"recentWilsonLowerBound": 0.018844606632512605, "recentWilsonLowerBound": 0.019516799596624657,
"running": 26, "running": 25,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 87.5, "throughputPerHour": 84.5,
"waiting": 2539 "waiting": 2539
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 88.69655172413793, "backlogHours": 92.38709677419355,
"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": 0.14025236200203867, "qualityFactor": 0.13408283492037218,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 36, "recentSuccess": 35,
"recentSuccessRate": 0.12413793103448276, "recentSuccessRate": 0.12544802867383512,
"recentTerminal": 290, "recentTerminal": 279,
"recentWilsonLowerBound": 0.09103051906997917, "recentWilsonLowerBound": 0.09159953956635114,
"running": 3, "running": 3,
"selectionWeight": 0.18232807060265027, "selectionWeight": 0.17430768539648384,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 48.333333333333336, "throughputPerHour": 46.5,
"waiting": 4287 "waiting": 4296
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2664.0, "backlogHours": 2740.114285714286,
"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": 1.551144073759706, "qualityFactor": 1.5646631670646138,
"queueFactor": 0.8663947661498259, "queueFactor": 0.8654759319980893,
"queueWeight": 0.8663947661498259, "queueWeight": 0.8654759319980893,
"recentSuccess": 15, "recentSuccess": 15,
"recentSuccessRate": 0.4166666666666667, "recentSuccessRate": 0.42857142857142855,
"recentTerminal": 36, "recentTerminal": 35,
"recentWilsonLowerBound": 0.2714033350508729, "recentWilsonLowerBound": 0.27984333081678914,
"running": 2, "running": 2,
"selectionWeight": 1.3439031070497287, "selectionWeight": 1.3541783127783287,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 6.0, "throughputPerHour": 5.833333333333333,
"waiting": 15984 "waiting": 15984
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 521.6279069767442, "backlogHours": 529.511811023622,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Kunlunxin_p-800", "gpu": "Kunlunxin_p-800",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 0.6404002289250234, "qualityFactor": 0.6257859741456816,
"queueFactor": 1.1064755723310864, "queueFactor": 1.1074877951745525,
"queueWeight": 1.1064755723310864, "queueWeight": 1.1074877951745525,
"recentSuccess": 32, "recentSuccess": 32,
"recentSuccessRate": 0.24806201550387597, "recentSuccessRate": 0.25196850393700787,
"recentTerminal": 129, "recentTerminal": 127,
"recentWilsonLowerBound": 0.1815425856479483, "recentWilsonLowerBound": 0.18450499480603022,
"running": 10, "running": 9,
"selectionWeight": 0.7085872098207739, "selectionWeight": 0.6930503287577604,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 21.5, "throughputPerHour": 21.166666666666668,
"waiting": 11215 "waiting": 11208
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 940.2162162162161, "backlogHours": 915.1578947368422,
"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": 0.9473276666416071, "qualityFactor": 0.744051568024023,
"queueFactor": 1.0128888550196773, "queueFactor": 1.0202248369569957,
"queueWeight": 1.0128888550196773, "queueWeight": 1.0202248369569957,
"recentSuccess": 23, "recentSuccess": 22,
"recentSuccessRate": 0.3108108108108108, "recentSuccessRate": 0.2894736842105263,
"recentTerminal": 74, "recentTerminal": 76,
"recentWilsonLowerBound": 0.21690691603479306, "recentWilsonLowerBound": 0.19960875564331393,
"running": 4, "running": 4,
"selectionWeight": 0.9595376355930799, "selectionWeight": 0.7590998896749058,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 12.333333333333334, "throughputPerHour": 12.666666666666666,
"waiting": 11596 "waiting": 11592
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 2497.2203389830506, "backlogHours": 2456.1,
"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": 2.4975590820667373, "qualityFactor": 2.5,
"queueFactor": 0.8748375660463971, "queueFactor": 0.8797988497906151,
"queueWeight": 0.8748375660463971, "queueWeight": 0.8797988497906151,
"recentSuccess": 27, "recentSuccess": 28,
"recentSuccessRate": 0.4576271186440678, "recentSuccessRate": 0.4666666666666667,
"recentTerminal": 59, "recentTerminal": 60,
"recentWilsonLowerBound": 0.33701102140242434, "recentWilsonLowerBound": 0.34627701540988,
"running": 4, "running": 4,
"selectionWeight": 2.184958508412338, "selectionWeight": 2.1994971244765376,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 9.833333333333334, "throughputPerHour": 10.0,
"waiting": 24556 "waiting": 24561
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 5175.666666666667, "backlogHours": 5177.0,
"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": 2.5, "qualityFactor": 2.3574864817106658,
"queueFactor": 0.7842436454700886, "queueFactor": 0.7866989524684359,
"queueWeight": 0.7842436454700886, "queueWeight": 0.7866989524684359,
"recentSuccess": 10, "recentSuccess": 10,
"recentSuccessRate": 0.5555555555555556, "recentSuccessRate": 0.5555555555555556,
"recentTerminal": 18, "recentTerminal": 18,
"recentWilsonLowerBound": 0.33716069428251627, "recentWilsonLowerBound": 0.33716069428251627,
"running": 2, "running": 2,
"selectionWeight": 1.9606091136752215, "selectionWeight": 1.8546321456202792,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 3.0, "throughputPerHour": 3.0,
"waiting": 15527 "waiting": 15531
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 1918.909090909091, "backlogHours": 1918.3636363636365,
"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": 0.06467294837014517, "qualityFactor": 0.06098624060599563,
"queueFactor": 0.9100972311692594, "queueFactor": 0.9130207686010736,
"queueWeight": 0.9100972311692594, "queueWeight": 0.9130207686010736,
"recentSuccess": 6, "recentSuccess": 6,
"recentSuccessRate": 0.13636363636363635, "recentSuccessRate": 0.13636363636363635,
"recentTerminal": 44, "recentTerminal": 44,
"recentWilsonLowerBound": 0.06402867407860051, "recentWilsonLowerBound": 0.06402867407860051,
"running": 17, "running": 16,
"selectionWeight": 0.05885867124322159, "selectionWeight": 0.05568170427217614,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 7.333333333333333, "throughputPerHour": 7.333333333333333,
"waiting": 14072 "waiting": 14068
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 810.3529411764706, "backlogHours": 818.7920792079209,
"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": 1.0966432640978767, "qualityFactor": 0.9724217524003625,
"queueFactor": 1.0357258633203983, "queueFactor": 1.0373952418602577,
"queueWeight": 1.0357258633203983, "queueWeight": 1.0373952418602577,
"recentSuccess": 32, "recentSuccess": 31,
"recentSuccessRate": 0.3137254901960784, "recentSuccessRate": 0.3069306930693069,
"recentTerminal": 102, "recentTerminal": 101,
"recentWilsonLowerBound": 0.23182840733684665, "recentWilsonLowerBound": 0.22543494459305355,
"running": 6, "running": 6,
"selectionWeight": 1.1358217914622728, "selectionWeight": 1.0087856990215498,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 17.0, "throughputPerHour": 16.833333333333332,
"waiting": 13776 "waiting": 13783
} }
}, },
"queueAttemptedAt": "2026-09-17T08:59:04.507619+00:00", "queueAttemptedAt": "2026-09-17T09:11:08.851921+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-09-17T08:59:04.507619+00:00", "queueUpdatedAt": "2026-09-17T09:11:08.851921+00:00",
"supportedGpus": [ "supportedGpus": [
"Vastai_va16", "Vastai_va16",
"Kunlunxin_p-800", "Kunlunxin_p-800",

1506
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

228
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-17T08:52:55.610811+00:00", "generatedAt": "2026-09-17T09:11:01.258740+00:00",
"lastSyncTime": "2026-09-17T08:52:54.637063+00:00", "lastSyncTime": "2026-09-17T09:11:00.510552+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -2023,14 +2023,15 @@
"unresolvedFailureCount": 78 "unresolvedFailureCount": 78
}, },
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": { "Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
"attributableFailureCount": 0, "attributableFailureCount": 1,
"decisionFailureRate": 0.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 1,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4 "ambiguous_runtime": 4,
"framework_architecture_unsupported": 1
}, },
"failureCount": 4, "failureCount": 5,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm-mlu", "framework": "vllm-mlu",
"pendingCount": 0, "pendingCount": 0,
@@ -2040,7 +2041,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 4, "total": 5,
"unresolvedFailureCount": 4 "unresolvedFailureCount": 4
}, },
"Cambricon_mlu-370-x8|unknown|text-generation": { "Cambricon_mlu-370-x8|unknown|text-generation": {
@@ -2414,30 +2415,30 @@
"unresolvedFailureCount": 58 "unresolvedFailureCount": 58
}, },
"MetaX_c-500|vllm|text-generation": { "MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 60, "attributableFailureCount": 61,
"decisionFailureRate": 0.8696, "decisionFailureRate": 0.8714,
"decisionSuccessRate": 0.1304, "decisionSuccessRate": 0.1286,
"decisionTotal": 69, "decisionTotal": 70,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 11, "ambiguous_runtime": 11,
"backend_operator": 29, "backend_operator": 30,
"framework_architecture_unsupported": 22, "framework_architecture_unsupported": 22,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 7, "model_load": 7,
"repository_structure": 1, "repository_structure": 1,
"参数/模板问题": 9 "参数/模板问题": 9
}, },
"failureCount": 80, "failureCount": 81,
"failureRate": 0.8989, "failureRate": 0.9,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 9, "successCount": 9,
"successRate": 0.1011, "successRate": 0.1,
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 89, "total": 90,
"unresolvedFailureCount": 20 "unresolvedFailureCount": 20
}, },
"Mthreads_s4000|llamacpp|text-generation": { "Mthreads_s4000|llamacpp|text-generation": {
@@ -2836,13 +2837,13 @@
"unresolvedFailureCount": 906 "unresolvedFailureCount": 906
}, },
"vllm": { "vllm": {
"attributableFailureCount": 392, "attributableFailureCount": 393,
"decisionFailureRate": 0.9584, "decisionFailureRate": 0.9585,
"decisionSuccessRate": 0.0416, "decisionSuccessRate": 0.0415,
"decisionTotal": 409, "decisionTotal": 410,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 230, "ambiguous_runtime": 230,
"backend_operator": 37, "backend_operator": 38,
"framework_architecture_unsupported": 294, "framework_architecture_unsupported": 294,
"memory_capacity": 7, "memory_capacity": 7,
"model_load": 31, "model_load": 31,
@@ -2852,35 +2853,35 @@
"tokenizer_compatibility": 9, "tokenizer_compatibility": 9,
"参数/模板问题": 40 "参数/模板问题": 40
}, },
"failureCount": 664, "failureCount": 665,
"failureRate": 0.975, "failureRate": 0.9751,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 2, "platformFailureCount": 2,
"successCount": 17, "successCount": 17,
"successRate": 0.025, "successRate": 0.0249,
"total": 681, "total": 682,
"unresolvedFailureCount": 270 "unresolvedFailureCount": 270
}, },
"vllm-mlu": { "vllm-mlu": {
"attributableFailureCount": 9, "attributableFailureCount": 10,
"decisionFailureRate": 0.9, "decisionFailureRate": 0.9091,
"decisionSuccessRate": 0.1, "decisionSuccessRate": 0.0909,
"decisionTotal": 10, "decisionTotal": 11,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 31, "ambiguous_runtime": 31,
"framework_architecture_unsupported": 8, "framework_architecture_unsupported": 9,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"参数/模板问题": 3 "参数/模板问题": 3
}, },
"failureCount": 43, "failureCount": 44,
"failureRate": 0.9773, "failureRate": 0.9778,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 1, "successCount": 1,
"successRate": 0.0227, "successRate": 0.0222,
"total": 44, "total": 45,
"unresolvedFailureCount": 34 "unresolvedFailureCount": 34
}, },
"vllm-patch-tokenizer": { "vllm-patch-tokenizer": {
@@ -2971,7 +2972,7 @@
"unresolvedFailureCount": 7 "unresolvedFailureCount": 7
} }
}, },
"generatedAt": "2026-09-17T08:52:55.605672+00:00", "generatedAt": "2026-09-17T09:11:01.252695+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 54, "attributableFailureCount": 54,
@@ -3048,26 +3049,26 @@
"unresolvedFailureCount": 60 "unresolvedFailureCount": 60
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"attributableFailureCount": 30, "attributableFailureCount": 31,
"decisionFailureRate": 0.8824, "decisionFailureRate": 0.8857,
"decisionSuccessRate": 0.1176, "decisionSuccessRate": 0.1143,
"decisionTotal": 34, "decisionTotal": 35,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 42, "ambiguous_runtime": 42,
"framework_architecture_unsupported": 27, "framework_architecture_unsupported": 28,
"memory_capacity": 1, "memory_capacity": 1,
"tokenizer_compatibility": 2, "tokenizer_compatibility": 2,
"参数/模板问题": 1, "参数/模板问题": 1,
"验证失败": 39 "验证失败": 39
}, },
"failureCount": 112, "failureCount": 113,
"failureRate": 0.9655, "failureRate": 0.9658,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 4, "successCount": 4,
"successRate": 0.0345, "successRate": 0.0342,
"total": 116, "total": 117,
"unresolvedFailureCount": 82 "unresolvedFailureCount": 82
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
@@ -3184,13 +3185,13 @@
"unresolvedFailureCount": 131 "unresolvedFailureCount": 131
}, },
"MetaX_c-500": { "MetaX_c-500": {
"attributableFailureCount": 60, "attributableFailureCount": 61,
"decisionFailureRate": 0.7692, "decisionFailureRate": 0.7722,
"decisionSuccessRate": 0.2308, "decisionSuccessRate": 0.2278,
"decisionTotal": 78, "decisionTotal": 79,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 11, "ambiguous_runtime": 11,
"backend_operator": 29, "backend_operator": 30,
"framework_architecture_unsupported": 22, "framework_architecture_unsupported": 22,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 7, "model_load": 7,
@@ -3198,14 +3199,14 @@
"参数/模板问题": 19, "参数/模板问题": 19,
"验证失败": 48 "验证失败": 48
}, },
"failureCount": 138, "failureCount": 139,
"failureRate": 0.8846, "failureRate": 0.8854,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 18, "successCount": 18,
"successRate": 0.1154, "successRate": 0.1146,
"total": 156, "total": 157,
"unresolvedFailureCount": 78 "unresolvedFailureCount": 78
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
@@ -3943,6 +3944,29 @@
"total": 4, "total": 4,
"unresolvedFailureCount": 4 "unresolvedFailureCount": 4
}, },
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|exl3": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|deepseek_v4_dspark|none": { "Cambricon_mlu-370-x8|vllm-mlu|text-generation|deepseek_v4_dspark|none": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
@@ -5641,15 +5665,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors": { "MetaX_c-500|vllm|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 14, "attributableFailureCount": 15,
"decisionFailureRate": 0.9333, "decisionFailureRate": 0.9375,
"decisionSuccessRate": 0.0667, "decisionSuccessRate": 0.0625,
"decisionTotal": 15, "decisionTotal": 16,
"failureBreakdown": { "failureBreakdown": {
"backend_operator": 14 "backend_operator": 15
}, },
"failureCount": 14, "failureCount": 15,
"failureRate": 0.9333, "failureRate": 0.9375,
"framework": "vllm", "framework": "vllm",
"modelType": "llama", "modelType": "llama",
"pendingCount": 0, "pendingCount": 0,
@@ -5657,10 +5681,10 @@
"platformFailureCount": 0, "platformFailureCount": 0,
"quantizationMethod": "compressed-tensors", "quantizationMethod": "compressed-tensors",
"successCount": 1, "successCount": 1,
"successRate": 0.0667, "successRate": 0.0625,
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 15, "total": 16,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"MetaX_c-500|vllm|text-generation|nanbeige|compressed-tensors": { "MetaX_c-500|vllm|text-generation|nanbeige|compressed-tensors": {
@@ -8250,6 +8274,30 @@
"total": 4, "total": 4,
"unresolvedFailureCount": 4 "unresolvedFailureCount": 4
}, },
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|exl3|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|deepseek_v4_dspark|none|33": { "Cambricon_mlu-370-x8|vllm-mlu|text-generation|deepseek_v4_dspark|none|33": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
@@ -10952,6 +11000,30 @@
"total": 7, "total": 7,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"backend_operator": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|nanbeige|compressed-tensors|32": { "MetaX_c-500|vllm|text-generation|nanbeige|compressed-tensors|32": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
@@ -12316,17 +12388,17 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 2110, "terminalRecords": 2112,
"totalRecords": 2213, "totalRecords": 2215,
"totals": { "totals": {
"attributableFailureCount": 686, "attributableFailureCount": 688,
"decisionFailureRate": 0.884, "decisionFailureRate": 0.8843,
"decisionSuccessRate": 0.116, "decisionSuccessRate": 0.1157,
"decisionTotal": 776, "decisionTotal": 778,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 518, "ambiguous_runtime": 518,
"backend_operator": 47, "backend_operator": 48,
"framework_architecture_unsupported": 456, "framework_architecture_unsupported": 457,
"memory_capacity": 12, "memory_capacity": 12,
"model_load": 85, "model_load": 85,
"platform_infrastructure": 10, "platform_infrastructure": 10,
@@ -12336,14 +12408,14 @@
"参数/模板问题": 133, "参数/模板问题": 133,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 2020, "failureCount": 2022,
"failureRate": 0.9573, "failureRate": 0.9574,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 10, "platformFailureCount": 10,
"successCount": 90, "successCount": 90,
"successRate": 0.0427, "successRate": 0.0426,
"total": 2110, "total": 2112,
"unresolvedFailureCount": 1324 "unresolvedFailureCount": 1324
}, },
"warnings": [ "warnings": [
@@ -12354,11 +12426,11 @@
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Biren_166m 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 Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", "GPU hygon_k100-ai 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。", "GPU Vastai_va16 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 Cambricon_mlu-370-x4 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 Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x8 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。",
"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。", "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。",
"组合 Biren_166m|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|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 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -12383,6 +12455,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 2213, "summarizedRecords": 2215,
"version": 1 "version": 1
} }

1020
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1138
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

20
manifest.json
View File

@@ -1,24 +1,24 @@
{ {
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "38caeda62d3cc748b8d1a2278faf8fbcaebc6ccb0ea2313fa7fbbd4024432011", ".modelhub_state/architecture_compatibility_blacklist.json": "53ce4660cf4b29429d034b6e0ff2c903700e34542d896251a22b945d5d42e8b6",
".modelhub_state/architecture_history_backfill.json": "875af567a17cf61cc671a4fd2cd9a19c22a2015c2a2bdfb6cdcc3a633b7b7492", ".modelhub_state/architecture_history_backfill.json": "2971806a808f34a9e1ad436afa148f4b51d0b48f8fedacd940334f91b1bd4c04",
".modelhub_state/market_intelligence.json": "7aef1d1ab7977d679b56f887feb0f619830528c3377ddb3402a369d9b2617642", ".modelhub_state/market_intelligence.json": "99afc8fbc708a318ce699fbaabe5b0a3c3f7c2669044fd6942221ba7a08db859",
".modelhub_state/official_capabilities.json": "271ce87a45cc2986cc5815a67a852456f63df698d27bcf577b5d9b2dbcd31e3d", ".modelhub_state/official_capabilities.json": "acc4b76f7775bfb0e0b006fc68bb7e5d0c3aa075eedc2780bd85308b5acf78fb",
".modelhub_state/outcome_checkpoint.json": "2587c9437a217c7f58de1d62e9151dea46336b96119c9a36e9730bdfe69783f0", ".modelhub_state/outcome_checkpoint.json": "82cf79a3369c74b9aabbd88a3633fb7b228752b47deb3985090ce3cd8fc99b68",
".modelhub_state/queue_cleanup_latest.json": "4be02869ade05ead6def3f33db6297b95930841c24c0c7cab3372f7790acadd8", ".modelhub_state/queue_cleanup_latest.json": "4be02869ade05ead6def3f33db6297b95930841c24c0c7cab3372f7790acadd8",
".modelhub_state/recent_outcomes.jsonl": "5ab5fc797be370f400e8d98ac12d5ddd7a35d71c41220204421ac14d9f907be0", ".modelhub_state/recent_outcomes.jsonl": "5ab5fc797be370f400e8d98ac12d5ddd7a35d71c41220204421ac14d9f907be0",
".modelhub_state/recovery_active_tasks.jsonl": "88d618e993935992a4b134cb123245256454b0c3c17b535078a8eec18022c7a3", ".modelhub_state/recovery_active_tasks.jsonl": "cebb4b21a3f8a07a9acd185e0d1ba86fe0074904a9f6583b10eca0c30a2928bd",
".modelhub_state/recovery_intents.jsonl": "23ef29f4bbcb8bfa53b49a137318f896bb3773376d1f716573e4090212017359", ".modelhub_state/recovery_intents.jsonl": "f9a9be2d22eb9d3447ead26a98041b754df5e873384d7aeb398e9baa40630a5c",
".modelhub_state/routing_intelligence.json": "ca7e6b2966be70c0bbfb29b20dfe8fcfb0cb3c18ba00878e2ca3dc4fd468b308", ".modelhub_state/routing_intelligence.json": "ca7e6b2966be70c0bbfb29b20dfe8fcfb0cb3c18ba00878e2ca3dc4fd468b308",
".modelhub_state/submission_exclusions.jsonl": "a0cb4e822e4b6d26c26c3bf22698cacbab31f2df5f3402ecf04fdfb3a3577ef7", ".modelhub_state/submission_exclusions.jsonl": "a0cb4e822e4b6d26c26c3bf22698cacbab31f2df5f3402ecf04fdfb3a3577ef7",
".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983", ".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
"ledger/submissions.jsonl": "a50a13362c7735f155821c452bb5f9f61cba9c6d333eda730ae0cacc269c9bf1", "ledger/submissions.jsonl": "a50a13362c7735f155821c452bb5f9f61cba9c6d333eda730ae0cacc269c9bf1",
"outcomes/submissions.jsonl": "17181e645b22335fbbf66a714f2ee10a43e1414e197c56169ce18ea7666fd348" "outcomes/submissions.jsonl": "7f976aa4c94b9402cca7080aa3e1ffc185cea3eb9d5c107965b28b24c9101a8c"
}, },
"generation": 8646, "generation": 8647,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-17T09:09:59.906765+00:00", "updatedAt": "2026-09-17T09:13:21.040037+00:00",
"writerId": "eccb3e0018f640d19e578c271a207b5c" "writerId": "eccb3e0018f640d19e578c271a207b5c"
} }

2
outcomes/submissions.jsonl
View File

@@ -6,7 +6,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T12:43:05.302380+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:34:21.518508+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611265", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T12:43:05.302380+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:34:21.518508+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611265", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-04T12:43:05.302313+00:00", "modelId": "b77968543/Spark-X2.5-4B-Q8_0", "modelProfile": {"architectures": [], "configFingerprint": "054a7592edf89d789e18b12765c567c3c34b2ebb58661fdd49255aad03c66d40", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021152, "estimatedRequiredGiB": 4.889, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4375025003, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "library:", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4375025003}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:40:16.372199+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4611339", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-04T12:43:05.302313+00:00", "modelId": "b77968543/Spark-X2.5-4B-Q8_0", "modelProfile": {"architectures": [], "configFingerprint": "054a7592edf89d789e18b12765c567c3c34b2ebb58661fdd49255aad03c66d40", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021152, "estimatedRequiredGiB": 4.889, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4375025003, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "library:", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4375025003}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:40:16.372199+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4611339", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T15:14:29.722109+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29952487299, "estimatedRequiredGiB": 33.498, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29973198172, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8027131120, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29973198172}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T07:12:30.054811+00:00", "targetGpu": "Biren_166m", "taskId": "4621809", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T15:14:29.722109+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29952487299, "estimatedRequiredGiB": 33.498, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29973198172, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8027131120, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29973198172}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T07:12:30.054811+00:00", "targetGpu": "Biren_166m", "taskId": "4621809", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-04T16:14:29.511220+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "modelhub_preflight_oom:49"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:14:12.544960+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4622655", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T20:39:27.718139+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:8"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-04T12:34:49.403585+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4626360", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T20:39:27.718139+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:8"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-04T12:34:49.403585+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4626360", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T22:53:17.234593+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T14:46:47.882785+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4628625", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T22:53:17.234593+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T14:46:47.882785+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4628625", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T23:04:36.601749+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "published_card_spec", "sourceUrl": "https://aclanthology.org/2025.emnlp-main.1630.pdf"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T15:01:53.788146+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4628814", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T23:04:36.601749+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "published_card_spec", "sourceUrl": "https://aclanthology.org/2025.emnlp-main.1630.pdf"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T15:01:53.788146+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4628814", "taskType": "text-generation", "verifyResult": null}
@@ -31,7 +30,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:20:02.142845+00:00", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21921675140, "estimatedRequiredGiB": 24.525, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 21944922993, "modelscopeLicense": "apache-2.0", "modelscopeParams": 18589348592, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:vllm", "custom_tag:sm121", "custom_tag:gb10", "custom_tag:dgx-spark", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:modelopt"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21944922993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:17:16.438354+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641791", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:20:02.142845+00:00", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21921675140, "estimatedRequiredGiB": 24.525, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 21944922993, "modelscopeLicense": "apache-2.0", "modelscopeParams": 18589348592, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:vllm", "custom_tag:sm121", "custom_tag:gb10", "custom_tag:dgx-spark", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:modelopt"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21944922993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:17:16.438354+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641791", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T14:51:17.315106+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 44221632439, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T06:48:32.398253+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4643046", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T14:51:17.315106+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 44221632439, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T06:48:32.398253+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4643046", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T17:06:08.800571+00:00", "modelId": "LiquidAI/LFM2.5-230M-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "c331f3d8906467b7947cec00daebfec4ccad1f351223a1eced4dea452a1012df", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 149080928, "estimatedRequiredGiB": 2.218, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1984559598, "modelscopeLicense": "other", "modelscopeParams": 229693184, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:gguf", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1984559598}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T09:04:21.884770+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4645136", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T17:06:08.800571+00:00", "modelId": "LiquidAI/LFM2.5-230M-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "c331f3d8906467b7947cec00daebfec4ccad1f351223a1eced4dea452a1012df", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 149080928, "estimatedRequiredGiB": 2.218, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1984559598, "modelscopeLicense": "other", "modelscopeParams": 229693184, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:gguf", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1984559598}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T09:04:21.884770+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4645136", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T17:46:46.041785+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-Non-Uniform-compressed-tensors", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20041566112, "estimatedRequiredGiB": 22.408, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 20050750527, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-05T03:28:46.602358+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 20050750527}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T09:38:43.506267+00:00", "targetGpu": "MetaX_c-500", "taskId": "4645748", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T20:12:28.913845+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "e023b149992af42872de3c0c0c07dafd6a98d965e5bdb5a29ec5869e58d45725", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T12:03:37.084154+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4648146", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T20:12:28.913845+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "e023b149992af42872de3c0c0c07dafd6a98d965e5bdb5a29ec5869e58d45725", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T12:03:37.084154+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4648146", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T20:12:28.913926+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31263441624, "estimatedRequiredGiB": 34.958, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-05T12:03:37.105603+00:00", "targetGpu": "MetaX_c-500", "taskId": "4648141", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T20:12:28.913926+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31263441624, "estimatedRequiredGiB": 34.958, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-05T12:03:37.105603+00:00", "targetGpu": "MetaX_c-500", "taskId": "4648141", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T21:15:28.523439+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "0dce7c4be445254429760db90c7969177ecdca460563778d8b3371a37cc1a50e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:07:23.099409+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4649238", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T21:15:28.523439+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "0dce7c4be445254429760db90c7969177ecdca460563778d8b3371a37cc1a50e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:07:23.099409+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4649238", "taskType": "text-generation", "verifyResult": null}