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

state: generation 22116 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-08 08:58:49 +00:00
parent 62b70ae209
commit a4b6b2ac75
9 changed files with 2828 additions and 2886 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -2382,7 +2382,7 @@
"metax_c-500|vllm|text-generation|model_type:mini_k3": { "metax_c-500|vllm|text-generation|model_type:mini_k3": {
"architectureSignature": "model_type:mini_k3", "architectureSignature": "model_type:mini_k3",
"architectures": [], "architectures": [],
"evidenceCount": 5, "evidenceCount": 6,
"expiresAt": "2026-10-22T02:29:17.944417+00:00", "expiresAt": "2026-10-22T02:29:17.944417+00:00",
"framework": "vllm", "framework": "vllm",
"latestFailureAt": "2026-09-22T02:29:17.944417+00:00", "latestFailureAt": "2026-09-22T02:29:17.944417+00:00",
@@ -2393,15 +2393,15 @@
"nkkbr/Mini-K3-1H-decay-g1-v2_B", "nkkbr/Mini-K3-1H-decay-g1-v2_B",
"nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C",
"nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B",
"nkkbr/Mini-K3-1H-decay-g16-v2_B", "nkkbr/Mini-K3-1H-decay-g2-v2_C",
"nkkbr/Mini-K3-1H-attnres-block6-v1_C" "nkkbr/Mini-K3-1H-decay-g16-v2_B"
], ],
"sourceTaskIds": [ "sourceTaskIds": [
"5011010", "5011010",
"5009394", "5009394",
"5009165", "5009165",
"5007347", "5007393",
"5007123" "5007347"
], ],
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation" "taskType": "text-generation"
@@ -2910,7 +2910,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-10-08T08:35:05.574243+00:00", "generatedAt": "2026-10-08T08:53:06.829265+00:00",
"summary": { "summary": {
"activeBlockCount": 145, "activeBlockCount": 145,
"byGpuFramework": { "byGpuFramework": {

290
.modelhub_state/market_intelligence.json
View File

@@ -434,121 +434,121 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-10-08T08:49:20.568888+00:00", "generatedAt": "2026-10-08T08:54:34.355459+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 900.3567567567568, "backlogHours": 921.2154696132596,
"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": 0.4686818383359282, "qualityFactor": 0.6782633578826197,
"queueFactor": 0.9962644890002852, "queueFactor": 0.9976838388153688,
"queueWeight": 0.9962644890002852, "queueWeight": 0.9976838388153688,
"recentSuccess": 38, "recentSuccess": 42,
"recentSuccessRate": 0.20540540540540542, "recentSuccessRate": 0.23204419889502761,
"recentTerminal": 185, "recentTerminal": 181,
"recentWilsonLowerBound": 0.15346583999549976, "recentWilsonLowerBound": 0.17650202226032258,
"running": 9, "running": 8,
"selectionWeight": 0.46693107217345775, "selectionWeight": 0.6766923906201344,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 30.833333333333332, "throughputPerHour": 30.166666666666668,
"waiting": 27761 "waiting": 27790
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1148.7721518987341, "backlogHours": 1128.447204968944,
"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": 2.0756479152940113, "qualityFactor": 2.2071010541786165,
"queueFactor": 0.9605097106659901, "queueFactor": 0.9677761917582034,
"queueWeight": 0.9605097106659901, "queueWeight": 0.9677761917582034,
"recentSuccess": 59, "recentSuccess": 60,
"recentSuccessRate": 0.37341772151898733, "recentSuccessRate": 0.37267080745341613,
"recentTerminal": 158, "recentTerminal": 161,
"recentWilsonLowerBound": 0.30183760092886086, "recentWilsonLowerBound": 0.3017655254139041,
"running": 8, "running": 8,
"selectionWeight": 1.9936799785635164, "selectionWeight": 2.1359798530384975,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 26.333333333333332, "throughputPerHour": 26.833333333333332,
"waiting": 30251 "waiting": 30280
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 174.23529411764707, "backlogHours": 176.90066225165563,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Biren_166m", "gpu": "Biren_166m",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 0.8776981846648344, "qualityFactor": 0.7901369908771471,
"queueFactor": 1.2745780199900802, "queueFactor": 1.277873022686215,
"queueWeight": 1.2745780199900802, "queueWeight": 1.277873022686215,
"recentSuccess": 41, "recentSuccess": 38,
"recentSuccessRate": 0.2679738562091503, "recentSuccessRate": 0.25165562913907286,
"recentTerminal": 153, "recentTerminal": 151,
"recentWilsonLowerBound": 0.20410817120383035, "recentWilsonLowerBound": 0.18918551648503334,
"running": 9, "running": 8,
"selectionWeight": 1.1186948143589925, "selectionWeight": 1.0096947448683702,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 25.5, "throughputPerHour": 25.166666666666668,
"waiting": 4443 "waiting": 4452
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1180.344827586207, "backlogHours": 1180.6206896551723,
"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": 0.255574510647093, "qualityFactor": 0.2719031545791549,
"queueFactor": 0.9566113063487629, "queueFactor": 0.9612371832873559,
"queueWeight": 0.9566113063487629, "queueWeight": 0.9612371832873559,
"recentSuccess": 16, "recentSuccess": 16,
"recentSuccessRate": 0.1839080459770115, "recentSuccessRate": 0.1839080459770115,
"recentTerminal": 87, "recentTerminal": 87,
"recentWilsonLowerBound": 0.1164936795956926, "recentWilsonLowerBound": 0.1164936795956926,
"running": 7, "running": 7,
"selectionWeight": 0.24448546649956146, "selectionWeight": 0.2613634224346134,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 14.5, "throughputPerHour": 14.5,
"waiting": 17115 "waiting": 17119
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 364.4025974025974, "backlogHours": 369.0394736842105,
"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": 0.16801084560451957, "qualityFactor": 0.20736699645391155,
"queueFactor": 1.1410367315083487, "queueFactor": 1.144421998228848,
"queueWeight": 1.1410367315083487, "queueWeight": 1.144421998228848,
"recentSuccess": 22, "recentSuccess": 23,
"recentSuccessRate": 0.14285714285714285, "recentSuccessRate": 0.1513157894736842,
"recentTerminal": 154, "recentTerminal": 152,
"recentWilsonLowerBound": 0.09627048775425198, "recentWilsonLowerBound": 0.10299446940668534,
"running": 7, "running": 7,
"selectionWeight": 0.19170654612653482, "selectionWeight": 0.23731535244849988,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 25.666666666666668, "throughputPerHour": 25.333333333333332,
"waiting": 9353 "waiting": 9349
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 65.70394736842105, "backlogHours": 67.4391891891892,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -557,197 +557,197 @@
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 7, "recentSuccess": 5,
"recentSuccessRate": 0.023026315789473683, "recentSuccessRate": 0.016891891891891893,
"recentTerminal": 304, "recentTerminal": 296,
"recentWilsonLowerBound": 0.011197619445592749, "recentWilsonLowerBound": 0.007236132272172945,
"running": 24, "running": 23,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 50.666666666666664, "throughputPerHour": 49.333333333333336,
"waiting": 3329 "waiting": 3327
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 196.28571428571428, "backlogHours": 204.09183673469389,
"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": 0.28495682229119557, "qualityFactor": 0.3805349077948067,
"queueFactor": 1.2519977282412929, "queueFactor": 1.2507579600377012,
"queueWeight": 1.2519977282412929, "queueWeight": 1.2507579600377012,
"recentSuccess": 34, "recentSuccess": 36,
"recentSuccessRate": 0.16748768472906403, "recentSuccessRate": 0.1836734693877551,
"recentTerminal": 203, "recentTerminal": 196,
"recentWilsonLowerBound": 0.12240097375480329, "recentWilsonLowerBound": 0.13572411705027793,
"running": 2, "running": 3,
"selectionWeight": 0.3567652941554346, "selectionWeight": 0.47595706499656715,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 33.833333333333336, "throughputPerHour": 32.666666666666664,
"waiting": 6641 "waiting": 6667
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 1780.7307692307693, "backlogHours": 1714.4444444444443,
"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": 0.36653779663226277, "qualityFactor": 0.357660161451154,
"queueFactor": 0.8993880343225531, "queueFactor": 0.9089261704473152,
"queueWeight": 0.8993880343225531, "queueWeight": 0.9089261704473152,
"recentSuccess": 12, "recentSuccess": 12,
"recentSuccessRate": 0.23076923076923078, "recentSuccessRate": 0.2222222222222222,
"recentTerminal": 52, "recentTerminal": 54,
"recentWilsonLowerBound": 0.13724127341871611, "recentWilsonLowerBound": 0.13195287989578958,
"running": 2, "running": 2,
"selectionWeight": 0.3296597084180105, "selectionWeight": 0.3250866808693658,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 8.666666666666666, "throughputPerHour": 9.0,
"waiting": 15433 "waiting": 15430
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 364.0263157894737, "backlogHours": 376.0816326530612,
"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": 0.24349201670039258, "qualityFactor": 0.27932976139933086,
"queueFactor": 1.141213571461706, "queueFactor": 1.1411817089027336,
"queueWeight": 1.141213571461706, "queueWeight": 1.1411817089027336,
"recentSuccess": 25, "recentSuccess": 25,
"recentSuccessRate": 0.16447368421052633, "recentSuccessRate": 0.17006802721088435,
"recentTerminal": 152, "recentTerminal": 147,
"recentWilsonLowerBound": 0.11395725895038367, "recentWilsonLowerBound": 0.11792934662143166,
"running": 10, "running": 6,
"selectionWeight": 0.2778763940010684, "selectionWeight": 0.3187660144610812,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 25.333333333333332, "throughputPerHour": 24.5,
"waiting": 9222 "waiting": 9214
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 590.5945945945946, "backlogHours": 601.4311926605504,
"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": 0.3517015309317872, "qualityFactor": 0.3438167605210237,
"queueFactor": 1.0613128549841049, "queueFactor": 1.0635777132293716,
"queueWeight": 1.0613128549841049, "queueWeight": 1.0635777132293716,
"recentSuccess": 22, "recentSuccess": 21,
"recentSuccessRate": 0.1981981981981982, "recentSuccessRate": 0.1926605504587156,
"recentTerminal": 111, "recentTerminal": 109,
"recentWilsonLowerBound": 0.1346877647184602, "recentWilsonLowerBound": 0.12960637450184612,
"running": 4, "running": 4,
"selectionWeight": 0.37326535589549553, "selectionWeight": 0.3656758439248809,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 18.5, "throughputPerHour": 18.166666666666668,
"waiting": 10926 "waiting": 10926
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 2093.904761904762, "backlogHours": 1887.3428571428572,
"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": 2.5, "qualityFactor": 2.5,
"queueFactor": 0.8777954109730078, "queueFactor": 0.8959205543086315,
"queueWeight": 0.8777954109730078, "queueWeight": 0.8959205543086315,
"recentSuccess": 28, "recentSuccess": 30,
"recentSuccessRate": 0.4444444444444444, "recentSuccessRate": 0.42857142857142855,
"recentTerminal": 63, "recentTerminal": 70,
"recentWilsonLowerBound": 0.3284690053363268, "recentWilsonLowerBound": 0.31935124886212546,
"running": 4, "running": 4,
"selectionWeight": 2.1944885274325197, "selectionWeight": 2.2398013857715786,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.5, "throughputPerHour": 11.666666666666666,
"waiting": 21986 "waiting": 22019
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 2338.5, "backlogHours": 2509.609756097561,
"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": 0.163651485927655, "qualityFactor": 0.20449299371849367,
"queueFactor": 0.8633685780072269, "queueFactor": 0.8584325790258226,
"queueWeight": 0.8633685780072269, "queueWeight": 0.8584325790258226,
"recentSuccess": 8, "recentSuccess": 8,
"recentSuccessRate": 0.18181818181818182, "recentSuccessRate": 0.1951219512195122,
"recentTerminal": 44, "recentTerminal": 41,
"recentWilsonLowerBound": 0.09512692558258554, "recentWilsonLowerBound": 0.1023431574920593,
"running": 2, "running": 2,
"selectionWeight": 0.1412915506941292, "selectionWeight": 0.17554344799047786,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 7.333333333333333, "throughputPerHour": 6.833333333333333,
"waiting": 17149 "waiting": 17149
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 1337.6, "backlogHours": 1374.2465753424658,
"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": 0.05, "qualityFactor": 0.05,
"queueFactor": 0.938832046848514, "queueFactor": 0.9395879125555199,
"queueWeight": 0.938832046848514, "queueWeight": 0.9395879125555199,
"recentSuccess": 3, "recentSuccess": 3,
"recentSuccessRate": 0.04, "recentSuccessRate": 0.0410958904109589,
"recentTerminal": 75, "recentTerminal": 73,
"recentWilsonLowerBound": 0.013695816001486477, "recentWilsonLowerBound": 0.014073685234288726,
"running": 17, "running": 15,
"selectionWeight": 0.0469416023424257, "selectionWeight": 0.046979395627776,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 12.5, "throughputPerHour": 12.166666666666666,
"waiting": 16720 "waiting": 16720
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 855.9847328244275, "backlogHours": 892.952380952381,
"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": 0.18694000336749578, "qualityFactor": 0.1888688266043279,
"queueFactor": 1.0038456512705034, "queueFactor": 1.0023580340714795,
"queueWeight": 1.0038456512705034, "queueWeight": 1.0023580340714795,
"recentSuccess": 20, "recentSuccess": 19,
"recentSuccessRate": 0.15267175572519084, "recentSuccessRate": 0.15079365079365079,
"recentTerminal": 131, "recentTerminal": 126,
"recentWilsonLowerBound": 0.10105740445609404, "recentWilsonLowerBound": 0.09871172541981235,
"running": 6, "running": 6,
"selectionWeight": 0.18765890942895389, "selectionWeight": 0.18931418573250128,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 21.833333333333332, "throughputPerHour": 21.0,
"waiting": 18689 "waiting": 18752
} }
}, },
"queueAttemptedAt": "2026-10-08T08:41:44.473312+00:00", "queueAttemptedAt": "2026-10-08T08:54:34.355459+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-10-08T08:41:44.473312+00:00", "queueUpdatedAt": "2026-10-08T08:54:34.355459+00:00",
"supportedGpus": [ "supportedGpus": [
"Cambricon_mlu-370-x4", "Cambricon_mlu-370-x4",
"Kunlunxin_p-800", "Kunlunxin_p-800",

1677
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

253
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-10-08T07:25:08.019763+00:00", "generatedAt": "2026-10-08T08:53:06.736240+00:00",
"lastSyncTime": "2026-10-08T07:25:07.760885+00:00", "lastSyncTime": "2026-10-08T08:53:06.467995+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -2386,7 +2386,7 @@
"metax_c-500|vllm|text-generation|model_type:mini_k3": { "metax_c-500|vllm|text-generation|model_type:mini_k3": {
"architectureSignature": "model_type:mini_k3", "architectureSignature": "model_type:mini_k3",
"architectures": [], "architectures": [],
"evidenceCount": 5, "evidenceCount": 6,
"expiresAt": "2026-10-22T02:29:17.944417+00:00", "expiresAt": "2026-10-22T02:29:17.944417+00:00",
"framework": "vllm", "framework": "vllm",
"latestFailureAt": "2026-09-22T02:29:17.944417+00:00", "latestFailureAt": "2026-09-22T02:29:17.944417+00:00",
@@ -2397,15 +2397,15 @@
"nkkbr/Mini-K3-1H-decay-g1-v2_B", "nkkbr/Mini-K3-1H-decay-g1-v2_B",
"nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C",
"nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B",
"nkkbr/Mini-K3-1H-decay-g16-v2_B", "nkkbr/Mini-K3-1H-decay-g2-v2_C",
"nkkbr/Mini-K3-1H-attnres-block6-v1_C" "nkkbr/Mini-K3-1H-decay-g16-v2_B"
], ],
"sourceTaskIds": [ "sourceTaskIds": [
"5011010", "5011010",
"5009394", "5009394",
"5009165", "5009165",
"5007347", "5007393",
"5007123" "5007347"
], ],
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation" "taskType": "text-generation"
@@ -3353,11 +3353,11 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 1, "decisionTotal": 1,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 139, "ambiguous_runtime": 140,
"memory_capacity": 1, "memory_capacity": 1,
"参数/模板问题": 1 "参数/模板问题": 1
}, },
"failureCount": 141, "failureCount": 142,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"pendingCount": 0, "pendingCount": 0,
@@ -3367,8 +3367,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 141, "total": 142,
"unresolvedFailureCount": 140 "unresolvedFailureCount": 141
}, },
"Biren_166m|vllm|text-generation": { "Biren_166m|vllm|text-generation": {
"attributableFailureCount": 50, "attributableFailureCount": 50,
@@ -4819,16 +4819,16 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"MetaX_c-500|vllm|text-generation": { "MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 638, "attributableFailureCount": 639,
"decisionFailureRate": 0.9608, "decisionFailureRate": 0.9609,
"decisionSuccessRate": 0.0392, "decisionSuccessRate": 0.0391,
"decisionTotal": 664, "decisionTotal": 665,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 134, "ambiguous_runtime": 134,
"architecture_compatibility": 20, "architecture_compatibility": 20,
"backend_operator": 43, "backend_operator": 43,
"context_length": 46, "context_length": 46,
"framework_architecture_unsupported": 201, "framework_architecture_unsupported": 202,
"memory_capacity": 84, "memory_capacity": 84,
"model_load": 65, "model_load": 65,
"platform_infrastructure": 3, "platform_infrastructure": 3,
@@ -4837,17 +4837,17 @@
"tokenizer_compatibility": 79, "tokenizer_compatibility": 79,
"参数/模板问题": 10 "参数/模板问题": 10
}, },
"failureCount": 785, "failureCount": 786,
"failureRate": 0.9679, "failureRate": 0.968,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 3, "platformFailureCount": 3,
"successCount": 26, "successCount": 26,
"successRate": 0.0321, "successRate": 0.032,
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 811, "total": 812,
"unresolvedFailureCount": 144 "unresolvedFailureCount": 144
}, },
"MetaX_c-500|vllm|unknown": { "MetaX_c-500|vllm|unknown": {
@@ -5641,17 +5641,17 @@
"unresolvedFailureCount": 6477 "unresolvedFailureCount": 6477
}, },
"vllm": { "vllm": {
"attributableFailureCount": 3680, "attributableFailureCount": 3681,
"decisionFailureRate": 0.972, "decisionFailureRate": 0.972,
"decisionSuccessRate": 0.028, "decisionSuccessRate": 0.028,
"decisionTotal": 3786, "decisionTotal": 3787,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1602, "ambiguous_runtime": 1602,
"architecture_compatibility": 112, "architecture_compatibility": 112,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 95, "backend_operator": 95,
"context_length": 161, "context_length": 161,
"framework_architecture_unsupported": 1400, "framework_architecture_unsupported": 1401,
"memory_capacity": 725, "memory_capacity": 725,
"model_load": 228, "model_load": 228,
"platform_infrastructure": 880, "platform_infrastructure": 880,
@@ -5660,14 +5660,14 @@
"tokenizer_compatibility": 420, "tokenizer_compatibility": 420,
"参数/模板问题": 52 "参数/模板问题": 52
}, },
"failureCount": 6214, "failureCount": 6215,
"failureRate": 0.9832, "failureRate": 0.9832,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 880, "platformFailureCount": 880,
"successCount": 106, "successCount": 106,
"successRate": 0.0168, "successRate": 0.0168,
"total": 6320, "total": 6321,
"unresolvedFailureCount": 1654 "unresolvedFailureCount": 1654
}, },
"vllm-customized": { "vllm-customized": {
@@ -5770,7 +5770,7 @@
"decisionSuccessRate": 0.0272, "decisionSuccessRate": 0.0272,
"decisionTotal": 184, "decisionTotal": 184,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 392, "ambiguous_runtime": 393,
"backend_operator": 9, "backend_operator": 9,
"framework_architecture_unsupported": 51, "framework_architecture_unsupported": 51,
"memory_capacity": 10, "memory_capacity": 10,
@@ -5779,15 +5779,15 @@
"tokenizer_compatibility": 96, "tokenizer_compatibility": 96,
"参数/模板问题": 16 "参数/模板问题": 16
}, },
"failureCount": 614, "failureCount": 615,
"failureRate": 0.9919, "failureRate": 0.9919,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 27, "platformFailureCount": 27,
"successCount": 5, "successCount": 5,
"successRate": 0.0081, "successRate": 0.0081,
"total": 619, "total": 620,
"unresolvedFailureCount": 408 "unresolvedFailureCount": 409
}, },
"vllm_tokenizer_patch": { "vllm_tokenizer_patch": {
"attributableFailureCount": 164, "attributableFailureCount": 164,
@@ -5818,7 +5818,7 @@
"unresolvedFailureCount": 304 "unresolvedFailureCount": 304
} }
}, },
"generatedAt": "2026-10-08T07:25:08.004827+00:00", "generatedAt": "2026-10-08T08:53:06.722272+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 124, "attributableFailureCount": 124,
@@ -5881,7 +5881,7 @@
"decisionSuccessRate": 0.1147, "decisionSuccessRate": 0.1147,
"decisionTotal": 218, "decisionTotal": 218,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 283, "ambiguous_runtime": 284,
"backend_operator": 4, "backend_operator": 4,
"context_length": 10, "context_length": 10,
"framework_architecture_unsupported": 125, "framework_architecture_unsupported": 125,
@@ -5895,15 +5895,15 @@
"日志缺失": 62, "日志缺失": 62,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 782, "failureCount": 783,
"failureRate": 0.969, "failureRate": 0.9691,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 2, "platformFailureCount": 2,
"successCount": 25, "successCount": 25,
"successRate": 0.031, "successRate": 0.0309,
"total": 807, "total": 808,
"unresolvedFailureCount": 587 "unresolvedFailureCount": 588
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"attributableFailureCount": 761, "attributableFailureCount": 761,
@@ -6093,16 +6093,16 @@
"unresolvedFailureCount": 170 "unresolvedFailureCount": 170
}, },
"MetaX_c-500": { "MetaX_c-500": {
"attributableFailureCount": 678, "attributableFailureCount": 679,
"decisionFailureRate": 0.8218, "decisionFailureRate": 0.822,
"decisionSuccessRate": 0.1782, "decisionSuccessRate": 0.178,
"decisionTotal": 825, "decisionTotal": 826,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 306, "ambiguous_runtime": 306,
"architecture_compatibility": 21, "architecture_compatibility": 21,
"backend_operator": 43, "backend_operator": 43,
"context_length": 59, "context_length": 59,
"framework_architecture_unsupported": 209, "framework_architecture_unsupported": 210,
"memory_capacity": 85, "memory_capacity": 85,
"model_load": 66, "model_load": 66,
"platform_infrastructure": 5, "platform_infrastructure": 5,
@@ -6113,14 +6113,14 @@
"日志缺失": 15, "日志缺失": 15,
"验证失败": 48 "验证失败": 48
}, },
"failureCount": 1471, "failureCount": 1472,
"failureRate": 0.9091, "failureRate": 0.9092,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 5, "platformFailureCount": 5,
"successCount": 147, "successCount": 147,
"successRate": 0.0909, "successRate": 0.0908,
"total": 1618, "total": 1619,
"unresolvedFailureCount": 788 "unresolvedFailureCount": 788
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
@@ -9392,9 +9392,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 10 "ambiguous_runtime": 11
}, },
"failureCount": 10, "failureCount": 11,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"modelType": "mini_k3", "modelType": "mini_k3",
@@ -9406,8 +9406,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 10, "total": 11,
"unresolvedFailureCount": 10 "unresolvedFailureCount": 11
}, },
"Biren_166m|vllm_fix_tokenizer|text-generation|mistral3|none": { "Biren_166m|vllm_fix_tokenizer|text-generation|mistral3|none": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -21483,14 +21483,14 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"MetaX_c-500|vllm|text-generation|mini_k3|none": { "MetaX_c-500|vllm|text-generation|mini_k3|none": {
"attributableFailureCount": 5, "attributableFailureCount": 6,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 5, "decisionTotal": 6,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 5 "framework_architecture_unsupported": 6
}, },
"failureCount": 5, "failureCount": 6,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"modelType": "mini_k3", "modelType": "mini_k3",
@@ -21502,7 +21502,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 5, "total": 6,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"MetaX_c-500|vllm|text-generation|muse_glimmer|none": { "MetaX_c-500|vllm|text-generation|muse_glimmer|none": {
@@ -25933,9 +25933,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 13 "ambiguous_runtime": 14
}, },
"failureCount": 13, "failureCount": 14,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
@@ -25947,8 +25947,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 13, "total": 14,
"unresolvedFailureCount": 13 "unresolvedFailureCount": 14
}, },
"Cambricon_mlu-370-x4|vllm-customized|text-generation": { "Cambricon_mlu-370-x4|vllm-customized|text-generation": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
@@ -26257,18 +26257,17 @@
"unresolvedFailureCount": 13 "unresolvedFailureCount": 13
}, },
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": { "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 3, "attributableFailureCount": 1,
"consecutiveFailures": 3, "consecutiveFailures": 1,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 3, "decisionTotal": 1,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1, "ambiguous_runtime": 1,
"backend_operator": 1, "model_load": 1
"model_load": 2
}, },
"failureCount": 4, "failureCount": 2,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
@@ -26280,7 +26279,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Kunlunxin_p-800", "targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation", "taskType": "text-generation",
"total": 4, "total": 2,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Kunlunxin_p-800|vllm|text-generation": { "Kunlunxin_p-800|vllm|text-generation": {
@@ -26337,16 +26336,16 @@
"unresolvedFailureCount": 16 "unresolvedFailureCount": 16
}, },
"MetaX_c-500|vllm|text-generation": { "MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 5, "attributableFailureCount": 6,
"consecutiveFailures": 5, "consecutiveFailures": 6,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 5, "decisionTotal": 6,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 5 "framework_architecture_unsupported": 6
}, },
"failureCount": 5, "failureCount": 6,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
@@ -26358,7 +26357,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 5, "total": 6,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Mthreads_s4000|vllm|text-generation": { "Mthreads_s4000|vllm|text-generation": {
@@ -26697,9 +26696,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 10 "ambiguous_runtime": 11
}, },
"failureCount": 10, "failureCount": 11,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-10-08T02:59:38.470312+00:00", "lastTerminalAt": "2026-10-08T02:59:38.470312+00:00",
@@ -26712,8 +26711,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 10, "total": 11,
"unresolvedFailureCount": 10 "unresolvedFailureCount": 11
}, },
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|none": { "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|none": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -27315,56 +27314,6 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-24T04:45:29.199678+00:00",
"modelType": "mistral",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"backend_operator": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-24T05:02:37.758196+00:00",
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Kunlunxin_p-800|vllm|text-generation|llama|compressed-tensors": { "Kunlunxin_p-800|vllm|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
"consecutiveFailures": 1, "consecutiveFailures": 1,
@@ -27516,15 +27465,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"MetaX_c-500|vllm|text-generation|mini_k3|none": { "MetaX_c-500|vllm|text-generation|mini_k3|none": {
"attributableFailureCount": 5, "attributableFailureCount": 6,
"consecutiveFailures": 5, "consecutiveFailures": 6,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 5, "decisionTotal": 6,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 5 "framework_architecture_unsupported": 6
}, },
"failureCount": 5, "failureCount": 6,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"lastTerminalAt": "2026-10-08T03:44:24.154872+00:00", "lastTerminalAt": "2026-10-08T03:44:24.154872+00:00",
@@ -27537,7 +27486,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 5, "total": 6,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Mthreads_s4000|vllm|text-generation|mini_k3|none": { "Mthreads_s4000|vllm|text-generation|mini_k3|none": {
@@ -33017,9 +32966,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 10 "ambiguous_runtime": 11
}, },
"failureCount": 10, "failureCount": 11,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 30, "loadSizeLog2Bucket": 30,
@@ -33032,8 +32981,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 10, "total": 11,
"unresolvedFailureCount": 10 "unresolvedFailureCount": 11
}, },
"Biren_166m|vllm_fix_tokenizer|text-generation|mistral3|none|34": { "Biren_166m|vllm_fix_tokenizer|text-generation|mistral3|none|34": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -51007,14 +50956,14 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"MetaX_c-500|vllm|text-generation|mini_k3|none|30": { "MetaX_c-500|vllm|text-generation|mini_k3|none|30": {
"attributableFailureCount": 5, "attributableFailureCount": 6,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 5, "decisionTotal": 6,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 5 "framework_architecture_unsupported": 6
}, },
"failureCount": 5, "failureCount": 6,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"loadSizeLog2Bucket": 30, "loadSizeLog2Bucket": 30,
@@ -51027,7 +50976,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 5, "total": 6,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"MetaX_c-500|vllm|text-generation|muse_glimmer|none|34": { "MetaX_c-500|vllm|text-generation|muse_glimmer|none|34": {
@@ -57547,20 +57496,20 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 17609, "terminalRecords": 17611,
"totalRecords": 18096, "totalRecords": 18098,
"totals": { "totals": {
"attributableFailureCount": 6289, "attributableFailureCount": 6290,
"decisionFailureRate": 0.8653, "decisionFailureRate": 0.8653,
"decisionSuccessRate": 0.1347, "decisionSuccessRate": 0.1347,
"decisionTotal": 7268, "decisionTotal": 7269,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4591, "ambiguous_runtime": 4592,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 130, "backend_operator": 130,
"context_length": 327, "context_length": 327,
"framework_architecture_unsupported": 2307, "framework_architecture_unsupported": 2308,
"memory_capacity": 1206, "memory_capacity": 1206,
"model_load": 571, "model_load": 571,
"platform_infrastructure": 955, "platform_infrastructure": 955,
@@ -57571,15 +57520,15 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 16630, "failureCount": 16632,
"failureRate": 0.9444, "failureRate": 0.9444,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 955, "platformFailureCount": 955,
"successCount": 979, "successCount": 979,
"successRate": 0.0556, "successRate": 0.0556,
"total": 17609, "total": 17611,
"unresolvedFailureCount": 9386 "unresolvedFailureCount": 9387
}, },
"warnings": [ "warnings": [
"GPU MetaX_c-500 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。",
@@ -57588,14 +57537,14 @@
"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 Vastai_va16 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 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 Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Sunrise_pt-200-x1 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 Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-100 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 Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Vastai_va16|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|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b3|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 Ascend_910-b3|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 Iluvatar_mrv-100|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 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -57641,6 +57590,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 18096, "summarizedRecords": 18098,
"version": 1 "version": 1
} }

4
.modelhub_state/recent_outcomes.jsonl
View File

@@ -196,6 +196,7 @@
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-22T01:23:49.082807+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:23:32+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4881076", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-22T01:23:49.082807+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:23:32+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4881076", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-22T01:23:49.082789+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:23:31+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4925021", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-22T01:23:49.082789+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:23:31+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4925021", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T04:30:44.383961+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:12:42.625199+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5010136", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T04:30:44.383961+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:12:42.625199+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5010136", "taskType": "text-generation", "verifyResult": null}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T08:53:06.467968+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g64-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2032454776, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2040816815}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T01:11:32.582811+00:00", "targetGpu": "Biren_166m", "taskId": "5010128", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T04:30:44.383858+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T00:52:32.483120+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5009939", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T04:30:44.383858+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T00:52:32.483120+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5009939", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T04:30:44.383850+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T00:42:42.849387+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5009810", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T04:30:44.383850+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T00:42:42.849387+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5009810", "taskType": "text-generation", "verifyResult": null}
{"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": ["mini_k3"], "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T01:09:06.056781+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042280856}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T00:42:42.844085+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5009809", "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": ["mini_k3"], "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T01:09:06.056781+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042280856}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T00:42:42.844085+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5009809", "taskType": "text-generation", "verifyResult": -1}
@@ -213,6 +214,7 @@
{"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": ["mini_k3"], "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T05:42:37.051690+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T21:58:45.645484+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5007793", "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": ["mini_k3"], "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T05:42:37.051690+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T21:58:45.645484+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5007793", "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": ["mini_k3"], "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T05:42:37.051732+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T21:44:40.148404+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5007665", "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": ["mini_k3"], "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T05:42:37.051732+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T21:44:40.148404+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5007665", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T05:06:44.255704+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T21:20:52.905137+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5007448", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T05:06:44.255704+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T21:20:52.905137+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5007448", "taskType": "text-generation", "verifyResult": null}
{"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": ["mini_k3"], "framework": "vllm", "lastSyncTime": "2026-10-08T08:53:06.467995+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039076183}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T21:14:33.510085+00:00", "targetGpu": "MetaX_c-500", "taskId": "5007393", "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": ["mini_k3"], "framework": "vllm", "lastSyncTime": "2026-10-08T03:44:24.154857+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T21:10:26.048602+00:00", "targetGpu": "MetaX_c-500", "taskId": "5007347", "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": ["mini_k3"], "framework": "vllm", "lastSyncTime": "2026-10-08T03:44:24.154857+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T21:10:26.048602+00:00", "targetGpu": "MetaX_c-500", "taskId": "5007347", "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": ["mini_k3"], "framework": "vllm", "lastSyncTime": "2026-10-08T03:44:24.154695+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T21:06:49.754370+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5007313", "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": ["mini_k3"], "framework": "vllm", "lastSyncTime": "2026-10-08T03:44:24.154695+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T21:06:49.754370+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5007313", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T03:19:51.851207+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T21:04:43.408226+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5007290", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T03:19:51.851207+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T21:04:43.408226+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5007290", "taskType": "text-generation", "verifyResult": null}
@@ -296,5 +298,3 @@
{"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": "vllm", "lastSyncTime": "2026-09-24T10:56:20.956238+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5469228368, "estimatedRequiredGiB": 6.118, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 5473985594, "modelscopeLicense": "mit", "modelscopeParams": 1922048000, "modelscopeTags": ["license:mit", "model_type:mpt", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5473985594}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:24:26.638177+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005440", "taskType": "text-generation", "verifyResult": -1} {"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-24T10:56:20.956238+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5469228368, "estimatedRequiredGiB": 6.118, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 5473985594, "modelscopeLicense": "mit", "modelscopeParams": 1922048000, "modelscopeTags": ["license:mit", "model_type:mpt", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5473985594}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:24:26.638177+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005440", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-23T10:53:27.671921+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093251763, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093251763}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:24:26.526740+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005439", "taskType": "text-generation", "verifyResult": -1} {"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-23T10:53:27.671921+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093251763, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093251763}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:24:26.526740+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005439", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T04:54:21.054731+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:24:26.404225+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005438", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T04:54:21.054731+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:24:26.404225+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005438", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T04:45:29.199678+00:00", "modelId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221450, "modelscopeLicense": "llama2", "modelscopeParams": 12247782400, "modelscopeTags": ["license:llama2", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8338221450}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:24:26.292133+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005437", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T05:02:37.758196+00:00", "modelId": "RedHatAI/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7855165704, "estimatedRequiredGiB": 8.783, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7858540940, "modelscopeLicense": "other", "modelscopeParams": 7400416256, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7858540940}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:24:26.079648+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005436", "taskType": "text-generation", "verifyResult": -1}

1666
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1790
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

20
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1", ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "011af8ada36692691244936681e00a038acd6a70c3c8decfd684bf1a6fbce8e2", ".modelhub_state/architecture_compatibility_blacklist.json": "9fddef9e72de6f69d8c75f456bfd4d0f5e22502d43dad0e421765efc9d02cacf",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "71b66ead4635a8e6d681c5a0eb06c6b4c030a382218164d610453fede6955eba", ".modelhub_state/market_intelligence.json": "97330d807d3b4e90b43a6b6011ac82fbc352581910e7d077e7d6fa9cba25cf13",
".modelhub_state/official_capabilities.json": "c5e0482c71e35b6daebd5088d67e60ae43068f842dc148346a4b6fac39c59a2a", ".modelhub_state/official_capabilities.json": "7e643e18607ddc7a1b5e6eb5c80036da5d37b51693879e3fcb57b717f0fdc985",
".modelhub_state/outcome_checkpoint.json": "558e909dcc293bd74f6cc8165b7a5bd41d22a94e390d862f1df66acd1bf7a3ce", ".modelhub_state/outcome_checkpoint.json": "2e8d1a8bbd45d11b5033fb96ef288adbc004d93e3b9cf49e02636cfa42952b53",
".modelhub_state/queue_cleanup_latest.json": "24a54db5e2d713e487bc3003e70f1f1003bc27e86ee9eb2ae2e3d08443dcb9e4", ".modelhub_state/queue_cleanup_latest.json": "24a54db5e2d713e487bc3003e70f1f1003bc27e86ee9eb2ae2e3d08443dcb9e4",
".modelhub_state/recent_outcomes.jsonl": "36ca1d87e215948d4e6be9a725ba7ef549741dc4465b75d3f71fa497810ef4b8", ".modelhub_state/recent_outcomes.jsonl": "1d8ebca9ff4aa3dd357115f1228cf865eaa874e9c2995921a54b412c2c7239f2",
".modelhub_state/recovery_active_tasks.jsonl": "3b87e31c4b58085dc0c0fda0d789fec31e2064ced072d3464204de3574c4e9a8", ".modelhub_state/recovery_active_tasks.jsonl": "f1a71e2da3a17138531ebf46ba929c02ad9e9c90f0a18d7caf35e3fee0787d5d",
".modelhub_state/recovery_intents.jsonl": "1ee782044f5b29bcda2069795366cc848d50d6697de8ce729621d2958fee8e06", ".modelhub_state/recovery_intents.jsonl": "5c92cd600010d9d86b01bba2a11a161c37d3f7b8ed1e67244793bb88ef83016a",
".modelhub_state/routing_intelligence.json": "d644a654a7bb72cb2d9a0f6c859f940d9995caa66f79a509546427e20571e808", ".modelhub_state/routing_intelligence.json": "d644a654a7bb72cb2d9a0f6c859f940d9995caa66f79a509546427e20571e808",
".modelhub_state/submission_exclusions.jsonl": "dca7091e8b1da8bf9b3ecb95fe573b2a41666601edf86cea13ce9ce738b9eb7b", ".modelhub_state/submission_exclusions.jsonl": "dca7091e8b1da8bf9b3ecb95fe573b2a41666601edf86cea13ce9ce738b9eb7b",
".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f", ".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
"ledger/submissions.jsonl": "bc6055d874509912682a8bc9f768f06641cd2d3a569653fff58fe873f7691a90", "ledger/submissions.jsonl": "bc6055d874509912682a8bc9f768f06641cd2d3a569653fff58fe873f7691a90",
"outcomes/submissions.jsonl": "65e79d360c72684650dfdb7f955ce77861d61ce5fbe42c00b5745f9f0c67b7b7" "outcomes/submissions.jsonl": "cd618dffecf20974aa98f70eb1b181a7824cb5d00180d7141184432601b45b10"
}, },
"generation": 22115, "generation": 22116,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-10-08T08:52:05.255575+00:00", "updatedAt": "2026-10-08T08:58:49.751399+00:00",
"writerId": "33ed03361c5848e88b8ce6204fb4f7d2" "writerId": "33ed03361c5848e88b8ce6204fb4f7d2"
} }

2
outcomes/submissions.jsonl
View File

@@ -210,7 +210,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:05:58.563212+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2009388256, "estimatedRequiredGiB": 2.25, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2012995244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:05:51.057293+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006049", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:05:58.563212+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2009388256, "estimatedRequiredGiB": 2.25, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2012995244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:05:51.057293+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006049", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:05:58.563180+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030882272, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 1015108684, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039244968}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:05:50.750203+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006047", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:05:58.563180+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030882272, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 1015108684, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039244968}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:05:50.750203+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006047", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T04:37:48.672578+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2044205392, "estimatedRequiredGiB": 2.469, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2168994941, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2209448692}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T20:37:39.959415+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5007016", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T04:37:48.672578+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2044205392, "estimatedRequiredGiB": 2.469, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2168994941, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2209448692}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T20:37:39.959415+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5007016", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T05:14:49.361921+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039076183}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T21:14:33.510085+00:00", "targetGpu": "MetaX_c-500", "taskId": "5007393", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-22T06:03:39.773018+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19329296879}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T22:02:39.078952+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5007818", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-22T06:03:39.773018+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19329296879}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T22:02:39.078952+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5007818", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T07:42:35.356576+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042280856}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T23:00:55.147214+00:00", "targetGpu": "MetaX_c-500", "taskId": "5008520", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T07:42:35.356576+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042280856}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T23:00:55.147214+00:00", "targetGpu": "MetaX_c-500", "taskId": "5008520", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T07:42:35.356653+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T23:28:51.084949+00:00", "targetGpu": "Vastai_va16", "taskId": "5008886", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T07:42:35.356653+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T23:28:51.084949+00:00", "targetGpu": "Vastai_va16", "taskId": "5008886", "taskType": "text-generation", "verifyResult": null}
@@ -226,7 +225,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T08:13:39.456351+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042280856}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T00:12:27.760772+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009428", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T08:13:39.456351+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042280856}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T00:12:27.760772+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009428", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T08:29:00.965107+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039076183}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T00:28:30.059124+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5009647", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T08:29:00.965107+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039076183}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T00:28:30.059124+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5009647", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T09:01:27.058096+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042280856}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T00:58:16.750277+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5010000", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T09:01:27.058096+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042280856}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T00:58:16.750277+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5010000", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T09:12:16.751624+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g64-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2032454776, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2040816815}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T01:11:32.582811+00:00", "targetGpu": "Biren_166m", "taskId": "5010128", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T09:59:25.057595+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2037838088, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2041445091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T01:56:27.860891+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5010580", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T09:59:25.057595+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2037838088, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2041445091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T01:56:27.860891+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5010580", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T09:59:25.057651+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871528, "estimatedRequiredGiB": 2.26, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2022478516}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T01:58:27.285909+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5010597", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T09:59:25.057651+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871528, "estimatedRequiredGiB": 2.26, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2022478516}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T01:58:27.285909+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5010597", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T10:15:00.768930+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2044205392, "estimatedRequiredGiB": 2.469, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2209448692, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2209448692}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T02:14:32.985862+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5010817", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T10:15:00.768930+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2044205392, "estimatedRequiredGiB": 2.469, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2209448692, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2209448692}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T02:14:32.985862+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5010817", "taskType": "text-generation", "verifyResult": null}