state: generation 8671 (intent)

This commit is contained in:
2026-09-17 10:12:04 +00:00
parent a3f395d970
commit 757c64915d
8 changed files with 1513 additions and 1625 deletions

View File

@@ -749,26 +749,26 @@
"hygon_k100-ai|vllm|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 5,
"expiresAt": "2026-10-17T00:41:21+00:00",
"evidenceCount": 6,
"expiresAt": "2026-10-17T10:05:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-17T00:41:21+00:00",
"latestFailureAt": "2026-09-17T10:05:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5",
"sourceModelIds": [
"ewinregirgojr/Qwen3.8-14B-Instruct-Turbo",
"VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU",
"EschaLabs/Qwen3.8-27B-Escha-W2",
"douyamv/Qwen3.8-27B-FP8",
"cyankiwi/Ornith-1.5-9B-AWQ-FP8",
"groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128"
"cyankiwi/Ornith-1.5-9B-AWQ-FP8"
],
"sourceTaskIds": [
"4490374",
"4460362",
"4595432",
"4609095",
"4592744",
"4590765"
"4592744"
],
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation"
@@ -1741,7 +1741,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-17T10:09:01.489270+00:00",
"generatedAt": "2026-09-17T10:10:02.956231+00:00",
"summary": {
"activeBlockCount": 84,
"byGpuFramework": {

View File

@@ -416,121 +416,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-17T10:01:48.255307+00:00",
"generatedAt": "2026-09-17T10:10:12.809155+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 1191.05,
"backlogHours": 1134.1904761904761,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.2669899929867803,
"queueFactor": 0.9762023661905197,
"queueWeight": 0.9762023661905197,
"recentSuccess": 42,
"recentSuccessRate": 0.35,
"recentTerminal": 120,
"recentWilsonLowerBound": 0.27051765896559277,
"qualityFactor": 1.1641300039189184,
"queueFactor": 0.9762880827546113,
"queueWeight": 0.9762880827546113,
"recentSuccess": 44,
"recentSuccessRate": 0.3492063492063492,
"recentTerminal": 126,
"recentWilsonLowerBound": 0.271546946719581,
"running": 8,
"selectionWeight": 1.2368386290934048,
"selectionWeight": 1.136526249603119,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 20.0,
"waiting": 23821
"throughputPerHour": 21.0,
"waiting": 23818
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1458.5172413793105,
"backlogHours": 1421.6470588235295,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.640265654525205,
"queueFactor": 0.9469839532788666,
"queueWeight": 0.9469839532788666,
"recentSuccess": 45,
"recentSuccessRate": 0.3879310344827586,
"recentTerminal": 116,
"recentWilsonLowerBound": 0.3042067212212056,
"qualityFactor": 1.328580824328955,
"queueFactor": 0.943761200484507,
"queueWeight": 0.943761200484507,
"recentSuccess": 44,
"recentSuccessRate": 0.3697478991596639,
"recentTerminal": 119,
"recentWilsonLowerBound": 0.28835646669807535,
"running": 8,
"selectionWeight": 1.5533052539498264,
"selectionWeight": 1.2538630337093903,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 19.333333333333332,
"waiting": 28198
"throughputPerHour": 19.833333333333332,
"waiting": 28196
},
"Biren_166m": {
"available": true,
"backlogHours": 186.6206896551724,
"backlogHours": 181.44134078212292,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 5,
"qualityFactor": 0.24610845533054515,
"queueFactor": 1.289096373102387,
"queueWeight": 1.289096373102387,
"recentSuccess": 31,
"recentSuccessRate": 0.1781609195402299,
"recentTerminal": 174,
"recentWilsonLowerBound": 0.12844578887249997,
"qualityFactor": 0.1930569970064974,
"queueFactor": 1.285199211707479,
"queueWeight": 1.285199211707479,
"recentSuccess": 30,
"recentSuccessRate": 0.16759776536312848,
"recentTerminal": 179,
"recentWilsonLowerBound": 0.11999298633240804,
"running": 5,
"selectionWeight": 0.3172575171564366,
"selectionWeight": 0.2481167003673636,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 29.0,
"waiting": 5412
"throughputPerHour": 29.833333333333332,
"waiting": 5413
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1369.5223880597016,
"backlogHours": 1274.25,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.24741666407983168,
"queueFactor": 0.9559693858808829,
"queueWeight": 0.9559693858808829,
"recentSuccess": 14,
"recentSuccessRate": 0.208955223880597,
"recentTerminal": 67,
"recentWilsonLowerBound": 0.12875568729828918,
"qualityFactor": 0.23228858419188447,
"queueFactor": 0.9593844856262324,
"queueWeight": 0.9593844856262324,
"recentSuccess": 15,
"recentSuccessRate": 0.20833333333333334,
"recentTerminal": 72,
"recentWilsonLowerBound": 0.1305194089904011,
"running": 7,
"selectionWeight": 0.2365227564170934,
"selectionWeight": 0.22285406386177686,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 11.166666666666666,
"waiting": 15293
"throughputPerHour": 12.0,
"waiting": 15291
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 641.9325842696629,
"backlogHours": 595.125,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.4517329470397938,
"queueFactor": 1.071040619509809,
"queueWeight": 1.071040619509809,
"recentSuccess": 22,
"recentSuccessRate": 0.24719101123595505,
"recentTerminal": 89,
"recentWilsonLowerBound": 0.16928115452187478,
"qualityFactor": 0.3905111334377115,
"queueFactor": 1.075448599396953,
"queueWeight": 1.075448599396953,
"recentSuccess": 23,
"recentSuccessRate": 0.23958333333333334,
"recentTerminal": 96,
"recentWilsonLowerBound": 0.16528105536529172,
"running": 7,
"selectionWeight": 0.48382433545049247,
"selectionWeight": 0.4199746515045034,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 14.833333333333334,
"throughputPerHour": 16.0,
"waiting": 9522
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 27.258064516129032,
"backlogHours": 28.829545454545453,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -540,103 +540,103 @@
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 17,
"recentSuccessRate": 0.03046594982078853,
"recentTerminal": 558,
"recentWilsonLowerBound": 0.01910684080990929,
"recentSuccessRate": 0.032196969696969696,
"recentTerminal": 528,
"recentWilsonLowerBound": 0.020197604087014185,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 93.0,
"waiting": 2535
"throughputPerHour": 88.0,
"waiting": 2537
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 83.28617363344051,
"backlogHours": 84.49019607843137,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.0987075018382518,
"qualityFactor": 0.10006901285103705,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 36,
"recentSuccessRate": 0.1157556270096463,
"recentTerminal": 311,
"recentWilsonLowerBound": 0.08479436126544912,
"running": 4,
"selectionWeight": 0.12831975238972734,
"recentSuccess": 37,
"recentSuccessRate": 0.12091503267973856,
"recentTerminal": 306,
"recentWilsonLowerBound": 0.08900921775956208,
"running": 8,
"selectionWeight": 0.13008971670634817,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 51.833333333333336,
"waiting": 4317
"throughputPerHour": 51.0,
"waiting": 4309
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2740.285714285714,
"backlogHours": 2820.882352941176,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.1174335113685956,
"queueFactor": 0.8615093158602938,
"queueWeight": 0.8615093158602938,
"recentSuccess": 14,
"recentSuccessRate": 0.4,
"recentTerminal": 35,
"recentWilsonLowerBound": 0.25550504933307244,
"qualityFactor": 0.8790561710123432,
"queueFactor": 0.8515754670111132,
"queueWeight": 0.8515754670111132,
"recentSuccess": 13,
"recentSuccessRate": 0.38235294117647056,
"recentTerminal": 34,
"recentWilsonLowerBound": 0.23899964851608782,
"running": 2,
"selectionWeight": 0.9626793798985246,
"selectionWeight": 0.7485826693588372,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 5.833333333333333,
"throughputPerHour": 5.666666666666667,
"waiting": 15985
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 516.876923076923,
"backlogHours": 505.17293233082705,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.5176739844487941,
"queueFactor": 1.106423225267531,
"queueWeight": 1.106423225267531,
"qualityFactor": 0.4478165075592666,
"queueFactor": 1.1022113442545867,
"queueWeight": 1.1022113442545867,
"recentSuccess": 32,
"recentSuccessRate": 0.24615384615384617,
"recentTerminal": 130,
"recentWilsonLowerBound": 0.18009686195009067,
"recentSuccessRate": 0.24060150375939848,
"recentTerminal": 133,
"recentWilsonLowerBound": 0.17589495599674002,
"running": 8,
"selectionWeight": 0.5727665195109285,
"selectionWeight": 0.4935884347762935,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 21.666666666666668,
"waiting": 11199
"throughputPerHour": 22.166666666666668,
"waiting": 11198
},
"MetaX_c-500": {
"available": true,
"backlogHours": 837.6867469879518,
"backlogHours": 798.8275862068965,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.5981173413595386,
"queueFactor": 1.0291225827555341,
"queueWeight": 1.0291225827555341,
"recentSuccess": 23,
"recentSuccessRate": 0.27710843373493976,
"recentTerminal": 83,
"recentWilsonLowerBound": 0.1923179435941366,
"qualityFactor": 0.4335804493491625,
"queueFactor": 1.0289942059719743,
"queueWeight": 1.0289942059719743,
"recentSuccess": 22,
"recentSuccessRate": 0.25287356321839083,
"recentTerminal": 87,
"recentWilsonLowerBound": 0.17333087433749275,
"running": 4,
"selectionWeight": 0.6155360631308019,
"selectionWeight": 0.44615177020301333,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 13.833333333333334,
"waiting": 11588
"throughputPerHour": 14.5,
"waiting": 11583
},
"Mthreads_s4000": {
"available": true,
@@ -647,14 +647,14 @@
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 2.5,
"queueFactor": 0.8734310725755137,
"queueWeight": 0.8734310725755137,
"recentSuccess": 29,
"recentSuccessRate": 0.4915254237288136,
"queueFactor": 0.8671219311290588,
"queueWeight": 0.8671219311290588,
"recentSuccess": 30,
"recentSuccessRate": 0.5084745762711864,
"recentTerminal": 59,
"recentWilsonLowerBound": 0.36843625444816314,
"recentWilsonLowerBound": 0.3843492802145344,
"running": 4,
"selectionWeight": 2.183577681438784,
"selectionWeight": 2.167804827822647,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 9.833333333333334,
@@ -662,24 +662,24 @@
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 5482.941176470588,
"backlogHours": 6214.0,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.7052745993793028,
"queueFactor": 0.7763853234493449,
"queueWeight": 0.7763853234493449,
"recentSuccess": 9,
"recentSuccessRate": 0.5294117647058824,
"recentTerminal": 17,
"recentWilsonLowerBound": 0.3096289731154949,
"qualityFactor": 1.46189666858229,
"queueFactor": 0.756441243932855,
"queueWeight": 0.756441243932855,
"recentSuccess": 8,
"recentSuccessRate": 0.5333333333333333,
"recentTerminal": 15,
"recentWilsonLowerBound": 0.3011663015105079,
"running": 2,
"selectionWeight": 1.323950171409052,
"selectionWeight": 1.105838934483684,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 2.8333333333333335,
"throughputPerHour": 2.5,
"waiting": 15535
},
"Vastai_va16": {
@@ -690,15 +690,15 @@
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.09456555946572032,
"queueFactor": 0.9025345536111923,
"queueWeight": 0.9025345536111923,
"qualityFactor": 0.08616538375113811,
"queueFactor": 0.8960151860985902,
"queueWeight": 0.8960151860985902,
"recentSuccess": 7,
"recentSuccessRate": 0.16666666666666666,
"recentTerminal": 42,
"recentWilsonLowerBound": 0.08315811295836503,
"running": 16,
"selectionWeight": 0.08534868499938654,
"selectionWeight": 0.07720549235703246,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 7.0,
@@ -706,30 +706,30 @@
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 787.8285714285714,
"backlogHours": 766.0555555555555,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 0.7112194232058956,
"queueFactor": 1.0386389283224091,
"queueWeight": 1.0386389283224091,
"recentSuccess": 30,
"recentSuccessRate": 0.2857142857142857,
"recentTerminal": 105,
"recentWilsonLowerBound": 0.20806999151103064,
"qualityFactor": 0.6626744400477751,
"queueFactor": 1.0354803158290633,
"queueWeight": 1.0354803158290633,
"recentSuccess": 31,
"recentSuccessRate": 0.28703703703703703,
"recentTerminal": 108,
"recentWilsonLowerBound": 0.21019243295848952,
"running": 6,
"selectionWeight": 0.7387001795206534,
"selectionWeight": 0.6861863384725179,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.5,
"waiting": 13787
"throughputPerHour": 18.0,
"waiting": 13789
}
},
"queueAttemptedAt": "2026-09-17T09:54:49.253474+00:00",
"queueAttemptedAt": "2026-09-17T10:10:12.809155+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-17T09:54:49.253474+00:00",
"queueUpdatedAt": "2026-09-17T10:10:12.809155+00:00",
"supportedGpus": [
"Vastai_va16",
"Kunlunxin_p-800",

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-17T09:11:01.258740+00:00",
"lastSyncTime": "2026-09-17T09:11:00.510552+00:00",
"generatedAt": "2026-09-17T10:10:02.916569+00:00",
"lastSyncTime": "2026-09-17T10:10:02.608119+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -753,26 +753,26 @@
"hygon_k100-ai|vllm|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 5,
"expiresAt": "2026-10-17T00:41:21+00:00",
"evidenceCount": 6,
"expiresAt": "2026-10-17T10:05:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-17T00:41:21+00:00",
"latestFailureAt": "2026-09-17T10:05:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5",
"sourceModelIds": [
"ewinregirgojr/Qwen3.8-14B-Instruct-Turbo",
"VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU",
"EschaLabs/Qwen3.8-27B-Escha-W2",
"douyamv/Qwen3.8-27B-FP8",
"cyankiwi/Ornith-1.5-9B-AWQ-FP8",
"groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128"
"cyankiwi/Ornith-1.5-9B-AWQ-FP8"
],
"sourceTaskIds": [
"4490374",
"4460362",
"4595432",
"4609095",
"4592744",
"4590765"
"4592744"
],
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation"
@@ -1811,24 +1811,24 @@
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 7,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 7
},
"failureCount": 12,
"failureRate": 1.0,
"failureRate": 0.9231,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"successCount": 1,
"successRate": 0.0769,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 12,
"total": 13,
"unresolvedFailureCount": 5
},
"Ascend_910-b3|vllm|text-generation": {
@@ -1899,15 +1899,15 @@
"unresolvedFailureCount": 188
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 2,
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 2,
"framework_architecture_unsupported": 2
"ambiguous_runtime": 3,
"framework_architecture_unsupported": 3
},
"failureCount": 4,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
@@ -1917,8 +1917,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 2
"total": 6,
"unresolvedFailureCount": 3
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 58,
@@ -2745,19 +2745,19 @@
"unresolvedFailureCount": 11
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 55,
"attributableFailureCount": 56,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 55,
"decisionTotal": 56,
"failureBreakdown": {
"ambiguous_runtime": 24,
"framework_architecture_unsupported": 43,
"framework_architecture_unsupported": 44,
"memory_capacity": 1,
"model_load": 5,
"repository_structure": 4,
"runtime_memory": 2
},
"failureCount": 79,
"failureCount": 80,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2767,7 +2767,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 79,
"total": 80,
"unresolvedFailureCount": 24
}
},
@@ -2837,14 +2837,14 @@
"unresolvedFailureCount": 906
},
"vllm": {
"attributableFailureCount": 393,
"decisionFailureRate": 0.9585,
"decisionSuccessRate": 0.0415,
"decisionTotal": 410,
"attributableFailureCount": 394,
"decisionFailureRate": 0.9586,
"decisionSuccessRate": 0.0414,
"decisionTotal": 411,
"failureBreakdown": {
"ambiguous_runtime": 230,
"backend_operator": 38,
"framework_architecture_unsupported": 294,
"framework_architecture_unsupported": 295,
"memory_capacity": 7,
"model_load": 31,
"platform_infrastructure": 2,
@@ -2853,14 +2853,14 @@
"tokenizer_compatibility": 9,
"参数/模板问题": 40
},
"failureCount": 665,
"failureCount": 666,
"failureRate": 0.9751,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 17,
"successRate": 0.0249,
"total": 682,
"total": 683,
"unresolvedFailureCount": 270
},
"vllm-mlu": {
@@ -2953,32 +2953,32 @@
"unresolvedFailureCount": 72
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 9,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 9,
"attributableFailureCount": 10,
"decisionFailureRate": 0.9091,
"decisionSuccessRate": 0.0909,
"decisionTotal": 11,
"failureBreakdown": {
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 9
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 10
},
"failureCount": 16,
"failureRate": 1.0,
"failureCount": 18,
"failureRate": 0.9474,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 16,
"unresolvedFailureCount": 7
"successCount": 1,
"successRate": 0.0526,
"total": 19,
"unresolvedFailureCount": 8
}
},
"generatedAt": "2026-09-17T09:11:01.252695+00:00",
"generatedAt": "2026-09-17T10:10:02.910840+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 54,
"decisionFailureRate": 0.9643,
"decisionSuccessRate": 0.0357,
"decisionTotal": 56,
"decisionFailureRate": 0.9474,
"decisionSuccessRate": 0.0526,
"decisionTotal": 57,
"failureBreakdown": {
"ambiguous_runtime": 37,
"framework_architecture_unsupported": 52,
@@ -2988,23 +2988,23 @@
"验证失败": 27
},
"failureCount": 128,
"failureRate": 0.9846,
"failureRate": 0.9771,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0154,
"total": 130,
"successCount": 3,
"successRate": 0.0229,
"total": 131,
"unresolvedFailureCount": 74
},
"Ascend_910-b4": {
"attributableFailureCount": 61,
"decisionFailureRate": 0.9683,
"decisionSuccessRate": 0.0317,
"decisionTotal": 63,
"attributableFailureCount": 62,
"decisionFailureRate": 0.9688,
"decisionSuccessRate": 0.0312,
"decisionTotal": 64,
"failureBreakdown": {
"ambiguous_runtime": 45,
"framework_architecture_unsupported": 56,
"ambiguous_runtime": 46,
"framework_architecture_unsupported": 57,
"memory_capacity": 1,
"model_load": 1,
"repository_structure": 1,
@@ -3012,15 +3012,15 @@
"参数/模板问题": 13,
"验证失败": 175
},
"failureCount": 294,
"failureRate": 0.9932,
"failureCount": 296,
"failureRate": 0.9933,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0068,
"total": 296,
"unresolvedFailureCount": 233
"successRate": 0.0067,
"total": 298,
"unresolvedFailureCount": 234
},
"Biren_166m": {
"attributableFailureCount": 61,
@@ -3285,13 +3285,13 @@
"unresolvedFailureCount": 216
},
"hygon_k100-ai": {
"attributableFailureCount": 62,
"attributableFailureCount": 63,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 62,
"decisionTotal": 63,
"failureBreakdown": {
"ambiguous_runtime": 29,
"framework_architecture_unsupported": 49,
"framework_architecture_unsupported": 50,
"memory_capacity": 1,
"model_load": 5,
"repository_structure": 4,
@@ -3299,14 +3299,14 @@
"参数/模板问题": 10,
"验证失败": 27
},
"failureCount": 128,
"failureCount": 129,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 128,
"total": 129,
"unresolvedFailureCount": 66
}
},
@@ -3373,6 +3373,27 @@
"total": 4,
"unresolvedFailureCount": 4
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm_tokenizer_patch",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -3488,6 +3509,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|awq": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -3557,6 +3601,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|spark2_5|fp8": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|lfm2|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -7330,22 +7397,22 @@
"unresolvedFailureCount": 2
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 13,
"consecutiveFailures": 13,
"attributableFailureCount": 14,
"consecutiveFailures": 14,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 13,
"decisionTotal": 14,
"failureBreakdown": {
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 12,
"ambiguous_runtime": 6,
"framework_architecture_unsupported": 13,
"model_load": 1
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-17T01:19:27.449287+00:00",
"lastTerminalAt": "2026-09-17T10:10:02.608119+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -7354,7 +7421,7 @@
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 7
"unresolvedFailureCount": 6
}
},
"recentProfileCombinationStats": {
@@ -7582,6 +7649,28 @@
"total": 4,
"unresolvedFailureCount": 4
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral3|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -7702,6 +7791,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|awq|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -7774,6 +7887,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|lfm2|none|29": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -12388,17 +12525,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2112,
"totalRecords": 2215,
"terminalRecords": 2116,
"totalRecords": 2219,
"totals": {
"attributableFailureCount": 688,
"decisionFailureRate": 0.8843,
"decisionSuccessRate": 0.1157,
"decisionTotal": 778,
"attributableFailureCount": 690,
"decisionFailureRate": 0.8835,
"decisionSuccessRate": 0.1165,
"decisionTotal": 781,
"failureBreakdown": {
"ambiguous_runtime": 518,
"ambiguous_runtime": 519,
"backend_operator": 48,
"framework_architecture_unsupported": 457,
"framework_architecture_unsupported": 459,
"memory_capacity": 12,
"model_load": 85,
"platform_infrastructure": 10,
@@ -12408,30 +12545,31 @@
"参数/模板问题": 133,
"验证失败": 673
},
"failureCount": 2022,
"failureRate": 0.9574,
"failureCount": 2025,
"failureRate": 0.957,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 90,
"successRate": 0.0426,
"total": 2112,
"unresolvedFailureCount": 1324
"successCount": 91,
"successRate": 0.043,
"total": 2116,
"unresolvedFailureCount": 1325
},
"warnings": [
"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 Sunrise_pt-200-x1 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 Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU 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 Cambricon_mlu-370-x4 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高(≥50%),建议重点关注。",
"组合 Biren_166m|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b4|vllm_tokenizer_patch|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Biren_166m|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -12455,6 +12593,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2215,
"summarizedRecords": 2219,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-17T10:10:02.608119+00:00", "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T10:05:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4490374", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-17T04:34:21.545391+00:00", "modelId": "BAAI/Law_Justice-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T04:33:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471925", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-17T03:40:30.307157+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T03:37:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505133", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-17T03:22:03.500197+00:00", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T03:21:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4610340", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-11T07:43:04.407471+00:00", "modelId": "deepreinforce-ai/Ornith-1.0-35B-FP8", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-11T07:38:33+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079996", "taskType": "text-generation", "verifyResult": null}
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-11T07:33:47.206168+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T07:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523220", "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": "", "lastSyncTime": "2026-09-11T07:24:30.143494+00:00", "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T07:21:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4505135", "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": "", "lastSyncTime": "2026-09-11T07:05:27.006934+00:00", "modelId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T06:57:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523318", "taskType": "text-generation", "verifyResult": -1}

View File

@@ -850,6 +850,12 @@
{"batchId": "294c9562ba464b4a8e853e449ba1b081", "completedAt": "2026-09-17T09:19:08.761958+00:00", "configFingerprint": "bb269a9a8b4c1eeb18e3ef78bedcf638c3d1821a581b2f17113cde2fcd8be6c5", "configSource": "modelhub_live", "createdAt": "2026-09-17T09:19:01.631910+00:00", "framework": "llamacpp", "intentId": "4e3f0a34fcff42c2b79a2de7591874d7", "lastModified": "2026-09-15T17:45:24+00:00", "modelAddress": "https://modelscope.cn/models/RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "reason": null, "reconciledAt": "2026-09-17T09:58:08.161393+00:00", "repoId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4912678", "taskType": "text-generation"}
{"batchId": "e019a62d04644b2cbc061bb612a84b5b", "completedAt": "2026-09-17T09:36:08.206706+00:00", "configFingerprint": "7df61fc66119e362f4b324c308b44e18bd70c6e8415d3cf79ad822bc9e6377c3", "configSource": "modelhub_live", "createdAt": "2026-09-17T09:36:00.045061+00:00", "framework": "llamacpp", "intentId": "e18b1151a3e24d3c8abf64b5551abba2", "lastModified": "2026-09-15T17:45:24+00:00", "modelAddress": "https://modelscope.cn/models/RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "reason": null, "reconciledAt": "2026-09-17T09:58:08.161640+00:00", "repoId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "4912861", "taskType": "text-generation"}
{"batchId": "669cb773aa7741059aa95afb8f6a91e8", "completedAt": "2026-09-17T09:58:06.915357+00:00", "configFingerprint": "cde1dd013433575dd6e624ec4e742d4992d0b53d429ab95bc4dbe8884fc49e49", "configSource": "modelhub_live", "createdAt": "2026-09-17T09:57:54.614787+00:00", "framework": "llamacpp", "intentId": "cde1fbf266704e789cacd30a0d94aeea", "lastModified": "2026-09-15T17:45:24+00:00", "modelAddress": "https://modelscope.cn/models/RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "reason": null, "reconciledAt": "2026-09-17T09:58:08.161391+00:00", "repoId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "4913157", "taskType": "text-generation"}
{"batchId": "53f3db5388d74fe6bf4bf0dc53b4f28e", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-17T10:12:04.815150+00:00", "framework": "vllm_fix_tokenizer", "intentId": "da62f89a359a4371823c2fe2797e98e7", "lastModified": "2026-09-17T08:55:16+00:00", "modelAddress": "https://modelscope.cn/models/Edge0/Edge0-8B-A1B-preview", "repoId": "Edge0/Edge0-8B-A1B-preview", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "53f3db5388d74fe6bf4bf0dc53b4f28e", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-17T10:12:04.815264+00:00", "framework": "vllm_fix_tokenizer", "intentId": "89152678b5ec42a6952ae7deb677f781", "lastModified": "2026-09-17T02:59:52+00:00", "modelAddress": "https://modelscope.cn/models/XingChen-AGI/Xing4.0-29B-A4B", "repoId": "XingChen-AGI/Xing4.0-29B-A4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "53f3db5388d74fe6bf4bf0dc53b4f28e", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-17T10:12:04.815311+00:00", "framework": "vllm_fix_tokenizer", "intentId": "10ab1645079244889d582f596984ee9a", "lastModified": "2026-09-14T09:13:00+00:00", "modelAddress": "https://modelscope.cn/models/hcnote/SparkMuse-4B-INT8", "repoId": "hcnote/SparkMuse-4B-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "53f3db5388d74fe6bf4bf0dc53b4f28e", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-17T10:12:04.815356+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4c555b840cd943eaa30c673bd8781a1c", "lastModified": "2026-08-31T03:14:07+00:00", "modelAddress": "https://modelscope.cn/models/rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "repoId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "53f3db5388d74fe6bf4bf0dc53b4f28e", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-17T10:12:04.815401+00:00", "framework": "vllm_fix_tokenizer", "intentId": "01dee5f6227342dd9b7805abd5f0bc55", "lastModified": "2026-09-16T13:23:00+00:00", "modelAddress": "https://modelscope.cn/models/ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "repoId": "ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "53f3db5388d74fe6bf4bf0dc53b4f28e", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-17T10:12:04.815444+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2235e852e97c42219d7968bcfa91a0a5", "lastModified": "2026-08-20T03:16:06+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-6bit", "repoId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "dc557ed173284456b65de02d89689bdd", "completedAt": "2026-09-17T07:00:50.030789+00:00", "configFingerprint": "5ec090e92fba0f8471f90bb0af176a745ebf9604ae8d9957761f2bdcf7b7b894", "configSource": "modelhub_live", "createdAt": "2026-09-17T07:00:42.703320+00:00", "framework": "llamacpp", "intentId": "1e106c48321a4cdea39458e2629ff129", "repoId": "voconly/cohere-transcribe-03-2026-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "534b216536f14acab0831df3cca7c8b7", "completedAt": "2026-09-17T06:49:28.237705+00:00", "configFingerprint": "4ecf9a1a055b517fbf32a3498eaaf4a2d63b1c33abbcc170dd75fdec6cec9dc6", "configSource": "modelhub_live", "createdAt": "2026-09-17T06:49:18.457343+00:00", "framework": "llamacpp", "intentId": "b99b4231abe54ea698f0d5b126b52b6e", "repoId": "voconly/cohere-transcribe-03-2026-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "uniqueness_rejected", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
{"batchId": "88766ff730f64477804cc1605a44aaef", "completedAt": "2026-09-17T06:47:36.731565+00:00", "configFingerprint": "1ab708db1a2ba32a19914fb2b2a3e2674a900769ee64ff9790813f664f2605cb", "configSource": "modelhub_live", "createdAt": "2026-09-17T06:47:30.033650+00:00", "framework": "llamacpp", "intentId": "ab6c54fec18f414bae4f6b66156c2c6a", "repoId": "voconly/cohere-transcribe-03-2026-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}

View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "75ceb163aa9b04463a30f469eb572d1d22f7a0ec84fe5e218f29d37b64357e06",
".modelhub_state/architecture_compatibility_blacklist.json": "d0242f7c7daa562a721a800a23f163ed7a3bb6e361bd9e5e56eef707fec43135",
".modelhub_state/architecture_history_backfill.json": "ec69222819dfb5ddcd6cc695cf9ab0557e883fd0c72315af36f67dd4c316b0a6",
".modelhub_state/market_intelligence.json": "575e76ced9b9dee25e6458e9cbe1b1d26ef8c80d43b9d902322aa9fc72697460",
".modelhub_state/official_capabilities.json": "b0a8fad1e076f985c0f2a469bb7ccf66474bbd260203f7ab4a922f3037acbdbd",
".modelhub_state/outcome_checkpoint.json": "82cf79a3369c74b9aabbd88a3633fb7b228752b47deb3985090ce3cd8fc99b68",
".modelhub_state/market_intelligence.json": "a749b6350244f7209e6934a9ca938a895010a757e875ce23cb1a94b79f4af542",
".modelhub_state/official_capabilities.json": "b8f26127544e54da7f151359cde59f401daadc40b35d14a7a9656d249a31b515",
".modelhub_state/outcome_checkpoint.json": "f9e437879143fb79c16bb0e1f613b17fa7e42f1bd14ff5e425b95f2212830ce1",
".modelhub_state/queue_cleanup_latest.json": "4be02869ade05ead6def3f33db6297b95930841c24c0c7cab3372f7790acadd8",
".modelhub_state/recent_outcomes.jsonl": "5ab5fc797be370f400e8d98ac12d5ddd7a35d71c41220204421ac14d9f907be0",
".modelhub_state/recent_outcomes.jsonl": "178cc994b45fb46d1998a6236acd729b76eefa9cb0c6f5da9a9b2e12791ade7a",
".modelhub_state/recovery_active_tasks.jsonl": "94155459fd54babd8d0b6a5b4307e18c09dd87d8a8b790223ac2ce6a097efc7d",
".modelhub_state/recovery_intents.jsonl": "ea0b719c343b41d0bd9748cfea3f7647dfd55ec16b691932d4b9461927309ea9",
".modelhub_state/recovery_intents.jsonl": "b518fabc36f1ae11eba4d4a0c2bbaeb7da15b83809872c46364435b603bb39dc",
".modelhub_state/routing_intelligence.json": "c02c62111d8f54812143c8ebc34a0f697a4c45c5a65af8addaccf1d4076b365f",
".modelhub_state/submission_exclusions.jsonl": "a0cb4e822e4b6d26c26c3bf22698cacbab31f2df5f3402ecf04fdfb3a3577ef7",
".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
"ledger/submissions.jsonl": "d5ca916e1b572afafd5553f56ae5b42f23776615c2dccee48ca5836a0558bd7c",
"outcomes/submissions.jsonl": "86ed78a8336b6a3dbe5c824baace2345ae19e1014071825c67cddd629c64939a"
"outcomes/submissions.jsonl": "e386549ae3ced3d02079567f020c30cc489f307ce793b1d1d0540528d0030dd6"
},
"generation": 8670,
"phase": "cycle",
"generation": 8671,
"phase": "intent",
"schemaVersion": 1,
"updatedAt": "2026-09-17T10:09:01.573230+00:00",
"updatedAt": "2026-09-17T10:12:04.921183+00:00",
"writerId": "eccb3e0018f640d19e578c271a207b5c"
}

View File

@@ -9,7 +9,6 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T20:39:27.718139+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:8"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T12:34:49.403585+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4626360", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T22:53:17.234593+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T14:46:47.882785+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4628625", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T23:04:36.601749+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "published_card_spec", "sourceUrl": "https://aclanthology.org/2025.emnlp-main.1630.pdf"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T15:01:53.788146+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4628814", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T23:24:55.604371+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:8"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T15:17:04.545687+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4629090", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T23:24:55.604425+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T15:17:04.566515+00:00", "targetGpu": "Biren_166m", "taskId": "4629091", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-04T23:34:40.935439+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:15"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T15:32:11.649244+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4629295", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T00:12:22.613750+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:29"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 44221632439, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T16:10:19.951781+00:00", "targetGpu": "MetaX_c-500", "taskId": "4629851", "taskType": "text-generation", "verifyResult": null}
@@ -94,7 +93,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-07T20:52:41.332086+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T12:42:26.513703+00:00", "targetGpu": "Vastai_va16", "taskId": "4695130", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T20:52:41.332095+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "5f7f0613db77a9df3302ec352997953a9eba59a0aa6b38bb4fbb9466fb50fd7b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820112704, "estimatedRequiredGiB": 7.095, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 6348507357, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6348507357}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T12:50:14.422978+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4695252", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T21:18:24.608680+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "ea2321217291fd0be7b6ccbad7b7c81bf62a9ac5c888c7ee1e080e1ea85862ae", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820112704, "estimatedRequiredGiB": 7.095, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 6348507357, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6348507357}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T13:14:08.050211+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4695580", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-07T22:23:41.399386+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T14:21:55.293071+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4697078", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-07T22:50:29.406678+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T14:48:02.492557+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4697753", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-07T23:16:42.601405+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T15:08:53.697776+00:00", "targetGpu": "Vastai_va16", "taskId": "4698268", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T23:43:05.101242+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T15:35:43.483187+00:00", "targetGpu": "MetaX_c-500", "taskId": "4698954", "taskType": "text-generation", "verifyResult": null}
@@ -118,7 +116,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T17:52:18.933043+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426469123, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426469123}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T09:50:25.159456+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4716485", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T18:22:22.226463+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426469123, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426469123}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T10:18:12.673769+00:00", "targetGpu": "Biren_166m", "taskId": "4716910", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T18:32:01.542042+00:00", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "c03adae4b35c577b219efa214a72e6ba0eee2287660172b6efc70ec1f7b26139", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679710688, "estimatedRequiredGiB": 10.372, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 9280496017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9280496017}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T10:26:22.306973+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4717031", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-08T18:32:01.542105+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5044047987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5044047987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T10:26:22.313092+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4717029", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-08T18:32:01.542064+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426469123, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426469123}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T10:26:22.308491+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4717030", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-08T19:02:28.697202+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426469123, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426469123}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T10:53:08.602969+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4717458", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T20:16:09.104286+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426469123, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426469123}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T12:11:32.114244+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4718632", "taskType": "text-generation", "verifyResult": null}
@@ -591,9 +588,9 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-17T01:45:21.245303+00:00", "modelId": "ManniX-ITA/Ornith-1.5-27B-A3B-CoderX", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 52429250296, "estimatedRequiredGiB": 58.623, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe_text", "modelscopeFileSize": 52454809833, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26213016704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:expert-pruning", "custom_tag:code", "custom_tag:mtp", "custom_tag:ornith", "custom_tag:reap", "custom_tag:ream", "custom_tag:omnimergekit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 52454809833}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T17:39:01.676725+00:00", "targetGpu": "MetaX_c-500", "taskId": "4899817", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-17T01:54:16.705192+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293475486, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320427112, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320427112}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T17:52:33.017540+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4900094", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-17T02:10:59.211438+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293475486, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320427112, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320427112}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T18:09:58.859804+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4900532", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "BAAI/RoboBrain2.5-8B-NV", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918210, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918210}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-17T02:02:00.958898+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4906949", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293475486, "estimatedRequiredGiB": 18.239, "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": 16320427112, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320427112}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-17T02:02:00.949464+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4906948", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7276346365, "estimatedRequiredGiB": 8.156, "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": 7298158256, "modelscopeLicense": null, "modelscopeParams": 1959473664, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7298158256}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-17T02:02:00.946894+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4906950", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-17T10:10:02.608080+00:00", "modelId": "BAAI/RoboBrain2.5-8B-NV", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918210, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8767123696, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_vl", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17545918210}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T02:02:00.958898+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4906949", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-17T10:10:02.608087+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293475486, "estimatedRequiredGiB": 18.239, "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": 16320427112, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320427112}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T02:02:00.949464+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4906948", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-17T10:10:02.608073+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7276346365, "estimatedRequiredGiB": 8.156, "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": 7298158256, "modelscopeLicense": null, "modelscopeParams": 1959473664, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7298158256}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T02:02:00.946894+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4906950", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "bb269a9a8b4c1eeb18e3ef78bedcf638c3d1821a581b2f17113cde2fcd8be6c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629247648, "estimatedRequiredGiB": 25.142, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22496243465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:gguf", "task:text-generation", "custom_tag:qwen3", "custom_tag:qwen3.8", "custom_tag:orcarouter", "custom_tag:gsq", "custom_tag:rco", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-use", "custom_tag:16gb-vram", "custom_tag:image-text-to-text", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:mmproj", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22496243465}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-17T09:19:02.317218+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4912678", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7df61fc66119e362f4b324c308b44e18bd70c6e8415d3cf79ad822bc9e6377c3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629247648, "estimatedRequiredGiB": 25.142, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22496243465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:gguf", "task:text-generation", "custom_tag:qwen3", "custom_tag:qwen3.8", "custom_tag:orcarouter", "custom_tag:gsq", "custom_tag:rco", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-use", "custom_tag:16gb-vram", "custom_tag:image-text-to-text", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:mmproj", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22496243465}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-17T09:36:01.072109+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4912861", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cde1dd013433575dd6e624ec4e742d4992d0b53d429ab95bc4dbe8884fc49e49", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629247648, "estimatedRequiredGiB": 25.142, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22496243465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:gguf", "task:text-generation", "custom_tag:qwen3", "custom_tag:qwen3.8", "custom_tag:orcarouter", "custom_tag:gsq", "custom_tag:rco", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-use", "custom_tag:16gb-vram", "custom_tag:image-text-to-text", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:mmproj", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22496243465}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-17T09:57:55.404929+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4913157", "taskType": "text-generation", "verifyResult": null}