state: compacted generation 11601
This commit is contained in:
0
.manifest.json.lock
Normal file
0
.manifest.json.lock
Normal file
0
.modelhub_state/.market_intelligence.json.lock
Normal file
0
.modelhub_state/.market_intelligence.json.lock
Normal file
0
.modelhub_state/.official_capabilities.json.lock
Normal file
0
.modelhub_state/.official_capabilities.json.lock
Normal file
0
.modelhub_state/.recent_outcomes.jsonl.lock
Normal file
0
.modelhub_state/.recent_outcomes.jsonl.lock
Normal file
0
.modelhub_state/.worker_crashes.jsonl.lock
Normal file
0
.modelhub_state/.worker_crashes.jsonl.lock
Normal file
78
.modelhub_state/account_capacity.json
Normal file
78
.modelhub_state/account_capacity.json
Normal file
@@ -0,0 +1,78 @@
|
|||||||
|
{
|
||||||
|
"accounts": {
|
||||||
|
"116321aaaa71977e436a": {
|
||||||
|
"accountIndex": 5,
|
||||||
|
"calibrationResult": "saturated",
|
||||||
|
"calibrationWeek": "2026-W39",
|
||||||
|
"knownCap": 100
|
||||||
|
},
|
||||||
|
"203cf600e31a19e36522": {
|
||||||
|
"accountIndex": 4,
|
||||||
|
"calibrationResult": "saturated",
|
||||||
|
"calibrationWeek": "2026-W39",
|
||||||
|
"knownCap": 100
|
||||||
|
},
|
||||||
|
"23b36a0498728a5497ec": {
|
||||||
|
"accountIndex": 10,
|
||||||
|
"calibrationResult": "saturated",
|
||||||
|
"calibrationWeek": "2026-W39",
|
||||||
|
"knownCap": 100
|
||||||
|
},
|
||||||
|
"5d7e48ccd4ba2b34e49f": {
|
||||||
|
"accountIndex": 7,
|
||||||
|
"calibrationResult": "saturated",
|
||||||
|
"calibrationWeek": "2026-W39",
|
||||||
|
"knownCap": 100
|
||||||
|
},
|
||||||
|
"72046eb8a2d9d386504e": {
|
||||||
|
"accountIndex": 11,
|
||||||
|
"calibrationResult": "saturated",
|
||||||
|
"calibrationWeek": "2026-W39",
|
||||||
|
"knownCap": 100
|
||||||
|
},
|
||||||
|
"730c876d2910041553c8": {
|
||||||
|
"accountIndex": 9,
|
||||||
|
"calibrationResult": "saturated",
|
||||||
|
"calibrationWeek": "2026-W39",
|
||||||
|
"knownCap": 100
|
||||||
|
},
|
||||||
|
"b940824e4299693749aa": {
|
||||||
|
"accountIndex": 6,
|
||||||
|
"calibrationResult": "saturated",
|
||||||
|
"calibrationWeek": "2026-W39",
|
||||||
|
"knownCap": 100
|
||||||
|
},
|
||||||
|
"bc10735ccf9c93d0bc23": {
|
||||||
|
"accountIndex": 12,
|
||||||
|
"calibrationResult": "saturated",
|
||||||
|
"calibrationWeek": "2026-W39",
|
||||||
|
"knownCap": 100
|
||||||
|
},
|
||||||
|
"c5217a5fe9b938618a85": {
|
||||||
|
"accountIndex": 3,
|
||||||
|
"calibrationResult": "saturated",
|
||||||
|
"calibrationWeek": "2026-W39",
|
||||||
|
"knownCap": 100
|
||||||
|
},
|
||||||
|
"cef6a28aba11a67c2a45": {
|
||||||
|
"accountIndex": 2,
|
||||||
|
"calibrationResult": "saturated",
|
||||||
|
"calibrationWeek": "2026-W39",
|
||||||
|
"knownCap": 100
|
||||||
|
},
|
||||||
|
"efca47eed826bada0502": {
|
||||||
|
"accountIndex": 1,
|
||||||
|
"calibrationResult": "saturated",
|
||||||
|
"calibrationWeek": "2026-W39",
|
||||||
|
"knownCap": 100
|
||||||
|
},
|
||||||
|
"f0b5423ecb0841256040": {
|
||||||
|
"accountIndex": 8,
|
||||||
|
"calibrationResult": "saturated",
|
||||||
|
"calibrationWeek": "2026-W39",
|
||||||
|
"knownCap": 100
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"updatedAt": "2026-09-21T02:10:09.309449+00:00",
|
||||||
|
"version": 1
|
||||||
|
}
|
||||||
2781
.modelhub_state/architecture_compatibility_blacklist.json
Normal file
2781
.modelhub_state/architecture_compatibility_blacklist.json
Normal file
File diff suppressed because it is too large
Load Diff
113
.modelhub_state/architecture_history_backfill.json
Normal file
113
.modelhub_state/architecture_history_backfill.json
Normal file
@@ -0,0 +1,113 @@
|
|||||||
|
{
|
||||||
|
"accounts": {
|
||||||
|
"0": {
|
||||||
|
"complete": true,
|
||||||
|
"completedAt": "2026-09-20T03:07:33.790769+00:00",
|
||||||
|
"listingErrors": 738,
|
||||||
|
"nextPage": 14,
|
||||||
|
"recordsScanned": 1357,
|
||||||
|
"uniqueRecords": 1357
|
||||||
|
},
|
||||||
|
"1": {
|
||||||
|
"complete": true,
|
||||||
|
"completedAt": "2026-09-20T03:07:38.878048+00:00",
|
||||||
|
"listingErrors": 738,
|
||||||
|
"nextPage": 15,
|
||||||
|
"recordsScanned": 1427,
|
||||||
|
"uniqueRecords": 1427
|
||||||
|
},
|
||||||
|
"10": {
|
||||||
|
"complete": true,
|
||||||
|
"completedAt": "2026-09-20T03:03:03.225350+00:00",
|
||||||
|
"listingErrors": 737,
|
||||||
|
"nextPage": 7,
|
||||||
|
"recordsScanned": 689,
|
||||||
|
"uniqueRecords": 689
|
||||||
|
},
|
||||||
|
"11": {
|
||||||
|
"complete": true,
|
||||||
|
"completedAt": "2026-09-20T03:03:03.225350+00:00",
|
||||||
|
"listingErrors": 737,
|
||||||
|
"nextPage": 7,
|
||||||
|
"recordsScanned": 627,
|
||||||
|
"uniqueRecords": 627
|
||||||
|
},
|
||||||
|
"2": {
|
||||||
|
"complete": true,
|
||||||
|
"completedAt": "2026-09-20T03:07:33.790769+00:00",
|
||||||
|
"listingErrors": 738,
|
||||||
|
"nextPage": 13,
|
||||||
|
"recordsScanned": 1287,
|
||||||
|
"uniqueRecords": 1287
|
||||||
|
},
|
||||||
|
"3": {
|
||||||
|
"complete": true,
|
||||||
|
"completedAt": "2026-09-20T03:07:33.790769+00:00",
|
||||||
|
"listingErrors": 738,
|
||||||
|
"nextPage": 14,
|
||||||
|
"recordsScanned": 1340,
|
||||||
|
"uniqueRecords": 1340
|
||||||
|
},
|
||||||
|
"4": {
|
||||||
|
"complete": true,
|
||||||
|
"completedAt": "2026-09-20T03:07:33.790769+00:00",
|
||||||
|
"listingErrors": 738,
|
||||||
|
"nextPage": 14,
|
||||||
|
"recordsScanned": 1374,
|
||||||
|
"uniqueRecords": 1374
|
||||||
|
},
|
||||||
|
"5": {
|
||||||
|
"complete": true,
|
||||||
|
"completedAt": "2026-09-20T03:07:33.790769+00:00",
|
||||||
|
"listingErrors": 738,
|
||||||
|
"nextPage": 13,
|
||||||
|
"recordsScanned": 1228,
|
||||||
|
"uniqueRecords": 1228
|
||||||
|
},
|
||||||
|
"6": {
|
||||||
|
"complete": true,
|
||||||
|
"completedAt": "2026-09-20T03:07:33.790769+00:00",
|
||||||
|
"listingErrors": 738,
|
||||||
|
"nextPage": 13,
|
||||||
|
"recordsScanned": 1224,
|
||||||
|
"uniqueRecords": 1224
|
||||||
|
},
|
||||||
|
"7": {
|
||||||
|
"complete": true,
|
||||||
|
"completedAt": "2026-09-20T03:07:06.410931+00:00",
|
||||||
|
"listingErrors": 738,
|
||||||
|
"nextPage": 12,
|
||||||
|
"recordsScanned": 1130,
|
||||||
|
"uniqueRecords": 1130
|
||||||
|
},
|
||||||
|
"8": {
|
||||||
|
"complete": true,
|
||||||
|
"completedAt": "2026-09-20T03:07:06.410931+00:00",
|
||||||
|
"listingErrors": 738,
|
||||||
|
"nextPage": 12,
|
||||||
|
"recordsScanned": 1163,
|
||||||
|
"uniqueRecords": 1163
|
||||||
|
},
|
||||||
|
"9": {
|
||||||
|
"complete": true,
|
||||||
|
"completedAt": "2026-09-20T03:03:03.225350+00:00",
|
||||||
|
"listingErrors": 737,
|
||||||
|
"nextPage": 7,
|
||||||
|
"recordsScanned": 691,
|
||||||
|
"uniqueRecords": 691
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"architectureBlocks": 85,
|
||||||
|
"complete": true,
|
||||||
|
"completedAt": "2026-09-20T03:07:38.878048+00:00",
|
||||||
|
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
|
||||||
|
"failureLogsInspected": 8946,
|
||||||
|
"mode": "incremental_decision_only",
|
||||||
|
"nextAccountIndex": 2,
|
||||||
|
"recordsScanned": 13537,
|
||||||
|
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||||
|
"terminalRecords": 13375,
|
||||||
|
"uniqueRecords": 13537,
|
||||||
|
"updatedAt": "2026-09-20T03:07:38.878048+00:00",
|
||||||
|
"version": 1
|
||||||
|
}
|
||||||
772
.modelhub_state/market_intelligence.json
Normal file
772
.modelhub_state/market_intelligence.json
Normal file
@@ -0,0 +1,772 @@
|
|||||||
|
{
|
||||||
|
"communityAttemptedAt": "2026-09-21T18:17:55.042367+00:00",
|
||||||
|
"communityError": null,
|
||||||
|
"communitySample": {},
|
||||||
|
"communityUpdatedAt": "2026-09-21T18:17:55.042367+00:00",
|
||||||
|
"frameworkAttemptedAt": "2026-09-21T15:33:56.261808+00:00",
|
||||||
|
"frameworkError": null,
|
||||||
|
"frameworkStats": {
|
||||||
|
"text-generation": {
|
||||||
|
"Ascend_910-b3": {
|
||||||
|
"llamacpp": {
|
||||||
|
"framework": "llamacpp",
|
||||||
|
"modelCount": 39973,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 19362,
|
||||||
|
"successRate": 0.4843769544442499,
|
||||||
|
"wilsonLowerBound": 0.4794794297091189
|
||||||
|
},
|
||||||
|
"vllm": {
|
||||||
|
"framework": "vllm",
|
||||||
|
"modelCount": 53509,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 14911,
|
||||||
|
"successRate": 0.2786634024182848,
|
||||||
|
"wilsonLowerBound": 0.2748805496668656
|
||||||
|
},
|
||||||
|
"vllm_0.23.0": {
|
||||||
|
"framework": "vllm_0.23.0",
|
||||||
|
"modelCount": 0,
|
||||||
|
"officialConfigError": "framework_mismatch",
|
||||||
|
"officialConfigValid": false,
|
||||||
|
"successCount": 0,
|
||||||
|
"successRate": 0.0,
|
||||||
|
"wilsonLowerBound": 0.0
|
||||||
|
},
|
||||||
|
"vllm_tokenizer_patch": {
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"modelCount": 3030,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 857,
|
||||||
|
"successRate": 0.28283828382838283,
|
||||||
|
"wilsonLowerBound": 0.26708445830688887
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"Ascend_910-b4": {
|
||||||
|
"llamacpp": {
|
||||||
|
"framework": "llamacpp",
|
||||||
|
"modelCount": 33291,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 14791,
|
||||||
|
"successRate": 0.44429425370220177,
|
||||||
|
"wilsonLowerBound": 0.4389633308686534
|
||||||
|
},
|
||||||
|
"vllm": {
|
||||||
|
"framework": "vllm",
|
||||||
|
"modelCount": 37719,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 10702,
|
||||||
|
"successRate": 0.28372968530448844,
|
||||||
|
"wilsonLowerBound": 0.2792023547568335
|
||||||
|
},
|
||||||
|
"vllm_tokenizer_patch": {
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"modelCount": 9305,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 3950,
|
||||||
|
"successRate": 0.4245029554003224,
|
||||||
|
"wilsonLowerBound": 0.4144932208043317
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"Biren_166m": {
|
||||||
|
"vllm": {
|
||||||
|
"framework": "vllm",
|
||||||
|
"modelCount": 64034,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 12088,
|
||||||
|
"successRate": 0.18877471343348845,
|
||||||
|
"wilsonLowerBound": 0.1857623649808237
|
||||||
|
},
|
||||||
|
"vllm_fix_tokenizer": {
|
||||||
|
"framework": "vllm_fix_tokenizer",
|
||||||
|
"modelCount": 18911,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 3819,
|
||||||
|
"successRate": 0.20194595737930304,
|
||||||
|
"wilsonLowerBound": 0.19628495445786476
|
||||||
|
},
|
||||||
|
"vllm_tokenizer_patch": {
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"modelCount": 6242,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 62,
|
||||||
|
"successRate": 0.00993271387375841,
|
||||||
|
"wilsonLowerBound": 0.007756347606611726
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"Cambricon_mlu-370-x4": {
|
||||||
|
"vllm": {
|
||||||
|
"framework": "vllm",
|
||||||
|
"modelCount": 26188,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 3228,
|
||||||
|
"successRate": 0.12326256300595692,
|
||||||
|
"wilsonLowerBound": 0.11933614980668351
|
||||||
|
},
|
||||||
|
"vllm-customized": {
|
||||||
|
"framework": "vllm-customized",
|
||||||
|
"modelCount": 16470,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 1674,
|
||||||
|
"successRate": 0.10163934426229508,
|
||||||
|
"wilsonLowerBound": 0.09711690799427429
|
||||||
|
},
|
||||||
|
"vllm-mlu": {
|
||||||
|
"framework": "vllm-mlu",
|
||||||
|
"modelCount": 11582,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 4853,
|
||||||
|
"successRate": 0.4190122604040753,
|
||||||
|
"wilsonLowerBound": 0.4100546729588871
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"Cambricon_mlu-370-x8": {
|
||||||
|
"vllm": {
|
||||||
|
"framework": "vllm",
|
||||||
|
"modelCount": 24252,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 3788,
|
||||||
|
"successRate": 0.1561933036450602,
|
||||||
|
"wilsonLowerBound": 0.15167864712725093
|
||||||
|
},
|
||||||
|
"vllm-customized": {
|
||||||
|
"framework": "vllm-customized",
|
||||||
|
"modelCount": 8082,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 544,
|
||||||
|
"successRate": 0.06731007176441475,
|
||||||
|
"wilsonLowerBound": 0.06205039941839396
|
||||||
|
},
|
||||||
|
"vllm-mlu": {
|
||||||
|
"framework": "vllm-mlu",
|
||||||
|
"modelCount": 43890,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 10976,
|
||||||
|
"successRate": 0.2500797448165869,
|
||||||
|
"wilsonLowerBound": 0.2460501966140812
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"Iluvatar_bi-100": {
|
||||||
|
"transformers": {
|
||||||
|
"framework": "transformers",
|
||||||
|
"modelCount": 23378,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 3076,
|
||||||
|
"successRate": 0.13157669603901104,
|
||||||
|
"wilsonLowerBound": 0.12730397173909294
|
||||||
|
},
|
||||||
|
"vllm": {
|
||||||
|
"framework": "vllm",
|
||||||
|
"modelCount": 86685,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 9764,
|
||||||
|
"successRate": 0.1126377112533887,
|
||||||
|
"wilsonLowerBound": 0.11055022023005767
|
||||||
|
},
|
||||||
|
"vllm-patch-tokenizer": {
|
||||||
|
"framework": "vllm-patch-tokenizer",
|
||||||
|
"modelCount": 41042,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 5046,
|
||||||
|
"successRate": 0.12294722479411335,
|
||||||
|
"wilsonLowerBound": 0.11980549014925095
|
||||||
|
},
|
||||||
|
"vllm_fix_tokenizer": {
|
||||||
|
"framework": "vllm_fix_tokenizer",
|
||||||
|
"modelCount": 33005,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 3439,
|
||||||
|
"successRate": 0.10419633388880473,
|
||||||
|
"wilsonLowerBound": 0.10094617949716594
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"Iluvatar_bi-150": {
|
||||||
|
"llamacpp": {
|
||||||
|
"framework": "llamacpp",
|
||||||
|
"modelCount": 88909,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 21191,
|
||||||
|
"successRate": 0.23834482448346062,
|
||||||
|
"wilsonLowerBound": 0.23555547585716355
|
||||||
|
},
|
||||||
|
"transformers": {
|
||||||
|
"framework": "transformers",
|
||||||
|
"modelCount": 5244,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 568,
|
||||||
|
"successRate": 0.10831426392067124,
|
||||||
|
"wilsonLowerBound": 0.1001876830189251
|
||||||
|
},
|
||||||
|
"vllm": {
|
||||||
|
"framework": "vllm",
|
||||||
|
"modelCount": 112656,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 16517,
|
||||||
|
"successRate": 0.14661447237608294,
|
||||||
|
"wilsonLowerBound": 0.14456095234592153
|
||||||
|
},
|
||||||
|
"vllm_0_17_0_corex_4_4_0": {
|
||||||
|
"framework": "vllm_0_17_0_corex_4_4_0",
|
||||||
|
"modelCount": 18078,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 3539,
|
||||||
|
"successRate": 0.1957628056200907,
|
||||||
|
"wilsonLowerBound": 0.19004356596108474
|
||||||
|
},
|
||||||
|
"vllm_fix_tokenizer": {
|
||||||
|
"framework": "vllm_fix_tokenizer",
|
||||||
|
"modelCount": 42959,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 5586,
|
||||||
|
"successRate": 0.13003095975232198,
|
||||||
|
"wilsonLowerBound": 0.12688344637946813
|
||||||
|
},
|
||||||
|
"vllm_tokenizer_patch": {
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"modelCount": 6881,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 577,
|
||||||
|
"successRate": 0.08385409097514897,
|
||||||
|
"wilsonLowerBound": 0.07753500660988152
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"Iluvatar_mrv-100": {
|
||||||
|
"transformers": {
|
||||||
|
"framework": "transformers",
|
||||||
|
"modelCount": 200,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 36,
|
||||||
|
"successRate": 0.18,
|
||||||
|
"wilsonLowerBound": 0.1329455066253411
|
||||||
|
},
|
||||||
|
"vllm": {
|
||||||
|
"framework": "vllm",
|
||||||
|
"modelCount": 31418,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 5703,
|
||||||
|
"successRate": 0.18152014768603986,
|
||||||
|
"wilsonLowerBound": 0.17729697332814412
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"Kunlunxin_p-800": {
|
||||||
|
"vllm": {
|
||||||
|
"framework": "vllm",
|
||||||
|
"modelCount": 60943,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 12396,
|
||||||
|
"successRate": 0.20340318002067506,
|
||||||
|
"wilsonLowerBound": 0.2002260275601676
|
||||||
|
},
|
||||||
|
"vllm_fix_tokenizer": {
|
||||||
|
"framework": "vllm_fix_tokenizer",
|
||||||
|
"modelCount": 8503,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 2462,
|
||||||
|
"successRate": 0.2895448665176996,
|
||||||
|
"wilsonLowerBound": 0.2800011878435359
|
||||||
|
},
|
||||||
|
"vllm_tokenizer_patch": {
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"modelCount": 13199,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 3383,
|
||||||
|
"successRate": 0.25630729600727326,
|
||||||
|
"wilsonLowerBound": 0.24893055210903053
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"MetaX_c-500": {
|
||||||
|
"vllm": {
|
||||||
|
"framework": "vllm",
|
||||||
|
"modelCount": 61756,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 16921,
|
||||||
|
"successRate": 0.27399766824276184,
|
||||||
|
"wilsonLowerBound": 0.2704941063178307
|
||||||
|
},
|
||||||
|
"vllm_tokenizer_patch": {
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"modelCount": 0,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 0,
|
||||||
|
"successRate": 0.0,
|
||||||
|
"wilsonLowerBound": 0.0
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"Mthreads_s4000": {
|
||||||
|
"llamacpp": {
|
||||||
|
"framework": "llamacpp",
|
||||||
|
"modelCount": 46768,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 20510,
|
||||||
|
"successRate": 0.43854772494013,
|
||||||
|
"wilsonLowerBound": 0.43405570939604926
|
||||||
|
},
|
||||||
|
"vllm": {
|
||||||
|
"framework": "vllm",
|
||||||
|
"modelCount": 36819,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 3567,
|
||||||
|
"successRate": 0.09687932860751243,
|
||||||
|
"wilsonLowerBound": 0.09389984759374836
|
||||||
|
},
|
||||||
|
"vllm_tokenizer_patch": {
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"modelCount": 632,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 0,
|
||||||
|
"successRate": 0.0,
|
||||||
|
"wilsonLowerBound": 0.0
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"Sunrise_pt-200-x1": {
|
||||||
|
"sglang": {
|
||||||
|
"framework": "sglang",
|
||||||
|
"modelCount": 6280,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 192,
|
||||||
|
"successRate": 0.030573248407643312,
|
||||||
|
"wilsonLowerBound": 0.02659388008261268
|
||||||
|
},
|
||||||
|
"vllm": {
|
||||||
|
"framework": "vllm",
|
||||||
|
"modelCount": 10028,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 740,
|
||||||
|
"successRate": 0.07379337854008776,
|
||||||
|
"wilsonLowerBound": 0.06883801306073076
|
||||||
|
},
|
||||||
|
"vllm_fix_tokenizer": {
|
||||||
|
"framework": "vllm_fix_tokenizer",
|
||||||
|
"modelCount": 6043,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 2573,
|
||||||
|
"successRate": 0.42578189640906833,
|
||||||
|
"wilsonLowerBound": 0.41336592357712526
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"Vastai_va16": {
|
||||||
|
"vllm": {
|
||||||
|
"framework": "vllm",
|
||||||
|
"modelCount": 7378,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 235,
|
||||||
|
"successRate": 0.03185145025752236,
|
||||||
|
"wilsonLowerBound": 0.028081693938916925
|
||||||
|
},
|
||||||
|
"vllm_fix_tokenizer": {
|
||||||
|
"framework": "vllm_fix_tokenizer",
|
||||||
|
"modelCount": 12005,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 3886,
|
||||||
|
"successRate": 0.32369845897542693,
|
||||||
|
"wilsonLowerBound": 0.3153861982632824
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"hygon_k100-ai": {
|
||||||
|
"llamacpp": {
|
||||||
|
"framework": "llamacpp",
|
||||||
|
"modelCount": 26620,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 13512,
|
||||||
|
"successRate": 0.5075882794891059,
|
||||||
|
"wilsonLowerBound": 0.5015818016813248
|
||||||
|
},
|
||||||
|
"vllm": {
|
||||||
|
"framework": "vllm",
|
||||||
|
"modelCount": 62938,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 6368,
|
||||||
|
"successRate": 0.10117893800247862,
|
||||||
|
"wilsonLowerBound": 0.09884719332891848
|
||||||
|
},
|
||||||
|
"vllm-patch-tokenizer": {
|
||||||
|
"framework": "vllm-patch-tokenizer",
|
||||||
|
"modelCount": 12589,
|
||||||
|
"officialConfigError": null,
|
||||||
|
"officialConfigValid": true,
|
||||||
|
"successCount": 1827,
|
||||||
|
"successRate": 0.14512669791087457,
|
||||||
|
"wilsonLowerBound": 0.13908196978028875
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"frameworkUpdatedAt": null,
|
||||||
|
"generatedAt": "2026-09-21T18:20:48.641467+00:00",
|
||||||
|
"gpuStats": {
|
||||||
|
"Ascend_910-b3": {
|
||||||
|
"available": true,
|
||||||
|
"backlogHours": 905.7307692307693,
|
||||||
|
"canVerify": true,
|
||||||
|
"error": null,
|
||||||
|
"gpu": "Ascend_910-b3",
|
||||||
|
"healthFactor": 1.0,
|
||||||
|
"maxConcurrentTasks": 8,
|
||||||
|
"qualityFactor": 1.8568640775729421,
|
||||||
|
"queueFactor": 0.9188442299230395,
|
||||||
|
"queueWeight": 0.9188442299230395,
|
||||||
|
"recentSuccess": 49,
|
||||||
|
"recentSuccessRate": 0.3141025641025641,
|
||||||
|
"recentTerminal": 156,
|
||||||
|
"recentWilsonLowerBound": 0.24647424473527466,
|
||||||
|
"running": 8,
|
||||||
|
"selectionWeight": 1.706168843429265,
|
||||||
|
"stale": false,
|
||||||
|
"submissionEligible": true,
|
||||||
|
"throughputPerHour": 26.0,
|
||||||
|
"waiting": 23549
|
||||||
|
},
|
||||||
|
"Ascend_910-b4": {
|
||||||
|
"available": true,
|
||||||
|
"backlogHours": 1195.9014084507041,
|
||||||
|
"canVerify": true,
|
||||||
|
"error": null,
|
||||||
|
"gpu": "Ascend_910-b4",
|
||||||
|
"healthFactor": 1.0,
|
||||||
|
"maxConcurrentTasks": 8,
|
||||||
|
"qualityFactor": 1.8499717598306284,
|
||||||
|
"queueFactor": 0.8813277688689776,
|
||||||
|
"queueWeight": 0.8813277688689776,
|
||||||
|
"recentSuccess": 45,
|
||||||
|
"recentSuccessRate": 0.31690140845070425,
|
||||||
|
"recentTerminal": 142,
|
||||||
|
"recentWilsonLowerBound": 0.2460579755145257,
|
||||||
|
"running": 9,
|
||||||
|
"selectionWeight": 1.6304314835621438,
|
||||||
|
"stale": false,
|
||||||
|
"submissionEligible": true,
|
||||||
|
"throughputPerHour": 23.666666666666668,
|
||||||
|
"waiting": 28303
|
||||||
|
},
|
||||||
|
"Biren_166m": {
|
||||||
|
"available": true,
|
||||||
|
"backlogHours": 160.76190476190476,
|
||||||
|
"canVerify": true,
|
||||||
|
"error": null,
|
||||||
|
"gpu": "Biren_166m",
|
||||||
|
"healthFactor": 1.0,
|
||||||
|
"maxConcurrentTasks": 8,
|
||||||
|
"qualityFactor": 0.16702617055921037,
|
||||||
|
"queueFactor": 1.1908698201516055,
|
||||||
|
"queueWeight": 1.1908698201516055,
|
||||||
|
"recentSuccess": 23,
|
||||||
|
"recentSuccessRate": 0.12169312169312169,
|
||||||
|
"recentTerminal": 189,
|
||||||
|
"recentWilsonLowerBound": 0.08247436935353425,
|
||||||
|
"running": 10,
|
||||||
|
"selectionWeight": 0.19890642569445824,
|
||||||
|
"stale": false,
|
||||||
|
"submissionEligible": true,
|
||||||
|
"throughputPerHour": 31.5,
|
||||||
|
"waiting": 5064
|
||||||
|
},
|
||||||
|
"Cambricon_mlu-370-x4": {
|
||||||
|
"available": true,
|
||||||
|
"backlogHours": 482.3101604278075,
|
||||||
|
"canVerify": true,
|
||||||
|
"error": null,
|
||||||
|
"gpu": "Cambricon_mlu-370-x4",
|
||||||
|
"healthFactor": 1.0,
|
||||||
|
"maxConcurrentTasks": 7,
|
||||||
|
"qualityFactor": 0.05363065015660931,
|
||||||
|
"queueFactor": 1.00993354847409,
|
||||||
|
"queueWeight": 1.00993354847409,
|
||||||
|
"recentSuccess": 15,
|
||||||
|
"recentSuccessRate": 0.08021390374331551,
|
||||||
|
"recentTerminal": 187,
|
||||||
|
"recentWilsonLowerBound": 0.049210666584585235,
|
||||||
|
"running": 9,
|
||||||
|
"selectionWeight": 0.054163392819636946,
|
||||||
|
"stale": false,
|
||||||
|
"submissionEligible": false,
|
||||||
|
"throughputPerHour": 31.166666666666668,
|
||||||
|
"waiting": 15032
|
||||||
|
},
|
||||||
|
"Cambricon_mlu-370-x8": {
|
||||||
|
"available": true,
|
||||||
|
"backlogHours": 393.34285714285716,
|
||||||
|
"canVerify": true,
|
||||||
|
"error": null,
|
||||||
|
"gpu": "Cambricon_mlu-370-x8",
|
||||||
|
"healthFactor": 1.0,
|
||||||
|
"maxConcurrentTasks": 7,
|
||||||
|
"qualityFactor": 0.19570589585940476,
|
||||||
|
"queueFactor": 1.0413004845471356,
|
||||||
|
"queueWeight": 1.0413004845471356,
|
||||||
|
"recentSuccess": 19,
|
||||||
|
"recentSuccessRate": 0.1357142857142857,
|
||||||
|
"recentTerminal": 140,
|
||||||
|
"recentWilsonLowerBound": 0.08863403938424924,
|
||||||
|
"running": 7,
|
||||||
|
"selectionWeight": 0.20378864418712944,
|
||||||
|
"stale": false,
|
||||||
|
"submissionEligible": true,
|
||||||
|
"throughputPerHour": 23.333333333333332,
|
||||||
|
"waiting": 9178
|
||||||
|
},
|
||||||
|
"Iluvatar_bi-100": {
|
||||||
|
"available": true,
|
||||||
|
"backlogHours": 49.118644067796616,
|
||||||
|
"canVerify": true,
|
||||||
|
"error": null,
|
||||||
|
"gpu": "Iluvatar_bi-100",
|
||||||
|
"healthFactor": 1.0,
|
||||||
|
"maxConcurrentTasks": 24,
|
||||||
|
"qualityFactor": 0.05,
|
||||||
|
"queueFactor": 1.3,
|
||||||
|
"queueWeight": 1.3,
|
||||||
|
"recentSuccess": 20,
|
||||||
|
"recentSuccessRate": 0.06779661016949153,
|
||||||
|
"recentTerminal": 295,
|
||||||
|
"recentWilsonLowerBound": 0.04431284388757296,
|
||||||
|
"running": 25,
|
||||||
|
"selectionWeight": 0.065,
|
||||||
|
"stale": false,
|
||||||
|
"submissionEligible": false,
|
||||||
|
"throughputPerHour": 49.166666666666664,
|
||||||
|
"waiting": 2415
|
||||||
|
},
|
||||||
|
"Iluvatar_bi-150": {
|
||||||
|
"available": true,
|
||||||
|
"backlogHours": 130.0353982300885,
|
||||||
|
"canVerify": true,
|
||||||
|
"error": null,
|
||||||
|
"gpu": "Iluvatar_bi-150",
|
||||||
|
"healthFactor": 1.0,
|
||||||
|
"maxConcurrentTasks": 50,
|
||||||
|
"qualityFactor": 0.3627583302780072,
|
||||||
|
"queueFactor": 1.2293697479212138,
|
||||||
|
"queueWeight": 1.2293697479212138,
|
||||||
|
"recentSuccess": 36,
|
||||||
|
"recentSuccessRate": 0.1592920353982301,
|
||||||
|
"recentTerminal": 226,
|
||||||
|
"recentWilsonLowerBound": 0.11733426398615567,
|
||||||
|
"running": 8,
|
||||||
|
"selectionWeight": 0.4459641170501941,
|
||||||
|
"stale": false,
|
||||||
|
"submissionEligible": true,
|
||||||
|
"throughputPerHour": 37.666666666666664,
|
||||||
|
"waiting": 4898
|
||||||
|
},
|
||||||
|
"Iluvatar_mrv-100": {
|
||||||
|
"available": true,
|
||||||
|
"backlogHours": 746.9302325581396,
|
||||||
|
"canVerify": true,
|
||||||
|
"error": null,
|
||||||
|
"gpu": "Iluvatar_mrv-100",
|
||||||
|
"healthFactor": 1.0,
|
||||||
|
"maxConcurrentTasks": 2,
|
||||||
|
"qualityFactor": 0.051424625198907906,
|
||||||
|
"queueFactor": 0.9458009697309973,
|
||||||
|
"queueWeight": 0.9458009697309973,
|
||||||
|
"recentSuccess": 11,
|
||||||
|
"recentSuccessRate": 0.08527131782945736,
|
||||||
|
"recentTerminal": 129,
|
||||||
|
"recentWilsonLowerBound": 0.048280022399280746,
|
||||||
|
"running": 3,
|
||||||
|
"selectionWeight": 0.04863746038118018,
|
||||||
|
"stale": false,
|
||||||
|
"submissionEligible": false,
|
||||||
|
"throughputPerHour": 21.5,
|
||||||
|
"waiting": 16059
|
||||||
|
},
|
||||||
|
"Kunlunxin_p-800": {
|
||||||
|
"available": true,
|
||||||
|
"backlogHours": 448.6808510638298,
|
||||||
|
"canVerify": true,
|
||||||
|
"error": null,
|
||||||
|
"gpu": "Kunlunxin_p-800",
|
||||||
|
"healthFactor": 1.0,
|
||||||
|
"maxConcurrentTasks": 8,
|
||||||
|
"qualityFactor": 0.32249027905090133,
|
||||||
|
"queueFactor": 1.0209421411583268,
|
||||||
|
"queueWeight": 1.0209421411583268,
|
||||||
|
"recentSuccess": 23,
|
||||||
|
"recentSuccessRate": 0.16312056737588654,
|
||||||
|
"recentTerminal": 141,
|
||||||
|
"recentWilsonLowerBound": 0.11122367287919478,
|
||||||
|
"running": 8,
|
||||||
|
"selectionWeight": 0.3292439159969735,
|
||||||
|
"stale": false,
|
||||||
|
"submissionEligible": true,
|
||||||
|
"throughputPerHour": 23.5,
|
||||||
|
"waiting": 10544
|
||||||
|
},
|
||||||
|
"MetaX_c-500": {
|
||||||
|
"available": true,
|
||||||
|
"backlogHours": 548.0168067226891,
|
||||||
|
"canVerify": true,
|
||||||
|
"error": null,
|
||||||
|
"gpu": "MetaX_c-500",
|
||||||
|
"healthFactor": 1.0,
|
||||||
|
"maxConcurrentTasks": 4,
|
||||||
|
"qualityFactor": 0.5915678077728183,
|
||||||
|
"queueFactor": 0.9907696147439543,
|
||||||
|
"queueWeight": 0.9907696147439543,
|
||||||
|
"recentSuccess": 25,
|
||||||
|
"recentSuccessRate": 0.21008403361344538,
|
||||||
|
"recentTerminal": 119,
|
||||||
|
"recentWilsonLowerBound": 0.14654279199949027,
|
||||||
|
"running": 4,
|
||||||
|
"selectionWeight": 0.5861074090020008,
|
||||||
|
"stale": false,
|
||||||
|
"submissionEligible": true,
|
||||||
|
"throughputPerHour": 19.833333333333332,
|
||||||
|
"waiting": 10869
|
||||||
|
},
|
||||||
|
"Mthreads_s4000": {
|
||||||
|
"available": true,
|
||||||
|
"backlogHours": 2676.244897959184,
|
||||||
|
"canVerify": true,
|
||||||
|
"error": null,
|
||||||
|
"gpu": "Mthreads_s4000",
|
||||||
|
"healthFactor": 1.0,
|
||||||
|
"maxConcurrentTasks": 4,
|
||||||
|
"qualityFactor": 2.5,
|
||||||
|
"queueFactor": 0.781021308499512,
|
||||||
|
"queueWeight": 0.781021308499512,
|
||||||
|
"recentSuccess": 20,
|
||||||
|
"recentSuccessRate": 0.40816326530612246,
|
||||||
|
"recentTerminal": 49,
|
||||||
|
"recentWilsonLowerBound": 0.2821503460597105,
|
||||||
|
"running": 4,
|
||||||
|
"selectionWeight": 1.95255327124878,
|
||||||
|
"stale": false,
|
||||||
|
"submissionEligible": true,
|
||||||
|
"throughputPerHour": 8.166666666666666,
|
||||||
|
"waiting": 21856
|
||||||
|
},
|
||||||
|
"Sunrise_pt-200-x1": {
|
||||||
|
"available": true,
|
||||||
|
"backlogHours": 7900.0,
|
||||||
|
"canVerify": true,
|
||||||
|
"error": null,
|
||||||
|
"gpu": "Sunrise_pt-200-x1",
|
||||||
|
"healthFactor": 1.0,
|
||||||
|
"maxConcurrentTasks": 2,
|
||||||
|
"qualityFactor": 1.9800770636641265,
|
||||||
|
"queueFactor": 0.7,
|
||||||
|
"queueWeight": 0.7,
|
||||||
|
"recentSuccess": 6,
|
||||||
|
"recentSuccessRate": 0.5,
|
||||||
|
"recentTerminal": 12,
|
||||||
|
"recentWilsonLowerBound": 0.2537781703934222,
|
||||||
|
"running": 2,
|
||||||
|
"selectionWeight": 1.3860539445648885,
|
||||||
|
"stale": false,
|
||||||
|
"submissionEligible": false,
|
||||||
|
"throughputPerHour": 2.0,
|
||||||
|
"waiting": 15800
|
||||||
|
},
|
||||||
|
"Vastai_va16": {
|
||||||
|
"available": true,
|
||||||
|
"backlogHours": 471.65217391304344,
|
||||||
|
"canVerify": true,
|
||||||
|
"error": null,
|
||||||
|
"gpu": "Vastai_va16",
|
||||||
|
"healthFactor": 1.0,
|
||||||
|
"maxConcurrentTasks": 16,
|
||||||
|
"qualityFactor": 0.05,
|
||||||
|
"queueFactor": 1.0133243635804516,
|
||||||
|
"queueWeight": 1.0133243635804516,
|
||||||
|
"recentSuccess": 8,
|
||||||
|
"recentSuccessRate": 0.043478260869565216,
|
||||||
|
"recentTerminal": 184,
|
||||||
|
"recentWilsonLowerBound": 0.02219290788793925,
|
||||||
|
"running": 16,
|
||||||
|
"selectionWeight": 0.05066621817902259,
|
||||||
|
"stale": false,
|
||||||
|
"submissionEligible": false,
|
||||||
|
"throughputPerHour": 30.666666666666668,
|
||||||
|
"waiting": 14464
|
||||||
|
},
|
||||||
|
"hygon_k100-ai": {
|
||||||
|
"available": true,
|
||||||
|
"backlogHours": 603.8867924528302,
|
||||||
|
"canVerify": true,
|
||||||
|
"error": null,
|
||||||
|
"gpu": "hygon_k100-ai",
|
||||||
|
"healthFactor": 1.0,
|
||||||
|
"maxConcurrentTasks": 6,
|
||||||
|
"qualityFactor": 0.16902662598623625,
|
||||||
|
"queueFactor": 0.9764464503899792,
|
||||||
|
"queueWeight": 0.9764464503899792,
|
||||||
|
"recentSuccess": 20,
|
||||||
|
"recentSuccessRate": 0.12578616352201258,
|
||||||
|
"recentTerminal": 159,
|
||||||
|
"recentWilsonLowerBound": 0.08292190587236173,
|
||||||
|
"running": 7,
|
||||||
|
"selectionWeight": 0.165045448965655,
|
||||||
|
"stale": false,
|
||||||
|
"submissionEligible": true,
|
||||||
|
"throughputPerHour": 26.5,
|
||||||
|
"waiting": 16003
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"queueAttemptedAt": "2026-09-21T18:17:55.042367+00:00",
|
||||||
|
"queueError": null,
|
||||||
|
"queueUpdatedAt": "2026-09-21T18:17:55.042367+00:00",
|
||||||
|
"supportedGpus": [
|
||||||
|
"Vastai_va16",
|
||||||
|
"Kunlunxin_p-800",
|
||||||
|
"Cambricon_mlu-370-x4",
|
||||||
|
"Iluvatar_mrv-100",
|
||||||
|
"Iluvatar_bi-150",
|
||||||
|
"Ascend_910-b4",
|
||||||
|
"hygon_k100-ai",
|
||||||
|
"Ascend_910-b3",
|
||||||
|
"MetaX_c-500",
|
||||||
|
"Sunrise_pt-200-x1",
|
||||||
|
"Biren_166m",
|
||||||
|
"Iluvatar_bi-100",
|
||||||
|
"Cambricon_mlu-370-x8",
|
||||||
|
"Mthreads_s4000"
|
||||||
|
],
|
||||||
|
"taskTypes": [
|
||||||
|
"text-generation"
|
||||||
|
],
|
||||||
|
"throughputWindowHours": 6,
|
||||||
|
"version": 3
|
||||||
|
}
|
||||||
6864
.modelhub_state/official_capabilities.json
Normal file
6864
.modelhub_state/official_capabilities.json
Normal file
File diff suppressed because it is too large
Load Diff
36933
.modelhub_state/outcome_checkpoint.json
Normal file
36933
.modelhub_state/outcome_checkpoint.json
Normal file
File diff suppressed because it is too large
Load Diff
427
.modelhub_state/queue_cleanup_latest.json
Normal file
427
.modelhub_state/queue_cleanup_latest.json
Normal file
@@ -0,0 +1,427 @@
|
|||||||
|
{
|
||||||
|
"accountCapacityLimits": [
|
||||||
|
100,
|
||||||
|
100,
|
||||||
|
100,
|
||||||
|
100,
|
||||||
|
100,
|
||||||
|
100,
|
||||||
|
100,
|
||||||
|
100,
|
||||||
|
100,
|
||||||
|
100,
|
||||||
|
100,
|
||||||
|
100
|
||||||
|
],
|
||||||
|
"accounts": 12,
|
||||||
|
"activeScanned": 1140,
|
||||||
|
"ageCleanupMode": "admission_only",
|
||||||
|
"agePolicySkipped": {
|
||||||
|
"cleanupDisabled": true,
|
||||||
|
"reason": "admission_only"
|
||||||
|
},
|
||||||
|
"architectureBlockCount": 138,
|
||||||
|
"architectureFrameworkCatalog": {
|
||||||
|
"ascend_910-b3|text-generation": [
|
||||||
|
"llamacpp",
|
||||||
|
"vllm",
|
||||||
|
"vllm_0.23.0",
|
||||||
|
"vllm_tokenizer_patch"
|
||||||
|
],
|
||||||
|
"ascend_910-b4|text-generation": [
|
||||||
|
"llamacpp",
|
||||||
|
"vllm",
|
||||||
|
"vllm_tokenizer_patch"
|
||||||
|
],
|
||||||
|
"biren_166m|text-generation": [
|
||||||
|
"vllm",
|
||||||
|
"vllm_fix_tokenizer",
|
||||||
|
"vllm_tokenizer_patch"
|
||||||
|
],
|
||||||
|
"cambricon_mlu-370-x8|text-generation": [
|
||||||
|
"vllm",
|
||||||
|
"vllm-customized",
|
||||||
|
"vllm-mlu"
|
||||||
|
],
|
||||||
|
"hygon_k100-ai|text-generation": [
|
||||||
|
"llamacpp",
|
||||||
|
"vllm",
|
||||||
|
"vllm-patch-tokenizer"
|
||||||
|
],
|
||||||
|
"iluvatar_bi-150|text-generation": [
|
||||||
|
"llamacpp",
|
||||||
|
"transformers",
|
||||||
|
"vllm",
|
||||||
|
"vllm_0_17_0_corex_4_4_0",
|
||||||
|
"vllm_fix_tokenizer",
|
||||||
|
"vllm_tokenizer_patch"
|
||||||
|
],
|
||||||
|
"kunlunxin_p-800|text-generation": [
|
||||||
|
"vllm",
|
||||||
|
"vllm_fix_tokenizer",
|
||||||
|
"vllm_tokenizer_patch"
|
||||||
|
],
|
||||||
|
"mthreads_s4000|text-generation": [
|
||||||
|
"llamacpp",
|
||||||
|
"vllm",
|
||||||
|
"vllm_tokenizer_patch"
|
||||||
|
],
|
||||||
|
"sunrise_pt-200-x1|text-generation": [
|
||||||
|
"sglang",
|
||||||
|
"vllm",
|
||||||
|
"vllm_fix_tokenizer"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"architectureFrameworkCatalogErrors": {},
|
||||||
|
"architectureIncompatibleCount": 6,
|
||||||
|
"architectureIncompatibleTasks": [
|
||||||
|
{
|
||||||
|
"accountIndex": 5,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T03:57:37.896737+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm-customized"
|
||||||
|
],
|
||||||
|
"framework": "vllm-customized",
|
||||||
|
"gpuType": "Cambricon_mlu-370-x8",
|
||||||
|
"modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4925021,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"accountIndex": 6,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T03:57:37.896737+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm-customized"
|
||||||
|
],
|
||||||
|
"framework": "vllm-customized",
|
||||||
|
"gpuType": "Cambricon_mlu-370-x8",
|
||||||
|
"modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4939248,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"accountIndex": 10,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T03:57:37.896737+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm-customized"
|
||||||
|
],
|
||||||
|
"framework": "vllm-customized",
|
||||||
|
"gpuType": "Cambricon_mlu-370-x8",
|
||||||
|
"modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4850852,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"accountIndex": 10,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T03:57:37.896737+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm-customized"
|
||||||
|
],
|
||||||
|
"framework": "vllm-customized",
|
||||||
|
"gpuType": "Cambricon_mlu-370-x8",
|
||||||
|
"modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4881076,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"accountIndex": 11,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T03:57:37.896737+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm-customized"
|
||||||
|
],
|
||||||
|
"framework": "vllm-customized",
|
||||||
|
"gpuType": "Cambricon_mlu-370-x8",
|
||||||
|
"modelId": "Edge0/Edge0-35B-A3B-preview",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4850851,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"accountIndex": 12,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T03:57:37.896737+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm-customized"
|
||||||
|
],
|
||||||
|
"framework": "vllm-customized",
|
||||||
|
"gpuType": "Cambricon_mlu-370-x8",
|
||||||
|
"modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4881080,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"architectureModelConfigErrors": {
|
||||||
|
"GestaltLabs/Ornstein-3.5-9B-V2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/GestaltLabs/Ornstein-3.5-9B-V2-GGUF/resolve/master/config.json (status=404)",
|
||||||
|
"LiquidAI/LFM2.5-2.6B-DSpark-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B-DSpark-GGUF/resolve/master/config.json (status=404)",
|
||||||
|
"LiquidAI/LFM2.5-230M-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/LiquidAI/LFM2.5-230M-GGUF/resolve/master/config.json (status=404)",
|
||||||
|
"b77968543/Spark-X2.5-4B-Q8_0": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/b77968543/Spark-X2.5-4B-Q8_0/resolve/master/config.json (status=404)",
|
||||||
|
"cgisky/Ai00-X": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/cgisky/Ai00-X/resolve/master/config.json (status=404)",
|
||||||
|
"empero-ai/Qwen3.8-2B-Distill-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/empero-ai/Qwen3.8-2B-Distill-GGUF/resolve/master/config.json (status=404)",
|
||||||
|
"empero-ai/Qwen3.8-4B-Distill-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/empero-ai/Qwen3.8-4B-Distill-GGUF/resolve/master/config.json (status=404)",
|
||||||
|
"empero-ai/Qwen3.8-9B-Distill-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/empero-ai/Qwen3.8-9B-Distill-GGUF/resolve/master/config.json (status=404)",
|
||||||
|
"empero-ai/Qwen3.8-9B-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/empero-ai/Qwen3.8-9B-GGUF/resolve/master/config.json (status=404)",
|
||||||
|
"ewinregirgojr/Qwen3.8-14B-Instruct-Turbo-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/ewinregirgojr/Qwen3.8-14B-Instruct-Turbo-GGUF/resolve/master/config.json (status=404)",
|
||||||
|
"fengxiaohong/Qwen3.8-27B-Q8_0_GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/fengxiaohong/Qwen3.8-27B-Q8_0_GGUF/resolve/master/config.json (status=404)",
|
||||||
|
"guaidao2/XuanmuSec-2.6B": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/guaidao2/XuanmuSec-2.6B/resolve/master/config.json (status=404)",
|
||||||
|
"hf/douyamv-Qwen3.8-27B-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/hf/douyamv-Qwen3.8-27B-GGUF/resolve/master/config.json (status=404)",
|
||||||
|
"inclusionAI/Ling-3.0-tiny-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny-GGUF/resolve/master/config.json (status=500)",
|
||||||
|
"incoai/Qwen3.8-27B-DFlash2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/incoai/Qwen3.8-27B-DFlash2-GGUF/resolve/master/config.json (status=404)",
|
||||||
|
"ornith-ai/Ornith-1.0-9B-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/ornith-ai/Ornith-1.0-9B-GGUF/resolve/master/config.json (status=404)",
|
||||||
|
"ornith-ai/Ornith-1.5-9B-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-GGUF/resolve/master/config.json (status=404)",
|
||||||
|
"prithivMLmods/CogEvol-4B-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/prithivMLmods/CogEvol-4B-GGUF/resolve/master/config.json (status=404)",
|
||||||
|
"unsloth/LFM2-2.6B-Exp-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/unsloth/LFM2-2.6B-Exp-GGUF/resolve/master/config.json (status=500)",
|
||||||
|
"z-lab/Qwen3.8-27B-DFlash2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/master/config.json (status=404)"
|
||||||
|
},
|
||||||
|
"architectureModelConfigsComplete": 58,
|
||||||
|
"architectureOnly": true,
|
||||||
|
"architecturePolicySkipped": {
|
||||||
|
"frameworkCatalogUnknown": 0,
|
||||||
|
"frameworkContextUnknown": 64,
|
||||||
|
"modelArchitectureUnknown": 133,
|
||||||
|
"noMatchingBlock": 981,
|
||||||
|
"partiallyBlockedFrameworkSet": 20,
|
||||||
|
"runningMatchedProtected": 0,
|
||||||
|
"submissionContextMismatch": 0,
|
||||||
|
"submissionContextUnknown": 0
|
||||||
|
},
|
||||||
|
"cancelledCount": 6,
|
||||||
|
"cancelledTasks": [
|
||||||
|
{
|
||||||
|
"accountIndex": 5,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T03:57:37.896737+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"cleanupReasons": [
|
||||||
|
"known_framework_architecture_incompatible"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm-customized"
|
||||||
|
],
|
||||||
|
"framework": "vllm-customized",
|
||||||
|
"gpuType": "Cambricon_mlu-370-x8",
|
||||||
|
"modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4925021,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"accountIndex": 6,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T03:57:37.896737+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"cleanupReasons": [
|
||||||
|
"known_framework_architecture_incompatible"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm-customized"
|
||||||
|
],
|
||||||
|
"framework": "vllm-customized",
|
||||||
|
"gpuType": "Cambricon_mlu-370-x8",
|
||||||
|
"modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4939248,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"accountIndex": 10,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T03:57:37.896737+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"cleanupReasons": [
|
||||||
|
"known_framework_architecture_incompatible"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm-customized"
|
||||||
|
],
|
||||||
|
"framework": "vllm-customized",
|
||||||
|
"gpuType": "Cambricon_mlu-370-x8",
|
||||||
|
"modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4850852,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"accountIndex": 10,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T03:57:37.896737+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"cleanupReasons": [
|
||||||
|
"known_framework_architecture_incompatible"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm-customized"
|
||||||
|
],
|
||||||
|
"framework": "vllm-customized",
|
||||||
|
"gpuType": "Cambricon_mlu-370-x8",
|
||||||
|
"modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4881076,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"accountIndex": 11,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T03:57:37.896737+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"cleanupReasons": [
|
||||||
|
"known_framework_architecture_incompatible"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm-customized"
|
||||||
|
],
|
||||||
|
"framework": "vllm-customized",
|
||||||
|
"gpuType": "Cambricon_mlu-370-x8",
|
||||||
|
"modelId": "Edge0/Edge0-35B-A3B-preview",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4850851,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"accountIndex": 12,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T03:57:37.896737+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"cleanupReasons": [
|
||||||
|
"known_framework_architecture_incompatible"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm-customized"
|
||||||
|
],
|
||||||
|
"framework": "vllm-customized",
|
||||||
|
"gpuType": "Cambricon_mlu-370-x8",
|
||||||
|
"modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4881080,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"certainOomCount": 0,
|
||||||
|
"certainOomTasks": [],
|
||||||
|
"cleanupCandidateCount": 6,
|
||||||
|
"dryRun": false,
|
||||||
|
"listingErrors": {},
|
||||||
|
"modelAgeErrors": {},
|
||||||
|
"modelAgeMetadataComplete": 0,
|
||||||
|
"noLongerActiveCount": 0,
|
||||||
|
"officialCapabilityCatalogError": null,
|
||||||
|
"officialCapabilityInvalidCount": 0,
|
||||||
|
"officialCapabilityInvalidTasks": [],
|
||||||
|
"oldModelQueueThresholds": [
|
||||||
|
95,
|
||||||
|
95,
|
||||||
|
95,
|
||||||
|
95,
|
||||||
|
95,
|
||||||
|
95,
|
||||||
|
95,
|
||||||
|
95,
|
||||||
|
95,
|
||||||
|
95,
|
||||||
|
95,
|
||||||
|
95
|
||||||
|
],
|
||||||
|
"oldOverflowCount": 0,
|
||||||
|
"oldOverflowTasks": [],
|
||||||
|
"policyCancelledRecorded": 6,
|
||||||
|
"policyNoLongerAppliesCount": 0,
|
||||||
|
"policyNoLongerAppliesTasks": [],
|
||||||
|
"recentModelDays": 7,
|
||||||
|
"recentModelReserveSlots": 5,
|
||||||
|
"repositorySizeErrors": {},
|
||||||
|
"repositorySizesComplete": 0,
|
||||||
|
"skipped": {
|
||||||
|
"fitsKnownCapacity": 0,
|
||||||
|
"gpuCapacityUnknown": 0,
|
||||||
|
"repositorySizeUnknown": 0
|
||||||
|
},
|
||||||
|
"stopErrors": [],
|
||||||
|
"uniqueModels": 351
|
||||||
|
}
|
||||||
300
.modelhub_state/recent_outcomes.jsonl
Normal file
300
.modelhub_state/recent_outcomes.jsonl
Normal file
@@ -0,0 +1,300 @@
|
|||||||
|
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-21T16:50:30.559368+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T16:39:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610379", "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": "2026-09-21T16:50:30.559274+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T16:37:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4332638", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-21T15:58:04.749250+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T15:57:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4332444", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "", "lastSyncTime": "2026-09-21T15:14:12.874625+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T15:11:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610383", "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": "2026-09-21T15:02:24.876304+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T14:47:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4586965", "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": "2026-09-21T14:32:55.759858+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T14:23:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4584252", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-09-21T10:33:30.477632+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-8bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T10:23:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4609105", "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": "2026-09-21T10:33:30.477558+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T10:15:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4582656", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T09:54:21.980346+00:00", "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T09:52:44+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969634", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T09:54:21.980312+00:00", "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T09:52:43+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969630", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T09:54:21.980336+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T09:35:50+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969372", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T17:41:26.757140+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "5227b42f4cdd7539bb62412569c7d9c8b3cc2e321cdbac3654c73c95c5bc8a7b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5469228368, "estimatedRequiredGiB": 6.118, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-21T08:39:42.289781+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4997241", "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", "framework": "vllm", "lastSyncTime": "2026-09-21T07:56:18.163712+00:00", "modelId": "bharatgenai/Param2-17B-A2.4B-Thinking", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T07:55:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4592636", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T06:41:38.663921+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T06:27:41+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970364", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T06:41:38.664002+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T06:27:41+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4783202", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T06:41:38.663896+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T06:27:40+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4920239", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T06:41:38.663932+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T06:27:40+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4920434", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T05:59:02.567443+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T05:55:34+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4968995", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-21T05:51:50.448464+00:00", "modelId": "BAAI/Hospitality-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-21T05:49:22+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457981", "taskType": "text-generation", "verifyResult": 1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T05:42:03.443622+00:00", "modelId": "tencent-community/WeDLM-7B-Instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T05:29:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079933", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164989+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:49:27+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4895729", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164919+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:49:26+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4899358", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164954+00:00", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:49:26+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969013", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164848+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:49:25+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969016", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164881+00:00", "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:49:25+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969017", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164891+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:49:25+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969005", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164898+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:49:25+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4782245", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164811+00:00", "modelId": "BAAI/Finance-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-21T04:43:22+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457976", "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", "lastSyncTime": "2026-09-21T04:36:00.569175+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T04:35:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4576912", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569197+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:31:57+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969802", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569297+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:31:57+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969335", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569333+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:31:57+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969619", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569079+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:31:56+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969638", "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": "", "lastSyncTime": "2026-09-21T04:36:00.569316+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-8bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T04:21:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4332458", "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": "2026-09-21T04:36:00.569341+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T04:19:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4572698", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569325+00:00", "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:16:35+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969061", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569017+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:16:34+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4753715", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569262+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:16:34+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4938618", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569272+00:00", "modelId": "Edge0/Edge0-35B-A3B-preview", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:16:34+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4845402", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569347+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:16:34+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4845403", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569092+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:16:33+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4857814", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569134+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:16:33+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4857813", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569144+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:16:33+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4923523", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569235+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:16:33+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4795478", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-21T04:11:57.967213+00:00", "modelId": "BAAI/CareBot_Medical_multi-llama3-8b-base", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-21T04:11:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457983", "taskType": "text-generation", "verifyResult": 1}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:11:57.967175+00:00", "modelId": "BAAI/RoboBrain2.5-8B-NV", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:09:34+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969052", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"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": "2026-09-21T03:45:50.542891+00:00", "modelId": "AI-ModelScope/granite-20b-code-base", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T03:31:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4080015", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-21T03:09:23.977124+00:00", "modelId": "BAAI/Artificial-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-21T03:07:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457977", "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": "2026-09-21T03:05:47.759507+00:00", "modelId": "fla-hub/rwkv7-191M-world", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T03:05:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079091", "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": "2026-09-21T02:58:30.354798+00:00", "modelId": "tencent-community/WeDLM-7B-Instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:57:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079148", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T02:58:30.354826+00:00", "modelId": "tencent-community/WeDLM-7B-Instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:57:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4080024", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446730+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:08+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4860052", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446754+00:00", "modelId": "Edge0/Edge0-35B-A3B-preview", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:08+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4849007", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446763+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:08+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4860051", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446781+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:08+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4795634", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446625+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:07+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4849006", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446646+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:07+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969661", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446677+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:07+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754068", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446703+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:07+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4939007", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446712+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:07+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4923872", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-21T02:49:19.765032+00:00", "modelId": "BAAI/Aerospace-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-21T02:47:22+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457982", "taskType": "text-generation", "verifyResult": 1}
|
||||||
|
{"failReason": "runtime_memory", "failureAction": "lower_memory_risk_or_reject_combination", "failureCategory": "runtime_memory", "failureClassificationReason": "structured_device_oom", "failureCode": "DEVICE_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-21T02:38:57.372787+00:00", "modelId": "nv-community/Llama-3_3-Nemotron-Super-49B-v1_5-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:37:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079201", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-21T02:15:17.867390+00:00", "modelId": "BAAI/Automobile-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-21T02:07:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457986", "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", "lastSyncTime": "2026-09-21T01:35:45.556193+00:00", "modelId": "vllm-ascend/Qwen3-32B-w8a8sc-310-vllm-tp4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T01:23:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079972", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T18:20:35.656980+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612744, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788612744}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T00:12:58.737197+00:00", "targetGpu": "Biren_166m", "taskId": "4990141", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T15:54:37.859021+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093251901, "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": 9093251901}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T00:00:11.334848+00:00", "targetGpu": "Biren_166m", "taskId": "4989991", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-20T23:43:40.271809+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-8bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T23:43:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610385", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T23:08:35.573428+00:00", "modelId": "YOYO-AI/ZYH-LLM-Qwen2.5-14B-V2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T23:05:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079190", "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": "2026-09-20T22:43:47.754964+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T22:31:23+00:00", "targetGpu": "Biren_166m", "taskId": "4610366", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T16:50:30.559291+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794426, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4205751296, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794426}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T22:29:12.193862+00:00", "targetGpu": "Biren_166m", "taskId": "4988754", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "runtime_memory", "failureAction": "lower_memory_risk_or_reject_combination", "failureCategory": "runtime_memory", "failureClassificationReason": "structured_device_oom", "failureCode": "DEVICE_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-20T22:20:31.465723+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T22:19:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4587221", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T05:42:03.443541+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T21:19:40.047378+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4987847", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T16:50:30.559324+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998647728, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020563851, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 12020563851}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T21:15:43.436820+00:00", "targetGpu": "Biren_166m", "taskId": "4987805", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T16:50:30.559167+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "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", "modelscopeFileSize": 26090095180, "modelscopeLicense": "apache-2.0", "modelscopeParams": 21416999792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26090095180}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T21:13:47.960850+00:00", "targetGpu": "Biren_166m", "taskId": "4987803", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T16:50:30.559353+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "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", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:53:47.320072+00:00", "targetGpu": "Biren_166m", "taskId": "4987553", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T16:50:30.559306+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463599, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463599}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:39:13.053978+00:00", "targetGpu": "Biren_166m", "taskId": "4987256", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T16:50:30.559123+00:00", "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615496, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615496}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:33:30.958684+00:00", "targetGpu": "Biren_166m", "taskId": "4987157", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T16:50:30.559222+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "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": 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": "failed", "status": "success", "submitTime": "2026-09-20T20:21:26.745613+00:00", "targetGpu": "Biren_166m", "taskId": "4987023", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-21T05:42:03.443548+00:00", "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5222073830, "estimatedRequiredGiB": 5.872, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5254590634, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1140034851, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5254590634}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:09:24.421834+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986873", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-21T05:42:03.443484+00:00", "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelProfile": {"architectures": ["Mistral3ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17367755740, "estimatedRequiredGiB": 19.429, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral3", "modelscopeFileSize": 17385072379, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4929899520, "modelscopeTags": ["license:apache-2.0", "model_type:mistral3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:mistral", "custom_tag:mistral3", "custom_tag:devstral"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17385072379}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:09:24.418725+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986874", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "failureUnsupportedModelTypes": ["lfm2"], "framework": "transformers", "lastSyncTime": "2026-09-21T05:42:03.443562+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663396475}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:09:24.405809+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986872", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-21T05:42:03.443516+00:00", "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9003966484, "estimatedRequiredGiB": 10.099, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 9036402901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2463563824, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9036402901}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:09:24.258178+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986871", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-21T05:21:25.760211+00:00", "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21855018733, "estimatedRequiredGiB": 24.461, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 21887495988, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6144703054, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21887495988}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:09:24.251268+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986870", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-21T05:42:03.443597+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 23556606333}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:09:24.188484+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986865", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-21T05:17:51.457662+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25593158704, "estimatedRequiredGiB": 28.626, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 25613691403, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7626590448, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25613691403}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:09:24.182431+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986866", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-21T05:21:25.760156+00:00", "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5226595850, "estimatedRequiredGiB": 5.878, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5259113427, "modelscopeLicense": "gemma", "modelscopeParams": 1141165347, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5259113427}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:09:24.179348+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986864", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "transformers", "lastSyncTime": "2026-09-21T05:17:51.457633+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21930054875, "estimatedRequiredGiB": 24.532, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21950415614, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6024588416, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21950415614}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:09:24.174803+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986863", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-21T05:14:26.178403+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 9.768, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 8740644030, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8740644030}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:09:24.171826+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986869", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "transformers", "lastSyncTime": "2026-09-21T05:42:03.443575+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293473597, "estimatedRequiredGiB": 18.233, "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": 16314185171, "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:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16314185171}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:09:24.169691+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986868", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "transformers", "lastSyncTime": "2026-09-21T05:17:51.457611+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683239637, "estimatedRequiredGiB": 23.138, "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": 20703971805, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703971805}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:09:23.997557+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986862", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-21T05:17:51.457647+00:00", "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7486327132, "estimatedRequiredGiB": 8.403, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 7518908360, "modelscopeLicense": "gemma", "modelscopeParams": 2227418442, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7518908360}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:09:23.994993+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986861", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "failureUnsupportedModelTypes": ["qwen3_vl"], "framework": "transformers", "lastSyncTime": "2026-09-21T05:14:26.178418+00:00", "modelId": "BAAI/RoboBrain2.5-8B-MT", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918174, "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": 17545918174}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:09:23.991772+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986860", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "transformers", "lastSyncTime": "2026-09-21T05:25:05.959914+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474987, "estimatedRequiredGiB": 18.232, "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": 16313701503, "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:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16313701503}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:09:23.969433+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986859", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-21T12:09:51.363808+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955857175}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:09:23.967582+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986857", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "transformers", "lastSyncTime": "2026-09-21T05:21:25.760203+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683241105, "estimatedRequiredGiB": 23.138, "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": 20703487237, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703487237}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T20:09:23.966391+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4986858", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T12:58:50.741501+00:00", "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5222073830, "estimatedRequiredGiB": 5.872, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5254590634, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1140034851, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5254590634}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.804006+00:00", "targetGpu": "Biren_166m", "taskId": "4986623", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T16:50:30.559192+00:00", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8674988799, "estimatedRequiredGiB": 9.718, "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": 8695119291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2415484144, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:qwen3-5", "custom_tag:9b", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8695119291}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.745647+00:00", "targetGpu": "Biren_166m", "taskId": "4986622", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T18:20:35.656967+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663396475}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.739365+00:00", "targetGpu": "Biren_166m", "taskId": "4986621", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T12:09:51.363854+00:00", "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelProfile": {"architectures": ["Mistral3ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17367755740, "estimatedRequiredGiB": 19.429, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral3", "modelscopeFileSize": 17385072379, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4929899520, "modelscopeTags": ["license:apache-2.0", "model_type:mistral3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:mistral", "custom_tag:mistral3", "custom_tag:devstral"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17385072379}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.736283+00:00", "targetGpu": "Biren_166m", "taskId": "4986620", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T12:09:51.363816+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293473597, "estimatedRequiredGiB": 18.233, "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": 16314185171, "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:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16314185171}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.673114+00:00", "targetGpu": "Biren_166m", "taskId": "4986619", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T12:58:50.741528+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25593158704, "estimatedRequiredGiB": 28.626, "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", "modelscopeFileSize": 25613691403, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7626590448, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25613691403}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.653000+00:00", "targetGpu": "Biren_166m", "taskId": "4986616", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T12:58:50.741607+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21930054875, "estimatedRequiredGiB": 24.532, "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", "modelscopeFileSize": 21950415614, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6024588416, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21950415614}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.646752+00:00", "targetGpu": "Biren_166m", "taskId": "4986611", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T12:58:50.741542+00:00", "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21855018733, "estimatedRequiredGiB": 24.461, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 21887495988, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6144703054, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21887495988}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.643458+00:00", "targetGpu": "Biren_166m", "taskId": "4986613", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T12:58:50.741555+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 9.768, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 8740644030, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8740644030}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.640908+00:00", "targetGpu": "Biren_166m", "taskId": "4986612", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T12:58:50.741629+00:00", "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5226595850, "estimatedRequiredGiB": 5.878, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5259113427, "modelscopeLicense": "gemma", "modelscopeParams": 1141165347, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5259113427}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.639695+00:00", "targetGpu": "Biren_166m", "taskId": "4986615", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T12:58:50.741491+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 23556606333}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.636564+00:00", "targetGpu": "Biren_166m", "taskId": "4986617", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T12:58:50.741464+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37184031394, "estimatedRequiredGiB": 41.579, "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", "modelscopeFileSize": 37204398600, "modelscopeLicense": "apache-2.0", "modelscopeParams": 10061358960, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:mixed-precision", "custom_tag:qwen3.6", "custom_tag:agentic-search"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37204398600}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.595651+00:00", "targetGpu": "Biren_166m", "taskId": "4986618", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T12:58:50.741510+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.574218+00:00", "targetGpu": "Biren_166m", "taskId": "4986610", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T07:56:18.163682+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "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": 7550622334}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.549308+00:00", "targetGpu": "Biren_166m", "taskId": "4986609", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T07:56:18.163660+00:00", "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9003966484, "estimatedRequiredGiB": 10.099, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 9036402901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2463563824, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9036402901}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.535472+00:00", "targetGpu": "Biren_166m", "taskId": "4986608", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T07:56:18.163617+00:00", "modelId": "prithivMLmods/CEERS-2112-14B-Instruct", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29540133904, "estimatedRequiredGiB": 33.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 29547221374, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14770033664, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:Code", "custom_tag:Math", "custom_tag:Reasoning", "custom_tag:text-generation-inference", "custom_tag:Reinforcement-learning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29547221374}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.523364+00:00", "targetGpu": "Biren_166m", "taskId": "4986607", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T09:32:45.295708+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683239637, "estimatedRequiredGiB": 23.138, "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": 20703971805, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703971805}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.509974+00:00", "targetGpu": "Biren_166m", "taskId": "4986606", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T09:32:45.295632+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.502504+00:00", "targetGpu": "Biren_166m", "taskId": "4986605", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T09:32:45.295661+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.486486+00:00", "targetGpu": "Biren_166m", "taskId": "4986603", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T09:32:45.295567+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474987, "estimatedRequiredGiB": 18.232, "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": 16313701503, "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:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16313701503}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.482557+00:00", "targetGpu": "Biren_166m", "taskId": "4986602", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T09:32:45.295693+00:00", "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7486327132, "estimatedRequiredGiB": 8.403, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 7518908360, "modelscopeLicense": "gemma", "modelscopeParams": 2227418442, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7518908360}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.473777+00:00", "targetGpu": "Biren_166m", "taskId": "4986599", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T09:32:45.295647+00:00", "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10261168632, "estimatedRequiredGiB": 11.478, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 10270608122, "modelscopeLicense": "other", "modelscopeParams": 16754741248, "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 - mergekit - merge - facebook - meta - pytorch - llama - llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 10270608122}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.472448+00:00", "targetGpu": "Biren_166m", "taskId": "4986601", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T09:32:45.295736+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.461438+00:00", "targetGpu": "Biren_166m", "taskId": "4986600", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T09:32:45.295723+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683241105, "estimatedRequiredGiB": 23.138, "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": 20703487237, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703487237}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:48:14.450477+00:00", "targetGpu": "Biren_166m", "taskId": "4986598", "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": "2026-09-21T04:36:00.569307+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.621, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345554722, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345554722}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:28:11.202603+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4986310", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "runtime_memory", "failureAction": "lower_memory_risk_or_reject_combination", "failureCategory": "runtime_memory", "failureClassificationReason": "structured_device_oom", "failureCode": "DEVICE_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-20T19:33:34.552400+00:00", "modelId": "nv-community/Llama-3_3-Nemotron-Super-49B-v1_5-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:25:22+00:00", "targetGpu": "hygon_k100-ai", "taskId": "3986841", "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": "2026-09-20T18:53:01.472996+00:00", "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T18:51:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4523697", "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", "lastSyncTime": "2026-09-20T18:53:01.473044+00:00", "modelId": "fla-hub/rwkv7-191M-world", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T18:49:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079911", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "runtime_memory", "failureAction": "lower_memory_risk_or_reject_combination", "failureCategory": "runtime_memory", "failureClassificationReason": "structured_device_oom", "failureCode": "DEVICE_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-20T18:53:01.473084+00:00", "modelId": "vllm-ascend/Qwen3-32B-w8a8sc-310-vllm-tp4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T18:47:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079186", "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-customized", "lastSyncTime": "2026-09-21T17:22:47.256817+00:00", "modelId": "sapientinc/HRM-Text-1B", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2365606568, "estimatedRequiredGiB": 2.651, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 2371660433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1182795264, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:hrm", "custom_tag:hierarchical-reasoning", "custom_tag:prefix-lm", "custom_tag:pre-alignment", "custom_tag:non-chat", "custom_tag:non-instruction-tuned"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2371660433}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T18:47:15.075816+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4985774", "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": "2026-09-20T18:36:43.146458+00:00", "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T18:33:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4523880", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T05:07:16.468545+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-20T17:09:45.266093+00:00", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 20926892207}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T17:55:49.593955+00:00", "targetGpu": "Biren_166m", "taskId": "4984927", "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": "2026-09-21T05:07:16.468553+00:00", "modelId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7686303632, "estimatedRequiredGiB": 8.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 7688299919, "modelscopeLicense": "llama2", "modelscopeParams": 13960238080, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7688299919}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T17:27:17.434574+00:00", "targetGpu": "Biren_166m", "taskId": "4984467", "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, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-20T17:39:36.352421+00:00", "modelId": "bharatgenai/Param2-17B-A2.4B-Thinking", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T17:25:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4592187", "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", "framework": "vllm", "lastSyncTime": "2026-09-20T16:40:51.571551+00:00", "modelId": "KoboldAI/fairseq-dense-13B-Janeway", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T16:37:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079152", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T16:33:38.958026+00:00", "modelId": "YOYO-AI/Qwen2.5-14B-YOYO-V3", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T16:33:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079134", "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", "framework": "vllm", "lastSyncTime": "2026-09-20T16:12:47.264764+00:00", "modelId": "bharatgenai/Param2-17B-A2.4B-Thinking", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T16:11:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4592334", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T16:12:47.264793+00:00", "modelId": "KenDual3090tiNvlink/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-W4A16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T16:11:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4080000", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "quantization_error", "failureCode": "QUANTIZATION_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T05:48:19.353127+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T14:26:25.535380+00:00", "targetGpu": "Biren_166m", "taskId": "4980428", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-21T00:42:10.765041+00:00", "modelId": "LiquidAI/LFM2.5-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427456, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412393192, "modelscopeLicense": "other", "modelscopeParams": 2697198592, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412393192}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T14:26:18.189644+00:00", "targetGpu": "Biren_166m", "taskId": "4980427", "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": "2026-09-21T03:02:20.757790+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.742, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663548868, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663548868}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T14:26:11.835960+00:00", "targetGpu": "Biren_166m", "taskId": "4980425", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T14:32:15.260773+00:00", "modelId": "AI-ModelScope/granite-20b-code-base", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T14:25:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079181", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-09-21T04:36:00.569045+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T14:24:07.110246+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4980393", "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": "2026-09-20T14:18:03.259001+00:00", "modelId": "QuantTrio/Kimi-Dev-72B-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T14:17:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079164", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-20T13:34:22.859864+00:00", "modelId": "AI-ModelScope/granite-20b-code-instruct-8k", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-20T13:31:22+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079142", "taskType": "text-generation", "verifyResult": 1}
|
||||||
|
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-20T13:34:22.859810+00:00", "modelId": "KenDual3090tiNvlink/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-W4A16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T13:31:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079137", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T00:42:10.765026+00:00", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857274344, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860631926, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7860631926}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T13:22:06.962643+00:00", "targetGpu": "Biren_166m", "taskId": "4979624", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T21:06:45.850258+00:00", "modelId": "aisingapore/SEA-LION-v1-7B", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008115847, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008115847}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T12:55:19.835166+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4979183", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T17:22:47.256877+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663867, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788663867}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T12:51:33.437699+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4979144", "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": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-20T23:05:08.270726+00:00", "modelId": "pfnet/plamo-3-nict-8b-base", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16182734928, "estimatedRequiredGiB": 18.09, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 16186391993, "modelscopeLicense": "other", "modelscopeParams": 8091348992, "modelscopeTags": ["license:other", "model_type:plamo3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16186391993}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T12:42:11.634279+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4979087", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "transformers", "lastSyncTime": "2026-09-20T21:06:45.850266+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426233716, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "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": 1426233716}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T12:41:32.800701+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4979069", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T00:42:10.765034+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-Research", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "f7d2aee0bcf1396cd8ab3b1064b6a032eccc04f2d655a336023e13528574903d", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008118474, "modelscopeLicense": "cc-by-nc-sa-4.0", "modelscopeParams": 7501651968, "modelscopeTags": ["license:cc-by-nc-sa-4.0", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008118474}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T12:25:31.189161+00:00", "targetGpu": "Biren_166m", "taskId": "4978633", "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": "2026-09-21T08:17:25.672496+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093204103, "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", "custom_tag:quantized", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093204103}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T12:20:00.435973+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4978589", "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": "2026-09-20T12:21:49.901980+00:00", "modelId": "AI-ModelScope/granite-20b-code-base-8k", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T12:09:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079967", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T01:08:25.664308+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-20T11:54:11.089175+00:00", "targetGpu": "Biren_166m", "taskId": "4978283", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "transformers", "lastSyncTime": "2026-09-20T19:56:29.962428+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736540899, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756990943, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13756990943}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T11:44:01.235722+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4978143", "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": "2026-09-20T11:30:54.600461+00:00", "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T11:23:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4523512", "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": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-20T21:06:45.850234+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "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": 3430847031, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "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": null, "repositoryOnDiskBytes": 3430847031}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T10:32:04.275294+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4977311", "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", "framework": "vllm", "lastSyncTime": "2026-09-20T10:06:20.452855+00:00", "modelId": "KoboldAI/fairseq-dense-13B-Janeway", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T09:55:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079951", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-20T09:38:38.259110+00:00", "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T09:35:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4560061", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "transformers", "lastSyncTime": "2026-09-20T17:24:32.660503+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14864536516, "estimatedRequiredGiB": 16.635, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 14884986381, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3818458992, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14884986381}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T09:13:32.073259+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974772", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "transformers", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "transformers", "lastSyncTime": "2026-09-20T17:24:32.660488+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "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": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T09:13:31.973727+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974771", "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": "transformers", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "transformers", "lastSyncTime": "2026-09-20T17:24:32.660450+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20628596944, "estimatedRequiredGiB": 23.076, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 20647674585, "modelscopeLicense": "other", "modelscopeParams": 33943909952, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:int4", "custom_tag:int8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:mamba", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20647674585}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T09:13:31.862874+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974770", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-20T17:24:32.660406+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809686744, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809686744}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T09:13:31.707511+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974769", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T17:24:32.660469+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786133, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "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": 3487786133}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T09:12:07.635577+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974768", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T17:22:47.256939+00:00", "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10261168632, "estimatedRequiredGiB": 11.478, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 10270608122, "modelscopeLicense": "other", "modelscopeParams": 16754741248, "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 - mergekit - merge - facebook - meta - pytorch - llama - llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 10270608122}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T09:09:39.664442+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4974664", "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": "transformers", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "transformers", "lastSyncTime": "2026-09-20T17:24:32.660512+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "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": 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": "failed", "status": "success", "submitTime": "2026-09-20T09:04:12.649418+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974501", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T17:24:32.660478+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22210552448, "estimatedRequiredGiB": 24.849, "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": 22234091413, "modelscopeLicense": "apache-2.0", "modelscopeParams": 17463440388, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:blackwell", "custom_tag:a100"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 22234091413}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T09:03:34.948874+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974425", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T17:24:32.660496+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26090095180, "modelscopeLicense": "apache-2.0", "modelscopeParams": 21416999792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26090095180}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T09:03:34.821144+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974424", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T17:24:32.660459+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19342796520, "estimatedRequiredGiB": 21.64, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 19362750397, "modelscopeLicense": "other", "modelscopeParams": 18237772608, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19362750397}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T09:03:34.717422+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974423", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T17:24:32.660437+00:00", "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615496, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615496}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T09:03:34.603238+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974422", "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": "2026-09-21T08:17:25.672461+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "58bd440e460cf3e4d9271b3c32c451e80254e59faf47ce55dcda11588cf4117e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014789064, "estimatedRequiredGiB": 2.255, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018175215, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "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": 2018175215}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T08:56:10.450953+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4974352", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-20T17:09:45.266169+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "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": "failed", "status": "success", "submitTime": "2026-09-20T08:54:12.459339+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974306", "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": "transformers", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "transformers", "lastSyncTime": "2026-09-20T17:09:45.266025+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21561882284, "estimatedRequiredGiB": 24.122, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 21583784354, "modelscopeLicense": "other", "modelscopeParams": 17820210764, "modelscopeTags": ["license:other", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21583784354}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T08:53:35.105220+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974283", "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": "transformers", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "transformers", "lastSyncTime": "2026-09-20T17:09:45.266055+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23420419700, "estimatedRequiredGiB": 26.214, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23455515266, "modelscopeLicense": "mit", "modelscopeParams": 19528501104, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 23455515266}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T08:53:34.985766+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974282", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T17:09:45.266191+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T08:52:13.083499+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974280", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T17:22:47.256886+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786133, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "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": 3487786133}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T08:51:34.994683+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4974250", "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": "2026-09-20T16:54:50.062704+00:00", "modelId": "sapientinc/HRM-Text-1B", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2365606568, "estimatedRequiredGiB": 2.651, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 2371660433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1182795264, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:hrm", "custom_tag:hierarchical-reasoning", "custom_tag:prefix-lm", "custom_tag:pre-alignment", "custom_tag:non-chat", "custom_tag:non-instruction-tuned"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2371660433}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T08:43:32.500833+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974130", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-20T16:54:50.062652+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663410366, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663410366}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T08:42:29.837957+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4974129", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T17:22:47.256780+00:00", "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615496, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615496}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T08:38:08.235641+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4974086", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "transformers", "lastSyncTime": "2026-09-20T15:35:51.777956+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16936006912, "estimatedRequiredGiB": 18.948, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 16953948786, "modelscopeLicense": "other", "modelscopeParams": 8467856832, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16953948786}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T07:24:14.091402+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4973030", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T10:57:20.777331+00:00", "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221588, "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": 8338221588}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T06:34:00.535697+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4972450", "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_tokenizer_patch", "lastSyncTime": "2026-09-21T16:50:30.559083+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124714, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124714}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T06:32:07.434077+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4972417", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-20T06:27:54.872472+00:00", "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T06:21:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610365", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T14:47:45.260018+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T06:19:35.394755+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4972231", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T19:47:52.978269+00:00", "modelId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658310, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658310}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T06:17:57.834294+00:00", "targetGpu": "Biren_166m", "taskId": "4972230", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-20T05:59:18.862303+00:00", "modelId": "AI-ModelScope/granite-20b-code-base-8k", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-20T05:57:22+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079080", "taskType": "text-generation", "verifyResult": 1}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "vllm-customized", "lastSyncTime": "2026-09-21T06:41:38.663965+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-20T05:31:42.868717+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4971506", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "vllm-customized", "lastSyncTime": "2026-09-21T06:41:38.663950+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-20T05:31:42.867294+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4971507", "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": "transformers", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "transformers", "lastSyncTime": "2026-09-20T13:30:42.155956+00:00", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8674988799, "estimatedRequiredGiB": 9.718, "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": 8695119291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2415484144, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:qwen3-5", "custom_tag:9b", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8695119291}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T05:16:13.358703+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971314", "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", "framework": "vllm", "lastSyncTime": "2026-09-20T13:30:42.156020+00:00", "modelId": "BAAI/RoboBrain2.5-8B-MT", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918174, "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": 17545918174}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T05:16:13.351034+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971313", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-20T13:30:42.156007+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663396475}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T05:16:13.330122+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971312", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "transformers", "lastSyncTime": "2026-09-20T13:30:42.155996+00:00", "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelProfile": {"architectures": ["Mistral3ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17367755740, "estimatedRequiredGiB": 19.429, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral3", "modelscopeFileSize": 17385072379, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4929899520, "modelscopeTags": ["license:apache-2.0", "model_type:mistral3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:mistral", "custom_tag:mistral3", "custom_tag:devstral"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17385072379}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T05:16:13.323221+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971310", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "transformers", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "transformers", "lastSyncTime": "2026-09-20T13:30:42.155942+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293473597, "estimatedRequiredGiB": 18.233, "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": 16314185171, "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:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16314185171}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T05:16:13.300793+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971309", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T13:30:42.155978+00:00", "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5222073830, "estimatedRequiredGiB": 5.872, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5254590634, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1140034851, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5254590634}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T05:16:13.160907+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971308", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "transformers", "lastSyncTime": "2026-09-20T13:30:42.155893+00:00", "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7486327132, "estimatedRequiredGiB": 8.403, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 7518908360, "modelscopeLicense": "gemma", "modelscopeParams": 2227418442, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7518908360}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T05:16:13.158936+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971302", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T13:30:42.155916+00:00", "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9003966484, "estimatedRequiredGiB": 10.099, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 9036402901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2463563824, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9036402901}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T05:16:13.156477+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971306", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "transformers", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "transformers", "lastSyncTime": "2026-09-20T13:30:42.155934+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683239637, "estimatedRequiredGiB": 23.138, "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": 20703971805, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703971805}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T05:16:13.154796+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971307", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "transformers", "lastSyncTime": "2026-09-20T13:30:42.155926+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T05:16:13.151906+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971301", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "transformers", "lastSyncTime": "2026-09-20T13:30:42.155962+00:00", "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5226595850, "estimatedRequiredGiB": 5.878, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5259113427, "modelscopeLicense": "gemma", "modelscopeParams": 1141165347, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5259113427}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T05:16:13.149648+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971305", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "transformers", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "transformers", "lastSyncTime": "2026-09-20T13:30:42.156026+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683241105, "estimatedRequiredGiB": 23.138, "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": 20703487237, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703487237}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T05:16:13.144215+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971303", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T13:30:42.156013+00:00", "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21855018733, "estimatedRequiredGiB": 24.461, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 21887495988, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6144703054, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21887495988}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T05:16:13.142829+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971299", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "transformers", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "transformers", "lastSyncTime": "2026-09-20T13:30:42.155990+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474987, "estimatedRequiredGiB": 18.232, "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": 16313701503, "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:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16313701503}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T05:16:13.140867+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971304", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T13:30:42.156001+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25593158704, "estimatedRequiredGiB": 28.626, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 25613691403, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7626590448, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25613691403}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T05:16:13.139470+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971297", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T13:30:42.155948+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21930054875, "estimatedRequiredGiB": 24.532, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21950415614, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6024588416, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21950415614}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T05:16:13.138764+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971298", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T13:30:42.155984+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 23556606333}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T05:16:13.136785+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971300", "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_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-21T11:15:42.052921+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955857175}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T05:00:40.870810+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4971125", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T20:49:19.683254+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-20T04:46:07.939821+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970952", "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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["mistral3"], "framework": "vllm", "lastSyncTime": "2026-09-21T04:36:00.569168+00:00", "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelProfile": {"architectures": ["Mistral3ForConditionalGeneration"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17367755740, "estimatedRequiredGiB": 19.429, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral3", "modelscopeFileSize": 17385072379, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4929899520, "modelscopeTags": ["license:apache-2.0", "model_type:mistral3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:mistral", "custom_tag:mistral3", "custom_tag:devstral"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17385072379}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:42:19.140494+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970923", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:58:28.353121+00:00", "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7486327132, "estimatedRequiredGiB": 8.403, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 7518908360, "modelscopeLicense": "gemma", "modelscopeParams": 2227418442, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7518908360}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:42:19.137834+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970925", "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": ["gemma4_unified"], "framework": "vllm", "lastSyncTime": "2026-09-21T15:02:24.876330+00:00", "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9003966484, "estimatedRequiredGiB": 10.099, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 9036402901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2463563824, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9036402901}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:42:19.135971+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970924", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-20T04:34:35.568144+00:00", "modelId": "AI-ModelScope/granite-20b-code-instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-20T04:31:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079070", "taskType": "text-generation", "verifyResult": 1}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "vllm-customized", "lastSyncTime": "2026-09-21T06:41:38.663994+00:00", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-20T04:31:05.754543+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970791", "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", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:46:14.462925+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663396475}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:31:05.666143+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970790", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:46:14.462980+00:00", "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5226595850, "estimatedRequiredGiB": 5.878, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5259113427, "modelscopeLicense": "gemma", "modelscopeParams": 1141165347, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5259113427}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:27:06.277205+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970734", "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, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T13:30:37.066051+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:26:58.076866+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970733", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:46:14.462946+00:00", "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelProfile": {"architectures": ["Mistral3ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17367755740, "estimatedRequiredGiB": 19.429, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral3", "modelscopeFileSize": 17385072379, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4929899520, "modelscopeTags": ["license:apache-2.0", "model_type:mistral3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:mistral", "custom_tag:mistral3", "custom_tag:devstral"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17385072379}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:26:45.153348+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970732", "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": ["gemma4_unified"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:46:14.462967+00:00", "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9003966484, "estimatedRequiredGiB": 10.099, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 9036402901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2463563824, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9036402901}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:26:45.138158+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970728", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 24.0, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-21T17:22:47.256921+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:19:00.606791+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970641", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "vllm-customized", "lastSyncTime": "2026-09-21T06:41:38.663980+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-20T04:15:36.979619+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970617", "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-mlu", "lastSyncTime": "2026-09-21T08:44:09.587559+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663396475}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:15:36.970472+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970618", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:34:29.856403+00:00", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8674988799, "estimatedRequiredGiB": 9.718, "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": 8695119291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2415484144, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:qwen3-5", "custom_tag:9b", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8695119291}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:15:36.958375+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970614", "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": "transformers", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "transformers", "lastSyncTime": "2026-09-20T12:34:29.856377+00:00", "modelId": "BAAI/RoboBrain2.5-8B-MT", "modelProfile": {"architectures": ["Qwen3VLForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17534339552, "estimatedRequiredGiB": 19.609, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_vl", "modelscopeFileSize": 17545918174, "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": 17545918174}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:15:36.954828+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970615", "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-customized", "lastSyncTime": "2026-09-21T10:57:20.777281+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.621, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345554722, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345554722}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:14:42.081414+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970595", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-21T08:44:09.587595+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248516007, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248516007}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:14:42.077355+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970592", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-21T02:15:17.867294+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.622, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345693224, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345693224}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:14:42.074603+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970596", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-21T15:02:24.876374+00:00", "modelId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7d3121b7c0c577ab2334a07716695ad3f4016fc14badec71a6e0fbffc883b16d", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236742, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "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": 223236742}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:14:42.070470+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970598", "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", "lastSyncTime": "2026-09-21T04:51:55.164941+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:14:42.066492+00:00", "targetGpu": "MetaX_c-500", "taskId": "4970593", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-09-21T17:22:47.256854+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7686303632, "estimatedRequiredGiB": 8.592, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 7688299781, "modelscopeLicense": "llama2", "modelscopeParams": 13960238080, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7688299781}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:14:41.857836+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970585", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:34:29.856389+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {"architectures": ["AquilaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6968, "estimatedRequiredGiB": 18.386, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "aquila3", "modelscopeFileSize": 16451477782, "modelscopeLicense": "other", "modelscopeParams": 8223748096, "modelscopeTags": ["license:other", "model_type:aquila3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:arxiv:2406.12182"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16451477782}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:14:41.855366+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970587", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T10:57:20.777256+00:00", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2263018168, "estimatedRequiredGiB": 2.532, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 2265562651, "modelscopeLicense": "llama2", "modelscopeParams": 3821079552, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2265562651}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:14:41.850857+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970583", "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": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-20T14:34:57.856723+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504850, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504850}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:14:41.848764+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970580", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-20T12:34:29.856361+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955963132, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955963132}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:14:41.846486+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970590", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T20:49:19.683371+00:00", "modelId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8708787584, "estimatedRequiredGiB": 9.746, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 8720442075, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7615616512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8720442075}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:14:41.836936+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970582", "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_tokenizer_patch", "lastSyncTime": "2026-09-21T15:02:24.876390+00:00", "modelId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161034, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161034}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:14:34.909060+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970575", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-21T04:36:00.569113+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663410366, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663410366}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:10:03.083968+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970513", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:58:28.353096+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788663591}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:09:56.550329+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970503", "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": "2026-09-20T15:32:19.355892+00:00", "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221588, "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": 8338221588}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:09:56.548188+00:00", "targetGpu": "Biren_166m", "taskId": "4970505", "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": ["lfm2_moe"], "framework": "vllm", "lastSyncTime": "2026-09-21T04:51:55.164933+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16936006912, "estimatedRequiredGiB": 18.948, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 16953948786, "modelscopeLicense": "other", "modelscopeParams": 8467856832, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16953948786}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:09:56.546014+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970502", "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": "2026-09-20T19:47:52.978254+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "f7d2aee0bcf1396cd8ab3b1064b6a032eccc04f2d655a336023e13528574903d", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5469228368, "estimatedRequiredGiB": 6.118, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-20T04:09:56.541899+00:00", "targetGpu": "Biren_166m", "taskId": "4970509", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:34:29.856396+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-Research", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "17a693aa8ae65d96fb0c459d2e1f98ce1d8b2f8933e06b75903df1a5b48287eb", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008118474, "modelscopeLicense": "cc-by-nc-sa-4.0", "modelscopeParams": 7501651968, "modelscopeTags": ["license:cc-by-nc-sa-4.0", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008118474}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:09:56.540284+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970507", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:34:29.856340+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:09:56.493446+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970510", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-09-21T11:15:42.052833+00:00", "modelId": "pfnet/plamo-3-nict-8b-base", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16182734928, "estimatedRequiredGiB": 18.09, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 16186391993, "modelscopeLicense": "other", "modelscopeParams": 8091348992, "modelscopeTags": ["license:other", "model_type:plamo3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16186391993}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:09:56.487931+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970506", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3"], "framework": "vllm", "lastSyncTime": "2026-09-20T22:24:01.251292+00:00", "modelId": "whcl412/mlx-LycheeAI-coder-1.7b", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 968080210, "estimatedRequiredGiB": 1.095, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 979581804, "modelscopeLicense": "apache-2.0", "modelscopeParams": 268944384, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:coder", "custom_tag:lora", "custom_tag:code", "custom_tag:lychee", "custom_tag:finetune", "custom_tag:multilingual"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 979581804}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:52.200512+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970447", "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": ["muse_glimmer"], "framework": "vllm", "lastSyncTime": "2026-09-21T02:15:17.867369+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:52.182815+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970446", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T08:44:09.587529+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.352471+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970443", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T23:08:35.573468+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.350050+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970442", "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": ["zaya"], "framework": "vllm", "lastSyncTime": "2026-09-20T17:09:45.266103+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463197, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463197}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.346171+00:00", "targetGpu": "Biren_166m", "taskId": "4970445", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T04:51:55.164906+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109841981, "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": "awq", "repositoryOnDiskBytes": 2109841981}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.344449+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970441", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T22:27:36.960842+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.342540+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970435", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T04:51:55.164837+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "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": 1426233716, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "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": 1426233716}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.341085+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970438", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T22:27:36.960871+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.338954+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970440", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T10:57:20.777292+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "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": 7550622334}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.337459+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970434", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:21:49.901701+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.335178+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970437", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.902137+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21561882284, "estimatedRequiredGiB": 24.122, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 21583784354, "modelscopeLicense": "other", "modelscopeParams": 17820210764, "modelscopeTags": ["license:other", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21583784354}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:41.340891+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970366", "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": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "transformers", "lastSyncTime": "2026-09-20T12:21:49.902066+00:00", "modelId": "sapientinc/HRM-Text-1B", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2365606568, "estimatedRequiredGiB": 2.651, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 2371660433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1182795264, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:hrm", "custom_tag:hierarchical-reasoning", "custom_tag:prefix-lm", "custom_tag:pre-alignment", "custom_tag:non-chat", "custom_tag:non-instruction-tuned"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2371660433}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:41.338170+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970365", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901832+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474987, "estimatedRequiredGiB": 18.232, "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": 16313701503, "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:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16313701503}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:41.335892+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970367", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901876+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "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": 3430847031, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "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": null, "repositoryOnDiskBytes": 3430847031}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:41.302188+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970362", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901942+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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": "failed", "status": "success", "submitTime": "2026-09-20T03:58:41.300812+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970363", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901677+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293473597, "estimatedRequiredGiB": 18.233, "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": 16314185171, "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:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16314185171}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:41.299123+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970361", "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": ["gemma4"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:21:49.901731+00:00", "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5222073830, "estimatedRequiredGiB": 5.872, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5254590634, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1140034851, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5254590634}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:35.464742+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970359", "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": ["gemma4"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:21:49.902144+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 23556606333}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:35.460457+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970350", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-21T01:35:45.556133+00:00", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-20T03:58:35.458351+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970351", "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", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.902097+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "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": 8239718268, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "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": null, "repositoryOnDiskBytes": 8239718268}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:35.457045+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970357", "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": ["gemma4"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:21:49.901805+00:00", "modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21855018733, "estimatedRequiredGiB": 24.461, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 21887495988, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6144703054, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21887495988}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:35.451794+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970348", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901895+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683241105, "estimatedRequiredGiB": 23.138, "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": 20703487237, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703487237}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:35.449495+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970352", "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": "2026-09-21T03:25:53.878060+00:00", "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615496, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615496}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:57:37.934664+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970335", "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": "2026-09-21T10:57:20.777339+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:57:37.904873+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970336", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm-customized", "lastSyncTime": "2026-09-21T17:22:47.256960+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14864536516, "estimatedRequiredGiB": 16.635, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 14884986381, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3818458992, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14884986381}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:57:37.896737+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970334", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-21T11:15:42.052853+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504850, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504850}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:57:37.844895+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970333", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:08:06.464776+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.621, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345554722, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345554722}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:57:37.837081+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970332", "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, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:08:06.464814+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248516007, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248516007}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:57:37.834872+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970331", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T22:27:36.960757+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {"architectures": ["AquilaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6968, "estimatedRequiredGiB": 18.386, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "aquila3", "modelscopeFileSize": 16451477782, "modelscopeLicense": "other", "modelscopeParams": 8223748096, "modelscopeTags": ["license:other", "model_type:aquila3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:arxiv:2406.12182"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16451477782}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:57:37.823809+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970329", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:08:06.464803+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.622, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345693224, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345693224}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:57:37.819101+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970330", "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", "failureUnsupportedArchitectures": ["NemotronHForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-21T04:36:00.569246+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19342796520, "estimatedRequiredGiB": 21.64, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 19362750397, "modelscopeLicense": "other", "modelscopeParams": 18237772608, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19362750397}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:57:37.815898+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970328", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-20T20:49:19.683358+00:00", "modelId": "RedHatAI/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093325064, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093325064}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:57:37.806607+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970326", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T20:31:51.861095+00:00", "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19935028960, "estimatedRequiredGiB": 22.299, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 19953127685, "modelscopeLicense": "mit", "modelscopeParams": 32762123264, "modelscopeTags": ["license:mit", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 19953127685}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:57:37.777020+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970324", "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": ["lfm2"], "framework": "vllm", "lastSyncTime": "2026-09-21T11:15:42.052910+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955963132, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955963132}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:57:37.773695+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970322", "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_tokenizer_patch", "lastSyncTime": "2026-09-21T15:02:24.876345+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16564748304, "estimatedRequiredGiB": 18.516, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 16568142341, "modelscopeLicense": "other", "modelscopeParams": 15957889024, "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": 16568142341}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:57:31.484685+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970312", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "repository_structure", "failureAction": "require_framework_specific_root_files", "failureCategory": "repository_structure", "failureClassificationReason": "structured_missing_files", "failureCode": "MODEL_FILE_NOT_FOUND", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T16:21:18.661407+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-Research", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "ecd31d4ed4e0e92b9deabe3de0f18c75dc252004ba68826e4cfd561549549074", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008118474, "modelscopeLicense": "cc-by-nc-sa-4.0", "modelscopeParams": 7501651968, "modelscopeTags": ["license:cc-by-nc-sa-4.0", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008118474}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:53:33.643969+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970234", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T22:43:47.754882+00:00", "modelId": "IntervitensInc/kek_mk3", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3289069288, "estimatedRequiredGiB": 3.683, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 3295875324, "modelscopeLicense": null, "modelscopeParams": 1644515328, "modelscopeTags": ["model_type:stablelm", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3295875324}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:46:35.813804+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970120", "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": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-20T14:14:39.678925+00:00", "modelId": "aisingapore/SEA-LION-v1-7B", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "0335c7e4668aaa963303ebe91f80d6eb1e7e8d0299011bd85f7e05a4df031dc7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008115847, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008115847}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:46:35.801267+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970119", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T17:09:45.266093+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29274355224, "estimatedRequiredGiB": 32.761, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 29314389092, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 29314389092}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:46:35.789758+00:00", "targetGpu": "Biren_166m", "taskId": "4970118", "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": ["zaya"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:01:00.671056+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463197, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463197}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:46:35.783924+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970117", "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": ["muse_glimmer"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T13:58:33.470413+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:46:29.643802+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970111", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:01:00.670830+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21930054875, "estimatedRequiredGiB": 24.532, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21950415614, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6024588416, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21950415614}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:46:29.635942+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970115", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm-customized", "lastSyncTime": "2026-09-20T22:27:36.960800+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "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": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.651764+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970045", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm-customized", "lastSyncTime": "2026-09-21T04:51:55.164962+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "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": 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": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.636924+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970040", "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": ["gemma4"], "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-21T14:32:55.759813+00:00", "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5226595850, "estimatedRequiredGiB": 5.878, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5259113427, "modelscopeLicense": "gemma", "modelscopeParams": 1141165347, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5259113427}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.472121+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970033", "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": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "transformers", "lastSyncTime": "2026-09-20T12:01:00.670989+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "0335c7e4668aaa963303ebe91f80d6eb1e7e8d0299011bd85f7e05a4df031dc7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361928, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008164431, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008164431}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.365180+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970023", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671049+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20628596944, "estimatedRequiredGiB": 23.076, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 20647674585, "modelscopeLicense": "other", "modelscopeParams": 33943909952, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:int4", "custom_tag:int8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:mamba", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20647674585}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.339898+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970022", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:01:00.670660+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23420419700, "estimatedRequiredGiB": 26.214, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23455515266, "modelscopeLicense": "mit", "modelscopeParams": 19528501104, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 23455515266}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.302550+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970020", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:01:00.670747+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574767, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574767}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.299361+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970021", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671326+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14864536516, "estimatedRequiredGiB": 16.635, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 14884986381, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3818458992, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14884986381}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.297736+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970018", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671111+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683239637, "estimatedRequiredGiB": 23.138, "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": 20703971805, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703971805}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.292011+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970019", "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, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671190+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794426, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4205751296, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794426}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.160353+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970010", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T17:09:45.266141+00:00", "modelId": "OpenBMB/BitCPM-CANN-8B", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16370604914, "estimatedRequiredGiB": 18.305, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm", "modelscopeFileSize": 16378634956, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm", "library:pytorch", "library:transformer", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16378634956}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.155389+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970012", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T12:09:51.363789+00:00", "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19935028960, "estimatedRequiredGiB": 22.299, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 19953127685, "modelscopeLicense": "mit", "modelscopeParams": 32762123264, "modelscopeTags": ["license:mit", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 19953127685}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.153153+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4970011", "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", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-20T22:43:47.754917+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "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": 3430847031, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "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": null, "repositoryOnDiskBytes": 3430847031}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.149678+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970015", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T11:35:03.480257+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.145647+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4970009", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T16:51:24.761950+00:00", "modelId": "sapientinc/HRM-Text-1B", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2365606568, "estimatedRequiredGiB": 2.651, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 2371660433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1182795264, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:hrm", "custom_tag:hierarchical-reasoning", "custom_tag:prefix-lm", "custom_tag:pre-alignment", "custom_tag:non-chat", "custom_tag:non-instruction-tuned"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2371660433}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.140281+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970016", "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", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-20T16:47:50.886473+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "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": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.138985+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970013", "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", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-20T16:47:50.886464+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "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": 8239718268, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "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": null, "repositoryOnDiskBytes": 8239718268}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.135089+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970008", "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": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-20T15:25:28.950050+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21561882284, "estimatedRequiredGiB": 24.122, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 21583784354, "modelscopeLicense": "other", "modelscopeParams": 17820210764, "modelscopeTags": ["license:other", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21583784354}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.061655+00:00", "targetGpu": "Biren_166m", "taskId": "4970007", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T02:15:17.867324+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-20T03:41:49.051083+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970006", "taskType": "text-generation", "verifyResult": null}
|
||||||
1141
.modelhub_state/recovery_active_tasks.jsonl
Normal file
1141
.modelhub_state/recovery_active_tasks.jsonl
Normal file
File diff suppressed because it is too large
Load Diff
2565
.modelhub_state/recovery_intents.jsonl
Normal file
2565
.modelhub_state/recovery_intents.jsonl
Normal file
File diff suppressed because it is too large
Load Diff
45
.modelhub_state/routing_intelligence.json
Normal file
45
.modelhub_state/routing_intelligence.json
Normal file
@@ -0,0 +1,45 @@
|
|||||||
|
{
|
||||||
|
"acceptedByCategory": {
|
||||||
|
"unified_success_first": 2341
|
||||||
|
},
|
||||||
|
"acceptedByRoute": {
|
||||||
|
"text-generation|Ascend_910-b3|llamacpp": 17,
|
||||||
|
"text-generation|Ascend_910-b3|vllm": 40,
|
||||||
|
"text-generation|Ascend_910-b3|vllm_tokenizer_patch": 165,
|
||||||
|
"text-generation|Ascend_910-b4|llamacpp": 13,
|
||||||
|
"text-generation|Ascend_910-b4|vllm": 28,
|
||||||
|
"text-generation|Ascend_910-b4|vllm_tokenizer_patch": 151,
|
||||||
|
"text-generation|Biren_166m|vllm": 81,
|
||||||
|
"text-generation|Biren_166m|vllm_fix_tokenizer": 130,
|
||||||
|
"text-generation|Cambricon_mlu-370-x4|vllm": 72,
|
||||||
|
"text-generation|Cambricon_mlu-370-x4|vllm-customized": 6,
|
||||||
|
"text-generation|Cambricon_mlu-370-x4|vllm-mlu": 89,
|
||||||
|
"text-generation|Cambricon_mlu-370-x8|vllm": 55,
|
||||||
|
"text-generation|Cambricon_mlu-370-x8|vllm-customized": 70,
|
||||||
|
"text-generation|Cambricon_mlu-370-x8|vllm-mlu": 97,
|
||||||
|
"text-generation|Iluvatar_bi-100|transformers": 20,
|
||||||
|
"text-generation|Iluvatar_bi-150|llamacpp": 16,
|
||||||
|
"text-generation|Iluvatar_bi-150|transformers": 45,
|
||||||
|
"text-generation|Iluvatar_bi-150|vllm": 10,
|
||||||
|
"text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 102,
|
||||||
|
"text-generation|Iluvatar_bi-150|vllm_fix_tokenizer": 57,
|
||||||
|
"text-generation|Iluvatar_bi-150|vllm_tokenizer_patch": 14,
|
||||||
|
"text-generation|Iluvatar_mrv-100|vllm": 63,
|
||||||
|
"text-generation|Kunlunxin_p-800|vllm": 62,
|
||||||
|
"text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 187,
|
||||||
|
"text-generation|Kunlunxin_p-800|vllm_tokenizer_patch": 91,
|
||||||
|
"text-generation|MetaX_c-500|vllm": 105,
|
||||||
|
"text-generation|Mthreads_s4000|llamacpp": 17,
|
||||||
|
"text-generation|Mthreads_s4000|vllm": 106,
|
||||||
|
"text-generation|Sunrise_pt-200-x1|vllm": 85,
|
||||||
|
"text-generation|Sunrise_pt-200-x1|vllm_fix_tokenizer": 94,
|
||||||
|
"text-generation|Vastai_va16|vllm_fix_tokenizer": 75,
|
||||||
|
"text-generation|hygon_k100-ai|llamacpp": 18,
|
||||||
|
"text-generation|hygon_k100-ai|vllm": 26,
|
||||||
|
"text-generation|hygon_k100-ai|vllm-patch-tokenizer": 134
|
||||||
|
},
|
||||||
|
"acceptedSinceRefresh": 2341,
|
||||||
|
"acceptedTotal": 2341,
|
||||||
|
"generatedAt": "2026-09-21T18:17:49.831178+00:00",
|
||||||
|
"version": 1
|
||||||
|
}
|
||||||
147
.modelhub_state/submission_exclusions.jsonl
Normal file
147
.modelhub_state/submission_exclusions.jsonl
Normal file
@@ -0,0 +1,147 @@
|
|||||||
|
{"firstSeenAt": "2026-09-04T03:57:23.797048+00:00", "lastSeenAt": "2026-09-04T03:57:23.797048+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
|
||||||
|
{"firstSeenAt": "2026-09-04T03:57:29.674890+00:00", "lastSeenAt": "2026-09-04T03:57:29.674890+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Biren_166m"}
|
||||||
|
{"firstSeenAt": "2026-09-04T03:57:35.573847+00:00", "lastSeenAt": "2026-09-04T03:57:35.573847+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_mrv-100"}
|
||||||
|
{"firstSeenAt": "2026-09-04T03:57:49.185347+00:00", "lastSeenAt": "2026-09-04T03:57:49.185347+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
|
||||||
|
{"firstSeenAt": "2026-09-04T03:57:54.410921+00:00", "lastSeenAt": "2026-09-04T03:57:54.410921+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
|
||||||
|
{"firstSeenAt": "2026-09-04T03:57:59.490195+00:00", "lastSeenAt": "2026-09-04T03:57:59.490195+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
|
||||||
|
{"firstSeenAt": "2026-09-04T04:29:16.979261+00:00", "lastSeenAt": "2026-09-04T04:29:16.979261+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Sunrise_pt-200-x1"}
|
||||||
|
{"firstSeenAt": "2026-09-04T04:40:16.591240+00:00", "lastSeenAt": "2026-09-04T04:40:16.591240+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
|
||||||
|
{"firstSeenAt": "2026-09-04T06:49:06.281179+00:00", "lastSeenAt": "2026-09-04T06:49:06.281179+00:00", "modelId": "voconly/Qwen3-ASR-1.7B-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
|
||||||
|
{"firstSeenAt": "2026-09-04T07:00:32.615126+00:00", "lastSeenAt": "2026-09-04T07:00:32.615126+00:00", "modelId": "voconly/whisper-large-v3-turbo-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
|
||||||
|
{"firstSeenAt": "2026-09-04T07:00:32.616924+00:00", "lastSeenAt": "2026-09-04T07:00:32.616924+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
|
||||||
|
{"firstSeenAt": "2026-09-04T07:09:19.413394+00:00", "lastSeenAt": "2026-09-04T07:09:19.413394+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
|
||||||
|
{"firstSeenAt": "2026-09-04T07:16:43.841046+00:00", "lastSeenAt": "2026-09-04T07:16:43.841046+00:00", "modelId": "ggml-org/gpt-oss-20b-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
|
||||||
|
{"firstSeenAt": "2026-09-04T08:11:10.291594+00:00", "lastSeenAt": "2026-09-04T08:11:10.291594+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "MetaX_c-500"}
|
||||||
|
{"firstSeenAt": "2026-09-04T09:45:23.171369+00:00", "lastSeenAt": "2026-09-04T09:45:23.171369+00:00", "modelId": "voconly/whisper-large-v3-turbo-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
|
||||||
|
{"firstSeenAt": "2026-09-04T10:14:22.495811+00:00", "lastSeenAt": "2026-09-04T10:14:22.495811+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
|
||||||
|
{"firstSeenAt": "2026-09-04T11:55:25.074530+00:00", "lastSeenAt": "2026-09-04T11:55:25.074530+00:00", "modelId": "ggml-org/gpt-oss-20b-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
|
||||||
|
{"firstSeenAt": "2026-09-04T11:55:25.076100+00:00", "lastSeenAt": "2026-09-04T11:55:25.076100+00:00", "modelId": "RedHatAI/Qwen3.6-35B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
|
||||||
|
{"firstSeenAt": "2026-09-04T12:57:48.331515+00:00", "lastSeenAt": "2026-09-04T12:57:48.331515+00:00", "modelId": "voconly/Qwen3-ASR-1.7B-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
|
||||||
|
{"firstSeenAt": "2026-09-04T12:57:48.333103+00:00", "lastSeenAt": "2026-09-04T12:57:48.333103+00:00", "modelId": "ggml-org/gpt-oss-20b-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
|
||||||
|
{"firstSeenAt": "2026-09-04T13:21:50.254157+00:00", "lastSeenAt": "2026-09-04T13:21:50.254157+00:00", "modelId": "voconly/Qwen3-ASR-1.7B-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
|
||||||
|
{"firstSeenAt": "2026-09-04T13:40:36.168451+00:00", "lastSeenAt": "2026-09-04T13:40:36.168451+00:00", "modelId": "RedHatAI/Ornith-1.0-35B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
|
||||||
|
{"firstSeenAt": "2026-09-04T14:13:43.429448+00:00", "lastSeenAt": "2026-09-04T14:13:43.429448+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Sunrise_pt-200-x1"}
|
||||||
|
{"firstSeenAt": "2026-09-04T16:30:38.120052+00:00", "lastSeenAt": "2026-09-04T16:30:38.120052+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
|
||||||
|
{"firstSeenAt": "2026-09-04T16:49:34.985609+00:00", "lastSeenAt": "2026-09-04T16:49:34.985609+00:00", "modelId": "voconly/whisper-large-v3-turbo-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
|
||||||
|
{"firstSeenAt": "2026-09-04T16:59:32.121822+00:00", "lastSeenAt": "2026-09-04T16:59:32.121822+00:00", "modelId": "voconly/Qwen3-ASR-1.7B-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
|
||||||
|
{"firstSeenAt": "2026-09-04T17:30:31.477117+00:00", "lastSeenAt": "2026-09-04T17:30:31.477117+00:00", "modelId": "voconly/whisper-large-v3-turbo-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
|
||||||
|
{"firstSeenAt": "2026-09-04T18:10:12.844722+00:00", "lastSeenAt": "2026-09-04T18:10:12.844722+00:00", "modelId": "ggml-org/gpt-oss-20b-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
|
||||||
|
{"firstSeenAt": "2026-09-04T18:10:12.846446+00:00", "lastSeenAt": "2026-09-04T18:10:12.846446+00:00", "modelId": "RedHatAI/Ornith-1.0-35B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
|
||||||
|
{"firstSeenAt": "2026-09-04T18:31:29.728507+00:00", "lastSeenAt": "2026-09-04T18:31:29.728507+00:00", "modelId": "RedHatAI/Qwen3.6-35B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Sunrise_pt-200-x1"}
|
||||||
|
{"firstSeenAt": "2026-09-04T20:37:43.057350+00:00", "lastSeenAt": "2026-09-04T20:37:43.057350+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
|
||||||
|
{"firstSeenAt": "2026-09-04T20:46:08.566927+00:00", "lastSeenAt": "2026-09-04T20:46:08.566927+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
|
||||||
|
{"firstSeenAt": "2026-09-04T20:46:08.568661+00:00", "lastSeenAt": "2026-09-04T20:46:08.568661+00:00", "modelId": "RedHatAI/Ornith-1.0-35B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
|
||||||
|
{"firstSeenAt": "2026-09-04T21:01:14.928100+00:00", "lastSeenAt": "2026-09-04T21:01:14.928100+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
|
||||||
|
{"firstSeenAt": "2026-09-04T21:08:10.100427+00:00", "lastSeenAt": "2026-09-04T21:08:10.100427+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Cambricon_mlu-370-x4"}
|
||||||
|
{"firstSeenAt": "2026-09-04T21:17:56.214617+00:00", "lastSeenAt": "2026-09-04T21:17:56.214617+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Cambricon_mlu-370-x4"}
|
||||||
|
{"firstSeenAt": "2026-09-04T21:23:38.184741+00:00", "lastSeenAt": "2026-09-04T21:23:38.184741+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
|
||||||
|
{"firstSeenAt": "2026-09-04T21:34:39.157491+00:00", "lastSeenAt": "2026-09-04T21:34:39.157491+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Cambricon_mlu-370-x4"}
|
||||||
|
{"firstSeenAt": "2026-09-04T21:34:39.159318+00:00", "lastSeenAt": "2026-09-04T21:34:39.159318+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
|
||||||
|
{"firstSeenAt": "2026-09-04T21:34:39.160913+00:00", "lastSeenAt": "2026-09-04T21:34:39.160913+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
|
||||||
|
{"firstSeenAt": "2026-09-04T21:34:39.162060+00:00", "lastSeenAt": "2026-09-04T21:34:39.162060+00:00", "modelId": "RedHatAI/Qwen3.6-35B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
|
||||||
|
{"firstSeenAt": "2026-09-04T22:02:42.528424+00:00", "lastSeenAt": "2026-09-04T22:02:42.528424+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Cambricon_mlu-370-x4"}
|
||||||
|
{"firstSeenAt": "2026-09-04T22:02:42.530385+00:00", "lastSeenAt": "2026-09-04T22:02:42.530385+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
|
||||||
|
{"firstSeenAt": "2026-09-04T22:02:42.531558+00:00", "lastSeenAt": "2026-09-04T22:02:42.531558+00:00", "modelId": "RedHatAI/Ornith-1.0-35B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
|
||||||
|
{"firstSeenAt": "2026-09-04T22:08:39.423488+00:00", "lastSeenAt": "2026-09-04T22:08:39.423488+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
|
||||||
|
{"firstSeenAt": "2026-09-04T22:30:12.999411+00:00", "lastSeenAt": "2026-09-04T22:30:12.999411+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
|
||||||
|
{"firstSeenAt": "2026-09-04T23:01:40.210343+00:00", "lastSeenAt": "2026-09-04T23:01:40.210343+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
|
||||||
|
{"firstSeenAt": "2026-09-04T23:08:42.844010+00:00", "lastSeenAt": "2026-09-04T23:08:42.844010+00:00", "modelId": "RedHatAI/Qwen3.6-35B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
|
||||||
|
{"firstSeenAt": "2026-09-04T23:08:42.845836+00:00", "lastSeenAt": "2026-09-04T23:08:42.845836+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
|
||||||
|
{"firstSeenAt": "2026-09-04T23:08:42.847267+00:00", "lastSeenAt": "2026-09-04T23:08:42.847267+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
|
||||||
|
{"firstSeenAt": "2026-09-04T23:16:58.513168+00:00", "lastSeenAt": "2026-09-04T23:16:58.513168+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
|
||||||
|
{"firstSeenAt": "2026-09-04T23:24:51.833226+00:00", "lastSeenAt": "2026-09-04T23:24:51.833226+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
|
||||||
|
{"firstSeenAt": "2026-09-04T23:30:00.079681+00:00", "lastSeenAt": "2026-09-04T23:30:00.079681+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Cambricon_mlu-370-x8"}
|
||||||
|
{"firstSeenAt": "2026-09-05T00:50:30.239660+00:00", "lastSeenAt": "2026-09-05T00:50:30.239660+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Cambricon_mlu-370-x8"}
|
||||||
|
{"firstSeenAt": "2026-09-05T00:50:30.241369+00:00", "lastSeenAt": "2026-09-05T00:50:30.241369+00:00", "modelId": "RedHatAI/Qwen3.6-35B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Cambricon_mlu-370-x8"}
|
||||||
|
{"firstSeenAt": "2026-09-05T01:49:07.541676+00:00", "lastSeenAt": "2026-09-05T01:49:07.541676+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Cambricon_mlu-370-x8"}
|
||||||
|
{"firstSeenAt": "2026-09-05T02:29:40.646869+00:00", "lastSeenAt": "2026-09-05T02:29:40.646869+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Cambricon_mlu-370-x8"}
|
||||||
|
{"firstSeenAt": "2026-09-05T02:42:56.679757+00:00", "lastSeenAt": "2026-09-05T02:42:56.679757+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
|
||||||
|
{"firstSeenAt": "2026-09-05T02:42:56.681931+00:00", "lastSeenAt": "2026-09-05T02:42:56.681931+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Sunrise_pt-200-x1"}
|
||||||
|
{"firstSeenAt": "2026-09-05T03:05:39.090955+00:00", "lastSeenAt": "2026-09-05T03:05:39.090955+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_mrv-100"}
|
||||||
|
{"firstSeenAt": "2026-09-05T03:25:37.922974+00:00", "lastSeenAt": "2026-09-05T03:25:37.922974+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Cambricon_mlu-370-x8"}
|
||||||
|
{"firstSeenAt": "2026-09-05T04:43:13.695708+00:00", "lastSeenAt": "2026-09-05T04:43:13.695708+00:00", "modelId": "ggml-org/gpt-oss-20b-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
|
||||||
|
{"firstSeenAt": "2026-09-05T05:00:03.356500+00:00", "lastSeenAt": "2026-09-05T05:00:03.356500+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
|
||||||
|
{"firstSeenAt": "2026-09-05T05:07:39.434421+00:00", "lastSeenAt": "2026-09-05T05:07:39.434421+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_mrv-100"}
|
||||||
|
{"firstSeenAt": "2026-09-05T05:07:39.436263+00:00", "lastSeenAt": "2026-09-05T05:07:39.436263+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_mrv-100"}
|
||||||
|
{"firstSeenAt": "2026-09-05T05:07:39.437496+00:00", "lastSeenAt": "2026-09-05T05:07:39.437496+00:00", "modelId": "RedHatAI/Ornith-1.0-35B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_mrv-100"}
|
||||||
|
{"firstSeenAt": "2026-09-05T05:30:45.668136+00:00", "lastSeenAt": "2026-09-05T05:30:45.668136+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Sunrise_pt-200-x1"}
|
||||||
|
{"firstSeenAt": "2026-09-05T05:41:06.398285+00:00", "lastSeenAt": "2026-09-05T05:41:06.398285+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "MetaX_c-500"}
|
||||||
|
{"firstSeenAt": "2026-09-05T06:46:47.510402+00:00", "lastSeenAt": "2026-09-05T06:46:47.510402+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "MetaX_c-500"}
|
||||||
|
{"firstSeenAt": "2026-09-05T06:46:47.512965+00:00", "lastSeenAt": "2026-09-05T06:46:47.512965+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
|
||||||
|
{"firstSeenAt": "2026-09-05T06:48:38.735121+00:00", "lastSeenAt": "2026-09-05T06:48:38.735121+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
|
||||||
|
{"firstSeenAt": "2026-09-05T07:02:15.303839+00:00", "lastSeenAt": "2026-09-05T07:02:15.303839+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "MetaX_c-500"}
|
||||||
|
{"firstSeenAt": "2026-09-05T09:06:33.202864+00:00", "lastSeenAt": "2026-09-05T09:06:33.202864+00:00", "modelId": "RedHatAI/Qwen3.6-35B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "MetaX_c-500"}
|
||||||
|
{"firstSeenAt": "2026-09-05T09:06:33.205809+00:00", "lastSeenAt": "2026-09-05T09:06:33.205809+00:00", "modelId": "voconly/whisper-large-v3-turbo-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
|
||||||
|
{"firstSeenAt": "2026-09-05T13:08:37.631159+00:00", "lastSeenAt": "2026-09-05T13:08:37.631159+00:00", "modelId": "voconly/Qwen3-ASR-1.7B-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
|
||||||
|
{"firstSeenAt": "2026-09-05T13:08:37.633069+00:00", "lastSeenAt": "2026-09-05T13:08:37.633069+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
|
||||||
|
{"firstSeenAt": "2026-09-05T13:08:37.635738+00:00", "lastSeenAt": "2026-09-05T13:08:37.635738+00:00", "modelId": "RedHatAI/Ornith-1.0-35B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
|
||||||
|
{"firstSeenAt": "2026-09-05T13:44:34.395810+00:00", "lastSeenAt": "2026-09-05T13:44:34.395810+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
|
||||||
|
{"firstSeenAt": "2026-09-05T16:21:23.838028+00:00", "lastSeenAt": "2026-09-05T16:21:23.838028+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Vastai_va16"}
|
||||||
|
{"firstSeenAt": "2026-09-05T16:21:23.840026+00:00", "lastSeenAt": "2026-09-05T16:21:23.840026+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Vastai_va16"}
|
||||||
|
{"firstSeenAt": "2026-09-05T16:24:16.092553+00:00", "lastSeenAt": "2026-09-05T16:24:16.092553+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Vastai_va16"}
|
||||||
|
{"firstSeenAt": "2026-09-05T16:24:16.095538+00:00", "lastSeenAt": "2026-09-05T16:24:16.095538+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Vastai_va16"}
|
||||||
|
{"firstSeenAt": "2026-09-05T16:24:16.097321+00:00", "lastSeenAt": "2026-09-05T16:24:16.097321+00:00", "modelId": "RedHatAI/Ornith-1.0-35B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Vastai_va16"}
|
||||||
|
{"firstSeenAt": "2026-09-05T16:24:16.099063+00:00", "lastSeenAt": "2026-09-05T16:24:16.099063+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Vastai_va16"}
|
||||||
|
{"firstSeenAt": "2026-09-06T00:33:12.804105+00:00", "lastSeenAt": "2026-09-06T00:33:12.804105+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Sunrise_pt-200-x1"}
|
||||||
|
{"firstSeenAt": "2026-09-06T00:53:48.753329+00:00", "lastSeenAt": "2026-09-06T00:53:48.753329+00:00", "modelId": "RedHatAI/Ornith-1.0-35B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Sunrise_pt-200-x1"}
|
||||||
|
{"firstSeenAt": "2026-09-06T07:37:25.003613+00:00", "lastSeenAt": "2026-09-06T07:37:25.003613+00:00", "modelId": "RedHatAI/Ornith-1.0-35B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "MetaX_c-500"}
|
||||||
|
{"firstSeenAt": "2026-09-06T07:37:25.006232+00:00", "lastSeenAt": "2026-09-06T07:37:25.006232+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "MetaX_c-500"}
|
||||||
|
{"firstSeenAt": "2026-09-06T10:24:57.089879+00:00", "lastSeenAt": "2026-09-06T10:24:57.089879+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_mrv-100"}
|
||||||
|
{"firstSeenAt": "2026-09-06T14:05:08.261809+00:00", "lastSeenAt": "2026-09-06T14:05:08.261809+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
|
||||||
|
{"firstSeenAt": "2026-09-06T14:05:08.263848+00:00", "lastSeenAt": "2026-09-06T14:05:08.263848+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-70B-Instruct-quantized.w8a16", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
|
||||||
|
{"firstSeenAt": "2026-09-06T14:05:08.265533+00:00", "lastSeenAt": "2026-09-06T14:05:08.265533+00:00", "modelId": "RedHatAI/Qwen3.6-35B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
|
||||||
|
{"firstSeenAt": "2026-09-06T14:05:08.267292+00:00", "lastSeenAt": "2026-09-06T14:05:08.267292+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
|
||||||
|
{"firstSeenAt": "2026-09-06T14:05:08.268964+00:00", "lastSeenAt": "2026-09-06T14:05:08.268964+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-70B-Instruct-quantized.w8a8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
|
||||||
|
{"firstSeenAt": "2026-09-06T14:38:36.123200+00:00", "lastSeenAt": "2026-09-06T14:38:36.123200+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
|
||||||
|
{"firstSeenAt": "2026-09-06T14:58:20.797485+00:00", "lastSeenAt": "2026-09-06T14:58:20.797485+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
|
||||||
|
{"firstSeenAt": "2026-09-06T15:12:15.892392+00:00", "lastSeenAt": "2026-09-06T15:12:15.892392+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
|
||||||
|
{"firstSeenAt": "2026-09-06T15:33:09.054073+00:00", "lastSeenAt": "2026-09-06T15:33:09.054073+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
|
||||||
|
{"firstSeenAt": "2026-09-06T21:26:08.088507+00:00", "lastSeenAt": "2026-09-06T21:26:08.088507+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Sunrise_pt-200-x1"}
|
||||||
|
{"firstSeenAt": "2026-09-08T05:54:38.612488+00:00", "lastSeenAt": "2026-09-08T05:54:38.612488+00:00", "modelId": "Mungert/s1-mini-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
|
||||||
|
{"firstSeenAt": "2026-09-08T05:59:06.169776+00:00", "lastSeenAt": "2026-09-08T05:59:06.169776+00:00", "modelId": "Mungert/s1-mini-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
|
||||||
|
{"firstSeenAt": "2026-09-08T06:03:32.307449+00:00", "lastSeenAt": "2026-09-08T06:03:32.307449+00:00", "modelId": "Mungert/s1-mini-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
|
||||||
|
{"firstSeenAt": "2026-09-08T06:08:08.143999+00:00", "lastSeenAt": "2026-09-08T06:08:08.143999+00:00", "modelId": "Mungert/s1-mini-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
|
||||||
|
{"firstSeenAt": "2026-09-08T07:15:24.577472+00:00", "lastSeenAt": "2026-09-08T07:15:24.577472+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Biren_166m"}
|
||||||
|
{"firstSeenAt": "2026-09-08T07:15:24.580859+00:00", "lastSeenAt": "2026-09-08T07:15:24.580859+00:00", "modelId": "RedHatAI/Qwen3.6-35B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Biren_166m"}
|
||||||
|
{"firstSeenAt": "2026-09-08T07:15:24.583178+00:00", "lastSeenAt": "2026-09-08T07:15:24.583178+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Biren_166m"}
|
||||||
|
{"firstSeenAt": "2026-09-08T07:15:24.585248+00:00", "lastSeenAt": "2026-09-08T07:15:24.585248+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Biren_166m"}
|
||||||
|
{"firstSeenAt": "2026-09-08T07:15:24.587116+00:00", "lastSeenAt": "2026-09-08T07:15:24.587116+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Biren_166m"}
|
||||||
|
{"firstSeenAt": "2026-09-08T10:26:28.569398+00:00", "lastSeenAt": "2026-09-08T10:26:28.569398+00:00", "modelId": "Mungert/s1-mini-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
|
||||||
|
{"firstSeenAt": "2026-09-08T23:04:21.864681+00:00", "lastSeenAt": "2026-09-08T23:04:21.864681+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
|
||||||
|
{"firstSeenAt": "2026-09-09T07:39:29.213764+00:00", "lastSeenAt": "2026-09-09T07:39:29.213764+00:00", "modelId": "prithivMLmods/NeoHorse-1-4B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
|
||||||
|
{"firstSeenAt": "2026-09-09T07:39:34.797658+00:00", "lastSeenAt": "2026-09-09T07:39:34.797658+00:00", "modelId": "prithivMLmods/NeoHorse-1-4B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
|
||||||
|
{"firstSeenAt": "2026-09-09T08:00:24.606551+00:00", "lastSeenAt": "2026-09-09T08:00:24.606551+00:00", "modelId": "prithivMLmods/NeoHorse-1-4B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
|
||||||
|
{"firstSeenAt": "2026-09-09T16:11:23.152273+00:00", "lastSeenAt": "2026-09-09T16:11:23.152273+00:00", "modelId": "nv-community/Qwen3.8-27B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
|
||||||
|
{"firstSeenAt": "2026-09-09T16:13:12.582481+00:00", "lastSeenAt": "2026-09-09T16:13:12.582481+00:00", "modelId": "nv-community/Qwen3.8-27B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Vastai_va16"}
|
||||||
|
{"firstSeenAt": "2026-09-09T16:14:47.383659+00:00", "lastSeenAt": "2026-09-09T16:14:47.383659+00:00", "modelId": "nv-community/Qwen3.8-27B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
|
||||||
|
{"firstSeenAt": "2026-09-09T16:16:23.871046+00:00", "lastSeenAt": "2026-09-09T16:16:23.871046+00:00", "modelId": "nv-community/Qwen3.8-27B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Sunrise_pt-200-x1"}
|
||||||
|
{"firstSeenAt": "2026-09-09T16:24:21.658361+00:00", "lastSeenAt": "2026-09-09T16:24:21.658361+00:00", "modelId": "nv-community/Qwen3.8-27B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Biren_166m"}
|
||||||
|
{"firstSeenAt": "2026-09-09T21:08:33.555529+00:00", "lastSeenAt": "2026-09-09T21:08:33.555529+00:00", "modelId": "nv-community/Qwen3.8-27B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
|
||||||
|
{"firstSeenAt": "2026-09-10T02:01:15.114573+00:00", "lastSeenAt": "2026-09-10T02:01:15.114573+00:00", "modelId": "nv-community/Qwen3.8-27B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_mrv-100"}
|
||||||
|
{"firstSeenAt": "2026-09-11T02:10:43.554485+00:00", "lastSeenAt": "2026-09-11T02:10:43.554485+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
|
||||||
|
{"firstSeenAt": "2026-09-11T02:12:44.707423+00:00", "lastSeenAt": "2026-09-11T02:12:44.707423+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
|
||||||
|
{"firstSeenAt": "2026-09-11T02:14:19.387716+00:00", "lastSeenAt": "2026-09-11T02:14:19.387716+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
|
||||||
|
{"firstSeenAt": "2026-09-11T10:27:40.959383+00:00", "lastSeenAt": "2026-09-11T10:27:40.959383+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
|
||||||
|
{"firstSeenAt": "2026-09-11T10:27:40.963126+00:00", "lastSeenAt": "2026-09-11T10:27:40.963126+00:00", "modelId": "nv-community/Qwen3.8-27B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
|
||||||
|
{"firstSeenAt": "2026-09-11T18:18:45.194944+00:00", "lastSeenAt": "2026-09-11T18:18:45.194944+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
|
||||||
|
{"firstSeenAt": "2026-09-13T12:37:34.507858+00:00", "lastSeenAt": "2026-09-13T12:37:34.507858+00:00", "modelId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
|
||||||
|
{"firstSeenAt": "2026-09-13T12:39:25.361679+00:00", "lastSeenAt": "2026-09-13T12:39:25.361679+00:00", "modelId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
|
||||||
|
{"firstSeenAt": "2026-09-13T12:41:31.581405+00:00", "lastSeenAt": "2026-09-13T12:41:31.581405+00:00", "modelId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
|
||||||
|
{"firstSeenAt": "2026-09-13T12:43:37.058665+00:00", "lastSeenAt": "2026-09-13T12:43:37.058665+00:00", "modelId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
|
||||||
|
{"firstSeenAt": "2026-09-14T06:07:56.582360+00:00", "lastSeenAt": "2026-09-14T06:07:56.582360+00:00", "modelId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
|
||||||
|
{"firstSeenAt": "2026-09-17T06:45:23.859600+00:00", "lastSeenAt": "2026-09-17T06:45:23.859600+00:00", "modelId": "voconly/cohere-transcribe-03-2026-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
|
||||||
|
{"firstSeenAt": "2026-09-17T06:47:36.673155+00:00", "lastSeenAt": "2026-09-17T06:47:36.673155+00:00", "modelId": "voconly/cohere-transcribe-03-2026-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
|
||||||
|
{"firstSeenAt": "2026-09-17T06:49:28.195806+00:00", "lastSeenAt": "2026-09-17T06:49:28.195806+00:00", "modelId": "voconly/cohere-transcribe-03-2026-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
|
||||||
|
{"firstSeenAt": "2026-09-17T07:00:49.984555+00:00", "lastSeenAt": "2026-09-17T07:00:49.984555+00:00", "modelId": "voconly/cohere-transcribe-03-2026-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
|
||||||
|
{"firstSeenAt": "2026-09-17T16:35:07.265274+00:00", "lastSeenAt": "2026-09-17T16:35:07.265274+00:00", "modelId": "voconly/cohere-transcribe-03-2026-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
|
||||||
|
{"firstSeenAt": "2026-09-17T23:35:22.588690+00:00", "lastSeenAt": "2026-09-17T23:35:22.588690+00:00", "modelId": "cix/DeepSeek-R1-Distill-Qwen-7B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
|
||||||
|
{"firstSeenAt": "2026-09-17T23:37:50.189547+00:00", "lastSeenAt": "2026-09-17T23:37:50.189547+00:00", "modelId": "cix/DeepSeek-R1-Distill-Qwen-7B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
|
||||||
|
{"firstSeenAt": "2026-09-17T23:40:36.565884+00:00", "lastSeenAt": "2026-09-17T23:40:36.565884+00:00", "modelId": "cix/DeepSeek-R1-Distill-Qwen-7B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
|
||||||
|
{"firstSeenAt": "2026-09-17T23:43:06.974214+00:00", "lastSeenAt": "2026-09-17T23:43:06.974214+00:00", "modelId": "cix/DeepSeek-R1-Distill-Qwen-7B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
|
||||||
|
{"firstSeenAt": "2026-09-17T23:45:59.486412+00:00", "lastSeenAt": "2026-09-17T23:45:59.486412+00:00", "modelId": "cix/DeepSeek-R1-Distill-Qwen-7B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
|
||||||
|
{"firstSeenAt": "2026-09-18T14:29:14.550998+00:00", "lastSeenAt": "2026-09-18T14:29:14.550998+00:00", "modelId": "voconly/parakeet-unified-en-0.6b-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
|
||||||
|
{"firstSeenAt": "2026-09-18T14:31:05.762015+00:00", "lastSeenAt": "2026-09-18T14:31:05.762015+00:00", "modelId": "voconly/parakeet-unified-en-0.6b-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
|
||||||
|
{"firstSeenAt": "2026-09-18T14:33:31.396914+00:00", "lastSeenAt": "2026-09-18T14:33:31.396914+00:00", "modelId": "voconly/parakeet-unified-en-0.6b-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
|
||||||
|
{"firstSeenAt": "2026-09-18T14:35:12.101808+00:00", "lastSeenAt": "2026-09-18T14:35:12.101808+00:00", "modelId": "voconly/parakeet-unified-en-0.6b-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
|
||||||
|
{"firstSeenAt": "2026-09-19T04:58:26.462238+00:00", "lastSeenAt": "2026-09-19T04:58:26.462238+00:00", "modelId": "voconly/parakeet-unified-en-0.6b-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
|
||||||
|
{"firstSeenAt": "2026-09-20T20:09:24.505720+00:00", "lastSeenAt": "2026-09-20T20:09:24.505720+00:00", "modelId": "nv-community/Qwen3.8-27B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-100"}
|
||||||
12
.modelhub_state/worker_crashes.jsonl
Normal file
12
.modelhub_state/worker_crashes.jsonl
Normal file
@@ -0,0 +1,12 @@
|
|||||||
|
{"at": "2026-09-04T19:47:19.971266+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 57088.798}
|
||||||
|
{"at": "2026-09-05T12:16:49.970366+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 59364.493}
|
||||||
|
{"at": "2026-09-06T07:29:16.402335+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 69140.926}
|
||||||
|
{"at": "2026-09-07T02:37:48.598308+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 68906.425}
|
||||||
|
{"at": "2026-09-08T23:49:36.488354+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 162702.112}
|
||||||
|
{"at": "2026-09-09T12:29:14.196778+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 45572.202}
|
||||||
|
{"at": "2026-09-10T15:27:02.083554+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 97062.112}
|
||||||
|
{"at": "2026-09-12T02:15:23.274335+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 125295.685}
|
||||||
|
{"at": "2026-09-13T12:45:13.097016+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 124184.315}
|
||||||
|
{"at": "2026-09-15T00:49:16.402533+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 129837.798}
|
||||||
|
{"at": "2026-09-17T15:52:24.741372+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 115115.066}
|
||||||
|
{"at": "2026-09-21T02:52:07.812931+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 77812.055}
|
||||||
0
ledger/.submissions.jsonl.lock
Normal file
0
ledger/.submissions.jsonl.lock
Normal file
1217
ledger/submissions.jsonl
Normal file
1217
ledger/submissions.jsonl
Normal file
File diff suppressed because it is too large
Load Diff
25
manifest.json
Normal file
25
manifest.json
Normal file
@@ -0,0 +1,25 @@
|
|||||||
|
{
|
||||||
|
"agentVersion": "2026.09.20.2",
|
||||||
|
"checksums": {
|
||||||
|
".modelhub_state/account_capacity.json": "68d2a8390ad022f2ddcd30841f3860c4535387fa64cb46dc7507eb16837e798f",
|
||||||
|
".modelhub_state/architecture_compatibility_blacklist.json": "2b9181648a09ac2afa999768ac9b96628b74f238715bde3051fd766db137d640",
|
||||||
|
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||||
|
".modelhub_state/market_intelligence.json": "95233aefbf161d3eab7f5e32df2ef3160b9d0cd7ed0023552ab9c9f902172be9",
|
||||||
|
".modelhub_state/official_capabilities.json": "1478dfdbea2908b4fb7c5b2c9c118b4d383504917607fe319948113c7cf4266a",
|
||||||
|
".modelhub_state/outcome_checkpoint.json": "81dd36b94f937a502f565be1a60174a1147d10ebfef71751d29cc920416c3781",
|
||||||
|
".modelhub_state/queue_cleanup_latest.json": "96de561331568d32afa16a3d1299e6bf6ad1009a8239697991dc48f28baf298b",
|
||||||
|
".modelhub_state/recent_outcomes.jsonl": "761386dbe1a1cb3e15422a3ad1434c5c04e712a852e10c411c2eb3fa31e1698b",
|
||||||
|
".modelhub_state/recovery_active_tasks.jsonl": "6ca21906bd22528ce7f4b9602d3c9f3e1350ac4955880121d3cfbd8d43308878",
|
||||||
|
".modelhub_state/recovery_intents.jsonl": "ba983686a13e26e5c4ee0351a680b0e84c1f0ec7fb38964ea47ff63e9f0f493b",
|
||||||
|
".modelhub_state/routing_intelligence.json": "ed2e6d51b340642eaf3181120fefb6520c100b5bc2223f380036da6bae6fc2e4",
|
||||||
|
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
|
||||||
|
".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
|
||||||
|
"ledger/submissions.jsonl": "180959aec410053184a1001b337b8cd2ee3ebd63aafa2d4411ab200b2f3ba15b",
|
||||||
|
"outcomes/submissions.jsonl": "01738a680ce6f553218c5faade18a36382c24badca7d661f8c8912d55555e350"
|
||||||
|
},
|
||||||
|
"generation": 11601,
|
||||||
|
"phase": "intent",
|
||||||
|
"schemaVersion": 1,
|
||||||
|
"updatedAt": "2026-09-21T18:22:37.346309+00:00",
|
||||||
|
"writerId": "8b35139af6674067a339a670222d4b67"
|
||||||
|
}
|
||||||
0
outcomes/.submissions.jsonl.lock
Normal file
0
outcomes/.submissions.jsonl.lock
Normal file
1170
outcomes/submissions.jsonl
Normal file
1170
outcomes/submissions.jsonl
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user