state: generation 21766 (intent)

This commit is contained in:
2026-10-07 08:32:31 +00:00
parent cad83b5b73
commit 6dc489545b
8 changed files with 1277 additions and 1470 deletions

View File

@@ -2836,7 +2836,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-10-07T08:07:30.552062+00:00",
"generatedAt": "2026-10-07T08:25:52.414436+00:00",
"summary": {
"activeBlockCount": 143,
"byGpuFramework": {

View File

@@ -434,121 +434,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-07T08:19:16.157347+00:00",
"generatedAt": "2026-10-07T08:29:47.682399+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 948.1724137931035,
"backlogHours": 964.5263157894736,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.469071900897221,
"queueFactor": 1.0062214506918723,
"queueWeight": 1.0062214506918723,
"recentSuccess": 60,
"recentSuccessRate": 0.3448275862068966,
"recentTerminal": 174,
"recentWilsonLowerBound": 0.2782408051721546,
"running": 6,
"selectionWeight": 1.4782116592914682,
"qualityFactor": 1.2552116853519304,
"queueFactor": 1.0055125593507104,
"queueWeight": 1.0055125593507104,
"recentSuccess": 56,
"recentSuccessRate": 0.32748538011695905,
"recentTerminal": 171,
"recentWilsonLowerBound": 0.2616093048335577,
"running": 8,
"selectionWeight": 1.2621311142651381,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 29.0,
"waiting": 27497
"throughputPerHour": 28.5,
"waiting": 27489
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1287.557142857143,
"backlogHours": 1365.1818181818182,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.427325787956916,
"queueFactor": 0.9610847627316748,
"queueWeight": 0.9610847627316748,
"recentSuccess": 60,
"recentSuccessRate": 0.42857142857142855,
"recentTerminal": 140,
"recentWilsonLowerBound": 0.3495830563292003,
"qualityFactor": 2.497046033291262,
"queueFactor": 0.9544562746335599,
"queueWeight": 0.9544562746335599,
"recentSuccess": 58,
"recentSuccessRate": 0.4393939393939394,
"recentTerminal": 132,
"recentWilsonLowerBound": 0.35762697262501736,
"running": 8,
"selectionWeight": 2.3328658289910478,
"selectionWeight": 2.3833212545236857,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 23.333333333333332,
"waiting": 30043
"throughputPerHour": 22.0,
"waiting": 30034
},
"Biren_166m": {
"available": true,
"backlogHours": 146.14525139664806,
"backlogHours": 143.57142857142858,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.3202743409603834,
"qualityFactor": 0.3501994035833828,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 34,
"recentSuccessRate": 0.18994413407821228,
"recentTerminal": 179,
"recentWilsonLowerBound": 0.1392289348331716,
"recentSuccess": 36,
"recentSuccessRate": 0.1978021978021978,
"recentTerminal": 182,
"recentWilsonLowerBound": 0.14643755613925674,
"running": 8,
"selectionWeight": 0.4163566432484984,
"selectionWeight": 0.4552592246583977,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 29.833333333333332,
"waiting": 4360
"throughputPerHour": 30.333333333333332,
"waiting": 4355
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1511.0294117647059,
"backlogHours": 1510.941176470588,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.16834177661300936,
"queueFactor": 0.9382870689028943,
"queueWeight": 0.9382870689028943,
"recentSuccess": 12,
"recentSuccessRate": 0.17647058823529413,
"qualityFactor": 0.2550942009603913,
"queueFactor": 0.9400424770020223,
"queueWeight": 0.9400424770020223,
"recentSuccess": 14,
"recentSuccessRate": 0.20588235294117646,
"recentTerminal": 68,
"recentWilsonLowerBound": 0.10393485385088719,
"recentWilsonLowerBound": 0.12679446140967612,
"running": 7,
"selectionWeight": 0.15795291215212634,
"selectionWeight": 0.2397993845396579,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 11.333333333333334,
"waiting": 17125
"waiting": 17124
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 444.234375,
"backlogHours": 443.8125,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.49304285220012545,
"queueFactor": 1.1274176890492984,
"queueWeight": 1.1274176890492984,
"recentSuccess": 30,
"recentSuccessRate": 0.234375,
"qualityFactor": 0.3649631155454703,
"queueFactor": 1.129678028809856,
"queueWeight": 1.129678028809856,
"recentSuccess": 27,
"recentSuccessRate": 0.2109375,
"recentTerminal": 128,
"recentWilsonLowerBound": 0.16939254101487963,
"recentWilsonLowerBound": 0.1492121185502459,
"running": 7,
"selectionWeight": 0.5558652330297402,
"selectionWeight": 0.4122908129577106,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 21.333333333333332,
"waiting": 9477
"waiting": 9468
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 40.312896405919666,
"backlogHours": 41.20261437908497,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -558,59 +558,59 @@
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 10,
"recentSuccessRate": 0.021141649048625793,
"recentTerminal": 473,
"recentWilsonLowerBound": 0.011523352995050359,
"running": 4,
"recentSuccessRate": 0.02178649237472767,
"recentTerminal": 459,
"recentWilsonLowerBound": 0.011876075699460344,
"running": 6,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 78.83333333333333,
"waiting": 3178
"throughputPerHour": 76.5,
"waiting": 3152
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 157.80246913580248,
"backlogHours": 161.56962025316454,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.137647015055832,
"qualityFactor": 0.15430778981692855,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 32,
"recentSuccessRate": 0.13168724279835392,
"recentTerminal": 243,
"recentWilsonLowerBound": 0.09484676530512468,
"running": 4,
"selectionWeight": 0.1789411195725816,
"recentSuccess": 33,
"recentSuccessRate": 0.13924050632911392,
"recentTerminal": 237,
"recentWilsonLowerBound": 0.100894437132915,
"running": 1,
"selectionWeight": 0.2006001267620071,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 40.5,
"waiting": 6391
"throughputPerHour": 39.5,
"waiting": 6382
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 1553.9,
"backlogHours": 1503.8709677419354,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.5055017670459307,
"queueFactor": 0.9343577856730408,
"queueWeight": 0.9343577856730408,
"recentSuccess": 16,
"recentSuccessRate": 0.26666666666666666,
"recentTerminal": 60,
"recentWilsonLowerBound": 0.17132496487078855,
"qualityFactor": 0.5434224550805266,
"queueFactor": 0.9407040751654723,
"queueWeight": 0.9407040751654723,
"recentSuccess": 17,
"recentSuccessRate": 0.27419354838709675,
"recentTerminal": 62,
"recentWilsonLowerBound": 0.17880918599092133,
"running": 2,
"selectionWeight": 0.4723195117108452,
"selectionWeight": 0.5111997180306771,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 10.0,
"waiting": 15539
"throughputPerHour": 10.333333333333334,
"waiting": 15540
},
"Kunlunxin_p-800": {
"available": true,
@@ -620,15 +620,15 @@
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.127925654125022,
"queueFactor": 1.1503182640276828,
"queueWeight": 1.1503182640276828,
"qualityFactor": 0.12517579669587456,
"queueFactor": 1.152460258910921,
"queueWeight": 1.152460258910921,
"recentSuccess": 20,
"recentSuccessRate": 0.1388888888888889,
"recentTerminal": 144,
"recentWilsonLowerBound": 0.09174107374377487,
"running": 8,
"selectionWeight": 0.14715521637770107,
"selectionWeight": 0.14426013106950838,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 24.0,
@@ -636,118 +636,118 @@
},
"MetaX_c-500": {
"available": true,
"backlogHours": 695.8105263157895,
"backlogHours": 688.1875,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 1.5835702611109583,
"queueFactor": 1.05403011544665,
"queueWeight": 1.05403011544665,
"recentSuccess": 36,
"recentSuccessRate": 0.37894736842105264,
"recentTerminal": 95,
"recentWilsonLowerBound": 0.28789651358466833,
"running": 3,
"selectionWeight": 1.6691307451366653,
"qualityFactor": 1.200905632282099,
"queueFactor": 1.0577391879033464,
"queueWeight": 1.0577391879033464,
"recentSuccess": 33,
"recentSuccessRate": 0.34375,
"recentTerminal": 96,
"recentWilsonLowerBound": 0.2564024884934557,
"running": 4,
"selectionWeight": 1.2702449482386222,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 15.833333333333334,
"waiting": 11017
"throughputPerHour": 16.0,
"waiting": 11011
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1980.8181818181818,
"backlogHours": 2074.8571428571427,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 2.5,
"queueFactor": 0.9009485210684333,
"queueWeight": 0.9009485210684333,
"recentSuccess": 31,
"recentSuccessRate": 0.4696969696969697,
"recentTerminal": 66,
"recentWilsonLowerBound": 0.35430230971911897,
"queueFactor": 0.8963680777851819,
"queueWeight": 0.8963680777851819,
"recentSuccess": 30,
"recentSuccessRate": 0.47619047619047616,
"recentTerminal": 63,
"recentWilsonLowerBound": 0.35781921387369653,
"running": 4,
"selectionWeight": 2.252371302671083,
"selectionWeight": 2.2409201944629547,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 11.0,
"waiting": 21789
"throughputPerHour": 10.5,
"waiting": 21786
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 2226.913043478261,
"backlogHours": 2275.866666666667,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.12522873141022464,
"queueFactor": 0.8852606902326638,
"queueWeight": 0.8852606902326638,
"qualityFactor": 0.12881146113657332,
"queueFactor": 0.8840210155107934,
"queueWeight": 0.8840210155107934,
"recentSuccess": 8,
"recentSuccessRate": 0.17391304347826086,
"recentTerminal": 46,
"recentWilsonLowerBound": 0.09085683568889252,
"recentSuccessRate": 0.17777777777777778,
"recentTerminal": 45,
"recentWilsonLowerBound": 0.0929427892585383,
"running": 2,
"selectionWeight": 0.11086007320517634,
"selectionWeight": 0.11387203868338265,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 7.666666666666667,
"waiting": 17073
"throughputPerHour": 7.5,
"waiting": 17069
},
"Vastai_va16": {
"available": true,
"backlogHours": 1386.5675675675675,
"backlogHours": 1444.9014084507041,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.05,
"queueFactor": 0.9504636521390459,
"queueWeight": 0.9504636521390459,
"recentSuccess": 4,
"recentSuccessRate": 0.05405405405405406,
"recentTerminal": 74,
"recentWilsonLowerBound": 0.021218668760240082,
"queueFactor": 0.9463654563305907,
"queueWeight": 0.9463654563305907,
"recentSuccess": 3,
"recentSuccessRate": 0.04225352112676056,
"recentTerminal": 71,
"recentWilsonLowerBound": 0.014472998249826657,
"running": 16,
"selectionWeight": 0.0475231826069523,
"selectionWeight": 0.04731827281652953,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 12.333333333333334,
"waiting": 17101
"throughputPerHour": 11.833333333333334,
"waiting": 17098
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 1028.225806451613,
"backlogHours": 1036.5365853658536,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 0.44149627614925935,
"queueFactor": 0.9940618202886115,
"queueWeight": 0.9940618202886115,
"qualityFactor": 0.4400318988244507,
"queueFactor": 0.9947109903425165,
"queueWeight": 0.9947109903425165,
"recentSuccess": 28,
"recentSuccessRate": 0.22580645161290322,
"recentTerminal": 124,
"recentWilsonLowerBound": 0.16109993441103604,
"running": 5,
"selectionWeight": 0.43887459191957623,
"recentSuccessRate": 0.22764227642276422,
"recentTerminal": 123,
"recentWilsonLowerBound": 0.16245354051668648,
"running": 6,
"selectionWeight": 0.4377045658619674,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 20.666666666666668,
"waiting": 21250
"throughputPerHour": 20.5,
"waiting": 21249
}
},
"queueAttemptedAt": "2026-10-07T08:14:12.055765+00:00",
"queueAttemptedAt": "2026-10-07T08:29:47.682399+00:00",
"queueError": null,
"queueUpdatedAt": "2026-10-07T08:14:12.055765+00:00",
"queueUpdatedAt": "2026-10-07T08:29:47.682399+00:00",
"supportedGpus": [
"Vastai_va16",
"Cambricon_mlu-370-x4",

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-07T06:48:39.332067+00:00",
"lastSyncTime": "2026-10-07T06:48:39.066266+00:00",
"generatedAt": "2026-10-07T08:25:52.297334+00:00",
"lastSyncTime": "2026-10-07T08:25:52.062262+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4507,10 +4507,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 163,
"ambiguous_runtime": 164,
"参数/模板问题": 3
},
"failureCount": 166,
"failureCount": 167,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -4520,8 +4520,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 166,
"unresolvedFailureCount": 166
"total": 167,
"unresolvedFailureCount": 167
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 61,
@@ -5691,7 +5691,7 @@
"decisionSuccessRate": 0.0281,
"decisionTotal": 178,
"failureBreakdown": {
"ambiguous_runtime": 363,
"ambiguous_runtime": 364,
"backend_operator": 9,
"framework_architecture_unsupported": 47,
"memory_capacity": 10,
@@ -5700,15 +5700,15 @@
"tokenizer_compatibility": 95,
"参数/模板问题": 13
},
"failureCount": 574,
"failureCount": 575,
"failureRate": 0.9914,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 25,
"successCount": 5,
"successRate": 0.0086,
"total": 579,
"unresolvedFailureCount": 376
"total": 580,
"unresolvedFailureCount": 377
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 153,
@@ -5739,7 +5739,7 @@
"unresolvedFailureCount": 237
}
},
"generatedAt": "2026-10-07T06:48:39.315587+00:00",
"generatedAt": "2026-10-07T08:25:52.279800+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 119,
@@ -5971,7 +5971,7 @@
"decisionSuccessRate": 0.066,
"decisionTotal": 106,
"failureBreakdown": {
"ambiguous_runtime": 252,
"ambiguous_runtime": 253,
"backend_operator": 23,
"framework_architecture_unsupported": 37,
"memory_capacity": 3,
@@ -5984,15 +5984,15 @@
"日志缺失": 1,
"验证失败": 23
},
"failureCount": 423,
"failureRate": 0.9837,
"failureCount": 424,
"failureRate": 0.9838,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 7,
"successRate": 0.0163,
"total": 430,
"unresolvedFailureCount": 323
"successRate": 0.0162,
"total": 431,
"unresolvedFailureCount": 324
},
"Kunlunxin_r-200-8f": {
"attributableFailureCount": 0,
@@ -18089,9 +18089,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
"ambiguous_runtime": 5
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "gemma2",
@@ -18103,8 +18103,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
"total": 5,
"unresolvedFailureCount": 5
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma3|compressed-tensors": {
"attributableFailureCount": 0,
@@ -47567,6 +47567,30 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "gemma2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma3|compressed-tensors|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -58373,15 +58397,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17361,
"totalRecords": 17618,
"terminalRecords": 17362,
"totalRecords": 17619,
"totals": {
"attributableFailureCount": 6244,
"decisionFailureRate": 0.8646,
"decisionSuccessRate": 0.1354,
"decisionTotal": 7222,
"failureBreakdown": {
"ambiguous_runtime": 4559,
"ambiguous_runtime": 4560,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 129,
@@ -58397,15 +58421,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16383,
"failureCount": 16384,
"failureRate": 0.9437,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 952,
"successCount": 978,
"successRate": 0.0563,
"total": 17361,
"unresolvedFailureCount": 9187
"total": 17362,
"unresolvedFailureCount": 9188
},
"warnings": [
"GPU MetaX_c-500 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -58414,14 +58438,14 @@
"GPU hygon_k100-ai 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Kunlunxin_p-800 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_bi-100 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高(≥50%),建议重点关注。",
"组合 Vastai_va16|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b3|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_mrv-100|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -58466,6 +58490,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17618,
"summarizedRecords": 17619,
"version": 1
}

View File

@@ -14,7 +14,7 @@
100
],
"accounts": 12,
"activeScanned": 1141,
"activeScanned": 1134,
"ageCleanupMode": "admission_only",
"agePolicySkipped": {
"cleanupDisabled": true,
@@ -33,6 +33,21 @@
"vllm",
"vllm_tokenizer_patch"
],
"biren_166m|text-generation": [
"vllm",
"vllm_fix_tokenizer",
"vllm_tokenizer_patch"
],
"cambricon_mlu-370-x4|text-generation": [
"vllm",
"vllm-customized",
"vllm-mlu"
],
"cambricon_mlu-370-x8|text-generation": [
"vllm",
"vllm-customized",
"vllm-mlu"
],
"hygon_k100-ai|text-generation": [
"llamacpp",
"vllm",
@@ -46,15 +61,32 @@
"vllm_fix_tokenizer",
"vllm_tokenizer_patch"
],
"iluvatar_mrv-100|text-generation": [
"transformers",
"vllm"
],
"kunlunxin_p-800|text-generation": [
"vllm",
"vllm_fix_tokenizer",
"vllm_tokenizer_patch"
],
"metax_c-500|text-generation": [
"vllm",
"vllm_tokenizer_patch"
],
"mthreads_s4000|text-generation": [
"llamacpp",
"vllm",
"vllm_tokenizer_patch"
],
"sunrise_pt-200-x1|text-generation": [
"sglang",
"vllm",
"vllm_fix_tokenizer"
],
"vastai_va16|text-generation": [
"vllm",
"vllm_fix_tokenizer"
]
},
"architectureFrameworkCatalogErrors": {},
@@ -82,12 +114,12 @@
"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=500)"
},
"architectureModelConfigsComplete": 39,
"architectureOnly": true,
"architectureOnly": false,
"architecturePolicySkipped": {
"frameworkCatalogUnknown": 0,
"frameworkContextUnknown": 44,
"modelArchitectureUnknown": 159,
"noMatchingBlock": 966,
"noMatchingBlock": 959,
"partiallyBlockedFrameworkSet": 16,
"runningMatchedProtected": 0,
"submissionContextMismatch": 0,
@@ -128,9 +160,9 @@
"recentModelDays": 7,
"recentModelReserveSlots": 5,
"repositorySizeErrors": {},
"repositorySizesComplete": 0,
"repositorySizesComplete": 310,
"skipped": {
"fitsKnownCapacity": 0,
"fitsKnownCapacity": 1134,
"gpuCapacityUnknown": 0,
"repositorySizeUnknown": 0
},

View File

@@ -3095,6 +3095,7 @@
{"batchId": "41429fd098ca466683071742028a8384", "completedAt": "2026-10-07T06:48:30.691662+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-10-07T06:46:57.141235+00:00", "framework": "vllm", "intentId": "61d8003afe9341158464ae258b8c8e1e", "lastModified": "2026-09-23T05:44:29+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Hemmingway-1-OptiQ-4bit", "reason": null, "reconciledAt": "2026-10-07T08:11:57.695907+00:00", "repoId": "mlx-community/Hemmingway-1-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "5349878", "taskType": "text-generation"}
{"batchId": "41429fd098ca466683071742028a8384", "completedAt": "2026-10-07T06:48:30.691681+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-10-07T06:46:57.141359+00:00", "framework": "vllm", "intentId": "e2a553ed94294263beaa4a438c114255", "lastModified": "2026-09-22T14:23:22+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "reason": null, "reconciledAt": "2026-10-07T08:11:57.691509+00:00", "repoId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "5349877", "taskType": "text-generation"}
{"batchId": "41429fd098ca466683071742028a8384", "completedAt": "2026-10-07T06:48:30.691685+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-10-07T06:46:57.141407+00:00", "framework": "vllm", "intentId": "6b77d3fea90049f6b55d4a20cbc27d96", "lastModified": "2026-09-22T13:08:25+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "reason": null, "reconciledAt": "2026-10-07T08:11:57.690359+00:00", "repoId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "5349876", "taskType": "text-generation"}
{"batchId": "8068d5da12d44c2eb3ece1b79c9b95a7", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-07T08:32:31.036762+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d7e09a92693c45a3b0a25e503743592a", "lastModified": "2026-09-15T15:06:14+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-9B-OptiQ-4bit", "repoId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "5a3af05bde6b4528bb47524ddacd472a", "completedAt": "2026-10-07T06:14:43.539705+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-10-07T06:12:05.847146+00:00", "framework": "vllm", "intentId": "af78ba5491bc477db71d598faf14f76f", "repoId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "9ed0f87cfac4476bb0a5d7b69f2156ff", "completedAt": "2026-10-07T05:31:07.029844+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-10-07T05:25:16.871626+00:00", "framework": "vllm", "intentId": "272f1c84633d4b26a0094c622e876d7f", "repoId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
{"batchId": "9ed0f87cfac4476bb0a5d7b69f2156ff", "completedAt": "2026-10-07T05:31:07.029840+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-07T05:25:16.871575+00:00", "framework": "vllm", "intentId": "16f4de0d509b4ad599717e6de899b1c3", "repoId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_mrv-100", "taskId": null, "taskType": "text-generation"}

View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "b1b24a9c0a9dc13ee9c43f5c7564eecaf7872adfbbef9cb739f7110a1b9da737",
".modelhub_state/architecture_compatibility_blacklist.json": "2e6412499b8c8ead5546fe113c611055f2fa34d8251c308cca7a4e2444d0b3f4",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "473e0fbba93e33867ce2a66b2ed60d61d7a0d5d21eb6611e7fabf2d25ba2cdd0",
".modelhub_state/official_capabilities.json": "21b11baa4ee4ef63a7052cdf8ce56e6ab2cb07a05f3f9e0bf48923aa92355a22",
".modelhub_state/outcome_checkpoint.json": "9217e11b1afbb0287852a5e139908f7dc3f0d40f30ce156afa80ea4110ee22ab",
".modelhub_state/queue_cleanup_latest.json": "7ba5b2e9d8a35073e8b52b22a2ea37272cba48d3d7994f2b45b6dac7f9a13765",
".modelhub_state/market_intelligence.json": "1e402cc093b3e7b843119c18e1b114beada7b0220657fda4cb27ad7920f4bfb2",
".modelhub_state/official_capabilities.json": "afea197b5d482576276334bbc0c7371069b5a73230ee817339b73a14beb5b9f0",
".modelhub_state/outcome_checkpoint.json": "14aafd75cd0b725b7338990c3d4f899f059d03f88d3b7852216715d71e646484",
".modelhub_state/queue_cleanup_latest.json": "7f569be3fbe746570a2cdb33f54784d130294aa154d93e9ad9102b01386bc4cf",
".modelhub_state/recent_outcomes.jsonl": "d5fbd67ab11ba282114e0a6e6e26d2b50a42a7a49656649d1663ca1840d97bc8",
".modelhub_state/recovery_active_tasks.jsonl": "3349251b4822893c989b90722f5bbe001d1bda5322233d01da5e216b2ecf4851",
".modelhub_state/recovery_intents.jsonl": "f7651f4920ded1aa1f6d940b26a6e9f5c29d39aaf37bfd10e8836a6b26212c9a",
".modelhub_state/recovery_intents.jsonl": "ec6e3b8d76ca30895f34868940d6d0df91e33365f48dec3956e712eecf7ac644",
".modelhub_state/routing_intelligence.json": "3e9a3e602c75c7436d7899557ac69612b84f5f6e00b468070cd028ed1da83c68",
".modelhub_state/submission_exclusions.jsonl": "43b628022463d9d87ea16d9daf4f7ef224ee1ed83550feb9eaa30a59a885b4a5",
".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
"ledger/submissions.jsonl": "9bacb979e2580bca397ef121f4ecdfba252442728cb4fd55f51f4879b0df7508",
"outcomes/submissions.jsonl": "24d99841f38757945795fbb394a1de9c0e9a72e6a9b719ca8085899b81435b83"
"outcomes/submissions.jsonl": "70420971a7521e51a9d14c291beec90212388840e815123ddcadf1424822a104"
},
"generation": 21765,
"phase": "cycle",
"generation": 21766,
"phase": "intent",
"schemaVersion": 1,
"updatedAt": "2026-10-07T08:24:48.481003+00:00",
"updatedAt": "2026-10-07T08:32:31.224956+00:00",
"writerId": "33ed03361c5848e88b8ce6204fb4f7d2"
}

View File

@@ -149,7 +149,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901870+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "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": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:15:36.946953+00:00", "targetGpu": "Vastai_va16", "taskId": "4970616", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:34:29.856383+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:26:45.109939+00:00", "targetGpu": "Vastai_va16", "taskId": "4970729", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:46:14.462938+00:00", "modelId": "empero-ai/Qwen3.8-35B-A3B-Distill", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 71903778536, "estimatedRequiredGiB": 80.392, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 71933964484, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.6", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:moe", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-15T22:59:41.110897+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 71933964484}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:42:19.067096+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970926", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T14:18:03.258951+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "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": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T06:16:07.269550+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4972172", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T16:51:24.761939+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T08:49:13.744928+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4974217", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.191977+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "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": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.438915+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981854", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.192042+00:00", "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "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": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.480303+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981856", "taskType": "text-generation", "verifyResult": null}