state: generation 11129 (intent)

This commit is contained in:
2026-09-21 03:11:09 +00:00
parent ec96f08a05
commit b0c0deb0cb
9 changed files with 2863 additions and 2405 deletions

View File

@@ -427,6 +427,25 @@
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation"
},
"ascend_910-b4|vllm_tokenizer_patch|text-generation|model_type:qwen3_5_moe": {
"architectureSignature": "model_type:qwen3_5_moe",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-20T02:52:50.869403+00:00",
"framework": "vllm_tokenizer_patch",
"latestFailureAt": "2026-09-20T02:52:50.869403+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5_moe",
"sourceModelIds": [
"mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit"
],
"sourceTaskIds": [
"4969009"
],
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation"
},
"ascend_910-b4|vllm|text-generation|architectures:nanbeigeforcausallm": {
"architectureSignature": "architectures:nanbeigeforcausallm",
"architectures": [
@@ -2414,14 +2433,14 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-21T03:05:49.745018+00:00",
"generatedAt": "2026-09-21T03:09:25.825930+00:00",
"summary": {
"activeBlockCount": 119,
"activeBlockCount": 120,
"byGpuFramework": {
"Ascend_910-b3|vllm": 13,
"Ascend_910-b3|vllm_tokenizer_patch": 5,
"Ascend_910-b4|vllm": 12,
"Ascend_910-b4|vllm_tokenizer_patch": 3,
"Ascend_910-b4|vllm_tokenizer_patch": 4,
"Biren_166m|vllm": 3,
"Cambricon_mlu-370-x4|vllm": 1,
"Cambricon_mlu-370-x8|vllm": 8,

View File

@@ -425,121 +425,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-21T03:08:16.717397+00:00",
"generatedAt": "2026-09-21T03:09:34.706780+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 819.4186046511628,
"backlogHours": 814.578034682081,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.7179320696110454,
"queueFactor": 0.9778693250472548,
"queueWeight": 0.9778693250472548,
"recentSuccess": 38,
"recentSuccessRate": 0.22093023255813954,
"recentTerminal": 172,
"recentWilsonLowerBound": 0.1654034598109465,
"qualityFactor": 0.8746743342176841,
"queueFactor": 0.9792588936973591,
"queueWeight": 0.9792588936973591,
"recentSuccess": 42,
"recentSuccessRate": 0.24277456647398843,
"recentTerminal": 173,
"recentWilsonLowerBound": 0.1849214930019377,
"running": 8,
"selectionWeight": 0.7020437483403317,
"selectionWeight": 0.8565326208714835,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 28.666666666666668,
"waiting": 23490
"throughputPerHour": 28.833333333333332,
"waiting": 23487
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1148.5945945945946,
"backlogHours": 1222.7482014388488,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.5,
"queueFactor": 0.9295691040474398,
"queueWeight": 0.9295691040474398,
"recentSuccess": 54,
"recentSuccessRate": 0.36486486486486486,
"recentTerminal": 148,
"recentWilsonLowerBound": 0.2916373002819259,
"queueFactor": 0.9213759540084548,
"queueWeight": 0.9213759540084548,
"recentSuccess": 52,
"recentSuccessRate": 0.37410071942446044,
"recentTerminal": 139,
"recentWilsonLowerBound": 0.2980592988538872,
"running": 8,
"selectionWeight": 2.323922760118599,
"selectionWeight": 2.3034398850211373,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 24.666666666666668,
"waiting": 28332
"throughputPerHour": 23.166666666666668,
"waiting": 28327
},
"Biren_166m": {
"available": true,
"backlogHours": 143.2248803827751,
"backlogHours": 141.14150943396226,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.6355132349431445,
"queueFactor": 1.270293060812849,
"queueWeight": 1.270293060812849,
"recentSuccess": 43,
"recentSuccessRate": 0.20574162679425836,
"recentTerminal": 209,
"recentWilsonLowerBound": 0.156484897123764,
"qualityFactor": 0.5522519196264482,
"queueFactor": 1.2737647178209728,
"queueWeight": 1.2737647178209728,
"recentSuccess": 42,
"recentSuccessRate": 0.19811320754716982,
"recentTerminal": 212,
"recentWilsonLowerBound": 0.1500411918346862,
"running": 8,
"selectionWeight": 0.8072880524030023,
"selectionWeight": 0.7034390105690733,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 34.833333333333336,
"waiting": 4989
"throughputPerHour": 35.333333333333336,
"waiting": 4987
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1328.5588235294117,
"backlogHours": 1347.8507462686568,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.6890858601676707,
"queueFactor": 0.9094934541994483,
"queueWeight": 0.9094934541994483,
"qualityFactor": 0.6795648430115433,
"queueFactor": 0.9080111014147382,
"queueWeight": 0.9080111014147382,
"recentSuccess": 17,
"recentSuccessRate": 0.25,
"recentTerminal": 68,
"recentWilsonLowerBound": 0.16234881695499528,
"recentSuccessRate": 0.2537313432835821,
"recentTerminal": 67,
"recentWilsonLowerBound": 0.1648777957769739,
"running": 7,
"selectionWeight": 0.6267190792038928,
"selectionWeight": 0.6170524215856451,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 11.333333333333334,
"waiting": 15057
"throughputPerHour": 11.166666666666666,
"waiting": 15051
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 415.02985074626866,
"backlogHours": 441.04761904761904,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.42037223414062097,
"queueFactor": 1.0829160632506116,
"queueWeight": 1.0829160632506116,
"recentSuccess": 25,
"recentSuccessRate": 0.1865671641791045,
"recentTerminal": 134,
"recentWilsonLowerBound": 0.1296838224720284,
"qualityFactor": 0.3684276794468997,
"queueFactor": 1.0736546428934282,
"queueWeight": 1.0736546428934282,
"recentSuccess": 23,
"recentSuccessRate": 0.18253968253968253,
"recentTerminal": 126,
"recentWilsonLowerBound": 0.12482691576112777,
"running": 7,
"selectionWeight": 0.4552278448954256,
"selectionWeight": 0.3955640886086155,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.333333333333332,
"waiting": 9269
"throughputPerHour": 21.0,
"waiting": 9262
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 47.70873786407767,
"backlogHours": 49.033112582781456,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -549,124 +549,124 @@
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 6,
"recentSuccessRate": 0.019417475728155338,
"recentTerminal": 309,
"recentWilsonLowerBound": 0.008928721406924705,
"recentSuccessRate": 0.019867549668874173,
"recentTerminal": 302,
"recentWilsonLowerBound": 0.009136386915106036,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 51.5,
"waiting": 2457
"throughputPerHour": 50.333333333333336,
"waiting": 2468
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 150.243654822335,
"backlogHours": 152.15384615384616,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.1585346901501332,
"queueFactor": 1.2612096207441725,
"queueWeight": 1.2612096207441725,
"qualityFactor": 0.15460840839702145,
"queueFactor": 1.2594907681530305,
"queueWeight": 1.2594907681530305,
"recentSuccess": 24,
"recentSuccessRate": 0.1218274111675127,
"recentTerminal": 197,
"recentWilsonLowerBound": 0.0832494527329842,
"running": 7,
"selectionWeight": 0.1999454764390444,
"recentSuccessRate": 0.12307692307692308,
"recentTerminal": 195,
"recentWilsonLowerBound": 0.08411829251882981,
"running": 8,
"selectionWeight": 0.194727863054882,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 32.833333333333336,
"waiting": 4933
"throughputPerHour": 32.5,
"waiting": 4945
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 3227.0,
"backlogHours": 2933.090909090909,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.7298470900129251,
"queueFactor": 0.7961352459138944,
"queueWeight": 0.7961352459138944,
"recentSuccess": 9,
"recentSuccessRate": 0.3,
"recentTerminal": 30,
"recentWilsonLowerBound": 0.16664562643958936,
"qualityFactor": 1.0109348495576476,
"queueFactor": 0.80805068025296,
"queueWeight": 0.80805068025296,
"recentSuccess": 11,
"recentSuccessRate": 0.3333333333333333,
"recentTerminal": 33,
"recentWilsonLowerBound": 0.197500294678037,
"running": 2,
"selectionWeight": 0.5810569924869804,
"selectionWeight": 0.8168865928764809,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 5.0,
"waiting": 16135
"throughputPerHour": 5.5,
"waiting": 16132
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 592.2777777777778,
"backlogHours": 576.3243243243244,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.6857634461365623,
"queueFactor": 1.0266629277988235,
"queueWeight": 1.0266629277988235,
"recentSuccess": 25,
"recentSuccessRate": 0.23148148148148148,
"recentTerminal": 108,
"recentWilsonLowerBound": 0.1619925471777863,
"qualityFactor": 0.6820860793425559,
"queueFactor": 1.0314243648344539,
"queueWeight": 1.0314243648344539,
"recentSuccess": 26,
"recentSuccessRate": 0.23423423423423423,
"recentTerminal": 111,
"recentWilsonLowerBound": 0.16515556448978605,
"running": 8,
"selectionWeight": 0.7040479073879738,
"selectionWeight": 0.7035202011483187,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.0,
"waiting": 10661
"throughputPerHour": 18.5,
"waiting": 10662
},
"MetaX_c-500": {
"available": true,
"backlogHours": 576.0521739130435,
"backlogHours": 602.1272727272727,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.47530730968866597,
"queueFactor": 1.0309495726355582,
"queueWeight": 1.0309495726355582,
"recentSuccess": 23,
"recentSuccessRate": 0.2,
"recentTerminal": 115,
"recentWilsonLowerBound": 0.1371296827840679,
"qualityFactor": 0.3919819083443804,
"queueFactor": 1.0246703840146045,
"queueWeight": 1.0246703840146045,
"recentSuccess": 21,
"recentSuccessRate": 0.19090909090909092,
"recentTerminal": 110,
"recentWilsonLowerBound": 0.12839312602494252,
"running": 4,
"selectionWeight": 0.49001786779408707,
"selectionWeight": 0.4016522525500138,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 19.166666666666668,
"waiting": 11041
"throughputPerHour": 18.333333333333332,
"waiting": 11039
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1514.3720930232557,
"backlogHours": 1447.0666666666666,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 1.2840319040486128,
"queueFactor": 0.8918089083739755,
"queueWeight": 0.8918089083739755,
"recentSuccess": 26,
"recentSuccessRate": 0.3023255813953488,
"recentTerminal": 86,
"recentWilsonLowerBound": 0.21543382392193752,
"qualityFactor": 1.219881330871374,
"queueFactor": 0.8983884251723906,
"queueWeight": 0.8983884251723906,
"recentSuccess": 27,
"recentSuccessRate": 0.3,
"recentTerminal": 90,
"recentWilsonLowerBound": 0.21510778051256527,
"running": 4,
"selectionWeight": 1.1451110906669506,
"selectionWeight": 1.0959272677387337,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 14.333333333333334,
"throughputPerHour": 15.0,
"waiting": 21706
},
"Sunrise_pt-200-x1": {
@@ -677,15 +677,15 @@
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.16650290574589705,
"queueFactor": 0.8604473934701,
"queueWeight": 0.8604473934701,
"recentSuccess": 8,
"recentSuccessRate": 0.16326530612244897,
"qualityFactor": 0.22500916514189215,
"queueFactor": 0.8609046551871198,
"queueWeight": 0.8609046551871198,
"recentSuccess": 9,
"recentSuccessRate": 0.1836734693877551,
"recentTerminal": 49,
"recentWilsonLowerBound": 0.08512596988208977,
"recentWilsonLowerBound": 0.09976228838458356,
"running": 2,
"selectionWeight": 0.14326699125425485,
"selectionWeight": 0.19371143773042235,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 8.166666666666666,
@@ -693,52 +693,52 @@
},
"Vastai_va16": {
"available": true,
"backlogHours": 1220.7042253521126,
"backlogHours": 1237.8857142857144,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.05,
"queueFactor": 0.9211177022285634,
"queueWeight": 0.9211177022285634,
"queueFactor": 0.9196770438070431,
"queueWeight": 0.9196770438070431,
"recentSuccess": 6,
"recentSuccessRate": 0.08450704225352113,
"recentTerminal": 71,
"recentWilsonLowerBound": 0.039305972354112026,
"recentSuccessRate": 0.08571428571428572,
"recentTerminal": 70,
"recentWilsonLowerBound": 0.03987612654032837,
"running": 16,
"selectionWeight": 0.04605588511142817,
"selectionWeight": 0.045983852190352156,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 11.833333333333334,
"waiting": 14445
"throughputPerHour": 11.666666666666666,
"waiting": 14442
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 316.6092715231788,
"backlogHours": 315.58415841584156,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 0.05,
"queueFactor": 1.1277897720528962,
"queueWeight": 1.1277897720528962,
"recentSuccess": 22,
"recentSuccessRate": 0.0728476821192053,
"recentTerminal": 302,
"recentWilsonLowerBound": 0.04859629433610135,
"qualityFactor": 0.05166531592922758,
"queueFactor": 1.1289381507458776,
"queueWeight": 1.1289381507458776,
"recentSuccess": 23,
"recentSuccessRate": 0.07590759075907591,
"recentTerminal": 303,
"recentWilsonLowerBound": 0.05111064345958137,
"running": 6,
"selectionWeight": 0.05638948860264481,
"selectionWeight": 0.05832694622284371,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 50.333333333333336,
"waiting": 15936
"submissionEligible": true,
"throughputPerHour": 50.5,
"waiting": 15937
}
},
"queueAttemptedAt": "2026-09-21T02:58:43.321969+00:00",
"queueAttemptedAt": "2026-09-21T03:09:34.706780+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-21T02:58:43.321969+00:00",
"queueUpdatedAt": "2026-09-21T03:09:34.706780+00:00",
"supportedGpus": [
"Vastai_va16",
"Kunlunxin_p-800",

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T03:05:49.686745+00:00",
"lastSyncTime": "2026-09-21T03:05:47.759507+00:00",
"generatedAt": "2026-09-21T03:09:34.638519+00:00",
"lastSyncTime": "2026-09-21T03:09:34.579964+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -431,6 +431,25 @@
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation"
},
"ascend_910-b4|vllm_tokenizer_patch|text-generation|model_type:qwen3_5_moe": {
"architectureSignature": "model_type:qwen3_5_moe",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-20T02:52:50.869403+00:00",
"framework": "vllm_tokenizer_patch",
"latestFailureAt": "2026-09-20T02:52:50.869403+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5_moe",
"sourceModelIds": [
"mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit"
],
"sourceTaskIds": [
"4969009"
],
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation"
},
"ascend_910-b4|vllm|text-generation|architectures:nanbeigeforcausallm": {
"architectureSignature": "architectures:nanbeigeforcausallm",
"architectures": [
@@ -2419,12 +2438,12 @@
}
},
"architectureCompatibilitySummary": {
"activeBlockCount": 119,
"activeBlockCount": 120,
"byGpuFramework": {
"Ascend_910-b3|vllm": 13,
"Ascend_910-b3|vllm_tokenizer_patch": 5,
"Ascend_910-b4|vllm": 12,
"Ascend_910-b4|vllm_tokenizer_patch": 3,
"Ascend_910-b4|vllm_tokenizer_patch": 4,
"Biren_166m|vllm": 3,
"Cambricon_mlu-370-x4|vllm": 1,
"Cambricon_mlu-370-x8|vllm": 8,
@@ -2717,15 +2736,15 @@
"unresolvedFailureCount": 17
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 17,
"attributableFailureCount": 18,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 17,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 26,
"framework_architecture_unsupported": 17
"framework_architecture_unsupported": 18
},
"failureCount": 43,
"failureCount": 44,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
@@ -2735,7 +2754,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 43,
"total": 44,
"unresolvedFailureCount": 26
},
"Ascend_910-b4|vllm|text-generation": {
@@ -4454,9 +4473,9 @@
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 13,
"decisionFailureRate": 0.13,
"decisionSuccessRate": 0.87,
"decisionTotal": 100,
"decisionFailureRate": 0.1287,
"decisionSuccessRate": 0.8713,
"decisionTotal": 101,
"failureBreakdown": {
"ambiguous_runtime": 52,
"context_length": 5,
@@ -4465,16 +4484,16 @@
"验证失败": 32
},
"failureCount": 309,
"failureRate": 0.7803,
"failureRate": 0.7783,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 87,
"successRate": 0.2197,
"successCount": 88,
"successRate": 0.2217,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 396,
"total": 397,
"unresolvedFailureCount": 296
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
@@ -4999,9 +5018,9 @@
},
"unknown": {
"attributableFailureCount": 1858,
"decisionFailureRate": 0.6969,
"decisionSuccessRate": 0.3031,
"decisionTotal": 2666,
"decisionFailureRate": 0.6967,
"decisionSuccessRate": 0.3033,
"decisionTotal": 2667,
"failureBreakdown": {
"ambiguous_runtime": 1964,
"architecture_compatibility": 100,
@@ -5019,13 +5038,13 @@
"验证失败": 673
},
"failureCount": 8315,
"failureRate": 0.9114,
"failureRate": 0.9113,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 42,
"successCount": 808,
"successRate": 0.0886,
"total": 9123,
"successCount": 809,
"successRate": 0.0887,
"total": 9124,
"unresolvedFailureCount": 6415
},
"vllm": {
@@ -5171,30 +5190,30 @@
"unresolvedFailureCount": 141
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 51,
"decisionFailureRate": 0.9623,
"decisionSuccessRate": 0.0377,
"decisionTotal": 53,
"attributableFailureCount": 52,
"decisionFailureRate": 0.963,
"decisionSuccessRate": 0.037,
"decisionTotal": 54,
"failureBreakdown": {
"ambiguous_runtime": 39,
"framework_architecture_unsupported": 48,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
"model_load": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 19
},
"failureCount": 109,
"failureRate": 0.982,
"failureCount": 110,
"failureRate": 0.9821,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.018,
"total": 111,
"successRate": 0.0179,
"total": 112,
"unresolvedFailureCount": 58
}
},
"generatedAt": "2026-09-21T03:05:49.677394+00:00",
"generatedAt": "2026-09-21T03:09:34.628728+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 90,
@@ -5222,14 +5241,14 @@
"unresolvedFailureCount": 128
},
"Ascend_910-b4": {
"attributableFailureCount": 310,
"decisionFailureRate": 0.8333,
"decisionSuccessRate": 0.1667,
"decisionTotal": 372,
"attributableFailureCount": 311,
"decisionFailureRate": 0.8338,
"decisionSuccessRate": 0.1662,
"decisionTotal": 373,
"failureBreakdown": {
"ambiguous_runtime": 158,
"context_length": 1,
"framework_architecture_unsupported": 170,
"framework_architecture_unsupported": 171,
"memory_capacity": 18,
"model_load": 85,
"platform_infrastructure": 1,
@@ -5239,14 +5258,14 @@
"日志缺失": 14,
"验证失败": 175
},
"failureCount": 912,
"failureRate": 0.9363,
"failureCount": 913,
"failureRate": 0.9364,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 62,
"successRate": 0.0637,
"total": 974,
"successRate": 0.0636,
"total": 975,
"unresolvedFailureCount": 601
},
"Biren_166m": {
@@ -5520,9 +5539,9 @@
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 732,
"decisionFailureRate": 0.8938,
"decisionSuccessRate": 0.1062,
"decisionTotal": 819,
"decisionFailureRate": 0.8927,
"decisionSuccessRate": 0.1073,
"decisionTotal": 820,
"failureBreakdown": {
"ambiguous_runtime": 162,
"architecture_compatibility": 44,
@@ -5538,13 +5557,13 @@
"验证失败": 32
},
"failureCount": 1372,
"failureRate": 0.9404,
"failureRate": 0.9397,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 218,
"successCount": 87,
"successRate": 0.0596,
"total": 1459,
"successCount": 88,
"successRate": 0.0603,
"total": 1460,
"unresolvedFailureCount": 422
},
"Vastai_va16": {
@@ -5624,7 +5643,7 @@
"hygon_k100-ai": 64.0
},
"pendingRecords": 0,
"policyCancelledRecords": 167,
"policyCancelledRecords": 173,
"profileCombinationStats": {
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|bailing_hybrid|none": {
"attributableFailureCount": 1,
@@ -6544,6 +6563,29 @@
"total": 3,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|none": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
@@ -13734,11 +13776,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 6,
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 6,
"tokenizer_compatibility": 1
},
"failureCount": 13,
"failureCount": 12,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -13750,21 +13792,21 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 13,
"unresolvedFailureCount": 6
"total": 12,
"unresolvedFailureCount": 5
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 9,
"framework_architecture_unsupported": 5
"framework_architecture_unsupported": 6
},
"failureCount": 14,
"failureCount": 15,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
@@ -13776,7 +13818,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 14,
"total": 15,
"unresolvedFailureCount": 9
},
"Ascend_910-b4|vllm|text-generation": {
@@ -14386,21 +14428,21 @@
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T02:49:19.765032+00:00",
"lastTerminalAt": "2026-09-21T03:09:23.977124+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successCount": 4,
"successRate": 1.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 3,
"total": 4,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
@@ -14482,10 +14524,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 13,
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 5
},
"failureCount": 18,
"failureCount": 17,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -14497,8 +14539,8 @@
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 18,
"unresolvedFailureCount": 13
"total": 17,
"unresolvedFailureCount": 12
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
@@ -15208,6 +15250,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-21T03:09:23.977064+00:00",
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -19524,6 +19591,30 @@
"total": 3,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -29955,20 +30046,20 @@
"unresolvedFailureCount": 1
}
},
"terminalRecords": 16062,
"totalRecords": 16229,
"terminalRecords": 16064,
"totalRecords": 16237,
"totals": {
"attributableFailureCount": 5832,
"decisionFailureRate": 0.8617,
"decisionSuccessRate": 0.1383,
"decisionTotal": 6768,
"attributableFailureCount": 5833,
"decisionFailureRate": 0.8616,
"decisionSuccessRate": 0.1384,
"decisionTotal": 6770,
"failureBreakdown": {
"ambiguous_runtime": 3839,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
"context_length": 318,
"framework_architecture_unsupported": 2036,
"framework_architecture_unsupported": 2037,
"memory_capacity": 1197,
"model_load": 489,
"platform_infrastructure": 922,
@@ -29979,14 +30070,14 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 15126,
"failureCount": 15127,
"failureRate": 0.9417,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 936,
"successCount": 937,
"successRate": 0.0583,
"total": 16062,
"total": 16064,
"unresolvedFailureCount": 8372
},
"warnings": [
@@ -30040,6 +30131,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16229,
"summarizedRecords": 16237,
"version": 1
}

View File

@@ -14,13 +14,13 @@
100
],
"accounts": 12,
"activeScanned": 1178,
"activeScanned": 1170,
"ageCleanupMode": "admission_only",
"agePolicySkipped": {
"cleanupDisabled": true,
"reason": "admission_only"
},
"architectureBlockCount": 119,
"architectureBlockCount": 120,
"architectureFrameworkCatalog": {
"ascend_910-b3|text-generation": [
"llamacpp",
@@ -37,11 +37,6 @@
"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",
@@ -52,12 +47,6 @@
"vllm",
"vllm-patch-tokenizer"
],
"iluvatar_bi-100|text-generation": [
"transformers",
"vllm",
"vllm-patch-tokenizer",
"vllm_fix_tokenizer"
],
"iluvatar_bi-150|text-generation": [
"llamacpp",
"transformers",
@@ -66,19 +55,11 @@
"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",
@@ -88,15 +69,138 @@
"sglang",
"vllm",
"vllm_fix_tokenizer"
],
"vastai_va16|text-generation": [
"vllm",
"vllm_fix_tokenizer"
]
},
"architectureFrameworkCatalogErrors": {},
"architectureIncompatibleCount": 0,
"architectureIncompatibleTasks": [],
"architectureIncompatibleCount": 6,
"architectureIncompatibleTasks": [
{
"accountIndex": 2,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4938406,
"taskType": "text-generation"
},
{
"accountIndex": 7,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "Edge0/Edge0-35B-A3B-preview",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4844610,
"taskType": "text-generation"
},
{
"accountIndex": 8,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4857321,
"taskType": "text-generation"
},
{
"accountIndex": 8,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4923309,
"taskType": "text-generation"
},
{
"accountIndex": 9,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4845112,
"taskType": "text-generation"
},
{
"accountIndex": 9,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4857320,
"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)",
@@ -120,22 +224,167 @@
"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": 59,
"architectureOnly": false,
"architectureOnly": true,
"architecturePolicySkipped": {
"frameworkCatalogUnknown": 0,
"frameworkContextUnknown": 70,
"modelArchitectureUnknown": 134,
"noMatchingBlock": 1021,
"noMatchingBlock": 1007,
"partiallyBlockedFrameworkSet": 23,
"runningMatchedProtected": 0,
"submissionContextMismatch": 0,
"submissionContextUnknown": 0
},
"cancelledCount": 0,
"cancelledTasks": [],
"cancelledCount": 6,
"cancelledTasks": [
{
"accountIndex": 2,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+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_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4938406,
"taskType": "text-generation"
},
{
"accountIndex": 7,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+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_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "Edge0/Edge0-35B-A3B-preview",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4844610,
"taskType": "text-generation"
},
{
"accountIndex": 8,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+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_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4857321,
"taskType": "text-generation"
},
{
"accountIndex": 8,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+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_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4923309,
"taskType": "text-generation"
},
{
"accountIndex": 9,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+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_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4845112,
"taskType": "text-generation"
},
{
"accountIndex": 9,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+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_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b4",
"modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 4857320,
"taskType": "text-generation"
}
],
"certainOomCount": 0,
"certainOomTasks": [],
"cleanupCandidateCount": 0,
"cleanupCandidateCount": 6,
"dryRun": false,
"listingErrors": {},
"modelAgeErrors": {},
@@ -160,19 +409,17 @@
],
"oldOverflowCount": 0,
"oldOverflowTasks": [],
"policyCancelledRecorded": 0,
"policyCancelledRecorded": 6,
"policyNoLongerAppliesCount": 0,
"policyNoLongerAppliesTasks": [],
"recentModelDays": 7,
"recentModelReserveSlots": 5,
"repositorySizeErrors": {
"empero-ai/Qwen3.8-9B-GGUF": "recursive_repository_size_incomplete"
},
"repositorySizesComplete": 337,
"repositorySizeErrors": {},
"repositorySizesComplete": 0,
"skipped": {
"fitsKnownCapacity": 1176,
"fitsKnownCapacity": 0,
"gpuCapacityUnknown": 0,
"repositorySizeUnknown": 2
"repositorySizeUnknown": 0
},
"stopErrors": [],
"uniqueModels": 338

View File

@@ -1,3 +1,4 @@
{"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}
@@ -242,6 +243,7 @@
{"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": "2026-09-21T01:35:45.556098+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "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": "2026-09-20T02:52:51.136367+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969024", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T18:53:01.473054+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v3-9B", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18483466448, "estimatedRequiredGiB": 20.702, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 18523972484, "modelscopeLicense": "gemma", "modelscopeParams": 9241705984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18523972484}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:50.898445+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969015", "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": "2026-09-20T21:33:11.158049+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "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": "2026-09-20T02:52:50.893989+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969012", "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_tokenizer_patch", "lastSyncTime": "2026-09-21T03:09:23.977064+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "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": "2026-09-20T02:52:50.869403+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969009", "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": "2026-09-20T21:06:45.850250+00:00", "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "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": "2026-09-20T02:52:50.839341+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969006", "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_tokenizer_patch", "lastSyncTime": "2026-09-21T03:02:20.757762+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "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": "2026-09-20T02:52:50.836633+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969008", "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": "2026-09-20T20:49:19.683277+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "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": "2026-09-20T02:52:43.837507+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969003", "taskType": "text-generation", "verifyResult": -1}
@@ -296,5 +298,3 @@
{"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": "2026-09-17T10:44:59.509445+00:00", "modelId": "RedHatAI/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T10:41:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497070", "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": "2026-09-17T10:35:53.413598+00:00", "modelId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T10:29:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610367", "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": "2026-09-17T10:10:02.608119+00:00", "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T10:05:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4490374", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-17T04:34:21.545391+00:00", "modelId": "BAAI/Law_Justice-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T04:33:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471925", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-17T03:40:30.307157+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T03:37:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505133", "taskType": "text-generation", "verifyResult": -1}

View File

@@ -1961,6 +1961,42 @@
{"batchId": "243f4088a4994c3cbc472ef19e52886e", "completedAt": "2026-09-21T02:21:28.412435+00:00", "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:21:26.798256+00:00", "framework": "vllm", "intentId": "444f704301f944879fae4a3fce3a65ea", "lastModified": "2026-09-20T14:39:27+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "reason": null, "reconciledAt": "2026-09-21T03:05:57.242885+00:00", "repoId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4992047", "taskType": "text-generation"}
{"batchId": "243f4088a4994c3cbc472ef19e52886e", "completedAt": "2026-09-21T02:21:28.412447+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:21:26.798380+00:00", "framework": "vllm", "intentId": "eea322d8e8624c00812a6ff7ecd1b244", "lastModified": "2026-09-17T13:36:05+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "reason": null, "reconciledAt": "2026-09-21T03:05:57.242585+00:00", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4992046", "taskType": "text-generation"}
{"batchId": "4ebeabe10e824f7ab597594406b6205f", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:51:56.239072+00:00", "framework": "vllm-customized", "intentId": "67b30ce588ad4c6f9412e291c75fcecc", "lastModified": "2026-09-20T14:50:03+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "reconciledAt": "2026-09-21T03:05:57.245438+00:00", "repoId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4992371", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.555968+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b21c2e9db2fc42c3899ad1b494c0bf78", "lastModified": "2026-08-24T20:05:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.556971+00:00", "framework": "vllm_fix_tokenizer", "intentId": "173ec5f2cbbc4148b47133e20aeaa56d", "lastModified": "2026-08-24T19:35:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557035+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8013c9089d2940268c91b114d9e94d80", "lastModified": "2026-08-24T19:10:38+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557080+00:00", "framework": "vllm-mlu", "intentId": "cc9dcafb85344e738976036273ab6593", "lastModified": "2026-08-24T19:57:49+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557149+00:00", "framework": "vllm", "intentId": "c2fd8f6e6f8447f08128dc9542eeef2d", "lastModified": "2026-08-24T19:39:27+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557210+00:00", "framework": "vllm", "intentId": "a9f13fb1dbcd4a5e9a765d11833ae2af", "lastModified": "2026-08-26T17:18:42+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557269+00:00", "framework": "vllm", "intentId": "b17c22a2aa37424fbe11665cb2950c32", "lastModified": "2026-08-24T19:39:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557328+00:00", "framework": "vllm", "intentId": "8fb2a00847a6422f83ecf92fd67fed9d", "lastModified": "2026-08-24T19:26:17+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557417+00:00", "framework": "vllm", "intentId": "021fa45a85de42d18cfee559fdf547cb", "lastModified": "2026-09-08T03:51:51+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557482+00:00", "framework": "vllm", "intentId": "b2a167588e084209b02d611dfbeb4c4e", "lastModified": "2026-08-24T19:41:12+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557539+00:00", "framework": "vllm", "intentId": "84f59afdbef04797be7aaea42bb5eb48", "lastModified": "2026-08-24T19:25:45+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-2-7b-chat-quantized.w8a8", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557596+00:00", "framework": "vllm", "intentId": "cc5c2e2b1a6a4aa49426be59fbb25f9d", "lastModified": "2026-08-24T20:17:00+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557653+00:00", "framework": "vllm", "intentId": "dedc7edf43ed4165be6036717cf3a883", "lastModified": "2026-08-24T20:08:44+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557729+00:00", "framework": "vllm", "intentId": "69d289f7399046dc9c71586dca9a3643", "lastModified": "2026-08-24T19:39:28+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557787+00:00", "framework": "vllm", "intentId": "505bf5f419ce4d968f7a2345cb17e447", "lastModified": "2026-08-24T19:59:13+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557844+00:00", "framework": "vllm", "intentId": "0964b2e4a372466394d03d9111957982", "lastModified": "2026-08-24T19:51:52+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557901+00:00", "framework": "vllm", "intentId": "8bc100ff46b642a6ab8e3bbee5a98d13", "lastModified": "2026-08-24T19:53:24+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557958+00:00", "framework": "vllm", "intentId": "6938b5953adc4b329152d78feb39399b", "lastModified": "2026-08-24T19:36:07+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558014+00:00", "framework": "vllm", "intentId": "d8bbf02d284041b396c8b89f6cca50de", "lastModified": "2026-09-10T07:49:50+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558070+00:00", "framework": "vllm", "intentId": "836b19cc3f5042738981ac6f021eaf55", "lastModified": "2026-09-01T03:52:21+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558127+00:00", "framework": "vllm", "intentId": "e6e7a276612c46f1a51d6a703587cb5a", "lastModified": "2026-09-08T13:43:47+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558184+00:00", "framework": "vllm", "intentId": "012b33523947498897c6ad2f2ca83a37", "lastModified": "2026-08-26T16:41:36+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558240+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2c109aecbd52404683c3fa072cf95a70", "lastModified": "2026-08-24T19:21:33+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558284+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a471d47e1acb4d368eec329e9f33e966", "lastModified": "2026-08-24T19:34:42+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-FP8", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558327+00:00", "framework": "vllm-patch-tokenizer", "intentId": "61b04169ae9049d8ab5c29366b9516d3", "lastModified": "2026-08-24T19:53:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558369+00:00", "framework": "vllm-patch-tokenizer", "intentId": "46f87227ec65464685bb60bf1f02a2cd", "lastModified": "2026-08-24T20:09:59+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-2-7b-chat-quantized.w8a8", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558412+00:00", "framework": "vllm-patch-tokenizer", "intentId": "6d99d70168954b6098d1fce1805d088c", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558455+00:00", "framework": "vllm-patch-tokenizer", "intentId": "674e8b31d1b141e6a518ad774cb216da", "lastModified": "2026-08-24T19:48:09+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558497+00:00", "framework": "vllm-patch-tokenizer", "intentId": "25997315b2d949189f7b7836f5a6f09c", "lastModified": "2026-08-24T19:42:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558538+00:00", "framework": "vllm-patch-tokenizer", "intentId": "ade5f3328390402fa3cb080ed30644f8", "lastModified": "2026-08-24T20:21:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558580+00:00", "framework": "vllm-patch-tokenizer", "intentId": "3e96bd2d86b74ea0b8fac8840c68fd6f", "lastModified": "2026-08-24T20:09:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-3B-Instruct-FP8", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558622+00:00", "framework": "vllm-patch-tokenizer", "intentId": "2e85fb1258b44b858d843e2774a38e23", "lastModified": "2026-08-24T19:20:59+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a8", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558673+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e8208942b81a41c4b1ac543edc23077d", "lastModified": "2026-08-24T20:18:47+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-27b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558719+00:00", "framework": "vllm-patch-tokenizer", "intentId": "621ca79f277541b3947fc7f43c3453f7", "lastModified": "2026-08-24T20:02:01+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558762+00:00", "framework": "vllm", "intentId": "8cd6962ffe23458d95ed285f9732a1dd", "lastModified": "2026-08-24T19:34:25+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558810+00:00", "framework": "vllm", "intentId": "765e405dd2454d4a8a84eaf0bb67d118", "lastModified": "2026-09-08T15:45:26+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "c4c47c96388a48c996d907d392c73b35", "completedAt": "2026-09-21T02:14:01.388181+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:07:21.135936+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1948200c63fd4072ac075656ec8053ee", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "c4c47c96388a48c996d907d392c73b35", "completedAt": "2026-09-21T02:14:01.388178+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:07:21.135881+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bf3aed8733f24050b6c911eb5a98d891", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
{"batchId": "c4c47c96388a48c996d907d392c73b35", "completedAt": "2026-09-21T02:14:01.388175+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:07:21.135828+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d6d64229eafe4036a52529aaa805b830", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}