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

state: generation 20702 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-05 02:50:58 +00:00
parent 62098850c5
commit 854a8708b3
8 changed files with 1525 additions and 1430 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -3074,7 +3074,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-10-05T02:38:37.805470+00:00",
"generatedAt": "2026-10-05T02:48:46.089539+00:00",
"summary": {
"activeBlockCount": 155,
"byGpuFramework": {

2
.modelhub_state/market_intelligence.json
View File

@@ -434,7 +434,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-05T02:47:39.072923+00:00",
"generatedAt": "2026-10-05T02:50:27.702531+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

73
.modelhub_state/official_capabilities.json
View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-10-05T02:47:39.072923+00:00",
"catalogUpdatedAt": "2026-10-05T02:50:27.702531+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-10-05T02:47:39.072923+00:00",
"generatedAt": "2026-10-05T02:50:32.255340+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -2817,12 +2817,6 @@
],
"updatedAt": "2026-10-04T23:21:14.715027+00:00"
},
"https://modelscope.cn/models/ProCreations/bonsai-2-27b-gsq-rco-gguf|2026-09-20T05:30:27+00:00|Kunlunxin_p-800": {
"taskTypes": [
"text-generation"
],
"updatedAt": "2026-10-04T23:11:32.863767+00:00"
},
"https://modelscope.cn/models/ProCreations/bonsai-2-27b-gsq-rco-gguf|2026-09-20T05:30:27+00:00|MetaX_c-500": {
"taskTypes": [
"feature_emb",
@@ -3783,12 +3777,6 @@
],
"updatedAt": "2026-10-04T23:21:14.935537+00:00"
},
"https://modelscope.cn/models/dealignai/Bonsai-2-27B-1bit-CRACK-GGUF|2026-09-18T13:05:43+00:00|Kunlunxin_p-800": {
"taskTypes": [
"text-generation"
],
"updatedAt": "2026-10-04T23:11:32.969694+00:00"
},
"https://modelscope.cn/models/dealignai/Bonsai-2-27B-1bit-CRACK-GGUF|2026-09-18T13:05:43+00:00|MetaX_c-500": {
"taskTypes": [
"feature_emb",
@@ -3855,12 +3843,6 @@
],
"updatedAt": "2026-10-04T23:21:14.934690+00:00"
},
"https://modelscope.cn/models/dealignai/Bonsai-2-27B-Ternary-CRACK-GGUF|2026-09-18T14:52:28+00:00|Kunlunxin_p-800": {
"taskTypes": [
"text-generation"
],
"updatedAt": "2026-10-04T23:11:32.968379+00:00"
},
"https://modelscope.cn/models/dealignai/Bonsai-2-27B-Ternary-CRACK-GGUF|2026-09-18T14:52:28+00:00|MetaX_c-500": {
"taskTypes": [
"feature_emb",
@@ -4952,6 +4934,43 @@
],
"updatedAt": "2026-10-05T02:34:04.887538+00:00"
},
"https://modelscope.cn/models/luocimm/lothys-glm53|2026-10-05T02:35:50+00:00|Ascend_910-b3": {
"taskTypes": [
"text-generation",
"text-to-image-generation",
"visual-multi-modal"
],
"updatedAt": "2026-10-05T02:50:32.156638+00:00"
},
"https://modelscope.cn/models/luocimm/lothys-glm53|2026-10-05T02:35:50+00:00|Ascend_910-b4": {
"taskTypes": [
"text-generation",
"text-to-image-generation",
"visual-multi-modal"
],
"updatedAt": "2026-10-05T02:50:31.951610+00:00"
},
"https://modelscope.cn/models/luocimm/lothys-glm53|2026-10-05T02:35:50+00:00|Biren_166m": {
"taskTypes": [
"text-generation"
],
"updatedAt": "2026-10-05T02:50:32.082262+00:00"
},
"https://modelscope.cn/models/luocimm/lothys-glm53|2026-10-05T02:35:50+00:00|Cambricon_mlu-370-x8": {
"taskTypes": [
"text-generation",
"text-to-image-generation",
"visual-multi-modal"
],
"updatedAt": "2026-10-05T02:50:32.255340+00:00"
},
"https://modelscope.cn/models/luocimm/lothys-glm53|2026-10-05T02:35:50+00:00|Mthreads_s4000": {
"taskTypes": [
"text-generation",
"visual-multi-modal"
],
"updatedAt": "2026-10-05T02:50:32.051566+00:00"
},
"https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-6bit|2026-09-30T17:45:40+00:00|Iluvatar_bi-150": {
"taskTypes": [
"asr",
@@ -5384,12 +5403,6 @@
],
"updatedAt": "2026-10-04T23:21:15.090319+00:00"
},
"https://modelscope.cn/models/prism-ml/Ternary-Bonsai-2-27B-gguf-dev|2026-09-18T05:30:35+00:00|Kunlunxin_p-800": {
"taskTypes": [
"text-generation"
],
"updatedAt": "2026-10-04T23:11:32.970212+00:00"
},
"https://modelscope.cn/models/prism-ml/Ternary-Bonsai-2-27B-gguf-dev|2026-09-18T05:30:35+00:00|MetaX_c-500": {
"taskTypes": [
"feature_emb",
@@ -6010,12 +6023,6 @@
],
"updatedAt": "2026-10-04T23:21:14.934241+00:00"
},
"https://modelscope.cn/models/wufubaoa/Nlp_Polylm_Assistant_13B_Text_Generation-15B-GGUF|2026-09-19T02:53:32+00:00|Kunlunxin_p-800": {
"taskTypes": [
"text-generation"
],
"updatedAt": "2026-10-04T23:11:32.967800+00:00"
},
"https://modelscope.cn/models/wufubaoa/Nlp_Polylm_Assistant_13B_Text_Generation-15B-GGUF|2026-09-19T02:53:32+00:00|MetaX_c-500": {
"taskTypes": [
"feature_emb",
@@ -6760,6 +6767,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-10-05T02:47:39.072923+00:00",
"taskTreeUpdatedAt": "2026-10-05T02:50:27.702531+00:00",
"version": 1
}

210
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-05T02:18:34.313096+00:00",
"lastSyncTime": "2026-10-05T02:18:34.057662+00:00",
"generatedAt": "2026-10-05T02:48:46.008162+00:00",
"lastSyncTime": "2026-10-05T02:48:45.759650+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3197,29 +3197,29 @@
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 46,
"decisionFailureRate": 0.92,
"decisionSuccessRate": 0.08,
"decisionTotal": 50,
"attributableFailureCount": 47,
"decisionFailureRate": 0.9216,
"decisionSuccessRate": 0.0784,
"decisionTotal": 51,
"failureBreakdown": {
"ambiguous_runtime": 90,
"context_length": 9,
"framework_architecture_unsupported": 36,
"framework_architecture_unsupported": 37,
"memory_capacity": 1,
"platform_infrastructure": 1,
"参数/模板问题": 8
},
"failureCount": 145,
"failureRate": 0.9732,
"failureCount": 146,
"failureRate": 0.9733,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 4,
"successRate": 0.0268,
"successRate": 0.0267,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 149,
"total": 150,
"unresolvedFailureCount": 98
},
"Ascend_910-b3|vllm|text-generation": {
@@ -5247,9 +5247,9 @@
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 619,
"decisionFailureRate": 0.9952,
"decisionSuccessRate": 0.0048,
"decisionTotal": 622,
"decisionFailureRate": 0.9936,
"decisionSuccessRate": 0.0064,
"decisionTotal": 623,
"failureBreakdown": {
"ambiguous_runtime": 109,
"architecture_compatibility": 43,
@@ -5264,16 +5264,16 @@
"参数/模板问题": 9
},
"failureCount": 950,
"failureRate": 0.9969,
"failureRate": 0.9958,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 213,
"successCount": 3,
"successRate": 0.0031,
"successCount": 4,
"successRate": 0.0042,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 953,
"total": 954,
"unresolvedFailureCount": 118
},
"Sunrise_pt-200-x1|vllm|unknown": {
@@ -5777,9 +5777,9 @@
},
"vllm": {
"attributableFailureCount": 3658,
"decisionFailureRate": 0.9726,
"decisionSuccessRate": 0.0274,
"decisionTotal": 3761,
"decisionFailureRate": 0.9724,
"decisionSuccessRate": 0.0276,
"decisionTotal": 3762,
"failureBreakdown": {
"ambiguous_runtime": 1598,
"architecture_compatibility": 112,
@@ -5796,13 +5796,13 @@
"参数/模板问题": 50
},
"failureCount": 6183,
"failureRate": 0.9836,
"failureRate": 0.9835,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 877,
"successCount": 103,
"successRate": 0.0164,
"total": 6286,
"successCount": 104,
"successRate": 0.0165,
"total": 6287,
"unresolvedFailureCount": 1648
},
"vllm-customized": {
@@ -5925,15 +5925,15 @@
"unresolvedFailureCount": 367
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 149,
"decisionFailureRate": 0.9371,
"decisionSuccessRate": 0.0629,
"decisionTotal": 159,
"attributableFailureCount": 150,
"decisionFailureRate": 0.9375,
"decisionSuccessRate": 0.0625,
"decisionTotal": 160,
"failureBreakdown": {
"ambiguous_runtime": 204,
"backend_operator": 15,
"context_length": 9,
"framework_architecture_unsupported": 92,
"framework_architecture_unsupported": 93,
"memory_capacity": 2,
"model_load": 23,
"platform_infrastructure": 3,
@@ -5942,28 +5942,28 @@
"tokenizer_compatibility": 2,
"参数/模板问题": 29
},
"failureCount": 385,
"failureCount": 386,
"failureRate": 0.9747,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 10,
"successRate": 0.0253,
"total": 395,
"total": 396,
"unresolvedFailureCount": 233
}
},
"generatedAt": "2026-10-05T02:18:34.299267+00:00",
"generatedAt": "2026-10-05T02:48:45.994739+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 118,
"decisionFailureRate": 0.8429,
"decisionSuccessRate": 0.1571,
"decisionTotal": 140,
"attributableFailureCount": 119,
"decisionFailureRate": 0.844,
"decisionSuccessRate": 0.156,
"decisionTotal": 141,
"failureBreakdown": {
"ambiguous_runtime": 159,
"context_length": 9,
"framework_architecture_unsupported": 103,
"framework_architecture_unsupported": 104,
"memory_capacity": 2,
"platform_infrastructure": 1,
"repository_structure": 1,
@@ -5972,14 +5972,14 @@
"日志缺失": 3,
"验证失败": 27
},
"failureCount": 348,
"failureRate": 0.9405,
"failureCount": 349,
"failureRate": 0.9407,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 22,
"successRate": 0.0595,
"total": 370,
"successRate": 0.0593,
"total": 371,
"unresolvedFailureCount": 229
},
"Ascend_910-b4": {
@@ -6290,9 +6290,9 @@
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 764,
"decisionFailureRate": 0.8884,
"decisionSuccessRate": 0.1116,
"decisionTotal": 860,
"decisionFailureRate": 0.8873,
"decisionSuccessRate": 0.1127,
"decisionTotal": 861,
"failureBreakdown": {
"ambiguous_runtime": 162,
"architecture_compatibility": 44,
@@ -6308,13 +6308,13 @@
"验证失败": 32
},
"failureCount": 1423,
"failureRate": 0.9368,
"failureRate": 0.9362,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 237,
"successCount": 96,
"successRate": 0.0632,
"total": 1519,
"successCount": 97,
"successRate": 0.0638,
"total": 1520,
"unresolvedFailureCount": 422
},
"Vastai_va16": {
@@ -6508,6 +6508,29 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma4_unified|compressed-tensors": {
"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": "gemma4_unified",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma4_unified|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -22557,6 +22580,27 @@
"total": 4,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|llama|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|qwen2|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -29056,6 +29100,30 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma4_unified|compressed-tensors|33": {
"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": 33,
"modelType": "gemma4_unified",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma4_unified|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -53652,6 +53720,28 @@
"total": 2,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|llama|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|qwen2|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -56992,20 +57082,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17310,
"totalRecords": 17534,
"terminalRecords": 17312,
"totalRecords": 17536,
"totals": {
"attributableFailureCount": 6219,
"decisionFailureRate": 0.8644,
"decisionSuccessRate": 0.1356,
"decisionTotal": 7195,
"attributableFailureCount": 6220,
"decisionFailureRate": 0.8642,
"decisionSuccessRate": 0.1358,
"decisionTotal": 7197,
"failureBreakdown": {
"ambiguous_runtime": 4538,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 128,
"context_length": 327,
"framework_architecture_unsupported": 2248,
"framework_architecture_unsupported": 2249,
"memory_capacity": 1206,
"model_load": 564,
"platform_infrastructure": 949,
@@ -57016,14 +57106,14 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16334,
"failureCount": 16335,
"failureRate": 0.9436,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 949,
"successCount": 976,
"successCount": 977,
"successRate": 0.0564,
"total": 17310,
"total": 17312,
"unresolvedFailureCount": 9166
},
"warnings": [
@@ -57084,6 +57174,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17534,
"summarizedRecords": 17536,
"version": 1
}

1212
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1434
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

18
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.22.1",
"checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "f9150936356a96ad18f33a1f970b4e1de481b7281b5131804a1bd178624c7f75",
".modelhub_state/architecture_compatibility_blacklist.json": "2c0d2e2d042b1972af141e226c037777bcc2e4a4373621deea07262a7b712169",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "8b454a35b796f3aa5e7dd8dcf7eeaad152337c200187b141c8a8e382c183c624",
".modelhub_state/official_capabilities.json": "5b80d8a951c3ae9cff0448d4aeae00b1e8bc4c78b5cdc9210f8a47cd92a946b2",
".modelhub_state/outcome_checkpoint.json": "79af5fcd83d64acfd17290e016061afade3d13ae7e796ee9dd5bbfab6cabdaba",
".modelhub_state/market_intelligence.json": "9fa00a8d8e706b9c2a5e045f9c505181d2a2c7d36287fd9dd11283b65959f129",
".modelhub_state/official_capabilities.json": "aa9046d52a2baf246303c95c37e207f4f36ead5ce6eca75eb445542de2027a92",
".modelhub_state/outcome_checkpoint.json": "5b5dc58228bbd442487e9eeb7d97644fad1036d8fa1e7c83801d17f20056e705",
".modelhub_state/queue_cleanup_latest.json": "73d3f29a4f9db7b9e289242bd87dbd209dc47759f5c0f48e1aeaf7388029df97",
".modelhub_state/recent_outcomes.jsonl": "66f65405defcf850f044e43e54c3dc291f18521f309cb9962d861b493cb049ac",
".modelhub_state/recovery_active_tasks.jsonl": "8c261516b85f818336895278230bbca532ce913d343bc7ae17086bddc034a96b",
".modelhub_state/recovery_intents.jsonl": "d8b59fcac57879b80a292ff3383b090946133e28c0a42d6a8f4123e9e35447a7",
".modelhub_state/recovery_active_tasks.jsonl": "bba876e83da3dbb7fbd3be052d8f0f5f354243564125aa27c658dd01d6b58167",
".modelhub_state/recovery_intents.jsonl": "9abf1cf8a9c84fc9c9a1493ce97828dc328fdd62970d18653613a6e4e14aa46a",
".modelhub_state/routing_intelligence.json": "0eda17137338380d4c945948c5b057eca4c84e12eb866a1ed814782a58f1243d",
".modelhub_state/submission_exclusions.jsonl": "8a533753b09639322718ffe59fad6a6f11e8cc3741d7be12085a149c97ca5507",
".modelhub_state/worker_crashes.jsonl": "50ffe2fb7a8d9d9967ff97b47af26f97753a0bbeae8a68113a221474751d9c2d",
"ledger/submissions.jsonl": "3cdc7adad2c8d9842ac32844ee90fd686a25b52a30640e89eeed4dbf66751d35",
"outcomes/submissions.jsonl": "f8621681d80b2cfe76045214e8b0a02fdba2421f72104b8e7a48e4b5b444f427"
"outcomes/submissions.jsonl": "a4ed1b3a0611782c4d487a67ab857fd54140f53a15e821d3089faeead1d010d8"
},
"generation": 20701,
"generation": 20702,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-10-05T02:47:42.655030+00:00",
"updatedAt": "2026-10-05T02:50:58.333148+00:00",
"writerId": "2a476b5b64aa45219c00032efc0102bb"
}

4
outcomes/submissions.jsonl
View File

@@ -35,7 +35,6 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T09:05:31.097932+00:00", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "78f026e44886f960cbcecb5cfbfc4b0b2239d86ba4b225a73df72965f73e0ed2", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679710688, "estimatedRequiredGiB": 10.371, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 9280253884, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9280253884}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T00:49:03.895304+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4707512", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T09:34:21.991798+00:00", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "e2a7b7c51552e96dae7e97291f0664b9c7fbde7d5b1322eb96e684dc410a4ec3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679710688, "estimatedRequiredGiB": 10.371, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 9280253884, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9280253884}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T01:08:15.662956+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4707808", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T09:34:21.991771+00:00", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "47b99bf102c8c855259a4427d2ee4726c9c38833b231e86c64e74198958fa242", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679710688, "estimatedRequiredGiB": 10.371, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 9280253884, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9280253884}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T01:27:22.581440+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4708072", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T13:16:14.206207+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043805854, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043805854}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T05:08:32.946681+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4711416", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T17:52:18.933043+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426469123, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426469123}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T09:50:25.159456+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4716485", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T18:32:01.542042+00:00", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "c03adae4b35c577b219efa214a72e6ba0eee2287660172b6efc70ec1f7b26139", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679710688, "estimatedRequiredGiB": 10.372, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 9280496017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9280496017}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T10:26:22.306973+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4717031", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T20:25:19.301759+00:00", "modelId": "Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "c0a22d315ebe878ba44106414a577af03c793aca1443a9ac1292a8dddeb30f64", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1908528192, "estimatedRequiredGiB": 5.052, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4520619452, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1791080448, "modelscopeTags": ["license:apache-2.0", "library:pytorch", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4520619479}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T12:23:10.100285+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4718771", "taskType": "text-generation", "verifyResult": null}
@@ -162,7 +161,6 @@
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T11:10:38.766358+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-09-20T03:09:17.840209+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969321", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:10:38.766033+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:18.555119+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969364", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:30:54.600185+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:24.241562+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969620", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600416+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 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": "2026-09-20T03:25:32.045316+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969632", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.599986+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.252209+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969648", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600049+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-20T03:25:32.237107+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969645", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.599773+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:23.763321+00:00", "targetGpu": "MetaX_c-500", "taskId": "4969808", "taskType": "text-generation", "verifyResult": null}
@@ -730,5 +728,5 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-04T03:01:41.555967+00:00", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20593110848, "estimatedRequiredGiB": 23.04, "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": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:sglang", "custom_tag:gptq", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:compressed-tensors", "custom_tag:llm-compressor", "custom_tag:safetensors", "custom_tag:qwen3.8", "custom_tag:conversational", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:roleplay", "custom_tag:character", "custom_tag:humanlike", "custom_tag:uncensored"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": "compressed-tensors", "recursiveRepositoryBytes": 20616225866, "repositoryOnDiskBytes": 20616225866}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T18:55:00.153550+00:00", "targetGpu": "Biren_166m", "taskId": "5263453", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-04T03:19:12.246914+00:00", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20593110848, "estimatedRequiredGiB": 23.04, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:sglang", "custom_tag:gptq", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:compressed-tensors", "custom_tag:llm-compressor", "custom_tag:safetensors", "custom_tag:qwen3.8", "custom_tag:conversational", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:roleplay", "custom_tag:character", "custom_tag:humanlike", "custom_tag:uncensored"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": "compressed-tensors", "recursiveRepositoryBytes": 20616225866, "repositoryOnDiskBytes": 20616225866}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T19:12:16.744930+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5264047", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-04T10:01:33.651736+00:00", "modelId": "SC117/Ornith-1.0-35B-Heretic-MTP", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 71908134368, "estimatedRequiredGiB": 80.398, "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": 71938541955, "modelscopeLicense": "mit", "modelscopeParams": 35951822704, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen3_5_moe", "custom_tag:reasoning", "custom_tag:agentic-coding", "custom_tag:heretic", "custom_tag:mtp", "custom_tag:apex", "custom_tag:quantization", "custom_tag:gguf", "custom_tag:multimodal", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 71938541955, "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-23T21:42:41.557218+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": 1, "unresolvedFailureCount": 1}, "recursiveRepositoryBytes": 71938541955, "repositoryOnDiskBytes": 71938541955}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-04T01:54:06.844290+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5270463", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "5f9f3c1607c4d592480a2bc6bf4bd3811708695139f6772f4b18a577c41a71ec", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 585441264, "estimatedRequiredGiB": 0.677, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "recursiveRepositoryBytes": 605680752, "repositoryOnDiskBytes": 605680752}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-04T18:41:34.446649+00:00", "targetGpu": "MetaX_c-500", "taskId": "5285150", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-05T02:48:45.759610+00:00", "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "5f9f3c1607c4d592480a2bc6bf4bd3811708695139f6772f4b18a577c41a71ec", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 585441264, "estimatedRequiredGiB": 0.677, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "recursiveRepositoryBytes": 605680752, "repositoryOnDiskBytes": 605680752}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-04T18:41:34.446649+00:00", "targetGpu": "MetaX_c-500", "taskId": "5285150", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 585441264, "estimatedRequiredGiB": 0.677, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "recursiveRepositoryBytes": 605680752, "repositoryOnDiskBytes": 605680752}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-04T18:58:49.550875+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5285433", "taskType": "text-generation", "verifyResult": null}