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

state: generation 35402 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-10-25 04:09:43 +00:00
parent 7207adbc00
commit 9f01c48455
7 changed files with 496 additions and 455 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -483,7 +483,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-10-25T04:07:36.351465+00:00",
"generatedAt": "2026-10-25T04:09:41.833699+00:00",
"summary": {
"activeBlockCount": 24,
"byGpuFramework": {

2
.modelhub_state/market_intelligence.json
View File

@@ -452,7 +452,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-25T04:07:36.457272+00:00",
"generatedAt": "2026-10-25T04:09:41.954417+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

751
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

160
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-25T02:41:12.970613+00:00",
"lastSyncTime": "2026-10-25T02:41:12.740710+00:00",
"generatedAt": "2026-10-25T04:09:41.734219+00:00",
"lastSyncTime": "2026-10-25T04:09:41.435062+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -600,25 +600,25 @@
"decisionSuccessRate": 0.0678,
"decisionTotal": 59,
"failureBreakdown": {
"ambiguous_runtime": 97,
"ambiguous_runtime": 98,
"context_length": 9,
"framework_architecture_unsupported": 45,
"memory_capacity": 1,
"platform_infrastructure": 1,
"参数/模板问题": 42
},
"failureCount": 195,
"failureRate": 0.9799,
"failureCount": 196,
"failureRate": 0.98,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 4,
"successRate": 0.0201,
"successRate": 0.02,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 199,
"unresolvedFailureCount": 139
"total": 200,
"unresolvedFailureCount": 140
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 75,
@@ -780,18 +780,18 @@
"unresolvedFailureCount": 17
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 39,
"attributableFailureCount": 40,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 39,
"decisionTotal": 40,
"failureBreakdown": {
"ambiguous_runtime": 104,
"framework_architecture_unsupported": 38,
"framework_architecture_unsupported": 39,
"platform_infrastructure": 1,
"repository_structure": 1,
"参数/模板问题": 36
},
"failureCount": 180,
"failureCount": 181,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
@@ -801,7 +801,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 180,
"total": 181,
"unresolvedFailureCount": 140
},
"Ascend_910-b4|vllm|text-generation": {
@@ -3356,15 +3356,15 @@
"unresolvedFailureCount": 486
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 177,
"decisionFailureRate": 0.9465,
"decisionSuccessRate": 0.0535,
"decisionTotal": 187,
"attributableFailureCount": 178,
"decisionFailureRate": 0.9468,
"decisionSuccessRate": 0.0532,
"decisionTotal": 188,
"failureBreakdown": {
"ambiguous_runtime": 216,
"ambiguous_runtime": 217,
"backend_operator": 17,
"context_length": 10,
"framework_architecture_unsupported": 115,
"framework_architecture_unsupported": 116,
"memory_capacity": 2,
"model_load": 25,
"platform_infrastructure": 3,
@@ -3373,18 +3373,18 @@
"tokenizer_compatibility": 2,
"参数/模板问题": 135
},
"failureCount": 531,
"failureRate": 0.9815,
"failureCount": 533,
"failureRate": 0.9816,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 10,
"successRate": 0.0185,
"total": 541,
"unresolvedFailureCount": 351
"successRate": 0.0184,
"total": 543,
"unresolvedFailureCount": 352
}
},
"generatedAt": "2026-10-25T02:41:12.957153+00:00",
"generatedAt": "2026-10-25T04:09:41.720984+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 133,
@@ -3392,7 +3392,7 @@
"decisionSuccessRate": 0.1419,
"decisionTotal": 155,
"failureBreakdown": {
"ambiguous_runtime": 166,
"ambiguous_runtime": 167,
"context_length": 9,
"framework_architecture_unsupported": 116,
"memory_capacity": 2,
@@ -3404,25 +3404,25 @@
"日志缺失": 3,
"验证失败": 27
},
"failureCount": 404,
"failureRate": 0.9484,
"failureCount": 405,
"failureRate": 0.9485,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 22,
"successRate": 0.0516,
"total": 426,
"unresolvedFailureCount": 270
"successRate": 0.0515,
"total": 427,
"unresolvedFailureCount": 271
},
"Ascend_910-b4": {
"attributableFailureCount": 339,
"decisionFailureRate": 0.8412,
"decisionSuccessRate": 0.1588,
"decisionTotal": 403,
"attributableFailureCount": 340,
"decisionFailureRate": 0.8416,
"decisionSuccessRate": 0.1584,
"decisionTotal": 404,
"failureBreakdown": {
"ambiguous_runtime": 255,
"context_length": 1,
"framework_architecture_unsupported": 195,
"framework_architecture_unsupported": 196,
"memory_capacity": 19,
"model_load": 85,
"platform_infrastructure": 3,
@@ -3432,14 +3432,14 @@
"日志缺失": 14,
"验证失败": 175
},
"failureCount": 1086,
"failureRate": 0.9443,
"failureCount": 1087,
"failureRate": 0.9444,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 64,
"successRate": 0.0557,
"total": 1150,
"successRate": 0.0556,
"total": 1151,
"unresolvedFailureCount": 744
},
"Biren_166m": {
@@ -4176,10 +4176,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2,
"ambiguous_runtime": 3,
"参数/模板问题": 2
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "k2_horizon",
@@ -4191,8 +4191,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
"total": 5,
"unresolvedFailureCount": 5
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|k2_horizon|none": {
"attributableFailureCount": 0,
@@ -6060,14 +6060,14 @@
"unresolvedFailureCount": 7
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|plamo3|none": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "plamo3",
@@ -6079,7 +6079,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|prism_hadamard_qwen35|none": {
@@ -28900,10 +28900,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1,
"ambiguous_runtime": 2,
"参数/模板问题": 1
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 32,
@@ -28916,8 +28916,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|k2_horizon|compressed-tensors|33": {
"attributableFailureCount": 0,
@@ -32228,6 +32228,30 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|plamo3|none|30": {
"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": 30,
"modelType": "plamo3",
"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|plamo3|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -62121,20 +62145,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 18049,
"totalRecords": 18593,
"terminalRecords": 18051,
"totalRecords": 18595,
"totals": {
"attributableFailureCount": 6374,
"decisionFailureRate": 0.866,
"decisionSuccessRate": 0.134,
"decisionTotal": 7360,
"attributableFailureCount": 6375,
"decisionFailureRate": 0.8661,
"decisionSuccessRate": 0.1339,
"decisionTotal": 7361,
"failureBreakdown": {
"ambiguous_runtime": 4683,
"ambiguous_runtime": 4684,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 137,
"context_length": 328,
"framework_architecture_unsupported": 2368,
"framework_architecture_unsupported": 2369,
"memory_capacity": 1207,
"model_load": 577,
"platform_infrastructure": 972,
@@ -62145,21 +62169,20 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 17063,
"failureCount": 17065,
"failureRate": 0.9454,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 972,
"successCount": 986,
"successRate": 0.0546,
"total": 18049,
"unresolvedFailureCount": 9717
"total": 18051,
"unresolvedFailureCount": 9718
},
"warnings": [
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -62167,8 +62190,9 @@
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 MetaX_c-500|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Biren_166m|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -62216,6 +62240,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 18593,
"summarizedRecords": 18595,
"version": 1
}

12
.modelhub_state/recovery_intents.jsonl
View File

@@ -3810,6 +3810,18 @@
{"batchId": "a3600559e38849dab8a537b39bd6c6b7", "completedAt": "2026-10-25T02:52:53.138378+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-25T02:52:50.883782+00:00", "framework": "vllm_tokenizer_patch", "intentId": "25dc79da915e45ffa87ae1c4aa1d37d2", "lastModified": "2026-10-24T12:01:13+00:00", "modelAddress": "https://modelscope.cn/models/kakarotter/calix", "reason": null, "reconciledAt": "2026-10-25T04:08:09.877212+00:00", "repoId": "kakarotter/calix", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5771333", "taskType": "text-generation"}
{"batchId": "3847981ede0c44208ee957b63c7529ab", "completedAt": "2026-10-25T03:12:44.632876+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T03:12:42.283230+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cefc269bf0bf4509a434e70429166d48", "lastModified": "2026-10-21T16:19:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-25T04:08:09.874912+00:00", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5771609", "taskType": "text-generation"}
{"batchId": "c2f0892325ba48a0911df4438b19ac90", "completedAt": "2026-10-25T03:50:03.824728+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-25T03:49:58.711717+00:00", "framework": "vllm_tokenizer_patch", "intentId": "598d845f0b0e48c4b68b25e922a1ee0f", "lastModified": "2026-10-21T17:02:31+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-25T04:08:09.874578+00:00", "repoId": "cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5772051", "taskType": "text-generation"}
{"batchId": "60f7b650d05c4b40b735c57ffec07191", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:09:43.341687+00:00", "framework": "vllm_tokenizer_patch", "intentId": "88f53d67883c4fc7a70fb3959666427e", "lastModified": "2026-10-21T15:40:57+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Explore-AWQ-8bit", "repoId": "cyankiwi/AgentCPM-Explore-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "60f7b650d05c4b40b735c57ffec07191", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:09:43.341787+00:00", "framework": "vllm_tokenizer_patch", "intentId": "af097b507be04180be3cae9c80fa9b10", "lastModified": "2026-10-21T16:21:36+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Report-AWQ-8bit", "repoId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "60f7b650d05c4b40b735c57ffec07191", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:09:43.341834+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fa417f509cc24974832d9859d510b9a0", "lastModified": "2026-10-21T17:24:35+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Orchestrator-8B-AWQ-4bit", "repoId": "cyankiwi/Orchestrator-8B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "60f7b650d05c4b40b735c57ffec07191", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:09:43.341878+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a90c038b6426465f8516c62fdb8f7061", "lastModified": "2026-10-21T16:41:10+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "60f7b650d05c4b40b735c57ffec07191", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:09:43.341921+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f9008447829343ae96229f1f59cbbdbe", "lastModified": "2026-10-21T16:33:24+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-4B-Instruct-2507-AWQ-4bit", "repoId": "cyankiwi/Qwen3-4B-Instruct-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "60f7b650d05c4b40b735c57ffec07191", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:09:43.341968+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bc98203b5dae4879acaa60423e945b45", "lastModified": "2026-10-22T01:37:07+00:00", "modelAddress": "https://modelscope.cn/models/RecursiveSI/flint-int4", "repoId": "RecursiveSI/flint-int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "60f7b650d05c4b40b735c57ffec07191", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:09:43.342011+00:00", "framework": "vllm_fix_tokenizer", "intentId": "10df607cf1124b8d86ffa5382593778a", "lastModified": "2026-10-22T14:14:09+00:00", "modelAddress": "https://modelscope.cn/models/InternScience/Sage-A1.5-FP8", "repoId": "InternScience/Sage-A1.5-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "60f7b650d05c4b40b735c57ffec07191", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:09:43.342053+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9facbb9a5fe94c128625418063eb7b41", "lastModified": "2026-10-21T16:19:52+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "repoId": "cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "60f7b650d05c4b40b735c57ffec07191", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:09:43.342096+00:00", "framework": "vllm_fix_tokenizer", "intentId": "29372921a99249b9b1cfc9dd115e950d", "lastModified": "2026-10-21T15:33:25+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/GLM-4.7-Flash-REAP-23B-A3B-AWQ-8bit", "repoId": "cyankiwi/GLM-4.7-Flash-REAP-23B-A3B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "60f7b650d05c4b40b735c57ffec07191", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:09:43.342137+00:00", "framework": "vllm_fix_tokenizer", "intentId": "45123a602b4648e58727b5c1fe5cc9b1", "lastModified": "2026-10-24T12:07:57+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-24B-A2B-Base", "repoId": "LiquidAI/LFM2.5-24B-A2B-Base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "60f7b650d05c4b40b735c57ffec07191", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:09:43.342188+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dd081201be434f7c9d72ffc69d073040", "lastModified": "2026-10-21T16:56:28+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "repoId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "60f7b650d05c4b40b735c57ffec07191", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:09:43.342231+00:00", "framework": "vllm_fix_tokenizer", "intentId": "260ae0802d6b4a6eaa3a135f5ca7eb20", "lastModified": "2026-10-21T16:38:24+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-4B-Instruct-2507-AWQ-8bit", "repoId": "cyankiwi/Qwen3-4B-Instruct-2507-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "5cd726cc6d2f4e5ab444c7f8c7465f2c", "completedAt": "2026-10-25T04:08:07.803695+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:08:05.267077+00:00", "framework": "vllm_fix_tokenizer", "intentId": "206eae01c50c476ea8da1caf116167a6", "repoId": "cyankiwi/Qwen3-4B-Instruct-2507-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "5cd726cc6d2f4e5ab444c7f8c7465f2c", "completedAt": "2026-10-25T04:08:07.803692+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:08:05.267034+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e0f388072b704ccb9661d6013080c3e3", "repoId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}
{"batchId": "5cd726cc6d2f4e5ab444c7f8c7465f2c", "completedAt": "2026-10-25T04:08:07.803690+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-25T04:08:05.266991+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7aec45dc35f144038aa48474032f8138", "repoId": "LiquidAI/LFM2.5-24B-A2B-Base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}

18
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/account_capacity.json": "1c7c5471875164d0ee02685db9ee0d91ff14a64a87227ade4c319c9a296c3067",
".modelhub_state/architecture_compatibility_blacklist.json": "1bdc66a3a981ec6402a481559aa030798e86b21d115034528eecdf8ed2b99163",
".modelhub_state/architecture_compatibility_blacklist.json": "ae3444c59a700562a3780070e5942634eba585fa43596b9a04c1370ed9aad11a",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "03972b70c7f12a4224452761d57ea29dd3e5934dd8045aaf1227b45f3ba1cf1c",
".modelhub_state/official_capabilities.json": "cf78b53522a240a5247ea350eca017b83a93ecc3a3fcd0af892e7da47c8abc4f",
".modelhub_state/outcome_checkpoint.json": "e6086aa544a83f55e0126ad493e3ee2e952b27113bfe97261e3a3d61a68b8fac",
".modelhub_state/market_intelligence.json": "558dc35d423aa84bb47e65abf74c52b205d32208fce147828a6abecec4912d17",
".modelhub_state/official_capabilities.json": "d81a3296ddbfd850d6ef38ee5994d26cb15b29b1771254d1d55b1cd3eddbbca8",
".modelhub_state/outcome_checkpoint.json": "14bec57ce67dff7eef57dfb1ed013b8d0bd3ab316dc69ee115eabe86f4ca9462",
".modelhub_state/queue_cleanup_latest.json": "341e6aae8ffd1a8bd62598f03da01e72fbe44f00f20996aa3f865cb969063921",
".modelhub_state/recent_outcomes.jsonl": "830c2ff111f59760a2ea62ad4bafc21041089715791d16819acba29dc71281a1",
".modelhub_state/recovery_active_tasks.jsonl": "f533e4583e721fd3252b2c73ca1daf5aafc19fc588bc50c5152d5a07047dcd89",
".modelhub_state/recovery_intents.jsonl": "20c221af19d827a7dd05ed89aaefab6f9155320c41507b8d463d14fd32ab3292",
".modelhub_state/recovery_intents.jsonl": "961dd105644da76394fbe96d7d74b0e5b02e9de4f2603d1f15837a96edd774a7",
".modelhub_state/routing_intelligence.json": "0ba3d1e5053bf0b2987c5062a5580f279d135ea55a47993d5d69bd499565861d",
".modelhub_state/submission_exclusions.jsonl": "ec0164a066e590a129ed69be5c4279284ccf1a85230e402be88754b03203581d",
".modelhub_state/worker_crashes.jsonl": "e436652d39bca5bcba31822ff9fb949a9d7ff0b7f509c170e258a53d7e01ce9a",
"ledger/submissions.jsonl": "148582f3d9ece7ca297d1037d42dae3b40edc3022aab65f6d64f59af8b7672c2",
"outcomes/submissions.jsonl": "932e2cea7a186ad716aafcfd38d02882dc72e83a8fc97ccdb73fe68c775578bf"
"outcomes/submissions.jsonl": "f441c281254f7eda929676310baa5d466c51ae369e9afe77cf30a704b2255fad"
},
"generation": 35401,
"phase": "cycle",
"generation": 35402,
"phase": "intent",
"schemaVersion": 1,
"updatedAt": "2026-10-25T04:08:10.075061+00:00",
"updatedAt": "2026-10-25T04:09:43.569598+00:00",
"writerId": "5c9906c400e2442789cb0c734d70dc03"
}

6
outcomes/submissions.jsonl
View File

@@ -177,7 +177,6 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-25T03:25:42.283046+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4749242120, "estimatedRequiredGiB": 5.332, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 4771310100, "modelscopeLicense": "apache-2.0", "modelscopeParams": 641597440, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4771310100}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T19:25:32.053050+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5067314", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-25T03:43:19.254270+00:00", "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:finance", "custom_tag:plamo", "custom_tag:japanese"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1784320455}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T19:41:33.877962+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5067516", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-25T04:01:29.477054+00:00", "modelId": "NovelAI/clio-v1-legacy", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6358779576, "estimatedRequiredGiB": 7.111, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": null, "modelscopeLicense": "gpl-2.0", "modelscopeParams": 550792704, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6362590564}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T19:58:03.287508+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5067706", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-25T04:01:29.477034+00:00", "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:finance", "custom_tag:plamo", "custom_tag:japanese"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1784320455}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T19:58:03.285795+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5067707", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-25T04:32:54.853030+00:00", "modelId": "bartowski/junshim_When2Think-ThinkOnly-1.5B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "6070792dbccc0c99f5d8084cd735fc62b3a83b09a4192b662e3ec76ed05d0097", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1077324288, "estimatedRequiredGiB": 30.563, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": null, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:reasoning", "custom_tag:mathematical", "custom_tag:hybrid-reasoning", "custom_tag:adaptive-reasoning", "custom_tag:efficient-reasoning", "custom_tag:reinforcement-learning", "custom_tag:rlvr", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 27347406407}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T20:29:28.351567+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5068184", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-25T04:49:22.358498+00:00", "modelId": "bartowski/junshim_When2Think-ThinkOnly-1.5B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "b14915854fdddc06b6a8c39ae8b301bc36a6f8013c018c670701ab21e4acf1d5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1077324288, "estimatedRequiredGiB": 30.563, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": null, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:reasoning", "custom_tag:mathematical", "custom_tag:hybrid-reasoning", "custom_tag:adaptive-reasoning", "custom_tag:efficient-reasoning", "custom_tag:reinforcement-learning", "custom_tag:rlvr", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 27347406407}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T20:45:41.553663+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5068454", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-25T05:31:58.654970+00:00", "modelId": "IFM/K2-Horizon-3.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "71b286877104f52ac286472d0633f723ac75ea7a5ffc4d00b05c6ed54f8e4d68", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5386404224, "estimatedRequiredGiB": 33.587, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 30053117770, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5058255360, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30053117770}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T21:31:50.103776+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5068916", "taskType": "text-generation", "verifyResult": null}
@@ -287,7 +286,6 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253519+00:00", "modelId": "PleIAs/baguettotron-600m", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1216600244, "estimatedRequiredGiB": 1.365, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1221756819, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1221756819}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:50.046146+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260125", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253594+00:00", "modelId": "Akahsizrr/Cyber-Prime-1.1-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427432, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412809492, "modelscopeLicense": "other", "modelscopeParams": 209741824, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412809492}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:50.055568+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260122", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253551+00:00", "modelId": "mlx-community/Mistral-Small-4-119B-2603-OptiQ-2bit", "modelProfile": {"architectures": ["Mistral3ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 45795315925, "estimatedRequiredGiB": 51.2, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral3", "modelscopeFileSize": 45812947877, "modelscopeLicense": "apache-2.0", "modelscopeParams": 13531266048, "modelscopeTags": ["license:apache-2.0", "model_type:mistral3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 45812947877}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:50.174543+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260127", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253624+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4749242120, "estimatedRequiredGiB": 5.332, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 4771310100, "modelscopeLicense": "apache-2.0", "modelscopeParams": 641597440, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4771310100}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:50.159779+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260129", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253257+00:00", "modelId": "danish-foundation-models/DFM-Mimir-v1.5", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3573566200, "estimatedRequiredGiB": 4.03, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 3606214195, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1786775040, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:danish", "custom_tag:english", "custom_tag:hrm-text", "custom_tag:instruction-tuned", "custom_tag:prefix-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3606214195}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:50.252031+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260130", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253310+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580733, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580733}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:50.259431+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260132", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253674+00:00", "modelId": "IFM/K2-Horizon-MoVA-36B-A4B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 48357709120, "estimatedRequiredGiB": 54.081, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 48390780116, "modelscopeLicense": "apache-2.0", "modelscopeParams": 37444792020, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:36b", "custom_tag:mova", "custom_tag:moe", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 48390780116}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:50.253737+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260131", "taskType": "text-generation", "verifyResult": null}
@@ -1087,8 +1085,8 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-25T01:29:02.231151+00:00", "modelId": "cyankiwi/MiroThinker-v1.0-30B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115836146, "modelscopeLicense": "mit", "modelscopeParams": 30532122624, "modelscopeTags": ["license:mit", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:open-source", "custom_tag:miromind", "custom_tag:deep-research"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115836146}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T17:28:41.168154+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5764371", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-25T01:55:12.935547+00:00", "modelId": "InternScience/Sage-A1.5-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 39365363088, "estimatedRequiredGiB": 44.025, "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": 39392487901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "task:text-generation", "custom_tag:moe", "custom_tag:vlm", "custom_tag:vision", "custom_tag:agentic", "custom_tag:code", "custom_tag:tool-use"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 39392487901}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T17:55:08.331226+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5764732", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T02:42:53.537287+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {"architectures": ["MiniCPMSALAForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6196491480, "estimatedRequiredGiB": 6.931, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm_sala", "modelscopeFileSize": 6201618087, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9477203968, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm_sala", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6201618087}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T18:41:25.446286+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5765199", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115902413, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115902413}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T20:08:37.639861+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5766311", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "kakarotter/calix", "modelProfile": {"architectures": [], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2290347504, "estimatedRequiredGiB": 2.562, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 2292275515, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1145157120, "modelscopeTags": ["license:apache-2.0", "library:safetensors", "task:text-generation", "custom_tag:text-generation", "custom_tag:pretraining"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2292275515}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T20:08:37.652020+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5766310", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T04:09:41.435018+00:00", "modelId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115902413, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115902413}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T20:08:37.639861+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5766311", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-25T04:09:41.435054+00:00", "modelId": "kakarotter/calix", "modelProfile": {"architectures": [], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2290347504, "estimatedRequiredGiB": 2.562, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 2292275515, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1145157120, "modelscopeTags": ["license:apache-2.0", "library:safetensors", "task:text-generation", "custom_tag:text-generation", "custom_tag:pretraining"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2292275515}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T20:08:37.652020+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5766310", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/AgentCPM-Explore-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3600063736, "estimatedRequiredGiB": 4.041, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3615960571, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3615960571}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T20:16:08.741643+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5766395", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921096, "estimatedRequiredGiB": 15.787, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 14125731418, "modelscopeLicense": "other", "modelscopeParams": 8190735360, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:Nemotron-Cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14125731418}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T20:16:08.740412+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5766394", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115902413, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115902413}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T20:52:23.183394+00:00", "targetGpu": "MetaX_c-500", "taskId": "5766836", "taskType": "text-generation", "verifyResult": null}