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

state: generation 26940 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-10-21 13:03:21 +00:00
parent 3dca7e4b07
commit 7f10ac1643
7 changed files with 102 additions and 111 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -850,7 +850,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-10-21T13:01:23.387983+00:00",
"generatedAt": "2026-10-21T13:03:10.508198+00:00",
"summary": {
"activeBlockCount": 41,
"byGpuFramework": {

2
.modelhub_state/market_intelligence.json
View File

@@ -452,7 +452,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-21T13:01:23.466490+00:00",
"generatedAt": "2026-10-21T13:03:10.576618+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

6
.modelhub_state/official_capabilities.json
View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-10-21T13:01:23.466490+00:00",
"catalogUpdatedAt": "2026-10-21T13:03:10.576618+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-10-21T13:01:23.466490+00:00",
"generatedAt": "2026-10-21T13:03:10.576618+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6696,6 +6696,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-10-21T13:01:23.466490+00:00",
"taskTreeUpdatedAt": "2026-10-21T13:03:10.576618+00:00",
"version": 1
}

167
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-21T12:36:20.529064+00:00",
"lastSyncTime": "2026-10-21T12:36:20.265435+00:00",
"generatedAt": "2026-10-21T13:03:10.412608+00:00",
"lastSyncTime": "2026-10-21T13:03:09.363168+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -649,25 +649,6 @@
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation"
},
"kunlunxin_p-800|vllm|text-generation|model_type:lfm2_moe": {
"architectureSignature": "model_type:lfm2_moe",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-21T12:49:01.246640+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-21T12:49:01.246640+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "lfm2_moe",
"sourceModelIds": [
"LiquidAI/LFM2.5-8B-A1B"
],
"sourceTaskIds": [
"5001066"
],
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation"
},
"metax_c-500|vllm_tokenizer_patch|text-generation|architectures:spark2_5forcausallm": {
"architectureSignature": "architectures:spark2_5forcausallm",
"architectures": [
@@ -874,7 +855,7 @@
}
},
"architectureCompatibilitySummary": {
"activeBlockCount": 42,
"activeBlockCount": 41,
"byGpuFramework": {
"Ascend_910-b3|vllm": 2,
"Ascend_910-b3|vllm_tokenizer_patch": 3,
@@ -887,7 +868,7 @@
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 2,
"Iluvatar_bi-150|vllm_tokenizer_patch": 1,
"Iluvatar_mrv-100|vllm": 4,
"Kunlunxin_p-800|vllm": 2,
"Kunlunxin_p-800|vllm": 1,
"Kunlunxin_p-800|vllm_tokenizer_patch": 1,
"MetaX_c-500|vllm": 1,
"MetaX_c-500|vllm_tokenizer_patch": 4,
@@ -1450,29 +1431,29 @@
"unresolvedFailureCount": 11
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
"attributableFailureCount": 32,
"decisionFailureRate": 0.7805,
"decisionSuccessRate": 0.2195,
"decisionTotal": 41,
"attributableFailureCount": 33,
"decisionFailureRate": 0.7857,
"decisionSuccessRate": 0.2143,
"decisionTotal": 42,
"failureBreakdown": {
"ambiguous_runtime": 52,
"framework_architecture_unsupported": 28,
"framework_architecture_unsupported": 29,
"model_load": 4,
"platform_infrastructure": 1,
"参数/模板问题": 5,
"验证失败": 3
},
"failureCount": 93,
"failureRate": 0.9118,
"failureCount": 94,
"failureRate": 0.9126,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 9,
"successRate": 0.0882,
"successRate": 0.0874,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 102,
"total": 103,
"unresolvedFailureCount": 60
},
"Cambricon_mlu-370-x4|vllm|text-generation": {
@@ -2539,10 +2520,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 191,
"ambiguous_runtime": 192,
"参数/模板问题": 9
},
"failureCount": 200,
"failureCount": 201,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2552,8 +2533,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 200,
"unresolvedFailureCount": 200
"total": 201,
"unresolvedFailureCount": 201
},
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 61,
@@ -3651,27 +3632,27 @@
"unresolvedFailureCount": 58
},
"vllm-mlu": {
"attributableFailureCount": 57,
"decisionFailureRate": 0.7215,
"decisionSuccessRate": 0.2785,
"decisionTotal": 79,
"attributableFailureCount": 58,
"decisionFailureRate": 0.725,
"decisionSuccessRate": 0.275,
"decisionTotal": 80,
"failureBreakdown": {
"ambiguous_runtime": 109,
"framework_architecture_unsupported": 49,
"framework_architecture_unsupported": 50,
"model_load": 7,
"platform_infrastructure": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 47,
"验证失败": 3
},
"failureCount": 217,
"failureRate": 0.9079,
"failureCount": 218,
"failureRate": 0.9083,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 22,
"successRate": 0.0921,
"total": 239,
"successRate": 0.0917,
"total": 240,
"unresolvedFailureCount": 159
},
"vllm-patch-tokenizer": {
@@ -3727,7 +3708,7 @@
"decisionSuccessRate": 0.0359,
"decisionTotal": 195,
"failureBreakdown": {
"ambiguous_runtime": 427,
"ambiguous_runtime": 428,
"backend_operator": 11,
"framework_architecture_unsupported": 56,
"memory_capacity": 11,
@@ -3736,15 +3717,15 @@
"tokenizer_compatibility": 97,
"参数/模板问题": 30
},
"failureCount": 680,
"failureCount": 681,
"failureRate": 0.9898,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 35,
"successCount": 7,
"successRate": 0.0102,
"total": 687,
"unresolvedFailureCount": 457
"total": 688,
"unresolvedFailureCount": 458
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 171,
@@ -3775,7 +3756,7 @@
"unresolvedFailureCount": 339
}
},
"generatedAt": "2026-10-21T12:36:20.512981+00:00",
"generatedAt": "2026-10-21T13:03:10.397691+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 132,
@@ -3864,15 +3845,15 @@
"unresolvedFailureCount": 605
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 766,
"decisionFailureRate": 0.9119,
"decisionSuccessRate": 0.0881,
"decisionTotal": 840,
"attributableFailureCount": 767,
"decisionFailureRate": 0.912,
"decisionSuccessRate": 0.088,
"decisionTotal": 841,
"failureBreakdown": {
"ambiguous_runtime": 517,
"architecture_compatibility": 53,
"context_length": 48,
"framework_architecture_unsupported": 318,
"framework_architecture_unsupported": 319,
"memory_capacity": 219,
"model_load": 8,
"platform_infrastructure": 16,
@@ -3882,14 +3863,14 @@
"日志缺失": 13,
"验证失败": 42
},
"failureCount": 1669,
"failureRate": 0.9575,
"failureCount": 1670,
"failureRate": 0.9576,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 16,
"successCount": 74,
"successRate": 0.0425,
"total": 1743,
"successRate": 0.0424,
"total": 1744,
"unresolvedFailureCount": 887
},
"Cambricon_mlu-370-x8": {
@@ -4008,7 +3989,7 @@
"decisionSuccessRate": 0.066,
"decisionTotal": 106,
"failureBreakdown": {
"ambiguous_runtime": 280,
"ambiguous_runtime": 281,
"backend_operator": 23,
"framework_architecture_unsupported": 37,
"memory_capacity": 3,
@@ -4021,15 +4002,15 @@
"日志缺失": 1,
"验证失败": 23
},
"failureCount": 457,
"failureCount": 458,
"failureRate": 0.9849,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 7,
"successRate": 0.0151,
"total": 464,
"unresolvedFailureCount": 357
"total": 465,
"unresolvedFailureCount": 358
},
"Kunlunxin_r-200-8f": {
"attributableFailureCount": 0,
@@ -10018,16 +9999,16 @@
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none": {
"attributableFailureCount": 6,
"attributableFailureCount": 7,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 7,
"failureBreakdown": {
"framework_architecture_unsupported": 6,
"framework_architecture_unsupported": 7,
"参数/模板问题": 1,
"验证失败": 1
},
"failureCount": 8,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "qwen3_5",
@@ -10039,7 +10020,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 8,
"total": 9,
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_vl|none": {
@@ -17820,10 +17801,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 19,
"ambiguous_runtime": 20,
"参数/模板问题": 2
},
"failureCount": 21,
"failureCount": 22,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5",
@@ -17835,8 +17816,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 21,
"unresolvedFailureCount": 21
"total": 22,
"unresolvedFailureCount": 22
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_moe|none": {
"attributableFailureCount": 0,
@@ -36506,14 +36487,14 @@
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none|34": {
"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-mlu",
"loadSizeLog2Bucket": 34,
@@ -36526,7 +36507,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_vl|none|34": {
@@ -48048,9 +48029,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 7
"ambiguous_runtime": 8
},
"failureCount": 7,
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
@@ -48063,8 +48044,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 7
"total": 8,
"unresolvedFailureCount": 8
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|none|34": {
"attributableFailureCount": 0,
@@ -59113,20 +59094,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17924,
"totalRecords": 18453,
"terminalRecords": 17926,
"totalRecords": 18455,
"totals": {
"attributableFailureCount": 6342,
"decisionFailureRate": 0.8654,
"decisionSuccessRate": 0.1346,
"decisionTotal": 7328,
"attributableFailureCount": 6343,
"decisionFailureRate": 0.8655,
"decisionSuccessRate": 0.1345,
"decisionTotal": 7329,
"failureBreakdown": {
"ambiguous_runtime": 4652,
"ambiguous_runtime": 4653,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 135,
"context_length": 327,
"framework_architecture_unsupported": 2344,
"framework_architecture_unsupported": 2345,
"memory_capacity": 1207,
"model_load": 575,
"platform_infrastructure": 971,
@@ -59137,15 +59118,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16938,
"failureCount": 16940,
"failureRate": 0.945,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 971,
"successCount": 986,
"successRate": 0.055,
"total": 17924,
"unresolvedFailureCount": 9625
"total": 17926,
"unresolvedFailureCount": 9626
},
"warnings": [
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -59208,6 +59189,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 18453,
"summarizedRecords": 18455,
"version": 1
}

12
.modelhub_state/recovery_intents.jsonl
View File

@@ -3668,6 +3668,18 @@
{"batchId": "2be41a3c0ddf47fea7a18dec16f75bf1", "completedAt": "2026-10-21T10:03:54.578225+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T10:03:52.009664+00:00", "framework": "vllm_tokenizer_patch", "intentId": "72dabf7c174648c3ac50e60f466e4581", "lastModified": "2026-10-19T07:00:41+00:00", "modelAddress": "https://modelscope.cn/models/iluvatar-corex/Qwen3-8B-W8A8", "reason": null, "reconciledAt": "2026-10-21T13:01:37.820187+00:00", "repoId": "iluvatar-corex/Qwen3-8B-W8A8", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5692570", "taskType": "text-generation"}
{"batchId": "ac919173e9b549668e5f79d4d4154344", "completedAt": "2026-10-21T12:05:07.909597+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:05:05.603070+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e466b3bec74f453eb1ee33b1b9ab4f6a", "lastModified": "2026-10-19T16:26:03+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Qwen3-30B-A3B-Thinking-2507-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-21T13:01:37.821813+00:00", "repoId": "cpatonn-mirror/Qwen3-30B-A3B-Thinking-2507-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5694040", "taskType": "text-generation"}
{"batchId": "1298d3044c5d4b4595a39868082d85ea", "completedAt": "2026-10-21T12:36:30.480397+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T12:36:27.987113+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ea6347a88beb4f91afccb8b667774938", "lastModified": "2026-10-19T18:17:12+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ", "reason": null, "reconciledAt": "2026-10-21T13:01:37.821341+00:00", "repoId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5694581", "taskType": "text-generation"}
{"batchId": "64f3fcf77b1147a894198b7617fbef51", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:03:20.980462+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e4ff1d53028d4f598a67339e8c2b2b95", "lastModified": "2026-10-19T17:09:46+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "repoId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "64f3fcf77b1147a894198b7617fbef51", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:03:20.980566+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e1507211de814500944f723635c3b472", "lastModified": "2026-10-19T18:03:45+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-4bit", "repoId": "cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "64f3fcf77b1147a894198b7617fbef51", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:03:20.980644+00:00", "framework": "vllm_tokenizer_patch", "intentId": "096eb15c6e4b49c089c71400d5e4a0d5", "lastModified": "2026-10-20T08:50:37+00:00", "modelAddress": "https://modelscope.cn/models/Haodong07/Qwen3-32B-TwinQuant-W4A4", "repoId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "64f3fcf77b1147a894198b7617fbef51", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:03:20.980722+00:00", "framework": "vllm_tokenizer_patch", "intentId": "36f147a6be4645319d74b5c89f67d14e", "lastModified": "2026-10-19T07:00:41+00:00", "modelAddress": "https://modelscope.cn/models/iluvatar-corex/Qwen3-8B-W8A8", "repoId": "iluvatar-corex/Qwen3-8B-W8A8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "64f3fcf77b1147a894198b7617fbef51", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:03:20.980780+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1d59fb765738443d8d49166b74c0fcd7", "lastModified": "2026-10-19T07:29:23+00:00", "modelAddress": "https://modelscope.cn/models/iluvatar-corex/Qwen3-14B-W8A8", "repoId": "iluvatar-corex/Qwen3-14B-W8A8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "64f3fcf77b1147a894198b7617fbef51", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:03:20.980823+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2896e4309ab14ea686074c22fe1e50df", "lastModified": "2026-10-19T17:23:16+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/granite-4.0-h-small-AWQ-4bit", "repoId": "cpatonn-mirror/granite-4.0-h-small-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "64f3fcf77b1147a894198b7617fbef51", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:03:20.980866+00:00", "framework": "vllm_tokenizer_patch", "intentId": "be9f01be12c74cb8a04fe418780163a2", "lastModified": "2026-10-19T18:03:21+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/granite-4.0-h-tiny-AWQ-4bit", "repoId": "cpatonn-mirror/granite-4.0-h-tiny-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "64f3fcf77b1147a894198b7617fbef51", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:03:20.980909+00:00", "framework": "vllm_tokenizer_patch", "intentId": "66343ca729a24366bb221b3f0923dfcc", "lastModified": "2026-10-21T12:17:17+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-24B-A2B", "repoId": "LiquidAI/LFM2.5-24B-A2B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "64f3fcf77b1147a894198b7617fbef51", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:03:20.980975+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ae04201616fb4fe6befd5aebf43a4136", "lastModified": "2026-10-19T18:55:19+00:00", "modelAddress": "https://modelscope.cn/models/shisa-ai/shisa-de-2.1-FP8-dynamic", "repoId": "shisa-ai/shisa-de-2.1-FP8-dynamic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "64f3fcf77b1147a894198b7617fbef51", "configFingerprint": "6227ad7464202af2fd72ed7ba47d960a6db14697bf850d85ff2e90b31777e3a8", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:03:20.981018+00:00", "framework": "llamacpp", "intentId": "a466fa7e4c614f73b8829535b73693da", "lastModified": "2026-10-21T03:15:59+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.6-4B-GGUF", "repoId": "XHToken/Spark-X2.6-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "64f3fcf77b1147a894198b7617fbef51", "configFingerprint": "0810a8dbec6a5bb8330373d71363e8e47f5ab88e5ca0b04cee0d7bb4fc33e81f", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:03:20.981080+00:00", "framework": "llamacpp", "intentId": "0158e624f708438dbae5e26a9d26c852", "lastModified": "2026-10-20T13:54:35+00:00", "modelAddress": "https://modelscope.cn/models/incoai/Muse-Glimmer-30B-DFlash2-GGUF", "repoId": "incoai/Muse-Glimmer-30B-DFlash2-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "64f3fcf77b1147a894198b7617fbef51", "configFingerprint": "e6a494afe49de43cfe2b51111d8b2495fcc9c2b24f0b475f84ce14dcdff5b462", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:03:20.981137+00:00", "framework": "llamacpp", "intentId": "07dec51d385747d893d950b8a4dcf3d6", "lastModified": "2026-10-20T05:58:12+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.7-1B-DSpark-gguf", "repoId": "OpenBMB/MiniCPM-V-4.7-1B-DSpark-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "8f0e9d819d20440b9f06552fbc2a12d4", "completedAt": "2026-10-21T13:01:34.659400+00:00", "configFingerprint": "e6a494afe49de43cfe2b51111d8b2495fcc9c2b24f0b475f84ce14dcdff5b462", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:01:32.028571+00:00", "framework": "llamacpp", "intentId": "6cf9752b77c04d1e8c663336cd781282", "repoId": "OpenBMB/MiniCPM-V-4.7-1B-DSpark-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "8f0e9d819d20440b9f06552fbc2a12d4", "completedAt": "2026-10-21T13:01:34.659395+00:00", "configFingerprint": "0810a8dbec6a5bb8330373d71363e8e47f5ab88e5ca0b04cee0d7bb4fc33e81f", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:01:32.028468+00:00", "framework": "llamacpp", "intentId": "fc87eebc56034f4da94b73ae9d8f66da", "repoId": "incoai/Muse-Glimmer-30B-DFlash2-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "8f0e9d819d20440b9f06552fbc2a12d4", "completedAt": "2026-10-21T13:01:34.659391+00:00", "configFingerprint": "6227ad7464202af2fd72ed7ba47d960a6db14697bf850d85ff2e90b31777e3a8", "configSource": "modelhub_live", "createdAt": "2026-10-21T13:01:32.028361+00:00", "framework": "llamacpp", "intentId": "d261fa8156934f60a7eda654867c5e61", "repoId": "XHToken/Spark-X2.6-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "hygon_k100-ai", "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": "9f2ea8a77c20bc91004cccc664b8f9f05369392fb4e828bfa376627c5414df8b",
".modelhub_state/architecture_compatibility_blacklist.json": "63a63a0396e68a0a0d0dfdf7757b3ce3b1a4b09711029fe375c2ea9d105c2f0d",
".modelhub_state/architecture_compatibility_blacklist.json": "d2585945c4c7c4af0d9d794896a425e8e574946dd2d8fe42422f54a70e15096a",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "348af39038fafc71bf3fab46e2e9692e47e0df0a126e4baa7e73c3e50f335ba9",
".modelhub_state/official_capabilities.json": "945c429b5dd5bdfa3603da0f83650e640917440333ce52ccf5424efb889718cf",
".modelhub_state/outcome_checkpoint.json": "5457645cb521f0c6b2d75b4fb40bdcf5168060096d887f73fa9e0fd142b453d2",
".modelhub_state/market_intelligence.json": "83ccbcd65618a8c365acc58a4e7f02242c8fbd2d3cb05df615bfe0be909219fa",
".modelhub_state/official_capabilities.json": "d8f1940f37729b30c38881dafe213846d80f057f0389c9ed2e4dc9d7a2b86353",
".modelhub_state/outcome_checkpoint.json": "8dcd3d4c1a3327cd0b7e91e692d7a4711a1d1bb005ce133412273e741cb8a551",
".modelhub_state/queue_cleanup_latest.json": "faba403bbf86f519f695408e5951e34fcd78a468ec45cf54e0d557540f7c963b",
".modelhub_state/recent_outcomes.jsonl": "9866e5e80f1a64f6d284a6410f90d9c0a833923d959b60e14ac5928b35d833c0",
".modelhub_state/recovery_active_tasks.jsonl": "899bf03ab5ab25cf923ed21cdb65c00800a5960d1776a81463646598fe25620e",
".modelhub_state/recovery_intents.jsonl": "fb98502e2c47b33f2a96beb7730a35ca987c497a7ff85581c19db4349a8aaf8b",
".modelhub_state/recovery_intents.jsonl": "2ac65841484521c3ff72bd9de49e2ac0b6c2e6b2575371ad92a4c850b91c2ff4",
".modelhub_state/routing_intelligence.json": "75701875142c98b128d2a6e9b585b23065e186283876b72de4494597fa6d8847",
".modelhub_state/submission_exclusions.jsonl": "07b0cf531e208c0d6ecfffb156a0cb39a09636bee94976f2a8a2e3b767cf06cc",
".modelhub_state/worker_crashes.jsonl": "d46c42c2991f2fda703c2ba17f2b6a21afa8e1453bf67666f1bc0ff3bb99e2e9",
"ledger/submissions.jsonl": "ed9926721ca3e9fee842f10481780f3f2890b222b2607f6028e03b40b70e103f",
"outcomes/submissions.jsonl": "4c3a402b444d551d5285013fa85fde90428bc612f0550c869726b690a595af42"
"outcomes/submissions.jsonl": "93c3f845c549037c95f5b1326fc9820572d55bfe3f332e317904559f08e20765"
},
"generation": 26939,
"phase": "cycle",
"generation": 26940,
"phase": "intent",
"schemaVersion": 1,
"updatedAt": "2026-10-21T13:01:38.026901+00:00",
"updatedAt": "2026-10-21T13:03:21.153497+00:00",
"writerId": "f9d6ac09a4c14ca19fc241d193853c55"
}

6
outcomes/submissions.jsonl
View File

@@ -160,7 +160,6 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-22T20:29:13.756800+00:00", "modelId": "z-lab/Muse-Glimmer-30B-DFlash2-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "b8a926f4d98c4c17ed728affade2dfee1910e905840c16a7c6d35cdf073f1b9a", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2959518912, "estimatedRequiredGiB": 11.359, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10163561928, "modelscopeLicense": "apache-2.0", "modelscopeParams": 81, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:dflash2", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10163561928}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T12:28:01.206856+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5018933", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-22T20:33:11.953328+00:00", "modelId": "LiquidAI/LFM2.5-2.6B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "415f9524ad0e8e6c9c3d7532026f319100b3d292f6c5a09cdc37467f1144a744", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491776, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219881017, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219881017}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T12:31:29.914227+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5019029", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-22T21:01:22.468510+00:00", "modelId": "z-lab/Muse-Glimmer-30B-DFlash2-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "31b0861ad56429ee42697dd4ce872a9717e970d3cf90166c4e6e2fe3b2f5bb19", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2959518912, "estimatedRequiredGiB": 11.359, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10163561928, "modelscopeLicense": "apache-2.0", "modelscopeParams": 81, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:dflash2", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10163561928}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T13:00:37.385261+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5019322", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-22T21:16:20.181095+00:00", "modelId": "empero-ai/Qwen3.8-9B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306305296, "estimatedRequiredGiB": 21.602, "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": 19329225494, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19329225494}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T13:12:58.697634+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5019448", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T21:31:27.760080+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2010737208, "estimatedRequiredGiB": 2.432, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2135575312, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2176034009}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T13:27:47.747400+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5019633", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T22:45:05.970820+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1987222504, "estimatedRequiredGiB": 2.406, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2112106349, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2152567281}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T14:44:16.051430+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5020425", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-23T02:54:50.764789+00:00", "modelId": "ProCreations/BetterWright-K2-Horizon-7B-Uno", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19395158128, "estimatedRequiredGiB": 21.699, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4022513664, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:betterwright", "custom_tag:browser-agent", "custom_tag:web-agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:diffusion-language-model", "custom_tag:uno", "custom_tag:k2-horizon", "custom_tag:full-finetune"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19416072650}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T18:54:21.887542+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5023400", "taskType": "text-generation", "verifyResult": null}
@@ -191,7 +190,6 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T19:28:25.557808+00:00", "modelId": "primitive-ai/DeepSeek-V4-Flash-Vision-Exp-REAP-145B", "modelProfile": {"architectures": ["DeepseekV4ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 83322353204, "estimatedRequiredGiB": 93.133, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4", "modelscopeFileSize": 83334245282, "modelscopeLicense": "mit", "modelscopeParams": 145799322711, "modelscopeTags": ["license:mit", "model_type:deepseek_v4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:deepseek_v4", "custom_tag:reap", "custom_tag:expert-pruning", "custom_tag:mxfp4", "custom_tag:vllm", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 83334245282}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T11:26:47.190154+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5060689", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-24T20:02:26.569159+00:00", "modelId": "Youssofal/MiMo-V2.6-Qwen-9B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8674987255, "estimatedRequiredGiB": 9.718, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8695114401, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:coding", "custom_tag:agentic", "custom_tag:mimo", "custom_tag:xiaomi", "custom_tag:qwen3.5", "custom_tag:qwen3-5", "custom_tag:9b", "custom_tag:6-bit", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-air", "custom_tag:macbook-pro", "custom_tag:mac-mini", "custom_tag:opencode", "custom_tag:claude-code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8695114401}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T12:00:45.393314+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5061113", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-24T20:02:26.569106+00:00", "modelId": "juspay/xor", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 70214495944, "estimatedRequiredGiB": 78.493, "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": 70234635423, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "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}, "repositoryOnDiskBytes": 70234635423}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T12:00:45.395392+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5061116", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-24T20:02:26.569152+00:00", "modelId": "togethercomputer/Tev1-4B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9319828096, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342812725, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342812725}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T12:00:45.398525+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5061114", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-24T20:02:26.569141+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907662447, "estimatedRequiredGiB": 20.038, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 17929422825, "modelscopeLicense": null, "modelscopeParams": 8953803264, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17929422825}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T12:00:45.396613+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5061115", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-24T21:29:59.059868+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20443542279, "estimatedRequiredGiB": 22.881, "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": 20473981039, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5678320880, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:qwen3", "custom_tag:qwen", "custom_tag:mtplx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20473981039}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T13:26:56.157380+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5062101", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-24T21:29:59.059896+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20443542279, "estimatedRequiredGiB": 22.881, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20473981039, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5678320880, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:qwen3", "custom_tag:qwen", "custom_tag:mtplx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20473981039}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T13:27:05.147174+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5062103", "taskType": "text-generation", "verifyResult": null}
@@ -1083,8 +1081,8 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-21T11:44:31.060430+00:00", "modelId": "bartowski/OpenPathAI_Orbit-3.2-Nano-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "fc78709d4e85c217c994d6286e817ec9d9eae27c62f744569fd17a8b92fdf5ec", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1602349632, "estimatedRequiredGiB": 46.16, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 41303483913, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:text-generation", "custom_tag:indonesian", "custom_tag:lfm2.5", "custom_tag:liquid", "custom_tag:fine-tuned", "custom_tag:sft", "custom_tag:instruction-tuning", "custom_tag:closed-qa", "custom_tag:reasoning", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 41303483913}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T03:43:19.854852+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5687774", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-21T12:34:33.758750+00:00", "modelId": "DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "a176de7307e2dc61f89a2b7736f608cc72777b656ee1791a550289b9666f12a7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3120573152, "estimatedRequiredGiB": 21.793, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 19499943398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2697198592, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:12 reasoning modes", "custom_tag:12 instruct modes", "custom_tag:Turbo-Brilliance", "custom_tag:NEO Imatrix", "custom_tag:Max Quants", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19499943398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T04:34:20.747882+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5688529", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-21T12:36:20.265412+00:00", "modelId": "cpatonn-mirror/Qwen3-Coder-30B-A3B-Instruct-AWQ", "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": 18115852009, "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": 18115852009}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T04:36:03.335412+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5688559", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "castorini/gaggle-nanochat-pretrained-climbmix-20260924", "modelProfile": {"architectures": ["GaggleForCausalLM"], "configFingerprint": "a7a7d00616db408ae5c0df2a7cb156b93da7e857ba3eeb80a28825bbcf98f013", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3493762176, "estimatedRequiredGiB": 37.765, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gaggle", "modelscopeFileSize": 33791316398, "modelscopeLicense": "mit", "modelscopeParams": 3286633962, "modelscopeTags": ["license:mit", "model_type:gaggle", "library:pytorch", "library:transformer", "library:gguf", "library:safetensors", "task:text-generation", "custom_tag:nanochat", "custom_tag:pretraining", "custom_tag:climbmix", "custom_tag:d34", "custom_tag:base-model", "custom_tag:custom_code", "custom_tag:vllm", "custom_tag:gaggle", "custom_tag:gguf", "custom_tag:ollama", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 33791316398}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T05:02:59.629168+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5688914", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3459874983, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3459874983}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T05:02:59.638626+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5688915", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-21T13:03:09.363160+00:00", "modelId": "castorini/gaggle-nanochat-pretrained-climbmix-20260924", "modelProfile": {"architectures": ["GaggleForCausalLM"], "configFingerprint": "a7a7d00616db408ae5c0df2a7cb156b93da7e857ba3eeb80a28825bbcf98f013", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3493762176, "estimatedRequiredGiB": 37.765, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gaggle", "modelscopeFileSize": 33791316398, "modelscopeLicense": "mit", "modelscopeParams": 3286633962, "modelscopeTags": ["license:mit", "model_type:gaggle", "library:pytorch", "library:transformer", "library:gguf", "library:safetensors", "task:text-generation", "custom_tag:nanochat", "custom_tag:pretraining", "custom_tag:climbmix", "custom_tag:d34", "custom_tag:base-model", "custom_tag:custom_code", "custom_tag:vllm", "custom_tag:gaggle", "custom_tag:gguf", "custom_tag:ollama", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 33791316398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T05:02:59.629168+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5688914", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-21T13:03:09.363122+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3459874983, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3459874983}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T05:02:59.638626+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5688915", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3459873078, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3459873078}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T05:05:58.860026+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5688937", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark-gguf", "modelProfile": {"architectures": [], "configFingerprint": "5ba0f3d0350c6aad95b8d320dd475d03180877733e000b4e0ec4e7a1a9599db3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 229976064, "estimatedRequiredGiB": 4.066, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 3638566160, "modelscopeLicense": "apache-2.0", "modelscopeParams": 389223169, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:dspark", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:quantized", "custom_tag:minicpmv", "custom_tag:minicpmv4.7", "custom_tag:text-generation", "custom_tag:vision-understanding", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3638566160}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T06:08:36.740120+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5689542", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15859925253, "modelscopeLicense": "other", "modelscopeParams": 4457894832, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15859925253}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T06:13:19.034567+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5689608", "taskType": "text-generation", "verifyResult": null}