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

state: generation 11353 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 09:02:20 +00:00
parent 3913cc4c6a
commit 39dfc07c33
7 changed files with 2703 additions and 2643 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -2654,7 +2654,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-21T08:44:12.237609+00:00", "generatedAt": "2026-09-21T09:00:36.219813+00:00",
"summary": { "summary": {
"activeBlockCount": 133, "activeBlockCount": 133,
"byGpuFramework": { "byGpuFramework": {

2
.modelhub_state/market_intelligence.json
View File

@@ -425,7 +425,7 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-21T08:59:32.774002+00:00", "generatedAt": "2026-09-21T09:00:43.220518+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,

5078
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

184
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-21T08:44:12.166191+00:00", "generatedAt": "2026-09-21T09:00:36.141304+00:00",
"lastSyncTime": "2026-09-21T08:44:09.587595+00:00", "lastSyncTime": "2026-09-21T09:00:33.862683+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -3212,23 +3212,23 @@
"decisionSuccessRate": 0.5, "decisionSuccessRate": 0.5,
"decisionTotal": 16, "decisionTotal": 16,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 16, "ambiguous_runtime": 17,
"framework_architecture_unsupported": 7, "framework_architecture_unsupported": 7,
"model_load": 1, "model_load": 1,
"验证失败": 1 "验证失败": 1
}, },
"failureCount": 25, "failureCount": 26,
"failureRate": 0.7576, "failureRate": 0.7647,
"framework": "vllm-mlu", "framework": "vllm-mlu",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 8, "successCount": 8,
"successRate": 0.2424, "successRate": 0.2353,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 33, "total": 34,
"unresolvedFailureCount": 17 "unresolvedFailureCount": 18
}, },
"Cambricon_mlu-370-x4|vllm|text-generation": { "Cambricon_mlu-370-x4|vllm|text-generation": {
"attributableFailureCount": 3, "attributableFailureCount": 3,
@@ -4655,7 +4655,7 @@
"decisionSuccessRate": 0.2444, "decisionSuccessRate": 0.2444,
"decisionTotal": 90, "decisionTotal": 90,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 64, "ambiguous_runtime": 65,
"backend_operator": 8, "backend_operator": 8,
"framework_architecture_unsupported": 50, "framework_architecture_unsupported": 50,
"memory_capacity": 1, "memory_capacity": 1,
@@ -4665,18 +4665,18 @@
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"参数/模板问题": 12 "参数/模板问题": 12
}, },
"failureCount": 144, "failureCount": 145,
"failureRate": 0.8675, "failureRate": 0.8683,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 22, "successCount": 22,
"successRate": 0.1325, "successRate": 0.1317,
"targetGpu": "Mthreads_s4000", "targetGpu": "Mthreads_s4000",
"taskType": "text-generation", "taskType": "text-generation",
"total": 166, "total": 167,
"unresolvedFailureCount": 76 "unresolvedFailureCount": 77
}, },
"Mthreads_s4000|vllm|visual-multi-modal": { "Mthreads_s4000|vllm|visual-multi-modal": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
@@ -5303,7 +5303,7 @@
"decisionSuccessRate": 0.0238, "decisionSuccessRate": 0.0238,
"decisionTotal": 3608, "decisionTotal": 3608,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1475, "ambiguous_runtime": 1476,
"architecture_compatibility": 112, "architecture_compatibility": 112,
"attention_backend": 1, "attention_backend": 1,
"backend_operator": 84, "backend_operator": 84,
@@ -5317,15 +5317,15 @@
"tokenizer_compatibility": 411, "tokenizer_compatibility": 411,
"参数/模板问题": 41 "参数/模板问题": 41
}, },
"failureCount": 5903, "failureCount": 5904,
"failureRate": 0.9856, "failureRate": 0.9856,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 865, "platformFailureCount": 865,
"successCount": 86, "successCount": 86,
"successRate": 0.0144, "successRate": 0.0144,
"total": 5989, "total": 5990,
"unresolvedFailureCount": 1516 "unresolvedFailureCount": 1517
}, },
"vllm-customized": { "vllm-customized": {
"attributableFailureCount": 3, "attributableFailureCount": 3,
@@ -5353,22 +5353,22 @@
"decisionSuccessRate": 0.4878, "decisionSuccessRate": 0.4878,
"decisionTotal": 41, "decisionTotal": 41,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 53, "ambiguous_runtime": 54,
"framework_architecture_unsupported": 18, "framework_architecture_unsupported": 18,
"model_load": 2, "model_load": 2,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"参数/模板问题": 3, "参数/模板问题": 3,
"验证失败": 1 "验证失败": 1
}, },
"failureCount": 78, "failureCount": 79,
"failureRate": 0.7959, "failureRate": 0.798,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 20, "successCount": 20,
"successRate": 0.2041, "successRate": 0.202,
"total": 98, "total": 99,
"unresolvedFailureCount": 57 "unresolvedFailureCount": 58
}, },
"vllm-patch-tokenizer": { "vllm-patch-tokenizer": {
"attributableFailureCount": 27, "attributableFailureCount": 27,
@@ -5468,7 +5468,7 @@
"unresolvedFailureCount": 70 "unresolvedFailureCount": 70
} }
}, },
"generatedAt": "2026-09-21T08:44:12.154585+00:00", "generatedAt": "2026-09-21T09:00:36.130088+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 91, "attributableFailureCount": 91,
@@ -5560,7 +5560,7 @@
"decisionSuccessRate": 0.0925, "decisionSuccessRate": 0.0925,
"decisionTotal": 789, "decisionTotal": 789,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 432, "ambiguous_runtime": 433,
"architecture_compatibility": 53, "architecture_compatibility": 53,
"context_length": 48, "context_length": 48,
"framework_architecture_unsupported": 272, "framework_architecture_unsupported": 272,
@@ -5573,15 +5573,15 @@
"日志缺失": 13, "日志缺失": 13,
"验证失败": 40 "验证失败": 40
}, },
"failureCount": 1500, "failureCount": 1501,
"failureRate": 0.9536, "failureRate": 0.9536,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 15, "platformFailureCount": 15,
"successCount": 73, "successCount": 73,
"successRate": 0.0464, "successRate": 0.0464,
"total": 1573, "total": 1574,
"unresolvedFailureCount": 769 "unresolvedFailureCount": 770
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"attributableFailureCount": 44, "attributableFailureCount": 44,
@@ -5771,7 +5771,7 @@
"decisionSuccessRate": 0.3684, "decisionSuccessRate": 0.3684,
"decisionTotal": 114, "decisionTotal": 114,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 110, "ambiguous_runtime": 111,
"backend_operator": 8, "backend_operator": 8,
"framework_architecture_unsupported": 51, "framework_architecture_unsupported": 51,
"memory_capacity": 1, "memory_capacity": 1,
@@ -5783,15 +5783,15 @@
"日志缺失": 96, "日志缺失": 96,
"验证失败": 26 "验证失败": 26
}, },
"failureCount": 360, "failureCount": 361,
"failureRate": 0.8955, "failureRate": 0.8958,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 42, "successCount": 42,
"successRate": 0.1045, "successRate": 0.1042,
"total": 402, "total": 403,
"unresolvedFailureCount": 288 "unresolvedFailureCount": 289
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"attributableFailureCount": 732, "attributableFailureCount": 732,
@@ -8223,6 +8223,29 @@
"total": 5, "total": 5,
"unresolvedFailureCount": 5 "unresolvedFailureCount": 5
}, },
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|minicpm|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "minicpm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|mpt|none": { "Cambricon_mlu-370-x4|vllm-mlu|text-generation|mpt|none": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
@@ -13808,6 +13831,29 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Mthreads_s4000|vllm|text-generation|granite|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "granite",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|lfm2|none": { "Mthreads_s4000|vllm|text-generation|lfm2|none": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
@@ -23021,6 +23067,30 @@
"total": 4, "total": 4,
"unresolvedFailureCount": 4 "unresolvedFailureCount": 4
}, },
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|minicpm|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 33,
"modelType": "minicpm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|mpt|none|33": { "Cambricon_mlu-370-x4|vllm-mlu|text-generation|mpt|none|33": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
@@ -31119,6 +31189,30 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Mthreads_s4000|vllm|text-generation|granite|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "granite",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|lfm2|none|29": { "Mthreads_s4000|vllm|text-generation|lfm2|none|29": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
@@ -33215,15 +33309,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 16192, "terminalRecords": 16194,
"totalRecords": 16375, "totalRecords": 16377,
"totals": { "totals": {
"attributableFailureCount": 5862, "attributableFailureCount": 5862,
"decisionFailureRate": 0.8614, "decisionFailureRate": 0.8614,
"decisionSuccessRate": 0.1386, "decisionSuccessRate": 0.1386,
"decisionTotal": 6805, "decisionTotal": 6805,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 3899, "ambiguous_runtime": 3901,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 1, "attention_backend": 1,
"backend_operator": 102, "backend_operator": 102,
@@ -33239,31 +33333,31 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 674 "验证失败": 674
}, },
"failureCount": 15249, "failureCount": 15251,
"failureRate": 0.9418, "failureRate": 0.9418,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 924, "platformFailureCount": 924,
"successCount": 943, "successCount": 943,
"successRate": 0.0582, "successRate": 0.0582,
"total": 16192, "total": 16194,
"unresolvedFailureCount": 8463 "unresolvedFailureCount": 8465
}, },
"warnings": [ "warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Mthreads_s4000 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 Kunlunxin_p-800 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 MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Biren_166m 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 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 Sunrise_pt-200-x1 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 Ascend_910-b3 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 Cambricon_mlu-370-x4 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-150 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。",
"GPU Cambricon_mlu-370-x8 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 hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b4 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 MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Iluvatar_bi-150|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 Iluvatar_bi-150|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 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -33303,6 +33397,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 16375, "summarizedRecords": 16377,
"version": 1 "version": 1
} }

58
.modelhub_state/recovery_intents.jsonl
View File

@@ -2020,6 +2020,64 @@
{"batchId": "5464b6ee30614a02be7c20a3cd2e0073", "completedAt": "2026-09-21T08:43:02.235686+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:42:52.873924+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1e28fad645484a6c88a3caad773fd67e", "lastModified": "2026-09-17T13:06:10+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "reason": null, "reconciledAt": "2026-09-21T08:59:29.865711+00:00", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "4997304", "taskType": "text-generation"} {"batchId": "5464b6ee30614a02be7c20a3cd2e0073", "completedAt": "2026-09-21T08:43:02.235686+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:42:52.873924+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1e28fad645484a6c88a3caad773fd67e", "lastModified": "2026-09-17T13:06:10+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "reason": null, "reconciledAt": "2026-09-21T08:59:29.865711+00:00", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "4997304", "taskType": "text-generation"}
{"batchId": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337007+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.901388+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e25e8f70e9444a82a5030a7a0cf3c216", "lastModified": "2026-08-24T18:24:11+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "reason": null, "reconciledAt": "2026-09-21T08:59:29.866073+00:00", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "4997349", "taskType": "text-generation"} {"batchId": "be812550208a4d26813e529259c65486", "completedAt": "2026-09-21T08:54:30.337007+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:46:02.901388+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e25e8f70e9444a82a5030a7a0cf3c216", "lastModified": "2026-08-24T18:24:11+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "reason": null, "reconciledAt": "2026-09-21T08:59:29.866073+00:00", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "4997349", "taskType": "text-generation"}
{"batchId": "40fd67bbb86a41268c0bca5d72f4fde3", "completedAt": "2026-09-21T08:59:28.269233+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:59:15.372528+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d96e2d593385433ab801342880c289c8", "lastModified": "2026-09-21T01:29:45+00:00", "modelAddress": "https://modelscope.cn/models/blue2star/Qwen-Image-2.1-PE-I2I-ComfyUI", "reason": null, "reconciledAt": "2026-09-21T08:59:29.865424+00:00", "repoId": "blue2star/Qwen-Image-2.1-PE-I2I-ComfyUI", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "4997528", "taskType": "text-generation"} {"batchId": "40fd67bbb86a41268c0bca5d72f4fde3", "completedAt": "2026-09-21T08:59:28.269233+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:59:15.372528+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d96e2d593385433ab801342880c289c8", "lastModified": "2026-09-21T01:29:45+00:00", "modelAddress": "https://modelscope.cn/models/blue2star/Qwen-Image-2.1-PE-I2I-ComfyUI", "reason": null, "reconciledAt": "2026-09-21T08:59:29.865424+00:00", "repoId": "blue2star/Qwen-Image-2.1-PE-I2I-ComfyUI", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "4997528", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.733479+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0d88dfff37b6403bbb48434cb1d229ae", "lastModified": "2026-08-24T17:58:05+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-one-shot-w4a16-group-packed", "repoId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.733615+00:00", "framework": "vllm_tokenizer_patch", "intentId": "dd8220d590924c89974e798bc0c1423c", "lastModified": "2026-08-24T19:10:38+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.733686+00:00", "framework": "vllm-mlu", "intentId": "b555ffd553a1479db2f10d69cf649799", "lastModified": "2026-08-24T19:08:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.733764+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0901e9b0aa9b4fc08411628fd9aedb03", "lastModified": "2026-08-24T18:24:11+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.733841+00:00", "framework": "vllm", "intentId": "f15ecbb837d64cf9b1007109f88a85ee", "lastModified": "2026-08-24T18:26:39+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a8-static-v2", "repoId": "nm-testing/tinyllama-oneshot-w8a8-static-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "c25be7d7c1bf173abe564916f8a370d9b648beb3aea2a79522523aaa6b69ee29", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.733901+00:00", "framework": "vllm", "intentId": "06f8a8f9217b430eb1753bef8ab31c82", "lastModified": "2026-08-24T18:28:40+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-marlin24-w4a16-group128", "repoId": "nm-testing/tinyllama-marlin24-w4a16-group128", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.733953+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e0df2eecb4764c20900db153c9dc8405", "lastModified": "2026-08-24T19:39:27+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.734024+00:00", "framework": "vllm_tokenizer_patch", "intentId": "06050d97fd6141dc9c7a56bb7db2eb3f", "lastModified": "2026-08-24T18:12:10+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.734076+00:00", "framework": "vllm_tokenizer_patch", "intentId": "69338885d8c04070981a442e145078b7", "lastModified": "2026-08-24T18:26:53+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8a16-per-channel", "repoId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.734132+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d1eb8dd0eeb14003bd5347fffbc876de", "lastModified": "2026-08-24T17:55:20+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "repoId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.734197+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6a0c4adcd3cf4d1c90c3df8e66b94775", "lastModified": "2026-08-24T18:26:59+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/nonuniform", "repoId": "nm-testing/nonuniform", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.734264+00:00", "framework": "vllm_tokenizer_patch", "intentId": "58a5233baf4f4f7e8faf4fc85b9d0438", "lastModified": "2026-08-24T19:41:12+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.734335+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d0875c4ae8ef43ba82ea4e401be7150c", "lastModified": "2026-08-24T19:34:42+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-FP8", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.734390+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1ffda52cef334102b4ed7537c3b0d424", "lastModified": "2026-08-24T20:05:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.734431+00:00", "framework": "vllm_tokenizer_patch", "intentId": "36e1d98ca2dc4763af46b9784427aad4", "lastModified": "2026-08-24T19:59:13+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.734478+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0ac3e9a66a6e4c1da2eafa30c614b9af", "lastModified": "2026-08-24T19:38:03+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.734519+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ff85bfb9d99042748121f803e2fa76c5", "lastModified": "2026-08-24T19:51:52+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.734574+00:00", "framework": "vllm_tokenizer_patch", "intentId": "127cefdbc3b148359c8dcaae773b3f1a", "lastModified": "2026-08-24T19:36:07+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.734628+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a82419204e434d3d9275e7b0a806b984", "lastModified": "2026-08-24T19:35:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.734679+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6b8b317553d147c39280dbeeff4e3597", "lastModified": "2026-08-24T19:06:55+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a8", "repoId": "RedHatAI/gemma-2-2b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.734722+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6ca2ef563eba482a80fb1d572688ce50", "lastModified": "2026-08-24T20:02:01+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.734768+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0c908fb496144fa5968a4c83755389b1", "lastModified": "2026-09-08T15:40:32+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Ling-2.6-flash-JANGTQ", "repoId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.734814+00:00", "framework": "vllm_tokenizer_patch", "intentId": "06df88781a2c4b829e17b3678dd9dcdd", "lastModified": "2026-08-24T19:21:33+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.734873+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3866bb58b7a6437492cbc531d9e864cf", "lastModified": "2026-08-24T19:26:17+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.734927+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8f800434b83d4dbe82c442dc025e4fe1", "lastModified": "2026-08-26T17:23:58+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.734986+00:00", "framework": "vllm_tokenizer_patch", "intentId": "bb635ddc8f454cdbb2674e376f221cb3", "lastModified": "2026-08-24T19:25:45+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-2-7b-chat-quantized.w8a8", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.735045+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b38c975a383e46a5ae368cf391af8ab5", "lastModified": "2026-08-24T20:17:00+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.735103+00:00", "framework": "vllm_tokenizer_patch", "intentId": "400d4f7213db40f68ea05fd38651e975", "lastModified": "2026-08-24T20:08:44+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.735156+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0040ba67800c4c43a7e40fb8a8a739b6", "lastModified": "2026-09-04T12:06:11+00:00", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.735214+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8ba02a65a99d457c8f3896463249ca0f", "lastModified": "2026-08-26T16:41:36+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.735278+00:00", "framework": "vllm", "intentId": "8c8140feb3684103805b027651b989cf", "lastModified": "2026-08-24T22:55:11+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "repoId": "BAAI/AquilaMed-RL", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.735360+00:00", "framework": "vllm", "intentId": "7b1d208789b04e958f0794d8aa78dd1e", "lastModified": "2026-08-25T12:06:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.735428+00:00", "framework": "vllm", "intentId": "99c3f16c4d3a48b28d5609fe0afbe19b", "lastModified": "2026-08-26T20:08:57+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.735521+00:00", "framework": "vllm", "intentId": "fac612173bb54888adef3945286da05e", "lastModified": "2026-09-04T07:05:43+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.735591+00:00", "framework": "vllm", "intentId": "4ee1ed6976f0406386c4c851a61e36ac", "lastModified": "2026-09-08T13:43:47+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.735696+00:00", "framework": "vllm", "intentId": "b5892a2527524a3d84851a5481c4eb6c", "lastModified": "2026-08-26T15:57:06+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "repoId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.735795+00:00", "framework": "vllm", "intentId": "75a5ae5fde694920acbf7bb62b045648", "lastModified": "2026-09-09T06:27:24+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.735859+00:00", "framework": "vllm", "intentId": "1e95c2c321334984866e4b56a8b51471", "lastModified": "2026-08-26T18:16:42+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-Research", "repoId": "aisingapore/SEA-LION-v1-7B-IT-Research", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.735923+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "b1498f804422469e97ffe05cd8f94a08", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-FP8", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.735990+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "727cf5d10382499091923cbff3d26890", "lastModified": "2026-08-26T19:43:40+00:00", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.736052+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a88f134602a84f7d85dea72d0a8e9c62", "lastModified": "2026-08-31T03:35:12+00:00", "modelAddress": "https://modelscope.cn/models/logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "repoId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.736125+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2caa3c6a02654202a1b34afa69ddeda5", "lastModified": "2026-09-10T14:58:25+00:00", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3", "repoId": "webAI-Official/TwIL-LM3", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.736202+00:00", "framework": "vllm-patch-tokenizer", "intentId": "d3b66f8c46a04262a21e1e3ff343240a", "lastModified": "2026-08-24T20:04:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.736274+00:00", "framework": "vllm-patch-tokenizer", "intentId": "2d957b842b5945acaf6d9b2a23f75019", "lastModified": "2026-08-24T19:53:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.736339+00:00", "framework": "vllm-patch-tokenizer", "intentId": "88f8cb9b210644d9986b50b616f4066f", "lastModified": "2026-08-24T20:09:59+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-2-7b-chat-quantized.w8a8", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.736401+00:00", "framework": "vllm-patch-tokenizer", "intentId": "36a16374815749248505d53275ca307f", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.736446+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e77b0f4aaaf1479e92fb70122d75799b", "lastModified": "2026-08-24T19:39:21+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.736492+00:00", "framework": "vllm-patch-tokenizer", "intentId": "59f0caf301b84d5492af1ac6e7cac72e", "lastModified": "2026-08-24T19:48:09+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.736541+00:00", "framework": "vllm-patch-tokenizer", "intentId": "68c5f3ae0e2a48ba9460841c87a8e096", "lastModified": "2026-08-24T19:42:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.736587+00:00", "framework": "vllm-patch-tokenizer", "intentId": "bedc8bad0e264224af340ecf6217eb7c", "lastModified": "2026-08-24T20:21:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.736638+00:00", "framework": "vllm-patch-tokenizer", "intentId": "0aded4b131aa46e8a0126ece2090e771", "lastModified": "2026-08-24T19:39:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.736698+00:00", "framework": "vllm-patch-tokenizer", "intentId": "a7c0dcdb3fee402d84f6e703f3333602", "lastModified": "2026-08-24T18:09:20+00:00", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "repoId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.736766+00:00", "framework": "vllm-patch-tokenizer", "intentId": "6d1e2251b9a04c628d2325c859443389", "lastModified": "2026-08-24T20:09:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-3B-Instruct-FP8", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.736824+00:00", "framework": "vllm-patch-tokenizer", "intentId": "7cc417176f4b4892affe6f7a75428050", "lastModified": "2026-08-26T16:45:23+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.736890+00:00", "framework": "vllm", "intentId": "b2dc46f0218c478fa4767599115a6eb4", "lastModified": "2026-08-24T20:10:55+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.736971+00:00", "framework": "vllm", "intentId": "bafc9ca5badc4e558eb1bd5f3b79e3f0", "lastModified": "2026-09-08T15:45:26+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.737053+00:00", "framework": "vllm", "intentId": "bf59544f660d4481bc6d0d2023df4ecc", "lastModified": "2026-08-26T17:29:18+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "7a4e99a005df42079c34f9f30db35d57", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T09:02:20.737132+00:00", "framework": "vllm-customized", "intentId": "242973e852624d3fb233f24fc6fbea86", "lastModified": "2026-09-09T12:19:20+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/BitCPM-CANN-8B", "repoId": "OpenBMB/BitCPM-CANN-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
{"batchId": "446773a075fd455ba07e05e02e8ffc1c", "completedAt": "2026-09-21T08:58:46.736254+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:54:31.174709+00:00", "framework": "vllm", "intentId": "8d11b4738ba346bc88ec9db400a65ea9", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "446773a075fd455ba07e05e02e8ffc1c", "completedAt": "2026-09-21T08:58:46.736254+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:54:31.174709+00:00", "framework": "vllm", "intentId": "8d11b4738ba346bc88ec9db400a65ea9", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "446773a075fd455ba07e05e02e8ffc1c", "completedAt": "2026-09-21T08:58:46.736251+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:54:31.174635+00:00", "framework": "vllm", "intentId": "a7d0808d9e50496d8b3596b13f16e310", "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "446773a075fd455ba07e05e02e8ffc1c", "completedAt": "2026-09-21T08:58:46.736251+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:54:31.174635+00:00", "framework": "vllm", "intentId": "a7d0808d9e50496d8b3596b13f16e310", "repoId": "RedHatAI/Qwen2-1.5B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "446773a075fd455ba07e05e02e8ffc1c", "completedAt": "2026-09-21T08:58:46.736248+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:54:31.174573+00:00", "framework": "vllm", "intentId": "687107bbe0474294b8602585fefb825e", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "446773a075fd455ba07e05e02e8ffc1c", "completedAt": "2026-09-21T08:58:46.736248+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T08:54:31.174573+00:00", "framework": "vllm", "intentId": "687107bbe0474294b8602585fefb825e", "repoId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}

18
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.20.2", "agentVersion": "2026.09.20.2",
"checksums": { "checksums": {
".modelhub_state/account_capacity.json": "68d2a8390ad022f2ddcd30841f3860c4535387fa64cb46dc7507eb16837e798f", ".modelhub_state/account_capacity.json": "68d2a8390ad022f2ddcd30841f3860c4535387fa64cb46dc7507eb16837e798f",
".modelhub_state/architecture_compatibility_blacklist.json": "c573547154767f9cd6b8b9fc231626a4174e6d7eee45337b9f9557ce48b756c9", ".modelhub_state/architecture_compatibility_blacklist.json": "80273824b59ed5f08efe8ee9b3a102f0ac8f8072074f51deb0be81a399e672af",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "918bd73a325f718d5c9f6408420abaa1f3082798412c2b1c8618a558df997302", ".modelhub_state/market_intelligence.json": "49cd933ac68e5df320f8d9fcd6cc479ef80ab7dc13a7750dec3d34423a5bbc7b",
".modelhub_state/official_capabilities.json": "85754d8466c7d6e49b8113bd633840b46c6782219c88e163c2373d93bfab54f6", ".modelhub_state/official_capabilities.json": "bd71f21f88f05c1fd527651c4e597b4ede6a4122f2f13d0bad102e8ca4d93555",
".modelhub_state/outcome_checkpoint.json": "a295b0568c30ae87c8475f8419f1abc379ff153d5b3227624c10ca7c4e55bac5", ".modelhub_state/outcome_checkpoint.json": "b57d383cc74fc1a91eca4bfd817a0a082c3e01321cf018d257ba5ce7326f9365",
".modelhub_state/queue_cleanup_latest.json": "f4afc5dbbf57b883780778e798518d72ad1770b7d52c2f9efa7ac7bca07813f7", ".modelhub_state/queue_cleanup_latest.json": "f4afc5dbbf57b883780778e798518d72ad1770b7d52c2f9efa7ac7bca07813f7",
".modelhub_state/recent_outcomes.jsonl": "29645852c80da99cdb708760921f2785d26a1b7f12d289cc38563a12f682ce62", ".modelhub_state/recent_outcomes.jsonl": "29645852c80da99cdb708760921f2785d26a1b7f12d289cc38563a12f682ce62",
".modelhub_state/recovery_active_tasks.jsonl": "095aa48769cacb1423393dd082378a0ba2ecd0a47de48b04fcdea8aadbd84932", ".modelhub_state/recovery_active_tasks.jsonl": "095aa48769cacb1423393dd082378a0ba2ecd0a47de48b04fcdea8aadbd84932",
".modelhub_state/recovery_intents.jsonl": "e63927897e011b16f1dc35a2f7a30ff6faf76193a733f2683141c3c567714207", ".modelhub_state/recovery_intents.jsonl": "2c71fd6aa32e5df8be51ea126a68847057ea94f1589c6c8c40836133ab077dda",
".modelhub_state/routing_intelligence.json": "79cc4554125434105e5513b2d5becf37059efb96981397c57958eb3045f4cc8c", ".modelhub_state/routing_intelligence.json": "79cc4554125434105e5513b2d5becf37059efb96981397c57958eb3045f4cc8c",
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
"ledger/submissions.jsonl": "1b4fa46e0586a1544ffe21c9405af03d21cd4cfecbd32954552f4a09dadd5709", "ledger/submissions.jsonl": "1b4fa46e0586a1544ffe21c9405af03d21cd4cfecbd32954552f4a09dadd5709",
"outcomes/submissions.jsonl": "db948436ae2570898921f7b580357da56d638d718355dbc02543e0ce43c9e639" "outcomes/submissions.jsonl": "bbb4e88c29809fcef62ca1d73d769979f48d70f41f8584ef16104df61057b080"
}, },
"generation": 11352, "generation": 11353,
"phase": "cycle", "phase": "intent",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-21T08:59:33.230043+00:00", "updatedAt": "2026-09-21T09:02:20.890097+00:00",
"writerId": "8b35139af6674067a339a670222d4b67" "writerId": "8b35139af6674067a339a670222d4b67"
} }

4
outcomes/submissions.jsonl
View File

@@ -397,7 +397,6 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647426+00:00", "modelId": "pfnet/plamo-3-nict-8b-base", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16182734928, "estimatedRequiredGiB": 18.09, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 16186391993, "modelscopeLicense": "other", "modelscopeParams": 8091348992, "modelscopeTags": ["license:other", "model_type:plamo3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16186391993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.038289+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969018", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647426+00:00", "modelId": "pfnet/plamo-3-nict-8b-base", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16182734928, "estimatedRequiredGiB": 18.09, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 16186391993, "modelscopeLicense": "other", "modelscopeParams": 8091348992, "modelscopeTags": ["license:other", "model_type:plamo3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16186391993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.038289+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969018", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647557+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.040710+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969021", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647557+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.040710+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969021", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647466+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.140009+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969028", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647466+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.140009+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969028", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T11:00:25.647787+00:00", "modelId": "OpenBMB/BitCPM-CANN-8B", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16370604914, "estimatedRequiredGiB": 18.305, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm", "modelscopeFileSize": 16378634956, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm", "library:pytorch", "library:transformer", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16378634956}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.100478+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969023", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T11:00:25.647880+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "b3ef6bcf57e6bb4fc9ede989e67a765b0e40b19fbd407f1f8452833c12bd5c38", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361928, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008164431, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008164431}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.138593+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969025", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T11:00:25.647880+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "b3ef6bcf57e6bb4fc9ede989e67a765b0e40b19fbd407f1f8452833c12bd5c38", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361928, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008164431, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008164431}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.138593+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969025", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647505+00:00", "modelId": "JANGQ-AI/MiniMax-M2.7-JANGTQ", "modelProfile": {"architectures": ["MiniMaxM2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 60671749474, "estimatedRequiredGiB": 67.825, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minimax_m2", "modelscopeFileSize": 60688949222, "modelscopeLicense": "other", "modelscopeParams": 15303312058, "modelscopeTags": ["license:other", "model_type:minimax_m2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:jangtq", "custom_tag:jangtq-prestack", "custom_tag:minimax", "custom_tag:minimax-m2", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:2bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 60688949222}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.187054+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969030", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647505+00:00", "modelId": "JANGQ-AI/MiniMax-M2.7-JANGTQ", "modelProfile": {"architectures": ["MiniMaxM2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 60671749474, "estimatedRequiredGiB": 67.825, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minimax_m2", "modelscopeFileSize": 60688949222, "modelscopeLicense": "other", "modelscopeParams": 15303312058, "modelscopeTags": ["license:other", "model_type:minimax_m2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:jangtq", "custom_tag:jangtq-prestack", "custom_tag:minimax", "custom_tag:minimax-m2", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:2bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 60688949222}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.187054+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969030", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647782+00:00", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelProfile": {"architectures": ["BailingMoeV2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30593642304, "estimatedRequiredGiB": 34.208, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 30608423891, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:mixture-of-experts", "custom_tag:hybrid-attention", "custom_tag:mla", "custom_tag:lightning-attention", "custom_tag:jangtq", "custom_tag:jangq-ai", "custom_tag:mlx", "custom_tag:bailing", "custom_tag:ling", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30608423891}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.291717+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969035", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647782+00:00", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelProfile": {"architectures": ["BailingMoeV2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30593642304, "estimatedRequiredGiB": 34.208, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 30608423891, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:mixture-of-experts", "custom_tag:hybrid-attention", "custom_tag:mla", "custom_tag:lightning-attention", "custom_tag:jangtq", "custom_tag:jangq-ai", "custom_tag:mlx", "custom_tag:bailing", "custom_tag:ling", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30608423891}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.291717+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969035", "taskType": "text-generation", "verifyResult": null}
@@ -412,7 +411,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647805+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736540899, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756990943, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13756990943}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.247958+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969088", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647805+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736540899, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756990943, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13756990943}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.247958+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969088", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647605+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11002488632, "estimatedRequiredGiB": 12.322, "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": 10176447713, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6340437856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:2-bit", "custom_tag:quantization", "custom_tag:escha", "custom_tag:sglang", "custom_tag:code", "custom_tag:reasoning", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "escha", "repositoryOnDiskBytes": 11025855102}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.244608+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969089", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647605+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11002488632, "estimatedRequiredGiB": 12.322, "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": 10176447713, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6340437856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:2-bit", "custom_tag:quantization", "custom_tag:escha", "custom_tag:sglang", "custom_tag:code", "custom_tag:reasoning", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "escha", "repositoryOnDiskBytes": 11025855102}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.244608+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969089", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647652+00:00", "modelId": "aisingapore/Llama-SEA-LION-v3.5-8B-R", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16060556344, "estimatedRequiredGiB": 17.97, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 16079585018, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16079585018}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.306108+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969091", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647652+00:00", "modelId": "aisingapore/Llama-SEA-LION-v3.5-8B-R", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16060556344, "estimatedRequiredGiB": 17.97, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 16079585018, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16079585018}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.306108+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969091", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647526+00:00", "modelId": "ibm-granite/granite-guardian-4.1-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16761144464, "estimatedRequiredGiB": 18.743, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 16770924251, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8380551168, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:granite", "custom_tag:guardian", "custom_tag:safety", "custom_tag:hallucination"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16770924251}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:52.310071+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4969093", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:10:38.766271+00:00", "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221588, "modelscopeLicense": "llama2", "modelscopeParams": 12247782400, "modelscopeTags": ["license:llama2", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8338221588}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:11.490200+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969296", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:10:38.766271+00:00", "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221588, "modelscopeLicense": "llama2", "modelscopeParams": 12247782400, "modelscopeTags": ["license:llama2", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8338221588}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:11.490200+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969296", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:10:38.766176+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16936006912, "estimatedRequiredGiB": 18.948, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 16953948786, "modelscopeLicense": "other", "modelscopeParams": 8467856832, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16953948786}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:11.550122+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969304", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:10:38.766176+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16936006912, "estimatedRequiredGiB": 18.948, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 16953948786, "modelscopeLicense": "other", "modelscopeParams": 8467856832, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16953948786}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:11.550122+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969304", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:10:38.766067+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663410366, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663410366}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:11.548946+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969298", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:10:38.766067+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663410366, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663410366}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:11.548946+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969298", "taskType": "text-generation", "verifyResult": null}
@@ -991,7 +989,7 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T08:44:09.587576+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109841981, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109841981}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T00:29:58.598630+00:00", "targetGpu": "Biren_166m", "taskId": "4990404", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T08:44:09.587576+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109841981, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109841981}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T00:29:58.598630+00:00", "targetGpu": "Biren_166m", "taskId": "4990404", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-21T08:44:09.587484+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443106, "modelscopeLicense": "apache-2.0", "modelscopeParams": 409007040, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 507443106}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T00:36:43.644698+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4990464", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-21T08:44:09.587484+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443106, "modelscopeLicense": "apache-2.0", "modelscopeParams": 409007040, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 507443106}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T00:36:43.644698+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4990464", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T08:44:09.587538+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T00:41:04.760036+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990527", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T08:44:09.587538+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T00:41:04.760036+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990527", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612744, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788612744}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T00:51:43.688289+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990612", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-21T09:00:33.862658+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612744, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788612744}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T00:51:43.688289+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990612", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-15b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16564748304, "estimatedRequiredGiB": 18.516, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 16568142065, "modelscopeLicense": "other", "modelscopeParams": 15957889024, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 16568142065}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T01:10:00.817297+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990878", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-15b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16564748304, "estimatedRequiredGiB": 18.516, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 16568142065, "modelscopeLicense": "other", "modelscopeParams": 15957889024, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 16568142065}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T01:10:00.817297+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4990878", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998647728, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020564058, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 12020564058}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T01:10:00.835785+00:00", "targetGpu": "Biren_166m", "taskId": "4990879", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998647728, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020564058, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 12020564058}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T01:10:00.835785+00:00", "targetGpu": "Biren_166m", "taskId": "4990879", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248516007, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248516007}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T01:10:01.025615+00:00", "targetGpu": "Biren_166m", "taskId": "4990910", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248516007, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248516007}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T01:10:01.025615+00:00", "targetGpu": "Biren_166m", "taskId": "4990910", "taskType": "text-generation", "verifyResult": null}