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

state: generation 30088 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-10-22 21:04:31 +00:00
parent dd8abd55e4
commit dbc2d6da58
7 changed files with 573 additions and 505 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -487,7 +487,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-10-22T21:02:24.446591+00:00", "generatedAt": "2026-10-22T21:04:29.197897+00:00",
"summary": { "summary": {
"activeBlockCount": 24, "activeBlockCount": 24,
"byGpuFramework": { "byGpuFramework": {

2
.modelhub_state/market_intelligence.json
View File

@@ -452,7 +452,7 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-10-22T21:02:24.564526+00:00", "generatedAt": "2026-10-22T21:04:29.265135+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,

918
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

123
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-10-22T20:45:01.829689+00:00", "generatedAt": "2026-10-22T21:04:29.105279+00:00",
"lastSyncTime": "2026-10-22T20:45:01.569715+00:00", "lastSyncTime": "2026-10-22T21:04:28.850938+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -2075,28 +2075,28 @@
"unresolvedFailureCount": 57 "unresolvedFailureCount": 57
}, },
"Iluvatar_mrv-100|vllm|text-generation": { "Iluvatar_mrv-100|vllm|text-generation": {
"attributableFailureCount": 42, "attributableFailureCount": 43,
"decisionFailureRate": 0.7241, "decisionFailureRate": 0.7288,
"decisionSuccessRate": 0.2759, "decisionSuccessRate": 0.2712,
"decisionTotal": 58, "decisionTotal": 59,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 15, "ambiguous_runtime": 15,
"framework_architecture_unsupported": 35, "framework_architecture_unsupported": 36,
"model_load": 5, "model_load": 5,
"tokenizer_compatibility": 2, "tokenizer_compatibility": 2,
"参数/模板问题": 24 "参数/模板问题": 24
}, },
"failureCount": 81, "failureCount": 82,
"failureRate": 0.8351, "failureRate": 0.8367,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 16, "successCount": 16,
"successRate": 0.1649, "successRate": 0.1633,
"targetGpu": "Iluvatar_mrv-100", "targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation", "taskType": "text-generation",
"total": 97, "total": 98,
"unresolvedFailureCount": 39 "unresolvedFailureCount": 39
}, },
"Kunlunxin_p-800|unknown|text-generation": { "Kunlunxin_p-800|unknown|text-generation": {
@@ -3213,17 +3213,17 @@
"unresolvedFailureCount": 6556 "unresolvedFailureCount": 6556
}, },
"vllm": { "vllm": {
"attributableFailureCount": 3713, "attributableFailureCount": 3714,
"decisionFailureRate": 0.971, "decisionFailureRate": 0.971,
"decisionSuccessRate": 0.029, "decisionSuccessRate": 0.029,
"decisionTotal": 3824, "decisionTotal": 3825,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1609, "ambiguous_runtime": 1609,
"architecture_compatibility": 112, "architecture_compatibility": 112,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 98, "backend_operator": 98,
"context_length": 161, "context_length": 161,
"framework_architecture_unsupported": 1423, "framework_architecture_unsupported": 1424,
"memory_capacity": 725, "memory_capacity": 725,
"model_load": 230, "model_load": 230,
"platform_infrastructure": 888, "platform_infrastructure": 888,
@@ -3232,14 +3232,14 @@
"tokenizer_compatibility": 425, "tokenizer_compatibility": 425,
"参数/模板问题": 99 "参数/模板问题": 99
}, },
"failureCount": 6309, "failureCount": 6310,
"failureRate": 0.9827, "failureRate": 0.9827,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 888, "platformFailureCount": 888,
"successCount": 111, "successCount": 111,
"successRate": 0.0173, "successRate": 0.0173,
"total": 6420, "total": 6421,
"unresolvedFailureCount": 1708 "unresolvedFailureCount": 1708
}, },
"vllm-customized": { "vllm-customized": {
@@ -3390,7 +3390,7 @@
"unresolvedFailureCount": 341 "unresolvedFailureCount": 341
} }
}, },
"generatedAt": "2026-10-22T20:45:01.815806+00:00", "generatedAt": "2026-10-22T21:04:29.091593+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 133, "attributableFailureCount": 133,
@@ -3587,16 +3587,16 @@
"unresolvedFailureCount": 1200 "unresolvedFailureCount": 1200
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"attributableFailureCount": 992, "attributableFailureCount": 993,
"decisionFailureRate": 0.8486, "decisionFailureRate": 0.8487,
"decisionSuccessRate": 0.1514, "decisionSuccessRate": 0.1513,
"decisionTotal": 1169, "decisionTotal": 1170,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 355, "ambiguous_runtime": 355,
"architecture_compatibility": 47, "architecture_compatibility": 47,
"backend_operator": 1, "backend_operator": 1,
"context_length": 77, "context_length": 77,
"framework_architecture_unsupported": 307, "framework_architecture_unsupported": 308,
"memory_capacity": 219, "memory_capacity": 219,
"model_load": 89, "model_load": 89,
"platform_infrastructure": 7, "platform_infrastructure": 7,
@@ -3607,14 +3607,14 @@
"日志缺失": 6, "日志缺失": 6,
"验证失败": 47 "验证失败": 47
}, },
"failureCount": 1766, "failureCount": 1767,
"failureRate": 0.9089, "failureRate": 0.909,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 7, "platformFailureCount": 7,
"successCount": 177, "successCount": 177,
"successRate": 0.0911, "successRate": 0.091,
"total": 1943, "total": 1944,
"unresolvedFailureCount": 767 "unresolvedFailureCount": 767
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
@@ -16114,6 +16114,29 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Iluvatar_mrv-100|vllm|text-generation|gemma4|modelopt": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "gemma4",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|gpt_oss|none": { "Iluvatar_mrv-100|vllm|text-generation|gpt_oss|none": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
@@ -46726,6 +46749,30 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Iluvatar_mrv-100|vllm|text-generation|gemma4|modelopt|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "gemma4",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|gpt_oss|none|33": { "Iluvatar_mrv-100|vllm|text-generation|gpt_oss|none|33": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
@@ -60913,20 +60960,20 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 17982, "terminalRecords": 17983,
"totalRecords": 18523, "totalRecords": 18524,
"totals": { "totals": {
"attributableFailureCount": 6364, "attributableFailureCount": 6365,
"decisionFailureRate": 0.8659, "decisionFailureRate": 0.8659,
"decisionSuccessRate": 0.1341, "decisionSuccessRate": 0.1341,
"decisionTotal": 7350, "decisionTotal": 7351,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4671, "ambiguous_runtime": 4671,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 136, "backend_operator": 136,
"context_length": 328, "context_length": 328,
"framework_architecture_unsupported": 2360, "framework_architecture_unsupported": 2361,
"memory_capacity": 1207, "memory_capacity": 1207,
"model_load": 577, "model_load": 577,
"platform_infrastructure": 971, "platform_infrastructure": 971,
@@ -60937,17 +60984,18 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 16996, "failureCount": 16997,
"failureRate": 0.9452, "failureRate": 0.9452,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 971, "platformFailureCount": 971,
"successCount": 986, "successCount": 986,
"successRate": 0.0548, "successRate": 0.0548,
"total": 17982, "total": 17983,
"unresolvedFailureCount": 9661 "unresolvedFailureCount": 9661
}, },
"warnings": [ "warnings": [
"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 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 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。",
@@ -60960,7 +61008,6 @@
"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 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 Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU 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。",
"组合 Biren_166m|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 Biren_166m|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 Mthreads_s4000|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Mthreads_s4000|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -60977,9 +61024,7 @@
"组合 Iluvatar_mrv-100|unknown|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_mrv-100|unknown|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 Vastai_va16|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 Vastai_va16|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 Kunlunxin_p-800|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Kunlunxin_p-800|vllm|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|vllm-customized|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|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|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 Iluvatar_bi-150|llamacpp|text-generation 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|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_mrv-100|vllm|text-generation 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_0_17_0_corex_4_4_0|text-generation 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_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -61004,10 +61049,12 @@
"组合 Cambricon_mlu-370-x8|vllm-mlu|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|vllm-mlu|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-x4|vllm-mlu|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-x4|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Mthreads_s4000|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Mthreads_s4000|vllm|text-generation 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_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 Iluvatar_bi-150|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|vllm-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 18523, "summarizedRecords": 18524,
"version": 1 "version": 1
} }

12
.modelhub_state/recovery_intents.jsonl
View File

@@ -3726,6 +3726,18 @@
{"batchId": "9189f5c453744760bed1aee56b9287af", "completedAt": "2026-10-22T17:55:09.184737+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-22T17:54:54.518512+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2943bc61f2714655a726db5ad1db11f8", "lastModified": "2026-10-21T16:19:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-22T21:02:56.048563+00:00", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5722886", "taskType": "text-generation"} {"batchId": "9189f5c453744760bed1aee56b9287af", "completedAt": "2026-10-22T17:55:09.184737+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-22T17:54:54.518512+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2943bc61f2714655a726db5ad1db11f8", "lastModified": "2026-10-21T16:19:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-22T21:02:56.048563+00:00", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5722886", "taskType": "text-generation"}
{"batchId": "d951efdc91554b1eb41d1bbf3ae1e0d7", "completedAt": "2026-10-22T20:21:06.258245+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:21:03.557699+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a36c6ca0622d46fc8f09c65b58529360", "lastModified": "2026-10-22T13:57:14+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/LFM2.5-8B-A1B-AWQ-INT4", "reason": null, "reconciledAt": "2026-10-22T21:02:56.047222+00:00", "repoId": "cyankiwi/LFM2.5-8B-A1B-AWQ-INT4", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5724977", "taskType": "text-generation"} {"batchId": "d951efdc91554b1eb41d1bbf3ae1e0d7", "completedAt": "2026-10-22T20:21:06.258245+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:21:03.557699+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a36c6ca0622d46fc8f09c65b58529360", "lastModified": "2026-10-22T13:57:14+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/LFM2.5-8B-A1B-AWQ-INT4", "reason": null, "reconciledAt": "2026-10-22T21:02:56.047222+00:00", "repoId": "cyankiwi/LFM2.5-8B-A1B-AWQ-INT4", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5724977", "taskType": "text-generation"}
{"batchId": "4da72fb9df654621af214d2580119d18", "completedAt": "2026-10-22T20:25:26.110649+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:25:23.630397+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5bcde5a40eb543eeb24ce85c99821717", "lastModified": "2026-10-21T16:49:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-22T21:02:56.046891+00:00", "repoId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5725025", "taskType": "text-generation"} {"batchId": "4da72fb9df654621af214d2580119d18", "completedAt": "2026-10-22T20:25:26.110649+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-22T20:25:23.630397+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5bcde5a40eb543eeb24ce85c99821717", "lastModified": "2026-10-21T16:49:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-22T21:02:56.046891+00:00", "repoId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5725025", "taskType": "text-generation"}
{"batchId": "55d2a54c7d404c7a8a8a2134fe60b15c", "configFingerprint": "1d8ba6e2bf36aa47c80ff7bd95383cf1571f55e0a76760eb56b3f847863afa7f", "configSource": "modelhub_live", "createdAt": "2026-10-22T21:04:31.502664+00:00", "framework": "llamacpp", "intentId": "730cd0eb462d498ca56908485ecadfaa", "lastModified": "2026-10-22T14:16:42+00:00", "modelAddress": "https://modelscope.cn/models/InternScience/Sage-A1.5-Q8_0-GGUF", "repoId": "InternScience/Sage-A1.5-Q8_0-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "55d2a54c7d404c7a8a8a2134fe60b15c", "configFingerprint": "705b8b3614c86a1ac722c97f43e177e84ca20282e9799fffb1b890510d641728", "configSource": "modelhub_live", "createdAt": "2026-10-22T21:04:31.502789+00:00", "framework": "llamacpp", "intentId": "08583a93705d49c8b71e043782c1b1d0", "lastModified": "2026-10-21T18:16:46+00:00", "modelAddress": "https://modelscope.cn/models/AtomicChat/Qwen3.5-9B-DFlash-GGUF", "repoId": "AtomicChat/Qwen3.5-9B-DFlash-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "55d2a54c7d404c7a8a8a2134fe60b15c", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-22T21:04:31.502846+00:00", "framework": "vllm_tokenizer_patch", "intentId": "373f743c41d04276a7318b8bfddeae48", "lastModified": "2026-10-21T16:58:14+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/KAT-Dev-AWQ-4bit", "repoId": "cyankiwi/KAT-Dev-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "55d2a54c7d404c7a8a8a2134fe60b15c", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-22T21:04:31.502900+00:00", "framework": "vllm_tokenizer_patch", "intentId": "053f0549089c459790ba0da9448e9fce", "lastModified": "2026-10-21T16:41:10+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "55d2a54c7d404c7a8a8a2134fe60b15c", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T21:04:31.502951+00:00", "framework": "vllm-mlu", "intentId": "e5d9bb24e9a34e79a594e44e4c0acc9b", "lastModified": "2026-10-21T17:03:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiniCPM-SALA-AWQ-4bit", "repoId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "55d2a54c7d404c7a8a8a2134fe60b15c", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T21:04:31.503004+00:00", "framework": "vllm-mlu", "intentId": "d9b9b080c4114048aeafbfa56bb2339a", "lastModified": "2026-10-21T16:56:28+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "repoId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "55d2a54c7d404c7a8a8a2134fe60b15c", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T21:04:31.503054+00:00", "framework": "vllm-mlu", "intentId": "ee3dd3d57d3b4d15aed108679adf61e9", "lastModified": "2026-10-21T16:21:36+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Report-AWQ-8bit", "repoId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "55d2a54c7d404c7a8a8a2134fe60b15c", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T21:04:31.503102+00:00", "framework": "vllm-mlu", "intentId": "7ce1bd6cf0814227ba03ce3e13041279", "lastModified": "2026-10-21T16:56:31+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "repoId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "55d2a54c7d404c7a8a8a2134fe60b15c", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T21:04:31.503151+00:00", "framework": "vllm-mlu", "intentId": "43841cde66784d90aeaf1d04608362e2", "lastModified": "2026-10-21T17:24:35+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Orchestrator-8B-AWQ-4bit", "repoId": "cyankiwi/Orchestrator-8B-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "55d2a54c7d404c7a8a8a2134fe60b15c", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T21:04:31.503205+00:00", "framework": "vllm-mlu", "intentId": "de5d327bd42346cfa015d9048673dff0", "lastModified": "2026-10-21T16:38:25+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "55d2a54c7d404c7a8a8a2134fe60b15c", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T21:04:31.503254+00:00", "framework": "vllm-mlu", "intentId": "e1d352ea7e34463c8f09480a2c34e78e", "lastModified": "2026-10-21T16:49:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "repoId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "55d2a54c7d404c7a8a8a2134fe60b15c", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T21:04:31.503303+00:00", "framework": "vllm-mlu", "intentId": "30a5fc76ff9d4c4abdc3fb4fafa5e33f", "lastModified": "2026-10-21T17:02:31+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
{"batchId": "f99c86fbe99f4865801b01a42a8aeb31", "completedAt": "2026-10-22T21:02:49.049537+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T21:02:45.339505+00:00", "framework": "vllm-mlu", "intentId": "4b3bfa01f7604216963911f99caf948d", "repoId": "cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} {"batchId": "f99c86fbe99f4865801b01a42a8aeb31", "completedAt": "2026-10-22T21:02:49.049537+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T21:02:45.339505+00:00", "framework": "vllm-mlu", "intentId": "4b3bfa01f7604216963911f99caf948d", "repoId": "cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "f99c86fbe99f4865801b01a42a8aeb31", "completedAt": "2026-10-22T21:02:49.049534+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T21:02:45.339456+00:00", "framework": "vllm-mlu", "intentId": "15d67824fdfd44daa07bbe2754accc9f", "repoId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} {"batchId": "f99c86fbe99f4865801b01a42a8aeb31", "completedAt": "2026-10-22T21:02:49.049534+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T21:02:45.339456+00:00", "framework": "vllm-mlu", "intentId": "15d67824fdfd44daa07bbe2754accc9f", "repoId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}
{"batchId": "f99c86fbe99f4865801b01a42a8aeb31", "completedAt": "2026-10-22T21:02:49.049531+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T21:02:45.339407+00:00", "framework": "vllm-mlu", "intentId": "412e01715f2a4d8fbeaa939f6e2be856", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} {"batchId": "f99c86fbe99f4865801b01a42a8aeb31", "completedAt": "2026-10-22T21:02:49.049531+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-22T21:02:45.339407+00:00", "framework": "vllm-mlu", "intentId": "412e01715f2a4d8fbeaa939f6e2be856", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"}

18
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/account_capacity.json": "d34274b13c4f245b374dc6796be576d276e56fd1ef7a37e423d73df308d61531", ".modelhub_state/account_capacity.json": "d34274b13c4f245b374dc6796be576d276e56fd1ef7a37e423d73df308d61531",
".modelhub_state/architecture_compatibility_blacklist.json": "bb672ab5feac381eb2153670283f34f24a8a60631dda0ba99bde57b706e20f24", ".modelhub_state/architecture_compatibility_blacklist.json": "d75f0f345f93384dc864446fee1371d6e83153bb7ea61b29d83d724ce969a0c4",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "75bf17b16a28030c37bad96e2245268e16db4188f0749051316336fa94c302cf", ".modelhub_state/market_intelligence.json": "c6dba0e30b79d2344e970c4be9723c115901f30c95a3c327df1f278071a601db",
".modelhub_state/official_capabilities.json": "a9ad17a06cdc793bd96346962fbbecd3a279b8ac12681873078c01f23d8435ae", ".modelhub_state/official_capabilities.json": "a814422380439cbadfcbcfe985d0cac882c7be7b3c377bc9ea4a48d4dcfa9505",
".modelhub_state/outcome_checkpoint.json": "95f4dc653c2e06984bab52b311d1ae9524471285f8d475d248aec541ea0a744d", ".modelhub_state/outcome_checkpoint.json": "95567a2a0b0ed3067eebdb7f2483f17c915323274506fa3f5d438ba68aa7c41d",
".modelhub_state/queue_cleanup_latest.json": "8334310d4dead516bef55821a2fcd0ee22b747cd886dc6d77a07cf9c439bb3f9", ".modelhub_state/queue_cleanup_latest.json": "8334310d4dead516bef55821a2fcd0ee22b747cd886dc6d77a07cf9c439bb3f9",
".modelhub_state/recent_outcomes.jsonl": "af80b03c1147019d447a3a33c5bbb83a8733c09983c2a9478b8d3b01bb7a779f", ".modelhub_state/recent_outcomes.jsonl": "af80b03c1147019d447a3a33c5bbb83a8733c09983c2a9478b8d3b01bb7a779f",
".modelhub_state/recovery_active_tasks.jsonl": "1c7406b552ac8d85869036120fa99eb77b6176a02becf7a1b88a0248708400b4", ".modelhub_state/recovery_active_tasks.jsonl": "1c7406b552ac8d85869036120fa99eb77b6176a02becf7a1b88a0248708400b4",
".modelhub_state/recovery_intents.jsonl": "6921bde043809b68fc1336975b0ed5b8726f245ddd049961bf452ce0c29911aa", ".modelhub_state/recovery_intents.jsonl": "c3f8d7c8f72a5988522615684b356f522be6b2720a82db89c8e142a67d4a2352",
".modelhub_state/routing_intelligence.json": "6692d87895d976b12ff569cfa418e73fbb304711591979c3cb3ba2f86445f827", ".modelhub_state/routing_intelligence.json": "6692d87895d976b12ff569cfa418e73fbb304711591979c3cb3ba2f86445f827",
".modelhub_state/submission_exclusions.jsonl": "e2677e09d968a0c44c65d7c030b9c8ea2c9d39dc378ce302c2a309ab54d600d9", ".modelhub_state/submission_exclusions.jsonl": "e2677e09d968a0c44c65d7c030b9c8ea2c9d39dc378ce302c2a309ab54d600d9",
".modelhub_state/worker_crashes.jsonl": "50e3ab320d986c635b0d4cb9b1de107b33f9ab8864ff5aa9ca00e1b4af9f30cc", ".modelhub_state/worker_crashes.jsonl": "50e3ab320d986c635b0d4cb9b1de107b33f9ab8864ff5aa9ca00e1b4af9f30cc",
"ledger/submissions.jsonl": "75058d9dcbd73536cfdc1dca6b376fd788ac11a297d305cdfea88ddebf0cbadf", "ledger/submissions.jsonl": "75058d9dcbd73536cfdc1dca6b376fd788ac11a297d305cdfea88ddebf0cbadf",
"outcomes/submissions.jsonl": "8c3ae961110c6cd512ccc9b44a583350a8376fa046eea6e59b4c665b468c39ee" "outcomes/submissions.jsonl": "c32476a9fadc0c72a2a708c90d6345da2069349acf119297faa6116b217f921b"
}, },
"generation": 30087, "generation": 30088,
"phase": "cycle", "phase": "intent",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-10-22T21:02:56.287116+00:00", "updatedAt": "2026-10-22T21:04:31.663320+00:00",
"writerId": "a94e2cbdfb3d4160878859cdc87771b0" "writerId": "a94e2cbdfb3d4160878859cdc87771b0"
} }

3
outcomes/submissions.jsonl
View File

@@ -313,7 +313,6 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253402+00:00", "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:50.261321+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260133", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253402+00:00", "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:50.261321+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260133", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-04T00:18:23.253359+00:00", "modelId": "Altworld/Hemmingway-1", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54641496528, "estimatedRequiredGiB": 61.09, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 54662159810, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:qwen3_5_text", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen3.8", "custom_tag:chat", "custom_tag:creative-writing", "custom_tag:altworld"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54662159810}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:50.371745+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5260134", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-04T00:18:23.253359+00:00", "modelId": "Altworld/Hemmingway-1", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54641496528, "estimatedRequiredGiB": 61.09, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 54662159810, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:qwen3_5_text", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen3.8", "custom_tag:chat", "custom_tag:creative-writing", "custom_tag:altworld"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54662159810}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:50.371745+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5260134", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-04T00:18:23.253446+00:00", "modelId": "OsaurusAI/Raptor-0.6-4B-JANG_4M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2635323720, "estimatedRequiredGiB": 2.962, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2650224659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2650224659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:50.548226+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5260141", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-04T00:18:23.253446+00:00", "modelId": "OsaurusAI/Raptor-0.6-4B-JANG_4M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2635323720, "estimatedRequiredGiB": 2.962, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2650224659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2650224659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:50.548226+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5260141", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-04T00:18:23.253514+00:00", "modelId": "juspay/Xor-26B-A4B-NVFP4", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18788485588, "estimatedRequiredGiB": 21.039, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 18825736695, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:gemma4", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 18825736695}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:50.658909+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5260143", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-04T03:01:41.555967+00:00", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20593110848, "estimatedRequiredGiB": 23.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:sglang", "custom_tag:gptq", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:compressed-tensors", "custom_tag:llm-compressor", "custom_tag:safetensors", "custom_tag:qwen3.8", "custom_tag:conversational", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:roleplay", "custom_tag:character", "custom_tag:humanlike", "custom_tag:uncensored"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": "compressed-tensors", "recursiveRepositoryBytes": 20616225866, "repositoryOnDiskBytes": 20616225866}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T18:55:00.153550+00:00", "targetGpu": "Biren_166m", "taskId": "5263453", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-04T03:01:41.555967+00:00", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20593110848, "estimatedRequiredGiB": 23.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:sglang", "custom_tag:gptq", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:compressed-tensors", "custom_tag:llm-compressor", "custom_tag:safetensors", "custom_tag:qwen3.8", "custom_tag:conversational", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:roleplay", "custom_tag:character", "custom_tag:humanlike", "custom_tag:uncensored"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": "compressed-tensors", "recursiveRepositoryBytes": 20616225866, "repositoryOnDiskBytes": 20616225866}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T18:55:00.153550+00:00", "targetGpu": "Biren_166m", "taskId": "5263453", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-04T03:19:12.246914+00:00", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20593110848, "estimatedRequiredGiB": 23.04, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:sglang", "custom_tag:gptq", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:compressed-tensors", "custom_tag:llm-compressor", "custom_tag:safetensors", "custom_tag:qwen3.8", "custom_tag:conversational", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:roleplay", "custom_tag:character", "custom_tag:humanlike", "custom_tag:uncensored"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": "compressed-tensors", "recursiveRepositoryBytes": 20616225866, "repositoryOnDiskBytes": 20616225866}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T19:12:16.744930+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5264047", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-04T03:19:12.246914+00:00", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20593110848, "estimatedRequiredGiB": 23.04, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:sglang", "custom_tag:gptq", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:compressed-tensors", "custom_tag:llm-compressor", "custom_tag:safetensors", "custom_tag:qwen3.8", "custom_tag:conversational", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:roleplay", "custom_tag:character", "custom_tag:humanlike", "custom_tag:uncensored"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": "compressed-tensors", "recursiveRepositoryBytes": 20616225866, "repositoryOnDiskBytes": 20616225866}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T19:12:16.744930+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5264047", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-04T10:01:33.651736+00:00", "modelId": "SC117/Ornith-1.0-35B-Heretic-MTP", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 71908134368, "estimatedRequiredGiB": 80.398, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 71938541955, "modelscopeLicense": "mit", "modelscopeParams": 35951822704, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen3_5_moe", "custom_tag:reasoning", "custom_tag:agentic-coding", "custom_tag:heretic", "custom_tag:mtp", "custom_tag:apex", "custom_tag:quantization", "custom_tag:gguf", "custom_tag:multimodal", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 71938541955, "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-23T21:42:41.557218+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "recursiveRepositoryBytes": 71938541955, "repositoryOnDiskBytes": 71938541955}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-04T01:54:06.844290+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5270463", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-04T10:01:33.651736+00:00", "modelId": "SC117/Ornith-1.0-35B-Heretic-MTP", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 71908134368, "estimatedRequiredGiB": 80.398, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 71938541955, "modelscopeLicense": "mit", "modelscopeParams": 35951822704, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen3_5_moe", "custom_tag:reasoning", "custom_tag:agentic-coding", "custom_tag:heretic", "custom_tag:mtp", "custom_tag:apex", "custom_tag:quantization", "custom_tag:gguf", "custom_tag:multimodal", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 71938541955, "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-23T21:42:41.557218+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "recursiveRepositoryBytes": 71938541955, "repositoryOnDiskBytes": 71938541955}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-04T01:54:06.844290+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5270463", "taskType": "text-generation", "verifyResult": null}
@@ -1086,7 +1085,7 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-22T19:32:16.160424+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {"architectures": ["MiniCPMSALAForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6196491480, "estimatedRequiredGiB": 6.931, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm_sala", "modelscopeFileSize": 6201618087, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9477203968, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm_sala", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6201618087}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-22T11:31:03.230185+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5716785", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-22T19:32:16.160424+00:00", "modelId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "modelProfile": {"architectures": ["MiniCPMSALAForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6196491480, "estimatedRequiredGiB": 6.931, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm_sala", "modelscopeFileSize": 6201618087, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9477203968, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm_sala", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6201618087}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-22T11:31:03.230185+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5716785", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-22T20:46:42.269110+00:00", "modelId": "InternScience/Sage-A1.5-Q8_0-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "6a1e6e554e778bcf41fd30fe0869e8c4a396cf7289db86fcce4b236e83d8b8a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37802150112, "estimatedRequiredGiB": 43.253, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 38701689630, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35505251456, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:moe", "custom_tag:vlm", "custom_tag:vision", "custom_tag:agentic", "custom_tag:code", "custom_tag:tool-use", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 38701689630}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-22T12:45:02.852710+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5717984", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-22T20:46:42.269110+00:00", "modelId": "InternScience/Sage-A1.5-Q8_0-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "6a1e6e554e778bcf41fd30fe0869e8c4a396cf7289db86fcce4b236e83d8b8a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37802150112, "estimatedRequiredGiB": 43.253, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 38701689630, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35505251456, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:moe", "custom_tag:vlm", "custom_tag:vision", "custom_tag:agentic", "custom_tag:code", "custom_tag:tool-use", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 38701689630}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-22T12:45:02.852710+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5717984", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-22T20:46:42.269087+00:00", "modelId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6691066608, "estimatedRequiredGiB": 7.498, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 6709196808, "modelscopeLicense": "other", "modelscopeParams": 2381547248, "modelscopeTags": ["license:other", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6709196808}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-22T12:45:02.861295+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5717983", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-22T20:46:42.269087+00:00", "modelId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6691066608, "estimatedRequiredGiB": 7.498, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 6709196808, "modelscopeLicense": "other", "modelscopeParams": 2381547248, "modelscopeTags": ["license:other", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6709196808}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-22T12:45:02.861295+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5717983", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/LFM2-8B-A1B-AWQ-4bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5806978504, "estimatedRequiredGiB": 6.496, "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": 5812546890, "modelscopeLicense": "other", "modelscopeParams": 8474148288, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2", "custom_tag:edge", "custom_tag:moe"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5812546890}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-22T13:03:02.572133+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5718269", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-22T21:04:28.850909+00:00", "modelId": "cyankiwi/LFM2-8B-A1B-AWQ-4bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5806978504, "estimatedRequiredGiB": 6.496, "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": 5812546890, "modelscopeLicense": "other", "modelscopeParams": 8474148288, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2", "custom_tag:edge", "custom_tag:moe"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5812546890}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-22T13:03:02.572133+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5718269", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921096, "estimatedRequiredGiB": 15.787, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 14125731418, "modelscopeLicense": "other", "modelscopeParams": 8190735360, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:Nemotron-Cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14125731418}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-22T14:09:40.270534+00:00", "targetGpu": "MetaX_c-500", "taskId": "5719482", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921096, "estimatedRequiredGiB": 15.787, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 14125731418, "modelscopeLicense": "other", "modelscopeParams": 8190735360, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:Nemotron-Cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14125731418}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-22T14:09:40.270534+00:00", "targetGpu": "MetaX_c-500", "taskId": "5719482", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/Hermes-4.3-36B-AWQ-8bit", "modelProfile": {"architectures": ["SeedOssForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 39901408344, "estimatedRequiredGiB": 44.607, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "seed_oss", "modelscopeFileSize": 39913484098, "modelscopeLicense": "apache-2.0", "modelscopeParams": 36151104512, "modelscopeTags": ["license:apache-2.0", "model_type:seed_oss", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:Bytedance Seed", "custom_tag:instruct", "custom_tag:finetune", "custom_tag:reasoning", "custom_tag:hybrid-mode", "custom_tag:chatml", "custom_tag:function calling", "custom_tag:tool use", "custom_tag:json mode", "custom_tag:structured outputs", "custom_tag:atropos", "custom_tag:dataforge", "custom_tag:long context", "custom_tag:roleplaying", "custom_tag:chat"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-22T15:19:19.077489+00:00", "modelType": "seed_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 39913484098}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-22T16:57:24.469812+00:00", "targetGpu": "MetaX_c-500", "taskId": "5721855", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/Hermes-4.3-36B-AWQ-8bit", "modelProfile": {"architectures": ["SeedOssForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 39901408344, "estimatedRequiredGiB": 44.607, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "seed_oss", "modelscopeFileSize": 39913484098, "modelscopeLicense": "apache-2.0", "modelscopeParams": 36151104512, "modelscopeTags": ["license:apache-2.0", "model_type:seed_oss", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:Bytedance Seed", "custom_tag:instruct", "custom_tag:finetune", "custom_tag:reasoning", "custom_tag:hybrid-mode", "custom_tag:chatml", "custom_tag:function calling", "custom_tag:tool use", "custom_tag:json mode", "custom_tag:structured outputs", "custom_tag:atropos", "custom_tag:dataforge", "custom_tag:long context", "custom_tag:roleplaying", "custom_tag:chat"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-22T15:19:19.077489+00:00", "modelType": "seed_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 39913484098}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-22T16:57:24.469812+00:00", "targetGpu": "MetaX_c-500", "taskId": "5721855", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/Trinity-Mini-AWQ-8bit", "modelProfile": {"architectures": ["AfmoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 28836491616, "estimatedRequiredGiB": 32.248, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "afmoe", "modelscopeFileSize": 28854576732, "modelscopeLicense": "other", "modelscopeParams": 26123974400, "modelscopeTags": ["license:other", "model_type:afmoe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 28854576732}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-22T17:54:56.135763+00:00", "targetGpu": "MetaX_c-500", "taskId": "5722885", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/Trinity-Mini-AWQ-8bit", "modelProfile": {"architectures": ["AfmoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 28836491616, "estimatedRequiredGiB": 32.248, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "afmoe", "modelscopeFileSize": 28854576732, "modelscopeLicense": "other", "modelscopeParams": 26123974400, "modelscopeTags": ["license:other", "model_type:afmoe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 28854576732}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-22T17:54:56.135763+00:00", "targetGpu": "MetaX_c-500", "taskId": "5722885", "taskType": "text-generation", "verifyResult": null}