state: generation 10661 (cycle)

This commit is contained in:
2026-09-20 15:18:44 +00:00
parent b8e512ab31
commit 8da26c9a6c
9 changed files with 2002 additions and 1960 deletions

View File

@@ -854,7 +854,7 @@
"hygon_k100-ai|vllm|text-generation|model_type:rwkv7": {
"architectureSignature": "model_type:rwkv7",
"architectures": [],
"evidenceCount": 2,
"evidenceCount": 1,
"expiresAt": "2026-10-15T15:26:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-15T15:26:21+00:00",
@@ -862,12 +862,10 @@
"matchType": "model_type",
"modelType": "rwkv7",
"sourceModelIds": [
"RWKV/RWKV7-7.2B-20260805",
"RWKV/RWKV7-13.3B-20260805"
"RWKV/RWKV7-7.2B-20260805"
],
"sourceTaskIds": [
"4609108",
"4592432"
"4609108"
],
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation"
@@ -1937,7 +1935,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-20T15:04:23.054828+00:00",
"generatedAt": "2026-09-20T15:18:37.338719+00:00",
"summary": {
"activeBlockCount": 94,
"byGpuFramework": {

View File

@@ -425,7 +425,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-20T15:18:21.688932+00:00",
"generatedAt": "2026-09-20T15:18:43.544150+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-09-20T15:18:21.688932+00:00",
"catalogUpdatedAt": "2026-09-20T15:18:43.544150+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-09-20T15:18:27.754031+00:00",
"generatedAt": "2026-09-20T15:18:43.544150+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6422,6 +6422,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-09-20T15:18:21.688932+00:00",
"taskTreeUpdatedAt": "2026-09-20T15:18:43.544150+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-20T14:47:45.558449+00:00",
"lastSyncTime": "2026-09-20T14:47:45.260018+00:00",
"generatedAt": "2026-09-20T15:18:37.282467+00:00",
"lastSyncTime": "2026-09-20T15:18:36.848623+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -858,7 +858,7 @@
"hygon_k100-ai|vllm|text-generation|model_type:rwkv7": {
"architectureSignature": "model_type:rwkv7",
"architectures": [],
"evidenceCount": 2,
"evidenceCount": 1,
"expiresAt": "2026-10-15T15:26:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-15T15:26:21+00:00",
@@ -866,12 +866,10 @@
"matchType": "model_type",
"modelType": "rwkv7",
"sourceModelIds": [
"RWKV/RWKV7-7.2B-20260805",
"RWKV/RWKV7-13.3B-20260805"
"RWKV/RWKV7-7.2B-20260805"
],
"sourceTaskIds": [
"4609108",
"4592432"
"4609108"
],
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation"
@@ -2079,24 +2077,24 @@
"decisionSuccessRate": 0.1549,
"decisionTotal": 71,
"failureBreakdown": {
"ambiguous_runtime": 51,
"ambiguous_runtime": 53,
"framework_architecture_unsupported": 57,
"memory_capacity": 1,
"repository_structure": 1,
"tokenizer_compatibility": 1
},
"failureCount": 111,
"failureRate": 0.9098,
"failureCount": 113,
"failureRate": 0.9113,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 11,
"successRate": 0.0902,
"successRate": 0.0887,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 122,
"unresolvedFailureCount": 51
"total": 124,
"unresolvedFailureCount": 53
},
"Ascend_910-b3|vllm|visual-multi-modal": {
"attributableFailureCount": 1,
@@ -4093,25 +4091,25 @@
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 9,
"decisionFailureRate": 0.8182,
"decisionSuccessRate": 0.1818,
"decisionTotal": 11,
"decisionFailureRate": 0.75,
"decisionSuccessRate": 0.25,
"decisionTotal": 12,
"failureBreakdown": {
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 8,
"model_load": 1
},
"failureCount": 20,
"failureRate": 0.9091,
"failureRate": 0.8696,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0909,
"successCount": 3,
"successRate": 0.1304,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 22,
"total": 23,
"unresolvedFailureCount": 11
},
"Vastai_va16|vllm|text-generation": {
@@ -4459,7 +4457,7 @@
"decisionSuccessRate": 0.0222,
"decisionTotal": 3553,
"failureBreakdown": {
"ambiguous_runtime": 1431,
"ambiguous_runtime": 1433,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
@@ -4473,15 +4471,15 @@
"tokenizer_compatibility": 408,
"参数/模板问题": 40
},
"failureCount": 5809,
"failureCount": 5811,
"failureRate": 0.9866,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 864,
"successCount": 79,
"successRate": 0.0134,
"total": 5888,
"unresolvedFailureCount": 1471
"total": 5890,
"unresolvedFailureCount": 1473
},
"vllm-customized": {
"attributableFailureCount": 1,
@@ -4571,9 +4569,9 @@
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 118,
"decisionFailureRate": 0.9833,
"decisionSuccessRate": 0.0167,
"decisionTotal": 120,
"decisionFailureRate": 0.9752,
"decisionSuccessRate": 0.0248,
"decisionTotal": 121,
"failureBreakdown": {
"ambiguous_runtime": 119,
"backend_operator": 8,
@@ -4585,13 +4583,13 @@
"参数/模板问题": 8
},
"failureCount": 261,
"failureRate": 0.9924,
"failureRate": 0.9886,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 16,
"successCount": 2,
"successRate": 0.0076,
"total": 263,
"successCount": 3,
"successRate": 0.0114,
"total": 264,
"unresolvedFailureCount": 127
},
"vllm_tokenizer_patch": {
@@ -4614,7 +4612,7 @@
"unresolvedFailureCount": 24
}
},
"generatedAt": "2026-09-20T14:47:45.550467+00:00",
"generatedAt": "2026-09-20T15:18:37.274107+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 75,
@@ -4622,7 +4620,7 @@
"decisionSuccessRate": 0.2021,
"decisionTotal": 94,
"failureBreakdown": {
"ambiguous_runtime": 59,
"ambiguous_runtime": 61,
"framework_architecture_unsupported": 72,
"memory_capacity": 1,
"repository_structure": 1,
@@ -4631,15 +4629,15 @@
"日志缺失": 3,
"验证失败": 27
},
"failureCount": 183,
"failureRate": 0.9059,
"failureCount": 185,
"failureRate": 0.9069,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 19,
"successRate": 0.0941,
"total": 202,
"unresolvedFailureCount": 108
"successRate": 0.0931,
"total": 204,
"unresolvedFailureCount": 110
},
"Ascend_910-b4": {
"attributableFailureCount": 305,
@@ -4967,9 +4965,9 @@
},
"Vastai_va16": {
"attributableFailureCount": 441,
"decisionFailureRate": 0.8909,
"decisionSuccessRate": 0.1091,
"decisionTotal": 495,
"decisionFailureRate": 0.8891,
"decisionSuccessRate": 0.1109,
"decisionTotal": 496,
"failureBreakdown": {
"ambiguous_runtime": 811,
"context_length": 9,
@@ -4984,13 +4982,13 @@
"验证失败": 130
},
"failureCount": 1758,
"failureRate": 0.9702,
"failureRate": 0.9697,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 14,
"successCount": 54,
"successRate": 0.0298,
"total": 1812,
"successCount": 55,
"successRate": 0.0303,
"total": 1813,
"unresolvedFailureCount": 1303
},
"hygon_k100-ai": {
@@ -5324,9 +5322,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 3
},
"failureCount": 1,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "llama",
@@ -5338,8 +5336,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 3,
"unresolvedFailureCount": 3
},
"Ascend_910-b3|vllm|text-generation|llama|none": {
"attributableFailureCount": 0,
@@ -10554,24 +10552,24 @@
"Vastai_va16|vllm_fix_tokenizer|text-generation|llama|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"failureRate": 0.5,
"framework": "vllm_fix_tokenizer",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"successCount": 1,
"successRate": 0.5,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 1
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|minicpm|none": {
@@ -11138,15 +11136,15 @@
"unresolvedFailureCount": 2
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 17,
"consecutiveFailures": 17,
"attributableFailureCount": 16,
"consecutiveFailures": 16,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 17,
"decisionTotal": 16,
"failureBreakdown": {
"ambiguous_runtime": 3,
"framework_architecture_unsupported": 17
"ambiguous_runtime": 4,
"framework_architecture_unsupported": 16
},
"failureCount": 20,
"failureRate": 1.0,
@@ -11161,7 +11159,7 @@
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 3
"unresolvedFailureCount": 4
},
"Ascend_910-b4|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -11796,18 +11794,18 @@
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 12,
"consecutiveFailures": 12,
"attributableFailureCount": 11,
"consecutiveFailures": 11,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 12,
"decisionTotal": 11,
"failureBreakdown": {
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 11,
"framework_architecture_unsupported": 10,
"model_load": 1
},
"failureCount": 19,
"failureCount": 18,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -11819,7 +11817,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 19,
"total": 18,
"unresolvedFailureCount": 7
}
},
@@ -11899,6 +11897,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm|text-generation|llama|awq": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-20T15:18:36.848582+00:00",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm|text-generation|qwen3|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -13581,6 +13604,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm|text-generation|llama|awq|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Ascend_910-b3|vllm|text-generation|llama|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -21570,13 +21617,13 @@
"Vastai_va16|vllm_fix_tokenizer|text-generation|llama|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"failureRate": 0.5,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
@@ -21584,11 +21631,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"successCount": 1,
"successRate": 0.5,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 1
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|minicpm|none|33": {
@@ -22267,15 +22314,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 15872,
"totalRecords": 15977,
"terminalRecords": 15875,
"totalRecords": 15980,
"totals": {
"attributableFailureCount": 5755,
"decisionFailureRate": 0.8614,
"decisionSuccessRate": 0.1386,
"decisionTotal": 6681,
"decisionFailureRate": 0.8613,
"decisionSuccessRate": 0.1387,
"decisionTotal": 6682,
"failureBreakdown": {
"ambiguous_runtime": 3767,
"ambiguous_runtime": 3769,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
@@ -22291,15 +22338,15 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 14946,
"failureRate": 0.9417,
"failureCount": 14948,
"failureRate": 0.9416,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 926,
"successRate": 0.0583,
"total": 15872,
"unresolvedFailureCount": 8269
"successCount": 927,
"successRate": 0.0584,
"total": 15875,
"unresolvedFailureCount": 8271
},
"warnings": [
"GPU Iluvatar_bi-100 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -22344,12 +22391,12 @@
"组合 Cambricon_mlu-370-x4|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 Ascend_910-b4|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|transformers|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|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 Ascend_910-b3|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|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
"组合 Ascend_910-b3|vllm|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",
"summarizedRecords": 15977,
"summarizedRecords": 15980,
"version": 1
}

View File

@@ -81,6 +81,8 @@
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600018+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26090095180, "modelscopeLicense": "apache-2.0", "modelscopeParams": 21416999792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26090095180}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:18.989339+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969386", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["zaya"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T11:30:54.600365+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463599, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463599}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:18.452113+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969361", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T14:32:15.260751+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16779959304, "estimatedRequiredGiB": 18.777, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16801630203, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8389956608, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16801630203}, "outcome": "success", "status": "success", "submitTime": "2026-09-20T03:09:18.440547+00:00", "targetGpu": "Biren_166m", "taskId": "4969359", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T15:18:36.848582+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "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:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.540705+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969050", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T15:18:36.848613+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.537909+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969049", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-19T23:13:47.695492+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-19T23:07:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477839", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-19T23:13:47.695526+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-19T23:07:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458016", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-19T23:04:02.598845+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-19T23:03:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4609086", "taskType": "text-generation", "verifyResult": -1}
@@ -296,5 +298,3 @@
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-14T02:14:40.319417+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T02:13:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4582655", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-09-14T00:51:56.404636+00:00", "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T00:43:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4490280", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "", "lastSyncTime": "2026-09-13T23:31:12.512853+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T23:25:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610393", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-13T23:13:14.924714+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T23:09:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4592432", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-13T21:45:41.613474+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:39:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4559290", "taskType": "text-generation", "verifyResult": -1}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.20.2",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "4baaa68c2f321bdb4927054c1a1d7cdd37342f28d533a84b668b6b0d39492466",
".modelhub_state/architecture_compatibility_blacklist.json": "596e5a95a6f2f34d78acc5a7138d60576f9e3dc78c13db5fbde07c5fccf6e0a9",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "5704d7558e47b7e3f77faf13d28e28c0fa095745576282cbfbbcde6dd6b80602",
".modelhub_state/official_capabilities.json": "6b778219498f1dddaff8c776edf48122796231bef7cda4b3fa1b86951a38ba95",
".modelhub_state/outcome_checkpoint.json": "6d7782c8c9fc862f97956cde907b6d480a0f7a456ac794050e320f9ed7087a41",
".modelhub_state/market_intelligence.json": "2f30c8738d86debdba38e2794f50fd986048b43ea1497ced4b3d84946e88c199",
".modelhub_state/official_capabilities.json": "8d46290bf6142c51d120c8810de645f9e5e2651c869f8b1f17778f92aa6ec3b4",
".modelhub_state/outcome_checkpoint.json": "a23f106b590d1ee27f0bf12e3d83f77d1b58cd9b3ff0997ef165377a7b40f01e",
".modelhub_state/queue_cleanup_latest.json": "eb01f106d0cd4018a0346c4a81182d6a9e67f5d4d14db22f5d0c685667977bc3",
".modelhub_state/recent_outcomes.jsonl": "c686c563ab48519884fd42d9952589ca0656ee5a5fab0f1556f4f5dc80e978ff",
".modelhub_state/recovery_active_tasks.jsonl": "a50fbf497e22afbdd48b6ea15cf693e30331daa818471aea80cea2654fa9822a",
".modelhub_state/recovery_intents.jsonl": "5f91676370bed4b9ccf95a18d8240ed3c889e1652031702942f2ab6f5fe4ae4b",
".modelhub_state/recent_outcomes.jsonl": "3a03e5214469a622c52ab28c45f4b795c0cb1fd17dcd22a5827ae30af60b5716",
".modelhub_state/recovery_active_tasks.jsonl": "551bbcaf5dd7a3a590cd445118ab262278b96e4be576a71a6b6bf1e687c45e05",
".modelhub_state/recovery_intents.jsonl": "46becb86b7096ac5bf633bf71b8e7832f40966dcedcb19955cea3769d174ef48",
".modelhub_state/routing_intelligence.json": "a88462c005b631d7d444c0c5e9f25343d7005c88c0d2eed54f74958e8f567859",
".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7",
".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
"ledger/submissions.jsonl": "f4362ab94c40479a82932013c5e2de1d237326ea2df827a2e131475e45089c2d",
"outcomes/submissions.jsonl": "5d2bcdace720bec0e953379de70f5dce35f11f11de3bceffcef71d29f838e82b"
"outcomes/submissions.jsonl": "63a267257a57957b39452f572c1738230645debea0f4b02b67fa258e7fdee497"
},
"generation": 10660,
"generation": 10661,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-20T15:18:34.135172+00:00",
"updatedAt": "2026-09-20T15:18:44.391846+00:00",
"writerId": "fc715c06e24c4db2ae3e425e435db996"
}

View File

@@ -124,7 +124,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T16:11:26.734418+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T08:10:45.450685+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4736922", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T16:11:26.734408+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574577, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574577}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T08:10:45.448357+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4736923", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T16:11:26.734435+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22263760648, "estimatedRequiredGiB": 24.908, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22286993822, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6019449856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22286993822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T08:10:45.445768+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4736921", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T18:09:45.834719+00:00", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777882, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043777882}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T10:01:35.815834+00:00", "targetGpu": "Vastai_va16", "taskId": "4738373", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T18:17:57.609954+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109838556, "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": 2109838556}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T10:15:29.199861+00:00", "targetGpu": "Vastai_va16", "taskId": "4738578", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T18:48:23.446781+00:00", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777882, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043777882}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T10:46:50.761768+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4739146", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T18:48:23.446807+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109838556, "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": 2109838556}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T10:46:50.760190+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4739145", "taskType": "text-generation", "verifyResult": null}
@@ -500,10 +499,8 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647685+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22263760648, "estimatedRequiredGiB": 24.908, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22286993822, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6019449856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22286993822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.443100+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969043", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647498+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25593158704, "estimatedRequiredGiB": 28.626, "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": 25613691403, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7626590448, "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": 25613691403}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.436311+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969042", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426233716, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426233716}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T02:52:51.449778+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969045", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "pending", "submitTime": "2026-09-20T02:52:51.537909+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969049", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647775+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "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": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.536043+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969046", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "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": 5737318602}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T02:52:51.547567+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969048", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "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:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T02:52:51.540705+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969050", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:00:25.647490+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "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:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.643751+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969053", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647352+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.575551+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969051", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19342796520, "estimatedRequiredGiB": 21.64, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 19362750397, "modelscopeLicense": "other", "modelscopeParams": 18237772608, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19362750397}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T02:52:51.639873+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969054", "taskType": "text-generation", "verifyResult": null}