|
|
|
|
@@ -913,14 +913,14 @@
|
|
|
|
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-12T19:13:20.252859+00:00", "modelId": "JetBrains/Mellum2.1-12B-A2.5B-Thinking", "modelProfile": {"architectures": ["MellumForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24300538808, "estimatedRequiredGiB": 27.167, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mellum", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:mellum", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24308363631}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T11:02:36.659532+00:00", "targetGpu": "Biren_166m", "taskId": "5486420", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-12T19:13:20.252892+00:00", "modelId": "JavaFamily/corvus-gov-3B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6425529048, "estimatedRequiredGiB": 7.2, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 6442887386, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 3212749824, "modelscopeTags": ["license:Apache License 2.0", "model_type:llama3", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:政衡", "custom_tag:政企大模型", "custom_tag:政务 AI 大模型", "custom_tag:JavaFamily", "custom_tag:微调", "custom_tag:LLaMA-Factory", "custom_tag:LoRA", "custom_tag:SFT", "custom_tag:政务领域", "custom_tag:中文对话"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6442887386}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T11:02:36.586782+00:00", "targetGpu": "Biren_166m", "taskId": "5486412", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-12T19:13:20.252880+00:00", "modelId": "tsinghua-sigs-robot-lab/VeriLoop-E2", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 55655301924, "estimatedRequiredGiB": 62.227, "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": 55679383091, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27872753616, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "task:text-generation", "custom_tag:conversational", "custom_tag:veriloop", "custom_tag:post-training", "custom_tag:coding-agent", "custom_tag:software-engineering", "custom_tag:mathematical-reasoning", "custom_tag:scientific-reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:safetensors", "custom_tag:vllm", "custom_tag:apache-2.0"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 55679383091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T11:02:36.551168+00:00", "targetGpu": "Biren_166m", "taskId": "5486417", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlx-community/humanizer-12b-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8964644930, "estimatedRequiredGiB": 10.055, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 8997071286, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1009125399, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:gemma4", "custom_tag:humanizer", "custom_tag:text-rewriting", "custom_tag:style-transfer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8997071286}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T13:07:17.665600+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5488465", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "OsaurusAI/Diplodocus-preview-7B-JANGH7", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6627366288, "estimatedRequiredGiB": 7.43, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6648353931, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1727664128, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "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:tool-use", "custom_tag:finance", "custom_tag:k2_horizon", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6648353931}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T13:07:17.672734+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5488469", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "yiku233/qwen2.5-coder-7b-nl2sql", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15715871392, "estimatedRequiredGiB": 17.582, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 15731820908, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7615616512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:nl2sql", "custom_tag:text-to-sql", "custom_tag:lora", "custom_tag:distillation", "custom_tag:dpo", "custom_tag:qwen2_5_coder", "custom_tag:mysql", "custom_tag:agent"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15731820908}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T13:07:17.667061+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5488466", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "Akahsizrr/Cyber-Prime-1.2", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427448, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412820060, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-09T19:18:55.559723+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 5412820060}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T13:07:17.673725+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5488464", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "ConwayResearch/Underdog-Woof-2B-1.1", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:4bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426023876}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T13:07:17.669202+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5488468", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "h2oai/h2o-lightning-4b-nemotron-nano", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7947142672, "estimatedRequiredGiB": 8.901, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 7964754709, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-making", "custom_tag:calibration", "custom_tag:jevbench", "custom_tag:nemotron"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7964754709}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T13:07:17.661134+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5488470", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "JavaFamily/corvus-gov-3B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6425529048, "estimatedRequiredGiB": 7.2, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 6442887386, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 3212749824, "modelscopeTags": ["license:Apache License 2.0", "model_type:llama3", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:政衡", "custom_tag:政企大模型", "custom_tag:政务 AI 大模型", "custom_tag:JavaFamily", "custom_tag:微调", "custom_tag:LLaMA-Factory", "custom_tag:LoRA", "custom_tag:SFT", "custom_tag:政务领域", "custom_tag:中文对话"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6442887386}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T13:07:17.671102+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5488467", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "ddalcu/Qwen3.6-35B-A3B-MLX-Serve-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20877335295, "estimatedRequiredGiB": 23.362, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20904301636, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5865901936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5_moe", "custom_tag:moe", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20904301636}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T13:07:17.664438+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5488471", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-12T21:14:07.664548+00:00", "modelId": "mlx-community/humanizer-12b-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8964644930, "estimatedRequiredGiB": 10.055, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 8997071286, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1009125399, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:gemma4", "custom_tag:humanizer", "custom_tag:text-rewriting", "custom_tag:style-transfer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8997071286}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T13:07:17.665600+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5488465", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-12T21:14:07.664525+00:00", "modelId": "OsaurusAI/Diplodocus-preview-7B-JANGH7", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6627366288, "estimatedRequiredGiB": 7.43, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6648353931, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1727664128, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "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:tool-use", "custom_tag:finance", "custom_tag:k2_horizon", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6648353931}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T13:07:17.672734+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5488469", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-12T21:14:07.664588+00:00", "modelId": "yiku233/qwen2.5-coder-7b-nl2sql", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15715871392, "estimatedRequiredGiB": 17.582, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 15731820908, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7615616512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:nl2sql", "custom_tag:text-to-sql", "custom_tag:lora", "custom_tag:distillation", "custom_tag:dpo", "custom_tag:qwen2_5_coder", "custom_tag:mysql", "custom_tag:agent"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15731820908}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T13:07:17.667061+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5488466", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-12T21:14:07.664583+00:00", "modelId": "Akahsizrr/Cyber-Prime-1.2", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427448, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412820060, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-09T19:18:55.559723+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 5412820060}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T13:07:17.673725+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5488464", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-12T21:14:07.664576+00:00", "modelId": "ConwayResearch/Underdog-Woof-2B-1.1", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:4bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426023876}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T13:07:17.669202+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5488468", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-12T21:14:07.664562+00:00", "modelId": "h2oai/h2o-lightning-4b-nemotron-nano", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7947142672, "estimatedRequiredGiB": 8.901, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 7964754709, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-making", "custom_tag:calibration", "custom_tag:jevbench", "custom_tag:nemotron"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7964754709}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T13:07:17.661134+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5488470", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-12T21:14:07.664556+00:00", "modelId": "JavaFamily/corvus-gov-3B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6425529048, "estimatedRequiredGiB": 7.2, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 6442887386, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 3212749824, "modelscopeTags": ["license:Apache License 2.0", "model_type:llama3", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:政衡", "custom_tag:政企大模型", "custom_tag:政务 AI 大模型", "custom_tag:JavaFamily", "custom_tag:微调", "custom_tag:LLaMA-Factory", "custom_tag:LoRA", "custom_tag:SFT", "custom_tag:政务领域", "custom_tag:中文对话"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6442887386}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T13:07:17.671102+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5488467", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-12T21:14:07.664570+00:00", "modelId": "ddalcu/Qwen3.6-35B-A3B-MLX-Serve-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20877335295, "estimatedRequiredGiB": 23.362, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20904301636, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5865901936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5_moe", "custom_tag:moe", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20904301636}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T13:07:17.664438+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5488471", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "h2oai/h2o-lightning-4b-nemotron-nano", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7947142672, "estimatedRequiredGiB": 8.901, "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": 7964754709, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-making", "custom_tag:calibration", "custom_tag:jevbench", "custom_tag:nemotron"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7964754709}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T14:15:43.751658+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5489787", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/plamo-2-translate-8bit", "modelProfile": {"architectures": ["Plamo2ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10124903941, "estimatedRequiredGiB": 11.995, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo2", "modelscopeFileSize": 10733363758, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:plamo", "custom_tag:translation", "custom_tag:custom_code", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10733363758}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T20:17:47.451311+00:00", "targetGpu": "MetaX_c-500", "taskId": "5495574", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/plamo-2-translate-bf16", "modelProfile": {"architectures": ["Plamo2ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19056520807, "estimatedRequiredGiB": 21.309, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo2", "modelscopeFileSize": 19067261675, "modelscopeLicense": "other", "modelscopeParams": 9528235008, "modelscopeTags": ["license:other", "model_type:plamo2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:plamo", "custom_tag:translation", "custom_tag:custom_code", "custom_tag:bf16"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19067261675}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T20:31:45.255675+00:00", "targetGpu": "MetaX_c-500", "taskId": "5495895", "taskType": "text-generation", "verifyResult": null}
|
|
|
|
|
|
