state: generation 12265 (intent)

This commit is contained in:
2026-10-27 18:21:23 +00:00
parent 0d61117648
commit 899bebee52
6 changed files with 198 additions and 178 deletions

View File

@@ -1149,54 +1149,54 @@
{"framework": null, "lastSyncTime": "2026-10-26T07:42:03.480036+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-70B-quantized.w8a8", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "4332423", "taskType": "text-generation"}
{"framework": null, "lastSyncTime": "2026-10-26T07:42:03.480059+00:00", "modelId": "z-lab/Qwen3.8-27B-DFlash2-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "4332399", "taskType": "text-generation"}
{"framework": null, "lastSyncTime": "2026-10-27T09:07:39.875389+00:00", "modelId": "cyankiwi/Nex-N2-mini-AWQ-INT4", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "hygon_k100-ai", "taskId": "4079930", "taskType": "text-generation"}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3459874983, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 3459874983, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 3459874983, "repositoryOnDiskBytes": 3459874983}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.061571+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824135", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115852073, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 18115852073, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2f008ff356aba06a", "recursiveRepositoryBytes": 18115852073, "repositoryOnDiskBytes": 18115852073}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.081308+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824139", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "pfnet/plamo-13b-instruct", "modelProfile": {"architectures": ["PlamoForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26199130400, "estimatedRequiredGiB": 29.281, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo", "modelscopeFileSize": 26200349563, "modelscopeLicense": "apache-2.0", "modelscopeParams": 13099545600, "modelscopeTags": ["license:apache-2.0", "model_type:plamo", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 26200349563, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 26200349563, "repositoryOnDiskBytes": 26200349563}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.175285+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824144", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115852009, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 18115852009, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2f008ff356aba06a", "recursiveRepositoryBytes": 18115852009, "repositoryOnDiskBytes": 18115852009}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.063227+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824134", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "pfnet/plamo-13b-instruct-nc", "modelProfile": {"architectures": ["PlamoForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26199130400, "estimatedRequiredGiB": 29.281, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo", "modelscopeFileSize": 26200357986, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 13099545600, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:plamo", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 26200357986, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 26200357986, "repositoryOnDiskBytes": 26200357986}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.082935+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824140", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115815143, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 18115815143, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:1c0587b0b0cf71b0", "recursiveRepositoryBytes": 18115815143, "repositoryOnDiskBytes": 18115815143}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.034492+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824161", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/MiroThinker-v1.5-30B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115840957, "modelscopeLicense": "mit", "modelscopeParams": 30532122624, "modelscopeTags": ["license:mit", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:open-source", "custom_tag:miromind", "custom_tag:deep-research"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 18115840957, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:5d1bf83368e103ed", "recursiveRepositoryBytes": 18115840957, "repositoryOnDiskBytes": 18115840957}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.094407+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824143", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.6-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4451626120, "estimatedRequiredGiB": 4.992, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4466699746, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 4466699746, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:792a878136ace20b", "recursiveRepositoryBytes": 4466699746, "repositoryOnDiskBytes": 4466699746}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.064273+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824136", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5416721872, "estimatedRequiredGiB": 6.072, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 5432699381, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 5432699381, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:9902073541f0c0c8", "recursiveRepositoryBytes": 5432699381, "repositoryOnDiskBytes": 5432699381}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.132633+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824141", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/KAT-V1-40B-AWQ", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23382751128, "estimatedRequiredGiB": 26.15, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 23398883380, "modelscopeLicense": "other", "modelscopeParams": 40565560320, "modelscopeTags": ["license:other", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23398883380, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 23398883380, "repositoryOnDiskBytes": 23398883380}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.059560+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824137", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.6-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.208, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8239287196, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 8239287196, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 8239287196, "repositoryOnDiskBytes": 8239287196}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.110784+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824138", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/KAT-V1-40B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23382751128, "estimatedRequiredGiB": 26.15, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 23398883380, "modelscopeLicense": "other", "modelscopeParams": 40565560320, "modelscopeTags": ["license:other", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23398883380, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 23398883380, "repositoryOnDiskBytes": 23398883380}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.203946+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824145", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Jan-v1-4B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5416721872, "estimatedRequiredGiB": 6.072, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 5432695293, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 5432695293, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:9902073541f0c0c8", "recursiveRepositoryBytes": 5432695293, "repositoryOnDiskBytes": 5432695293}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.169601+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824142", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14278393080, "estimatedRequiredGiB": 15.973, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 14292650823, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 14292650823, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:cefd4b27e758b1de", "recursiveRepositoryBytes": 14292650823, "repositoryOnDiskBytes": 14292650823}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.182449+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824146", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24682886272, "estimatedRequiredGiB": 27.602, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 24697709480, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 24697709480, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:59dd59959c7fd772", "recursiveRepositoryBytes": 24697709480, "repositoryOnDiskBytes": 24697709480}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.239218+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824147", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/KAT-Dev-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20666355744, "estimatedRequiredGiB": 23.114, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 20682426913, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32762123264, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 20682426913, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:d631cfb7fc7f8ffa", "recursiveRepositoryBytes": 20682426913, "repositoryOnDiskBytes": 20682426913}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.206139+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824150", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Hermes-4-14B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10544400664, "estimatedRequiredGiB": 11.802, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 10560388030, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14768307200, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:Qwen-3-14B", "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"], "publishedSizeBytes": 10560388030, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b91e1843aeaeb7f4", "recursiveRepositoryBytes": 10560388030, "repositoryOnDiskBytes": 10560388030}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.236296+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824149", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Hermes-4-14B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17150429576, "estimatedRequiredGiB": 19.185, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 17166416942, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14768307200, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:Qwen-3-14B", "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"], "publishedSizeBytes": 17166416942, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b0b0c9a002005922", "recursiveRepositoryBytes": 17166416942, "repositoryOnDiskBytes": 17166416942}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.256695+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824148", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077977948, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 11077977948, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:abf2795564ed82d1", "recursiveRepositoryBytes": 11077977948, "repositoryOnDiskBytes": 11077977948}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.252703+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824152", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/LFM2-8B-A1B-AWQ-8bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9682515680, "estimatedRequiredGiB": 10.827, "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": 9688084066, "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"], "publishedSizeBytes": 9688084066, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:0662089ef0756354", "recursiveRepositoryBytes": 9688084066, "repositoryOnDiskBytes": 9688084066}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.254577+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824151", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593025749, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 17593025749, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 17593025749, "repositoryOnDiskBytes": 17593025749}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.285428+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824153", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/Nemotron-Orchestrator-8B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921104, "estimatedRequiredGiB": 11.048, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 9885904129, "modelscopeLicense": null, "modelscopeParams": 8190735360, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 9885904129, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2b478ca1d5cf05e4", "recursiveRepositoryBytes": 9885904129, "repositoryOnDiskBytes": 9885904129}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.382051+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824159", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8122473440, "estimatedRequiredGiB": 9.103, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 8145039537, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 8145039537, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:06e1b44940b82d27", "recursiveRepositoryBytes": 8145039537, "repositoryOnDiskBytes": 8145039537}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.350896+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824155", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "primitive-ai/Nanbeige4.3-33B-NVFP4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22070410112, "estimatedRequiredGiB": 24.69, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 22091795362, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977388, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:nanbeige", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 22091795362, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:5179e7fa01f5b826", "recursiveRepositoryBytes": 22091795362, "repositoryOnDiskBytes": 22091795362}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.295226+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824166", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-MXFP8", "modelProfile": {"architectures": ["DoryForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4750755304, "estimatedRequiredGiB": 5.331, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "dory", "modelscopeFileSize": 4769740524, "modelscopeLicense": "other", "modelscopeParams": 3975229440, "modelscopeTags": ["license:other", "model_type:dory", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-labs", "custom_tag:dory"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 4769740524, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:402c90eb0b5de1c4", "recursiveRepositoryBytes": 4769740524, "repositoryOnDiskBytes": 4769740524}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.330346+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824154", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/NVIDIA-Nemotron-Nano-12B-v2-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8857194176, "estimatedRequiredGiB": 9.918, "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": 8874757118, "modelscopeLicense": "other", "modelscopeParams": 3057874704, "modelscopeTags": ["license:other", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 8874757118, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b63fa8ce792e9ecf", "recursiveRepositoryBytes": 8874757118, "repositoryOnDiskBytes": 8874757118}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.408272+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824160", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/granite-4.0-h-small-AWQ-4bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26166907992, "estimatedRequiredGiB": 29.255, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granitemoehybrid", "modelscopeFileSize": 26176736582, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32618379776, "modelscopeTags": ["license:apache-2.0", "model_type:granitemoehybrid", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:language", "custom_tag:granite-4.0"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 26176736582, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2b7e650901445ae6", "recursiveRepositoryBytes": 26176736582, "repositoryOnDiskBytes": 26176736582}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.375810+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824156", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/granite-4.0-h-tiny-AWQ-4bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5504236472, "estimatedRequiredGiB": 6.162, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granitemoehybrid", "modelscopeFileSize": 5514064765, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7093177920, "modelscopeTags": ["license:apache-2.0", "model_type:granitemoehybrid", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:language", "custom_tag:granite-4.0"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 5514064765, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2b7e650901445ae6", "recursiveRepositoryBytes": 5514064765, "repositoryOnDiskBytes": 5514064765}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.393599+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824158", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/LFM2-8B-A1B-AWQ-8bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9682515680, "estimatedRequiredGiB": 10.827, "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": 9688084066, "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"], "publishedSizeBytes": 9688084066, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:0662089ef0756354", "recursiveRepositoryBytes": 9688084066, "repositoryOnDiskBytes": 9688084066}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.406836+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824165", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/Nemotron-Cascade-2-30B-A3B-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20746036464, "estimatedRequiredGiB": 23.21, "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": 20767786487, "modelscopeLicense": "other", "modelscopeParams": 6674513776, "modelscopeTags": ["license:other", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:nemotron-cascade-2", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 20767786487, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:4e040710ef43272e", "recursiveRepositoryBytes": 20767786487, "repositoryOnDiskBytes": 20767786487}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.380443+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824157", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "GMUnitX/DeepSeek-R1-Distill-Qwen-1.5B-MPVDHS", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7108390440, "estimatedRequiredGiB": 7.957, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 7119857588, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:Apache License 2.0", "model_type:Qwen2", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 7119857588, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7119857588, "repositoryOnDiskBytes": 7119857588}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.390118+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824167", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-NVFP4", "modelProfile": {"architectures": ["DoryForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3202498032, "estimatedRequiredGiB": 3.6, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "dory", "modelscopeFileSize": 3221469377, "modelscopeLicense": "other", "modelscopeParams": 2323722240, "modelscopeTags": ["license:other", "model_type:dory", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-labs", "custom_tag:dory"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 3221469377, "quantizationMethod": "modelopt", "quantizationSignature": "modelopt:7f111f5ecf2660ff", "recursiveRepositoryBytes": 3221469377, "repositoryOnDiskBytes": 3221469377}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.432938+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5824162", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/Ornith-1.0-9B-AWQ-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11910385576, "estimatedRequiredGiB": 13.343, "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": 11938806923, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 11938806923, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:c2062c64dee96c04", "recursiveRepositoryBytes": 11938806923, "repositoryOnDiskBytes": 11938806923}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.479452+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5824164", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/Nemotron-Cascade-8B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921096, "estimatedRequiredGiB": 15.786, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 14125281593, "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"], "publishedSizeBytes": 14125281593, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:bd5110bb37ff4e58", "recursiveRepositoryBytes": 14125281593, "repositoryOnDiskBytes": 14125281593}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.481928+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5824163", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/Ornith-1.0-35B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24430419208, "estimatedRequiredGiB": 27.35, "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": 24472753002, "modelscopeLicense": "mit", "modelscopeParams": 35107181936, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 24472753002, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:cc806b483ebd2e69", "recursiveRepositoryBytes": 24472753002, "repositoryOnDiskBytes": 24472753002}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.147215+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824226", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "XingChen-AGI/Xing4.0-29B-Intent-FP8", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33165728400, "estimatedRequiredGiB": 37.07, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 33169542243, "modelscopeLicense": "apache-2.0", "modelscopeParams": 31215031088, "modelscopeTags": ["license:apache-2.0", "model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:intent-recognition", "custom_tag:slot-filling", "custom_tag:information-extraction", "custom_tag:schema-guided", "custom_tag:named-entity-recognition", "custom_tag:relation-extraction", "custom_tag:event-extraction"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 33169542243, "quantizationMethod": "fp8", "quantizationSignature": "fp8:0da8624bcb5e84df", "recursiveRepositoryBytes": 33169542243, "repositoryOnDiskBytes": 33169542243}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.137559+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824223", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "XingChen-AGI/Xing4.0-29B-Intent", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 62431083040, "estimatedRequiredGiB": 69.776, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 62434092643, "modelscopeLicense": "apache-2.0", "modelscopeParams": 31215031088, "modelscopeTags": ["license:apache-2.0", "model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:intent-recognition", "custom_tag:slot-filling", "custom_tag:information-extraction", "custom_tag:schema-guided", "custom_tag:named-entity-recognition", "custom_tag:relation-extraction", "custom_tag:event-extraction"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 62434092643, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 62434092643, "repositoryOnDiskBytes": 62434092643}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.139261+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824235", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "nanbeige/Nanbeige4.3-33B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 66238009168, "estimatedRequiredGiB": 74.051, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 66260067498, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 66260067498, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 66260067498, "repositoryOnDiskBytes": 66260067498}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.132903+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824233", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Tongyi-DeepResearch-30B-A3B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064318294, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 33064318294, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b74ddfdc145e58ff", "recursiveRepositoryBytes": 33064318294, "repositoryOnDiskBytes": 33064318294}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.135642+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824236", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/GLM-4.5-Air-AWQ-4bit", "modelProfile": {"architectures": ["Glm4MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 63400571960, "estimatedRequiredGiB": 70.884, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "glm4_moe", "modelscopeFileSize": 63425670208, "modelscopeLicense": "mit", "modelscopeParams": 106852251264, "modelscopeTags": ["license:mit", "model_type:glm4_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 63425670208, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e5192b47c94517b2", "recursiveRepositoryBytes": 63425670208, "repositoryOnDiskBytes": 63425670208}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.257369+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824227", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ", "modelProfile": {"architectures": ["DeciLMForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29020319488, "estimatedRequiredGiB": 32.453, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_nas", "modelscopeFileSize": 29038368655, "modelscopeLicense": "other", "modelscopeParams": 49867145216, "modelscopeTags": ["license:other", "model_type:nemotron_nas", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:llama-3", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 29038368655, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 29038368655, "repositoryOnDiskBytes": 29038368655}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.145395+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824224", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "primitive-ai/Nanbeige4.3-33B-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35526734272, "estimatedRequiredGiB": 39.728, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 35548056552, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:nanbeige", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 35548056552, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:423cd90dc537dded", "recursiveRepositoryBytes": 35548056552, "repositoryOnDiskBytes": 35548056552}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.149342+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824221", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Kimi-Dev-72B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 79588295928, "estimatedRequiredGiB": 88.967, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 79606715854, "modelscopeLicense": "mit", "modelscopeParams": 72706203648, "modelscopeTags": ["license:mit", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code", "custom_tag:swebench", "custom_tag:software", "custom_tag:issue-resolving"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 79606715854, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:08953c0a152f288b", "recursiveRepositoryBytes": 79606715854, "repositoryOnDiskBytes": 79606715854}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.152800+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824225", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit", "modelProfile": {"architectures": ["DeciLMForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29020319488, "estimatedRequiredGiB": 32.453, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_nas", "modelscopeFileSize": 29038368655, "modelscopeLicense": "other", "modelscopeParams": 49867145216, "modelscopeTags": ["license:other", "model_type:nemotron_nas", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:llama-3", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 29038368655, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 29038368655, "repositoryOnDiskBytes": 29038368655}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.140846+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824222", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/granite-4.0-h-small-AWQ-8bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 39756453136, "estimatedRequiredGiB": 44.442, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granitemoehybrid", "modelscopeFileSize": 39766281934, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32618379776, "modelscopeTags": ["license:apache-2.0", "model_type:granitemoehybrid", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:language", "custom_tag:granite-4.0"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 39766281934, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e379a948ff56dd79", "recursiveRepositoryBytes": 39766281934, "repositoryOnDiskBytes": 39766281934}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.373627+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824238", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064355224, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 33064355224, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:a1e46deb2f53e69c", "recursiveRepositoryBytes": 33064355224, "repositoryOnDiskBytes": 33064355224}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.363858+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824229", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-24B-A2B", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 47944143456, "estimatedRequiredGiB": 53.605, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 47964602717, "modelscopeLicense": "other", "modelscopeParams": 23971587712, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:moe"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 47964602717, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 47964602717, "repositoryOnDiskBytes": 47964602717}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.368106+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824228", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cyankiwi/MiroThinker-v1.0-30B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064339297, "modelscopeLicense": "mit", "modelscopeParams": 30532122624, "modelscopeTags": ["license:mit", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:open-source", "custom_tag:miromind", "custom_tag:deep-research"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 33064339297, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:a1e46deb2f53e69c", "recursiveRepositoryBytes": 33064339297, "repositoryOnDiskBytes": 33064339297}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.362612+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824230", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935099+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3459874983, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 3459874983, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 3459874983, "repositoryOnDiskBytes": 3459874983}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.061571+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824135", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935294+00:00", "modelId": "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115852073, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 18115852073, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2f008ff356aba06a", "recursiveRepositoryBytes": 18115852073, "repositoryOnDiskBytes": 18115852073}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.081308+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824139", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935186+00:00", "modelId": "pfnet/plamo-13b-instruct", "modelProfile": {"architectures": ["PlamoForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26199130400, "estimatedRequiredGiB": 29.281, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo", "modelscopeFileSize": 26200349563, "modelscopeLicense": "apache-2.0", "modelscopeParams": 13099545600, "modelscopeTags": ["license:apache-2.0", "model_type:plamo", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 26200349563, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 26200349563, "repositoryOnDiskBytes": 26200349563}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.175285+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824144", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935020+00:00", "modelId": "cpatonn-mirror/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115852009, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 18115852009, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2f008ff356aba06a", "recursiveRepositoryBytes": 18115852009, "repositoryOnDiskBytes": 18115852009}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.063227+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824134", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935283+00:00", "modelId": "pfnet/plamo-13b-instruct-nc", "modelProfile": {"architectures": ["PlamoForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26199130400, "estimatedRequiredGiB": 29.281, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo", "modelscopeFileSize": 26200357986, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 13099545600, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:plamo", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 26200357986, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 26200357986, "repositoryOnDiskBytes": 26200357986}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.082935+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824140", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935254+00:00", "modelId": "cpatonn-mirror/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115815143, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 18115815143, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:1c0587b0b0cf71b0", "recursiveRepositoryBytes": 18115815143, "repositoryOnDiskBytes": 18115815143}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.034492+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824161", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935328+00:00", "modelId": "cyankiwi/MiroThinker-v1.5-30B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115840957, "modelscopeLicense": "mit", "modelscopeParams": 30532122624, "modelscopeTags": ["license:mit", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:open-source", "custom_tag:miromind", "custom_tag:deep-research"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 18115840957, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:5d1bf83368e103ed", "recursiveRepositoryBytes": 18115840957, "repositoryOnDiskBytes": 18115840957}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.094407+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824143", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935066+00:00", "modelId": "XHToken/Spark-X2.6-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4451626120, "estimatedRequiredGiB": 4.992, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4466699746, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 4466699746, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:792a878136ace20b", "recursiveRepositoryBytes": 4466699746, "repositoryOnDiskBytes": 4466699746}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.064273+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824136", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935142+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5416721872, "estimatedRequiredGiB": 6.072, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 5432699381, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 5432699381, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:9902073541f0c0c8", "recursiveRepositoryBytes": 5432699381, "repositoryOnDiskBytes": 5432699381}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.132633+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824141", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935087+00:00", "modelId": "cpatonn-mirror/KAT-V1-40B-AWQ", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23382751128, "estimatedRequiredGiB": 26.15, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 23398883380, "modelscopeLicense": "other", "modelscopeParams": 40565560320, "modelscopeTags": ["license:other", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23398883380, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 23398883380, "repositoryOnDiskBytes": 23398883380}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.059560+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824137", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935230+00:00", "modelId": "XHToken/Spark-X2.6-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.208, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8239287196, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 8239287196, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 8239287196, "repositoryOnDiskBytes": 8239287196}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.110784+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824138", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935080+00:00", "modelId": "cpatonn-mirror/KAT-V1-40B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23382751128, "estimatedRequiredGiB": 26.15, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 23398883380, "modelscopeLicense": "other", "modelscopeParams": 40565560320, "modelscopeTags": ["license:other", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23398883380, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 23398883380, "repositoryOnDiskBytes": 23398883380}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.203946+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824145", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935206+00:00", "modelId": "cpatonn-mirror/Jan-v1-4B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5416721872, "estimatedRequiredGiB": 6.072, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 5432695293, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 5432695293, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:9902073541f0c0c8", "recursiveRepositoryBytes": 5432695293, "repositoryOnDiskBytes": 5432695293}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.169601+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824142", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935266+00:00", "modelId": "cpatonn-mirror/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14278393080, "estimatedRequiredGiB": 15.973, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 14292650823, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 14292650823, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:cefd4b27e758b1de", "recursiveRepositoryBytes": 14292650823, "repositoryOnDiskBytes": 14292650823}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.182449+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824146", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935057+00:00", "modelId": "cpatonn-mirror/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24682886272, "estimatedRequiredGiB": 27.602, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 24697709480, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 24697709480, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:59dd59959c7fd772", "recursiveRepositoryBytes": 24697709480, "repositoryOnDiskBytes": 24697709480}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.239218+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824147", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935093+00:00", "modelId": "cpatonn-mirror/KAT-Dev-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20666355744, "estimatedRequiredGiB": 23.114, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 20682426913, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32762123264, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 20682426913, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:d631cfb7fc7f8ffa", "recursiveRepositoryBytes": 20682426913, "repositoryOnDiskBytes": 20682426913}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.206139+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824150", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935009+00:00", "modelId": "cpatonn-mirror/Hermes-4-14B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10544400664, "estimatedRequiredGiB": 11.802, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 10560388030, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14768307200, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:Qwen-3-14B", "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"], "publishedSizeBytes": 10560388030, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b91e1843aeaeb7f4", "recursiveRepositoryBytes": 10560388030, "repositoryOnDiskBytes": 10560388030}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.236296+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824149", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935322+00:00", "modelId": "cpatonn-mirror/Hermes-4-14B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17150429576, "estimatedRequiredGiB": 19.185, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 17166416942, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14768307200, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:Qwen-3-14B", "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"], "publishedSizeBytes": 17166416942, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b0b0c9a002005922", "recursiveRepositoryBytes": 17166416942, "repositoryOnDiskBytes": 17166416942}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.256695+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824148", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935289+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077977948, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 11077977948, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:abf2795564ed82d1", "recursiveRepositoryBytes": 11077977948, "repositoryOnDiskBytes": 11077977948}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.252703+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824152", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935278+00:00", "modelId": "cpatonn-mirror/LFM2-8B-A1B-AWQ-8bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9682515680, "estimatedRequiredGiB": 10.827, "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": 9688084066, "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"], "publishedSizeBytes": 9688084066, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:0662089ef0756354", "recursiveRepositoryBytes": 9688084066, "repositoryOnDiskBytes": 9688084066}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.254577+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824151", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935224+00:00", "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593025749, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 17593025749, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 17593025749, "repositoryOnDiskBytes": 17593025749}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.285428+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824153", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935218+00:00", "modelId": "cyankiwi/Nemotron-Orchestrator-8B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921104, "estimatedRequiredGiB": 11.048, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 9885904129, "modelscopeLicense": null, "modelscopeParams": 8190735360, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 9885904129, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2b478ca1d5cf05e4", "recursiveRepositoryBytes": 9885904129, "repositoryOnDiskBytes": 9885904129}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.382051+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824159", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935170+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8122473440, "estimatedRequiredGiB": 9.103, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 8145039537, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 8145039537, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:06e1b44940b82d27", "recursiveRepositoryBytes": 8145039537, "repositoryOnDiskBytes": 8145039537}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.350896+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824155", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935128+00:00", "modelId": "primitive-ai/Nanbeige4.3-33B-NVFP4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22070410112, "estimatedRequiredGiB": 24.69, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 22091795362, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977388, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:nanbeige", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 22091795362, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:5179e7fa01f5b826", "recursiveRepositoryBytes": 22091795362, "repositoryOnDiskBytes": 22091795362}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.295226+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824166", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935200+00:00", "modelId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-MXFP8", "modelProfile": {"architectures": ["DoryForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4750755304, "estimatedRequiredGiB": 5.331, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "dory", "modelscopeFileSize": 4769740524, "modelscopeLicense": "other", "modelscopeParams": 3975229440, "modelscopeTags": ["license:other", "model_type:dory", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-labs", "custom_tag:dory"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 4769740524, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:402c90eb0b5de1c4", "recursiveRepositoryBytes": 4769740524, "repositoryOnDiskBytes": 4769740524}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.330346+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824154", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935272+00:00", "modelId": "cyankiwi/NVIDIA-Nemotron-Nano-12B-v2-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8857194176, "estimatedRequiredGiB": 9.918, "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": 8874757118, "modelscopeLicense": "other", "modelscopeParams": 3057874704, "modelscopeTags": ["license:other", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 8874757118, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b63fa8ce792e9ecf", "recursiveRepositoryBytes": 8874757118, "repositoryOnDiskBytes": 8874757118}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.408272+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824160", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935260+00:00", "modelId": "cyankiwi/granite-4.0-h-small-AWQ-4bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26166907992, "estimatedRequiredGiB": 29.255, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granitemoehybrid", "modelscopeFileSize": 26176736582, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32618379776, "modelscopeTags": ["license:apache-2.0", "model_type:granitemoehybrid", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:language", "custom_tag:granite-4.0"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 26176736582, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2b7e650901445ae6", "recursiveRepositoryBytes": 26176736582, "repositoryOnDiskBytes": 26176736582}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.375810+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824156", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935047+00:00", "modelId": "cyankiwi/granite-4.0-h-tiny-AWQ-4bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5504236472, "estimatedRequiredGiB": 6.162, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granitemoehybrid", "modelscopeFileSize": 5514064765, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7093177920, "modelscopeTags": ["license:apache-2.0", "model_type:granitemoehybrid", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:language", "custom_tag:granite-4.0"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 5514064765, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2b7e650901445ae6", "recursiveRepositoryBytes": 5514064765, "repositoryOnDiskBytes": 5514064765}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.393599+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824158", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935163+00:00", "modelId": "cyankiwi/LFM2-8B-A1B-AWQ-8bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9682515680, "estimatedRequiredGiB": 10.827, "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": 9688084066, "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"], "publishedSizeBytes": 9688084066, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:0662089ef0756354", "recursiveRepositoryBytes": 9688084066, "repositoryOnDiskBytes": 9688084066}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.406836+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824165", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935072+00:00", "modelId": "cyankiwi/Nemotron-Cascade-2-30B-A3B-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20746036464, "estimatedRequiredGiB": 23.21, "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": 20767786487, "modelscopeLicense": "other", "modelscopeParams": 6674513776, "modelscopeTags": ["license:other", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:nemotron-cascade-2", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 20767786487, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:4e040710ef43272e", "recursiveRepositoryBytes": 20767786487, "repositoryOnDiskBytes": 20767786487}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.380443+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824157", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.934983+00:00", "modelId": "GMUnitX/DeepSeek-R1-Distill-Qwen-1.5B-MPVDHS", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7108390440, "estimatedRequiredGiB": 7.957, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 7119857588, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:Apache License 2.0", "model_type:Qwen2", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 7119857588, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7119857588, "repositoryOnDiskBytes": 7119857588}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.390118+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824167", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935317+00:00", "modelId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-NVFP4", "modelProfile": {"architectures": ["DoryForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3202498032, "estimatedRequiredGiB": 3.6, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "dory", "modelscopeFileSize": 3221469377, "modelscopeLicense": "other", "modelscopeParams": 2323722240, "modelscopeTags": ["license:other", "model_type:dory", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-labs", "custom_tag:dory"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 3221469377, "quantizationMethod": "modelopt", "quantizationSignature": "modelopt:7f111f5ecf2660ff", "recursiveRepositoryBytes": 3221469377, "repositoryOnDiskBytes": 3221469377}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.432938+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5824162", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935136+00:00", "modelId": "cyankiwi/Ornith-1.0-9B-AWQ-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11910385576, "estimatedRequiredGiB": 13.343, "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": 11938806923, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 11938806923, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:c2062c64dee96c04", "recursiveRepositoryBytes": 11938806923, "repositoryOnDiskBytes": 11938806923}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.479452+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5824164", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935194+00:00", "modelId": "cyankiwi/Nemotron-Cascade-8B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921096, "estimatedRequiredGiB": 15.786, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 14125281593, "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"], "publishedSizeBytes": 14125281593, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:bd5110bb37ff4e58", "recursiveRepositoryBytes": 14125281593, "repositoryOnDiskBytes": 14125281593}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.481928+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5824163", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935312+00:00", "modelId": "cyankiwi/Ornith-1.0-35B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24430419208, "estimatedRequiredGiB": 27.35, "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": 24472753002, "modelscopeLicense": "mit", "modelscopeParams": 35107181936, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 24472753002, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:cc806b483ebd2e69", "recursiveRepositoryBytes": 24472753002, "repositoryOnDiskBytes": 24472753002}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.147215+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824226", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935115+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-Intent-FP8", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33165728400, "estimatedRequiredGiB": 37.07, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 33169542243, "modelscopeLicense": "apache-2.0", "modelscopeParams": 31215031088, "modelscopeTags": ["license:apache-2.0", "model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:intent-recognition", "custom_tag:slot-filling", "custom_tag:information-extraction", "custom_tag:schema-guided", "custom_tag:named-entity-recognition", "custom_tag:relation-extraction", "custom_tag:event-extraction"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 33169542243, "quantizationMethod": "fp8", "quantizationSignature": "fp8:0da8624bcb5e84df", "recursiveRepositoryBytes": 33169542243, "repositoryOnDiskBytes": 33169542243}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.137559+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824223", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935156+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-Intent", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 62431083040, "estimatedRequiredGiB": 69.776, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 62434092643, "modelscopeLicense": "apache-2.0", "modelscopeParams": 31215031088, "modelscopeTags": ["license:apache-2.0", "model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:intent-recognition", "custom_tag:slot-filling", "custom_tag:information-extraction", "custom_tag:schema-guided", "custom_tag:named-entity-recognition", "custom_tag:relation-extraction", "custom_tag:event-extraction"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 62434092643, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 62434092643, "repositoryOnDiskBytes": 62434092643}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.139261+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824235", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935236+00:00", "modelId": "nanbeige/Nanbeige4.3-33B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 66238009168, "estimatedRequiredGiB": 74.051, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 66260067498, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 66260067498, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 66260067498, "repositoryOnDiskBytes": 66260067498}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.132903+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824233", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935300+00:00", "modelId": "cpatonn-mirror/Tongyi-DeepResearch-30B-A3B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064318294, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 33064318294, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b74ddfdc145e58ff", "recursiveRepositoryBytes": 33064318294, "repositoryOnDiskBytes": 33064318294}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.135642+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824236", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935029+00:00", "modelId": "cyankiwi/GLM-4.5-Air-AWQ-4bit", "modelProfile": {"architectures": ["Glm4MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 63400571960, "estimatedRequiredGiB": 70.884, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "glm4_moe", "modelscopeFileSize": 63425670208, "modelscopeLicense": "mit", "modelscopeParams": 106852251264, "modelscopeTags": ["license:mit", "model_type:glm4_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 63425670208, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e5192b47c94517b2", "recursiveRepositoryBytes": 63425670208, "repositoryOnDiskBytes": 63425670208}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.257369+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824227", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935037+00:00", "modelId": "cpatonn-mirror/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ", "modelProfile": {"architectures": ["DeciLMForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29020319488, "estimatedRequiredGiB": 32.453, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_nas", "modelscopeFileSize": 29038368655, "modelscopeLicense": "other", "modelscopeParams": 49867145216, "modelscopeTags": ["license:other", "model_type:nemotron_nas", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:llama-3", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 29038368655, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 29038368655, "repositoryOnDiskBytes": 29038368655}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.145395+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824224", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935121+00:00", "modelId": "primitive-ai/Nanbeige4.3-33B-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35526734272, "estimatedRequiredGiB": 39.728, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 35548056552, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:nanbeige", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 35548056552, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:423cd90dc537dded", "recursiveRepositoryBytes": 35548056552, "repositoryOnDiskBytes": 35548056552}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.149342+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824221", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935242+00:00", "modelId": "cpatonn-mirror/Kimi-Dev-72B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 79588295928, "estimatedRequiredGiB": 88.967, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 79606715854, "modelscopeLicense": "mit", "modelscopeParams": 72706203648, "modelscopeTags": ["license:mit", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code", "custom_tag:swebench", "custom_tag:software", "custom_tag:issue-resolving"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 79606715854, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:08953c0a152f288b", "recursiveRepositoryBytes": 79606715854, "repositoryOnDiskBytes": 79606715854}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.152800+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824225", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935249+00:00", "modelId": "cpatonn-mirror/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit", "modelProfile": {"architectures": ["DeciLMForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29020319488, "estimatedRequiredGiB": 32.453, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_nas", "modelscopeFileSize": 29038368655, "modelscopeLicense": "other", "modelscopeParams": 49867145216, "modelscopeTags": ["license:other", "model_type:nemotron_nas", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:llama-3", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 29038368655, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 29038368655, "repositoryOnDiskBytes": 29038368655}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.140846+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824222", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935149+00:00", "modelId": "cpatonn-mirror/granite-4.0-h-small-AWQ-8bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 39756453136, "estimatedRequiredGiB": 44.442, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granitemoehybrid", "modelscopeFileSize": 39766281934, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32618379776, "modelscopeTags": ["license:apache-2.0", "model_type:granitemoehybrid", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:language", "custom_tag:granite-4.0"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 39766281934, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e379a948ff56dd79", "recursiveRepositoryBytes": 39766281934, "repositoryOnDiskBytes": 39766281934}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.373627+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824238", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935212+00:00", "modelId": "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064355224, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 33064355224, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:a1e46deb2f53e69c", "recursiveRepositoryBytes": 33064355224, "repositoryOnDiskBytes": 33064355224}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.363858+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824229", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935108+00:00", "modelId": "LiquidAI/LFM2.5-24B-A2B", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 47944143456, "estimatedRequiredGiB": 53.605, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 47964602717, "modelscopeLicense": "other", "modelscopeParams": 23971587712, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:moe"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 47964602717, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 47964602717, "repositoryOnDiskBytes": 47964602717}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.368106+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824228", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": "2026-10-27T18:21:18.935306+00:00", "modelId": "cyankiwi/MiroThinker-v1.0-30B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064339297, "modelscopeLicense": "mit", "modelscopeParams": 30532122624, "modelscopeTags": ["license:mit", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:open-source", "custom_tag:miromind", "custom_tag:deep-research"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 33064339297, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:a1e46deb2f53e69c", "recursiveRepositoryBytes": 33064339297, "repositoryOnDiskBytes": 33064339297}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.362612+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824230", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "pfnet/plamo-13b-instruct", "modelProfile": {"architectures": ["PlamoForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26199130400, "estimatedRequiredGiB": 29.281, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo", "modelscopeFileSize": 26200349563, "modelscopeLicense": "apache-2.0", "modelscopeParams": 13099545600, "modelscopeTags": ["license:apache-2.0", "model_type:plamo", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 26200349563, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 26200349563, "repositoryOnDiskBytes": 26200349563}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T11:09:55.619795+00:00", "targetGpu": "MetaX_c-500", "taskId": "5824879", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "cpatonn-mirror/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14278393080, "estimatedRequiredGiB": 15.973, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 14292650823, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 14292650823, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:cefd4b27e758b1de", "recursiveRepositoryBytes": 14292650823, "repositoryOnDiskBytes": 14292650823}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T12:21:38.039985+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5825974", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastSyncTime": null, "modelId": "pfnet/plamo-13b-instruct-nc", "modelProfile": {"architectures": ["PlamoForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26199130400, "estimatedRequiredGiB": 29.281, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo", "modelscopeFileSize": 26200357986, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 13099545600, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:plamo", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 26200357986, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 26200357986, "repositoryOnDiskBytes": 26200357986}, "outcome": "pending", "status": "pending", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T13:23:26.475444+00:00", "targetGpu": "MetaX_c-500", "taskId": "5826874", "taskType": "text-generation", "verifyResult": null}