state: generation 31826 (cycle)

This commit is contained in:
CoolBoy committed 2026-11-13 20:57:09 +00:00
1 parent 73552dc569
commit b4d3c64d40
7 files changed
+1301 -1301

No files matched your search

+7 -7
View File
@@ -854,10 +854,10 @@
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T20:22:45.636663+00:00", "lastSyncTime": "2026-11-13T20:22:48.274536+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", "lastOutcomeReconcileAt": "2026-11-13T12:48:05.033718+00:00", "lastSyncTime": "2026-11-13T12:48:08.476462+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", "lastOutcomeReconcileAt": "2026-11-13T12:48:05.033718+00:00", "lastSyncTime": "2026-11-13T12:48:08.476424+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", "lastOutcomeReconcileAt": "2026-11-13T12:40:13.222611+00:00", "lastSyncTime": "2026-11-13T12:40:16.880888+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", "lastOutcomeReconcileAt": "2026-11-13T12:40:13.222611+00:00", "lastSyncTime": "2026-11-13T12:40:16.880911+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", "lastOutcomeReconcileAt": "2026-11-13T20:56:17.901749+00:00", "lastSyncTime": "2026-11-13T20:56:20.553866+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", "lastOutcomeReconcileAt": "2026-11-13T20:56:17.901749+00:00", "lastSyncTime": "2026-11-13T20:56:20.553907+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", "lastOutcomeReconcileAt": "2026-11-13T12:48:05.033718+00:00", "lastSyncTime": "2026-11-13T12:48:08.476431+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", "lastOutcomeReconcileAt": "2026-11-13T12:44:07.939061+00:00", "lastSyncTime": "2026-11-13T12:44:11.375982+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", "lastOutcomeReconcileAt": "2026-11-13T20:56:17.901749+00:00", "lastSyncTime": "2026-11-13T20:56:20.553939+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", "lastOutcomeReconcileAt": "2026-11-13T12:44:07.939061+00:00", "lastSyncTime": "2026-11-13T12:44:11.375988+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", "lastOutcomeReconcileAt": "2026-11-13T13:40:02.145873+00:00", "lastSyncTime": "2026-11-13T13:40:03.435761+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", "lastOutcomeReconcileAt": "2026-11-13T12:52:36.033614+00:00", "lastSyncTime": "2026-11-13T12:52:39.268193+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}
@@ -890,7 +890,7 @@
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T19:11:45.404087+00:00", "lastSyncTime": "2026-11-13T19:11:48.747010+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", "lastOutcomeReconcileAt": "2026-11-13T14:01:55.430162+00:00", "lastSyncTime": "2026-11-13T14:01:58.441129+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", "lastOutcomeReconcileAt": "2026-11-13T16:48:49.737870+00:00", "lastSyncTime": "2026-11-13T16:48:52.429032+00:00", "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": "waiting", "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", "lastOutcomeReconcileAt": "2026-11-13T12:40:13.222611+00:00", "lastSyncTime": "2026-11-13T12:40:16.880897+00:00", "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": "waiting", "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-mlu", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T20:56:17.901749+00:00", "lastSyncTime": "2026-11-13T20:56:20.553896+00:00", "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": "waiting", "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", "lastOutcomeReconcileAt": "2026-11-13T16:53:44.024038+00:00", "lastSyncTime": "2026-11-13T16:53:46.849975+00:00", "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": "waiting", "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}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T12:48:05.033718+00:00", "lastSyncTime": "2026-11-13T12:48:08.476456+00:00", "modelId": "cpatonn-mirror/KAT-V1-40B-AWQ", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23382751128, "estimatedRequiredGiB": 26.15, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-10-27T13:23:26.463076+00:00", "targetGpu": "MetaX_c-500", "taskId": "5826873", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T20:22:45.636663+00:00", "lastSyncTime": "2026-11-13T20:22:48.274521+00:00", "modelId": "XHToken/Spark-X2.6-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.208, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "published_repository_upper_bound", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8239287201, "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": 8239287201, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 8239287196, "repositoryOnDiskBytes": 8239287201}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T13:23:26.470863+00:00", "targetGpu": "MetaX_c-500", "taskId": "5826870", "taskType": "text-generation", "verifyResult": null}
@@ -899,10 +899,10 @@
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T12:48:05.033718+00:00", "lastSyncTime": "2026-11-13T12:48:08.476416+00:00", "modelId": "cpatonn-mirror/Jan-v1-4B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5416721872, "estimatedRequiredGiB": 6.072, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-10-27T13:23:26.459274+00:00", "targetGpu": "MetaX_c-500", "taskId": "5826871", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T12:44:07.939061+00:00", "lastSyncTime": "2026-11-13T12:44:11.376002+00:00", "modelId": "cpatonn-mirror/Hermes-4-70B-AWQ-4bit", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 42709261480, "estimatedRequiredGiB": 47.751, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 42726705025, "modelscopeLicense": "llama3", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:Llama-3.1", "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": 42726705025, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:35574ab300879f51", "recursiveRepositoryBytes": 42726705025, "repositoryOnDiskBytes": 42726705025}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T13:23:26.450854+00:00", "targetGpu": "MetaX_c-500", "taskId": "5826868", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T13:09:32.168012+00:00", "lastSyncTime": "2026-11-13T13:09:35.472764+00:00", "modelId": "cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-8bit", "modelProfile": {"architectures": ["SeedOssForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 39901408344, "estimatedRequiredGiB": 44.607, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "seed_oss", "modelscopeFileSize": 39913686628, "modelscopeLicense": "apache-2.0", "modelscopeParams": 36151104512, "modelscopeTags": ["license:apache-2.0", "model_type:seed_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 39913686628, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:709f150bd7f9420b", "recursiveRepositoryBytes": 39913686628, "repositoryOnDiskBytes": 39913686628}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T13:23:26.476691+00:00", "targetGpu": "MetaX_c-500", "taskId": "5826869", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T12:40:13.222611+00:00", "lastSyncTime": "2026-11-13T12:40:16.880904+00:00", "modelId": "cpatonn-mirror/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24682886272, "estimatedRequiredGiB": 27.602, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-10-27T13:23:26.532482+00:00", "targetGpu": "MetaX_c-500", "taskId": "5826878", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T20:56:17.901749+00:00", "lastSyncTime": "2026-11-13T20:56:20.553918+00:00", "modelId": "cpatonn-mirror/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24682886272, "estimatedRequiredGiB": 27.602, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-10-27T13:23:26.532482+00:00", "targetGpu": "MetaX_c-500", "taskId": "5826878", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T13:14:45.045164+00:00", "lastSyncTime": "2026-11-13T13:14:48.380531+00:00", "modelId": "cpatonn-mirror/granite-4.0-h-small-AWQ-8bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 39756453136, "estimatedRequiredGiB": 44.442, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-10-27T13:23:26.469121+00:00", "targetGpu": "MetaX_c-500", "taskId": "5826872", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T12:48:05.033718+00:00", "lastSyncTime": "2026-11-13T12:48:08.476438+00:00", "modelId": "cpatonn-mirror/KAT-Dev-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20666355744, "estimatedRequiredGiB": 23.114, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-10-27T13:23:26.533652+00:00", "targetGpu": "MetaX_c-500", "taskId": "5826875", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T12:44:07.939061+00:00", "lastSyncTime": "2026-11-13T12:44:11.375974+00:00", "modelId": "cpatonn-mirror/Hermes-4-14B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10544400664, "estimatedRequiredGiB": 11.802, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-10-27T13:23:26.578428+00:00", "targetGpu": "MetaX_c-500", "taskId": "5826876", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T20:56:17.901749+00:00", "lastSyncTime": "2026-11-13T20:56:20.553949+00:00", "modelId": "cpatonn-mirror/Hermes-4-14B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10544400664, "estimatedRequiredGiB": 11.802, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-10-27T13:23:26.578428+00:00", "targetGpu": "MetaX_c-500", "taskId": "5826876", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T14:53:24.255645+00:00", "lastSyncTime": "2026-11-13T14:53:27.751658+00:00", "modelId": "cyankiwi/granite-4.0-h-tiny-AWQ-4bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "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": "2026-10-27T13:23:35.140603+00:00", "targetGpu": "Vastai_va16", "taskId": "5826891", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T12:52:36.033614+00:00", "lastSyncTime": "2026-11-13T12:52:39.268221+00:00", "modelId": "cpatonn-mirror/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit", "modelProfile": {"architectures": ["DeciLMForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29020319488, "estimatedRequiredGiB": 32.453, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-10-27T14:06:48.823038+00:00", "targetGpu": "MetaX_c-500", "taskId": "5827510", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T15:28:12.719174+00:00", "lastSyncTime": "2026-11-13T15:28:15.451087+00:00", "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-10-27T14:36:37.144718+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5827949", "taskType": "text-generation", "verifyResult": null}
@@ -1019,7 +1019,7 @@
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T13:18:37.392679+00:00", "lastSyncTime": "2026-11-13T13:18:40.673763+00:00", "modelId": "cyankiwi/Agents-A1-AWQ-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926870808, "estimatedRequiredGiB": 26.791, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23972444278, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:vlm", "custom_tag:vision", "custom_tag:agentic"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23972444278, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:9bae5222b55fce6e", "recursiveRepositoryBytes": 23972444278, "repositoryOnDiskBytes": 23972444278}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-02T02:03:40.575244+00:00", "targetGpu": "Vastai_va16", "taskId": "5959370", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T20:14:05.144346+00:00", "lastSyncTime": "2026-11-13T20:14:07.728139+00:00", "modelId": "Tencent-Hunyuan/Hy-Memory-30B-A3B", "modelProfile": {"architectures": ["HYV3ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 60131744504, "estimatedRequiredGiB": 67.216, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hy_v3", "modelscopeFileSize": 60143805361, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30064725888, "modelscopeTags": ["license:apache-2.0", "model_type:hy_v3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 60143805361, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 60143805361, "repositoryOnDiskBytes": 60143805361}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-02T02:03:40.653244+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5959371", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T13:05:39.111734+00:00", "lastSyncTime": "2026-11-13T13:05:42.174472+00:00", "modelId": "cpatonn-mirror/Qwen3-Next-80B-A3B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3NextForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 49231450912, "estimatedRequiredGiB": 55.063, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_next", "modelscopeFileSize": 49269386372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 81324862720, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_next", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 49269386372, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:4a304b75ca89096b", "recursiveRepositoryBytes": 49269386372, "repositoryOnDiskBytes": 49269386372}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-02T02:03:44.970897+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5959372", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T12:40:13.222611+00:00", "lastSyncTime": "2026-11-13T12:40:16.880918+00:00", "modelId": "cpatonn-mirror/GLM-4.5-Air-AWQ", "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": 63425670209, "modelscopeLicense": "mit", "modelscopeParams": 106852251264, "modelscopeTags": ["license:mit", "model_type:glm4_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 63425670209, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e5192b47c94517b2", "recursiveRepositoryBytes": 63425670209, "repositoryOnDiskBytes": 63425670209}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-02T02:03:45.314200+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5959373", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T20:56:17.901749+00:00", "lastSyncTime": "2026-11-13T20:56:20.553929+00:00", "modelId": "cpatonn-mirror/GLM-4.5-Air-AWQ", "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": 63425670209, "modelscopeLicense": "mit", "modelscopeParams": 106852251264, "modelscopeTags": ["license:mit", "model_type:glm4_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 63425670209, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e5192b47c94517b2", "recursiveRepositoryBytes": 63425670209, "repositoryOnDiskBytes": 63425670209}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-02T02:03:45.314200+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5959373", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T12:44:07.939061+00:00", "lastSyncTime": "2026-11-13T12:44:11.376016+00:00", "modelId": "cpatonn-mirror/Hermes-4-70B-AWQ-8bit", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 76934782208, "estimatedRequiredGiB": 86.001, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 76952225655, "modelscopeLicense": "llama3", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:Llama-3.1", "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": 76952225655, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:709f150bd7f9420b", "recursiveRepositoryBytes": 76952225655, "repositoryOnDiskBytes": 76952225655}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-02T02:03:51.118150+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5959375", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T20:48:14.333919+00:00", "lastSyncTime": "2026-11-13T20:48:16.583503+00:00", "modelId": "bytkim/Qwen3.8-27B-pi-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 34715684264, "estimatedRequiredGiB": 38.825, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 34739621865, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:speculative-decoding", "custom_tag:vision", "custom_tag:image", "custom_tag:multimodal", "custom_tag:image-text-to-text", "custom_tag:text-generation-inference", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:qwen38", "custom_tag:27b", "custom_tag:pi", "custom_tag:coding", "custom_tag:coder", "custom_tag:code-generation", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:reasoning", "custom_tag:conversational", "custom_tag:sft", "custom_tag:grpo", "custom_tag:reinforcement-learning", "custom_tag:fp8", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 34739621865, "quantizationMethod": "fp8", "quantizationSignature": "fp8:a8794dc9a10580bc", "recursiveRepositoryBytes": 34739621865, "repositoryOnDiskBytes": 34739621865}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-02T02:03:56.414163+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5959376", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T17:35:58.409982+00:00", "lastSyncTime": "2026-11-13T17:36:00.782392+00:00", "modelId": "AgentScope/QwenPaw-Flash-4B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10350019328, "estimatedRequiredGiB": 11.589, "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": 10370026202, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5174964736, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwenpaw", "custom_tag:tool-use"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 10370026202, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 10370026202, "repositoryOnDiskBytes": 10370026202}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-02T23:50:32.461747+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5981019", "taskType": "text-generation", "verifyResult": null}