state: generation 31841 (cycle)

This commit is contained in:
CoolBoy committed 2026-11-13 21:17:21 +00:00
1 parent f48aa3f50f
commit 94fd300c40
7 files changed
+1061 -1061

No files matched your search

+6 -6
View File
@@ -585,7 +585,7 @@
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:01:55.430162+00:00", "lastSyncTime": "2026-11-13T14:01:58.441135+00:00", "modelId": "cyankiwi/MiroThinker-v1.0-30B-AWQ-8bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5701875", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T18:28:22.924369+00:00", "lastSyncTime": "2026-11-13T18:28:25.882898+00:00", "modelId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5697435", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:27:46.341486+00:00", "lastSyncTime": "2026-11-13T14:27:49.855357+00:00", "modelId": "cyankiwi/OmniCoder-9B-AWQ-BF16-INT4", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5697423", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T13:05:39.111734+00:00", "lastSyncTime": "2026-11-13T13:05:42.174423+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5688915", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T21:17:01.552484+00:00", "lastSyncTime": "2026-11-13T21:17:04.657375+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5688915", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T19:33:02.140259+00:00", "lastSyncTime": "2026-11-13T19:33:05.529108+00:00", "modelId": "OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark-gguf", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "5687537", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T16:06:35.908892+00:00", "lastSyncTime": "2026-11-13T16:06:38.852575+00:00", "modelId": "mrm8488/mistral-7b-ft-h4-no_robots_instructions", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5645314", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T18:39:46.328504+00:00", "lastSyncTime": "2026-11-13T18:39:50.072517+00:00", "modelId": "IFM/Jais-3-32B-FP8", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5633102", "taskType": "text-generation", "verifyResult": null}
@@ -795,7 +795,7 @@
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T13:36:09.184155+00:00", "lastSyncTime": "2026-11-13T13:36:11.979438+00:00", "modelId": "cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5697881", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T15:28:12.719174+00:00", "lastSyncTime": "2026-11-13T15:28:15.451109+00:00", "modelId": "iluvatar-corex/Qwen3-8B-W8A8", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5692570", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T16:44:47.682303+00:00", "lastSyncTime": "2026-11-13T16:44:50.457672+00:00", "modelId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-NVFP4", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5691022", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T13:01:38.740395+00:00", "lastSyncTime": "2026-11-13T13:01:42.275527+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5688937", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T21:17:01.552484+00:00", "lastSyncTime": "2026-11-13T21:17:04.657320+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5688937", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T20:14:05.144346+00:00", "lastSyncTime": "2026-11-13T20:14:07.728090+00:00", "modelId": "StartLuxAI/gdn-1.3b-isp-hybrid-3to1-50b", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5676921", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T19:36:48.327125+00:00", "lastSyncTime": "2026-11-13T19:36:51.152424+00:00", "modelId": "OsaurusAI/Diplodocus-preview-JANG_6M", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5645005", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T17:55:07.425384+00:00", "lastSyncTime": "2026-11-13T17:55:09.887742+00:00", "modelId": "BananaMind/Picolo-BananaMind", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5568494", "taskType": "text-generation", "verifyResult": null}
@@ -841,7 +841,7 @@
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T16:14:53.329076+00:00", "lastSyncTime": "2026-11-13T16:14:55.986692+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", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T17:45:43.916647+00:00", "lastSyncTime": "2026-11-13T17:45:46.973019+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", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:19:18.771613+00:00", "lastSyncTime": "2026-11-13T14:19:22.159969+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", "verifyResult": null}
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T13:01:38.740395+00:00", "lastSyncTime": "2026-11-13T13:01:42.275539+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", "lastOutcomeReconcileAt": "2026-11-13T21:17:01.552484+00:00", "lastSyncTime": "2026-11-13T21:17:04.657359+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", "lastOutcomeReconcileAt": "2026-11-13T14:40:34.336867+00:00", "lastSyncTime": "2026-11-13T14:40:37.780254+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", "lastOutcomeReconcileAt": "2026-11-13T16:48:49.737870+00:00", "lastSyncTime": "2026-11-13T16:48:52.429040+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", "lastOutcomeReconcileAt": "2026-11-13T13:05:39.111734+00:00", "lastSyncTime": "2026-11-13T13:05:42.174452+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}
@@ -849,7 +849,7 @@
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T13:09:32.168012+00:00", "lastSyncTime": "2026-11-13T13:09:35.472785+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", "lastOutcomeReconcileAt": "2026-11-13T14:06:32.706461+00:00", "lastSyncTime": "2026-11-13T14:06:35.769474+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", "lastOutcomeReconcileAt": "2026-11-13T20:22:45.636663+00:00", "lastSyncTime": "2026-11-13T20:22:48.274558+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", "lastOutcomeReconcileAt": "2026-11-13T13:01:38.740395+00:00", "lastSyncTime": "2026-11-13T13:01:42.275533+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", "lastOutcomeReconcileAt": "2026-11-13T21:17:01.552484+00:00", "lastSyncTime": "2026-11-13T21:17:04.657352+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", "lastOutcomeReconcileAt": "2026-11-13T21:04:26.533090+00:00", "lastSyncTime": "2026-11-13T21:04:29.467255+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", "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": "2026-11-13T21:04:26.533090+00:00", "lastSyncTime": "2026-11-13T21:04:29.467269+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}
@@ -915,7 +915,7 @@
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T20:36:23.407716+00:00", "lastSyncTime": "2026-11-13T20:36:26.068077+00:00", "modelId": "alkaid55555/rewrite2-4b-gguf", "modelProfile": {"architectures": [], "configFingerprint": "599b696754d742f615413500a637d0fa5409f7e104beb786ffc6c086b45b60ad", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4482402752, "estimatedRequiredGiB": 8.037, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 7191216091, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4205751296, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:rewrite2", "custom_tag:novel-rewrite", "custom_tag:qwen3.5", "custom_tag:4b", "custom_tag:gguf", "custom_tag:q8_0", "custom_tag:q4_k_m", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 7191216091, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7191216091, "repositoryOnDiskBytes": 7191216091}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-27T17:16:14.228264+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5830169", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T18:22:39.566339+00:00", "lastSyncTime": "2026-11-13T18:22:42.569235+00:00", "modelId": "GMUnitX/DeepSeek-R1-Distill-Qwen-1.5B-MPVDHS", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7108390440, "estimatedRequiredGiB": 7.957, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-27T18:35:56.327984+00:00", "targetGpu": "MetaX_c-500", "taskId": "5831259", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T13:05:39.111734+00:00", "lastSyncTime": "2026-11-13T13:05:42.174459+00:00", "modelId": "cpatonn-mirror/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-27T19:13:57.532146+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5831744", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T13:01:38.740395+00:00", "lastSyncTime": "2026-11-13T13:01:42.275521+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3459873078, "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": 3459873078, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 3459873078, "repositoryOnDiskBytes": 3459873078}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-27T19:13:57.528475+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5831743", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T21:17:01.552484+00:00", "lastSyncTime": "2026-11-13T21:17:04.657342+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3459873078, "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": 3459873078, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 3459873078, "repositoryOnDiskBytes": 3459873078}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-27T19:13:57.528475+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5831743", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T21:13:09.673686+00:00", "lastSyncTime": "2026-11-13T21:13:12.083464+00:00", "modelId": "cpatonn-mirror/Qwen3-30B-A3B-Thinking-2507-AWQ", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115830036, "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": 18115830036, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2f008ff356aba06a", "recursiveRepositoryBytes": 18115830036, "repositoryOnDiskBytes": 18115830036}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-27T19:13:57.533600+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5831742", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T19:44:55.672755+00:00", "lastSyncTime": "2026-11-13T19:44:58.283890+00:00", "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 6185547167, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 6185547167, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 6185547167, "repositoryOnDiskBytes": 6185547167}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-27T19:13:57.876745+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5831745", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T14:40:34.336867+00:00", "lastSyncTime": "2026-11-13T14:40:37.780235+00:00", "modelId": "cyankiwi/Qwen3-4B-Instruct-2507-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5416721872, "estimatedRequiredGiB": 6.072, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 5432699471, "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": 5432699471, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:9902073541f0c0c8", "recursiveRepositoryBytes": 5432699471, "repositoryOnDiskBytes": 5432699471}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-27T19:14:00.318874+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5831746", "taskType": "text-generation", "verifyResult": null}
@@ -938,7 +938,7 @@
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T13:09:32.168012+00:00", "lastSyncTime": "2026-11-13T13:09:35.472791+00:00", "modelId": "cpatonn-mirror/Tongyi-DeepResearch-30B-A3B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T00:47:44.905039+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5835985", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T13:57:28.135778+00:00", "lastSyncTime": "2026-11-13T13:57:31.851603+00:00", "modelId": "cyankiwi/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit", "modelProfile": {"architectures": ["DeciLMForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "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": 29038369021, "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": 29038369021, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 29038369021, "repositoryOnDiskBytes": 29038369021}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T00:47:44.924156+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5835986", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T15:44:47.897023+00:00", "lastSyncTime": "2026-11-13T15:44:51.554056+00:00", "modelId": "lightx2v/Qwen-Image-2.1-PE-I2I-GGUF-Q8_0", "modelProfile": {"architectures": [], "configFingerprint": "cab7fc6aa7d40ff1a1fb792b012eea9b42d2292eaf42910cf6cd04cdd52cd5f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9527501536, "estimatedRequiredGiB": 11.678, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10449230677, "modelscopeLicense": "other", "modelscopeParams": 8953803264, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama-cpp", "custom_tag:prompt-rewriting", "custom_tag:image-editing", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 10449230677, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 10449230677, "repositoryOnDiskBytes": 10449230677}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T04:31:21.831783+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5839196", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T13:05:39.111734+00:00", "lastSyncTime": "2026-11-13T13:05:42.174431+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T04:31:21.828449+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5839194", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T21:17:01.552484+00:00", "lastSyncTime": "2026-11-13T21:17:04.657367+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3443975440, "estimatedRequiredGiB": 3.867, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T04:31:21.828449+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5839194", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T20:36:23.407716+00:00", "lastSyncTime": "2026-11-13T20:36:26.068131+00:00", "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20321390048, "estimatedRequiredGiB": 22.734, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20341996128, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 20341996128, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:ee367b4119f8452e", "recursiveRepositoryBytes": 20341996128, "repositoryOnDiskBytes": 20341996128}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T04:31:22.094069+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5839195", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T19:20:39.262379+00:00", "lastSyncTime": "2026-11-13T19:20:41.881196+00:00", "modelId": "LiquidAI/LFM3-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "0982335f399aadf555d26a68c4a32fc931fff637da59bdb704789d18bd37378c", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1049615680, "estimatedRequiredGiB": 15.216, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 13615052335, "modelscopeLicense": "other", "modelscopeParams": 1728801600, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm3", "custom_tag:gguf", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 13615052335, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 13615052335, "repositoryOnDiskBytes": 13615052335}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T04:35:18.932433+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5839235", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T19:20:39.262379+00:00", "lastSyncTime": "2026-11-13T19:20:41.881204+00:00", "modelId": "LiquidAI/LFM3-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "6f99d13478c2693d5d7dc9c03ad21fe3c2b022197ddae65a19f5009028855cb7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1049615680, "estimatedRequiredGiB": 15.216, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 13615052335, "modelscopeLicense": "other", "modelscopeParams": 1728801600, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm3", "custom_tag:gguf", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 13615052335, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 13615052335, "repositoryOnDiskBytes": 13615052335}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T04:38:39.897162+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5839270", "taskType": "text-generation", "verifyResult": null}