state: generation 31325 (cycle)
This commit is contained in:
1 parent
ccb0a15f8e
commit
4b60247c5d
7 files changed
+1074
-1074
No files matched your search
+12
-12
@@ -78,7 +78,7 @@
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T07:52:46.055119+00:00", "lastSyncTime": "2026-11-13T07:52:49.355884+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-70B-quantized.w8a16", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "4332419", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T04:07:50.688784+00:00", "lastSyncTime": "2026-11-13T04:07:53.559051+00:00", "modelId": "cgisky/Ai00-X", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "4332410", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T07:44:39.016725+00:00", "lastSyncTime": "2026-11-13T07:44:42.653618+00:00", "modelId": "mlx-community/lille-130m-instruct-6bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "hygon_k100-ai", "taskId": "4080044", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T00:10:13.458725+00:00", "lastSyncTime": "2026-11-13T00:10:16.452401+00:00", "modelId": "primitive-ai/Nanbeige4.3-33B-FP8", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "5795821", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T08:43:02.269845+00:00", "lastSyncTime": "2026-11-13T08:43:05.757470+00:00", "modelId": "primitive-ai/Nanbeige4.3-33B-FP8", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "5795821", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T02:06:03.283218+00:00", "lastSyncTime": "2026-11-13T02:06:06.729846+00:00", "modelId": "InternScience/Sage-A1.5", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "5791562", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T05:55:13.952188+00:00", "lastSyncTime": "2026-11-13T05:55:16.987752+00:00", "modelId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "5791492", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T06:22:32.551047+00:00", "lastSyncTime": "2026-11-13T06:22:36.578805+00:00", "modelId": "cyankiwi/Trinity-Mini-AWQ-8bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "5789210", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -565,7 +565,7 @@
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T07:52:46.055119+00:00", "lastSyncTime": "2026-11-13T07:52:49.355869+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-70B-FP8", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "4667927", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T02:24:15.416080+00:00", "lastSyncTime": "2026-11-13T02:24:18.881409+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "hygon_k100-ai", "taskId": "4648146", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T03:49:44.384613+00:00", "lastSyncTime": "2026-11-13T03:49:47.567912+00:00", "modelId": "b77968543/Spark-X2.5-4B-Q8_0", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "4580780", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T00:10:13.458725+00:00", "lastSyncTime": "2026-11-13T00:10:16.452430+00:00", "modelId": "prithivMLmods/CogEvol-4B-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "4558951", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T08:43:02.269845+00:00", "lastSyncTime": "2026-11-13T08:43:05.757509+00:00", "modelId": "prithivMLmods/CogEvol-4B-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "4558951", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T06:36:42.213879+00:00", "lastSyncTime": "2026-11-13T06:36:45.682099+00:00", "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Mthreads_s4000", "taskId": "4492914", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T01:34:44.762155+00:00", "lastSyncTime": "2026-11-13T01:34:47.778001+00:00", "modelId": "GestaltLabs/Ornstein-3.5-9B-V2-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "hygon_k100-ai", "taskId": "4457975", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T06:36:42.213879+00:00", "lastSyncTime": "2026-11-13T06:36:45.682060+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "hygon_k100-ai", "taskId": "4376895", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -636,7 +636,7 @@
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T02:15:24.481719+00:00", "lastSyncTime": "2026-11-13T02:15:27.352311+00:00", "modelId": "LiquidAI/LFM2.5-2.6B-DSpark-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Mthreads_s4000", "taskId": "4592741", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T02:20:11.302769+00:00", "lastSyncTime": "2026-11-13T02:20:14.177358+00:00", "modelId": "LiquidAI/LFM2.5-230M-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "4581848", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T02:15:24.481719+00:00", "lastSyncTime": "2026-11-13T02:15:27.352317+00:00", "modelId": "LiquidAI/LFM2.5-2.6B-DSpark-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "4577673", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T00:10:13.458725+00:00", "lastSyncTime": "2026-11-13T00:10:16.452437+00:00", "modelId": "prithivMLmods/CogEvol-4B-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Mthreads_s4000", "taskId": "4559205", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T08:43:02.269845+00:00", "lastSyncTime": "2026-11-13T08:43:05.757516+00:00", "modelId": "prithivMLmods/CogEvol-4B-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Mthreads_s4000", "taskId": "4559205", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T06:49:31.631416+00:00", "lastSyncTime": "2026-11-13T06:49:34.554909+00:00", "modelId": "guaidao2/XuanmuSec-2.6B", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "4546529", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T07:58:01.825348+00:00", "lastSyncTime": "2026-11-13T07:58:04.852624+00:00", "modelId": "neuralmagic/Qwen2-72B-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "4332413", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T07:12:52.727811+00:00", "lastSyncTime": "2026-11-13T07:12:56.178641+00:00", "modelId": "incoai/Qwen3.8-27B-DFlash2-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "4332406", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -704,7 +704,7 @@
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T06:36:42.213879+00:00", "lastSyncTime": "2026-11-13T06:36:45.682073+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Iluvatar_bi-150", "taskId": "4641463", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T07:08:11.112894+00:00", "lastSyncTime": "2026-11-13T07:08:14.382844+00:00", "modelId": "inclusionAI/Ling-3.0-tiny-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "hygon_k100-ai", "taskId": "4609087", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T03:04:53.605379+00:00", "lastSyncTime": "2026-11-13T03:04:56.975020+00:00", "modelId": "RedHatAI/DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Mthreads_s4000", "taskId": "4590890", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T00:10:13.458725+00:00", "lastSyncTime": "2026-11-13T00:10:16.452444+00:00", "modelId": "prithivMLmods/CogEvol-4B-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "hygon_k100-ai", "taskId": "4558779", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T08:43:02.269845+00:00", "lastSyncTime": "2026-11-13T08:43:05.757522+00:00", "modelId": "prithivMLmods/CogEvol-4B-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "hygon_k100-ai", "taskId": "4558779", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T06:36:42.213879+00:00", "lastSyncTime": "2026-11-13T06:36:45.682112+00:00", "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "hygon_k100-ai", "taskId": "4492703", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T06:32:05.633898+00:00", "lastSyncTime": "2026-11-13T06:32:09.259455+00:00", "modelId": "empero-ai/Qwen3.8-2B-Distill-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "hygon_k100-ai", "taskId": "4376893", "taskType": "text-generation", "verifyResult": null}
|
||||
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T03:08:58.316168+00:00", "lastSyncTime": "2026-11-13T03:09:00.772426+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-70B-quantized.w8a16", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "4332434", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -872,7 +872,7 @@
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T07:03:34.535676+00:00", "lastSyncTime": "2026-11-13T07:03:38.171996+00:00", "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593025749, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 17593025749, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 17593025749, "repositoryOnDiskBytes": 17593025749}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.285428+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824153", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T05:51:11.002470+00:00", "lastSyncTime": "2026-11-13T05:51:14.547732+00:00", "modelId": "cyankiwi/Nemotron-Orchestrator-8B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921104, "estimatedRequiredGiB": 11.048, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 9885904129, "modelscopeLicense": null, "modelscopeParams": 8190735360, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 9885904129, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2b478ca1d5cf05e4", "recursiveRepositoryBytes": 9885904129, "repositoryOnDiskBytes": 9885904129}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.382051+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824159", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T05:14:34.200805+00:00", "lastSyncTime": "2026-11-13T05:14:37.673553+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8122473440, "estimatedRequiredGiB": 9.103, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 8145039537, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 8145039537, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:06e1b44940b82d27", "recursiveRepositoryBytes": 8145039537, "repositoryOnDiskBytes": 8145039537}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.350896+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824155", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T00:10:13.458725+00:00", "lastSyncTime": "2026-11-13T00:10:16.452423+00:00", "modelId": "primitive-ai/Nanbeige4.3-33B-NVFP4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22070410112, "estimatedRequiredGiB": 24.69, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 22091795362, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977388, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:nanbeige", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 22091795362, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:5179e7fa01f5b826", "recursiveRepositoryBytes": 22091795362, "repositoryOnDiskBytes": 22091795362}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.295226+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824166", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T08:43:02.269845+00:00", "lastSyncTime": "2026-11-13T08:43:05.757494+00:00", "modelId": "primitive-ai/Nanbeige4.3-33B-NVFP4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22070410112, "estimatedRequiredGiB": 24.69, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 22091795362, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977388, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:nanbeige", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 22091795362, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:5179e7fa01f5b826", "recursiveRepositoryBytes": 22091795362, "repositoryOnDiskBytes": 22091795362}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.295226+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824166", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T08:24:19.461103+00:00", "lastSyncTime": "2026-11-13T08:24:23.057516+00:00", "modelId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-MXFP8", "modelProfile": {"architectures": ["DoryForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4750755304, "estimatedRequiredGiB": 5.331, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "dory", "modelscopeFileSize": 4769740524, "modelscopeLicense": "other", "modelscopeParams": 3975229440, "modelscopeTags": ["license:other", "model_type:dory", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-labs", "custom_tag:dory"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 4769740524, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:402c90eb0b5de1c4", "recursiveRepositoryBytes": 4769740524, "repositoryOnDiskBytes": 4769740524}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.330346+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824154", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T05:42:02.370721+00:00", "lastSyncTime": "2026-11-13T05:42:05.386811+00:00", "modelId": "cyankiwi/NVIDIA-Nemotron-Nano-12B-v2-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8857194176, "estimatedRequiredGiB": 9.918, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 8874757118, "modelscopeLicense": "other", "modelscopeParams": 3057874704, "modelscopeTags": ["license:other", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 8874757118, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b63fa8ce792e9ecf", "recursiveRepositoryBytes": 8874757118, "repositoryOnDiskBytes": 8874757118}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.408272+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824160", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T06:26:31.766000+00:00", "lastSyncTime": "2026-11-13T06:26:35.278405+00:00", "modelId": "cyankiwi/granite-4.0-h-small-AWQ-4bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26166907992, "estimatedRequiredGiB": 29.255, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granitemoehybrid", "modelscopeFileSize": 26176736582, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32618379776, "modelscopeTags": ["license:apache-2.0", "model_type:granitemoehybrid", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:language", "custom_tag:granite-4.0"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 26176736582, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:2b7e650901445ae6", "recursiveRepositoryBytes": 26176736582, "repositoryOnDiskBytes": 26176736582}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:18:51.375810+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5824156", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -890,7 +890,7 @@
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T04:43:11.555537+00:00", "lastSyncTime": "2026-11-13T04:43:14.768509+00:00", "modelId": "cpatonn-mirror/Tongyi-DeepResearch-30B-A3B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064318294, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 33064318294, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:b74ddfdc145e58ff", "recursiveRepositoryBytes": 33064318294, "repositoryOnDiskBytes": 33064318294}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.135642+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824236", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T04:57:10.508531+00:00", "lastSyncTime": "2026-11-13T04:57:13.148714+00:00", "modelId": "cyankiwi/GLM-4.5-Air-AWQ-4bit", "modelProfile": {"architectures": ["Glm4MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 63400571960, "estimatedRequiredGiB": 70.884, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "glm4_moe", "modelscopeFileSize": 63425670208, "modelscopeLicense": "mit", "modelscopeParams": 106852251264, "modelscopeTags": ["license:mit", "model_type:glm4_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 63425670208, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e5192b47c94517b2", "recursiveRepositoryBytes": 63425670208, "repositoryOnDiskBytes": 63425670208}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.257369+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824227", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T04:21:10.533228+00:00", "lastSyncTime": "2026-11-13T04:21:14.150316+00:00", "modelId": "cpatonn-mirror/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ", "modelProfile": {"architectures": ["DeciLMForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29020319488, "estimatedRequiredGiB": 32.453, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_nas", "modelscopeFileSize": 29038368655, "modelscopeLicense": "other", "modelscopeParams": 49867145216, "modelscopeTags": ["license:other", "model_type:nemotron_nas", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:llama-3", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 29038368655, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 29038368655, "repositoryOnDiskBytes": 29038368655}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.145395+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824224", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T00:10:13.458725+00:00", "lastSyncTime": "2026-11-13T00:10:16.452408+00:00", "modelId": "primitive-ai/Nanbeige4.3-33B-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35526734272, "estimatedRequiredGiB": 39.728, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 35548056552, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:nanbeige", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 35548056552, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:423cd90dc537dded", "recursiveRepositoryBytes": 35548056552, "repositoryOnDiskBytes": 35548056552}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.149342+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824221", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T08:43:02.269845+00:00", "lastSyncTime": "2026-11-13T08:43:05.757479+00:00", "modelId": "primitive-ai/Nanbeige4.3-33B-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35526734272, "estimatedRequiredGiB": 39.728, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 35548056552, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:nanbeige", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 35548056552, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:423cd90dc537dded", "recursiveRepositoryBytes": 35548056552, "repositoryOnDiskBytes": 35548056552}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.149342+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824221", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T04:21:10.533228+00:00", "lastSyncTime": "2026-11-13T04:21:14.150288+00:00", "modelId": "cpatonn-mirror/Kimi-Dev-72B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 79588295928, "estimatedRequiredGiB": 88.967, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 79606715854, "modelscopeLicense": "mit", "modelscopeParams": 72706203648, "modelscopeTags": ["license:mit", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code", "custom_tag:swebench", "custom_tag:software", "custom_tag:issue-resolving"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 79606715854, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:08953c0a152f288b", "recursiveRepositoryBytes": 79606715854, "repositoryOnDiskBytes": 79606715854}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.152800+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824225", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T04:25:54.599544+00:00", "lastSyncTime": "2026-11-13T04:25:58.081889+00:00", "modelId": "cpatonn-mirror/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit", "modelProfile": {"architectures": ["DeciLMForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29020319488, "estimatedRequiredGiB": 32.453, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_nas", "modelscopeFileSize": 29038368655, "modelscopeLicense": "other", "modelscopeParams": 49867145216, "modelscopeTags": ["license:other", "model_type:nemotron_nas", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:llama-3", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 29038368655, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 29038368655, "repositoryOnDiskBytes": 29038368655}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.140846+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824222", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T04:43:11.555537+00:00", "lastSyncTime": "2026-11-13T04:43:14.768534+00:00", "modelId": "cpatonn-mirror/granite-4.0-h-small-AWQ-8bit", "modelProfile": {"architectures": ["GraniteMoeHybridForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 39756453136, "estimatedRequiredGiB": 44.442, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granitemoehybrid", "modelscopeFileSize": 39766281934, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32618379776, "modelscopeTags": ["license:apache-2.0", "model_type:granitemoehybrid", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:language", "custom_tag:granite-4.0"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 39766281934, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e379a948ff56dd79", "recursiveRepositoryBytes": 39766281934, "repositoryOnDiskBytes": 39766281934}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T10:20:56.373627+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5824238", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -918,7 +918,7 @@
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T05:32:40.790606+00:00", "lastSyncTime": "2026-11-13T05:32:44.030435+00:00", "modelId": "cyankiwi/MiniMax-M2.1-REAP-139B-A10B-AWQ-4bit", "modelProfile": {"architectures": ["MiniMaxM2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 80093556736, "estimatedRequiredGiB": 89.546, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minimax_m2", "modelscopeFileSize": 80124470126, "modelscopeLicense": "other", "modelscopeParams": 139149203788, "modelscopeTags": ["license:other", "model_type:minimax_m2", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minimax", "custom_tag:MOE", "custom_tag:pruning", "custom_tag:compression"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 80124470126, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:4fbcad1e55b4a8ec", "recursiveRepositoryBytes": 80124470126, "repositoryOnDiskBytes": 80124470126}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T14:41:34.908600+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5828032", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T06:17:13.848192+00:00", "lastSyncTime": "2026-11-13T06:17:16.593477+00:00", "modelId": "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "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": 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": "2026-10-27T15:48:43.873629+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5828882", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "llamacpp", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T07:12:52.727811+00:00", "lastSyncTime": "2026-11-13T07:12:56.178683+00:00", "modelId": "incoai/Qwen3.8-Flash-Next-DFlash2-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "4c98ab4ddc73d23ce303538ecd9a88bdd2af18582ee3c2a50f7f11f36d766187", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 652101024, "estimatedRequiredGiB": 3.543, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 3169866081, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:dflash2", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 3169866081, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 3169866081, "repositoryOnDiskBytes": 3169866081}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T16:05:55.287834+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5829160", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T00:10:13.458725+00:00", "lastSyncTime": "2026-11-13T00:10:16.452416+00:00", "modelId": "primitive-ai/Nanbeige4.3-33B-NVFP4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22070410112, "estimatedRequiredGiB": 24.69, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 22091795362, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977388, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:nanbeige", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 22091795362, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:5179e7fa01f5b826", "recursiveRepositoryBytes": 22091795362, "repositoryOnDiskBytes": 22091795362}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T16:05:55.379121+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5829196", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.27.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "a121b811cf073610087b", "lastOutcomeReconcileAt": "2026-11-13T08:43:02.269845+00:00", "lastSyncTime": "2026-11-13T08:43:05.757487+00:00", "modelId": "primitive-ai/Nanbeige4.3-33B-NVFP4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22070410112, "estimatedRequiredGiB": 24.69, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 22091795362, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977388, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:nanbeige", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 22091795362, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:5179e7fa01f5b826", "recursiveRepositoryBytes": 22091795362, "repositoryOnDiskBytes": 22091795362}, "outcome": "pending", "status": "waiting", "strategyId": "93638504-0c6b-4ef7-b366-bb4f69d27f55", "submitTime": "2026-10-27T16:05:55.379121+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5829196", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T04:39:14.717873+00:00", "lastSyncTime": "2026-11-13T04:39:17.567468+00:00", "modelId": "cpatonn-mirror/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "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": 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": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-27T16:45:00.029092+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5829779", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T03:45:44.297249+00:00", "lastSyncTime": "2026-11-13T03:45:47.365792+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": "2026-11-13T01:30:40.241557+00:00", "lastSyncTime": "2026-11-13T01:30:43.562306+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}
|
||||
@@ -1076,7 +1076,7 @@
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T01:08:42.264934+00:00", "lastSyncTime": "2026-11-13T01:08:45.937278+00:00", "modelId": "BigCui/qwen2.5-0.5b-instruct-q8_0", "modelProfile": {"architectures": [], "configFingerprint": "fb0bf11c3989c049a5cd4a65f4fa76b9a173537e0bd5468d90b14489b272033e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 675710816, "estimatedRequiredGiB": 1.304, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1167114365, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:Apache License 2.0", "library:gguf", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 1167114365, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 1167114365, "repositoryOnDiskBytes": 1167114365}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T17:05:54.037833+00:00", "targetGpu": "hygon_k100-ai", "taskId": "6164312", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T00:32:08.287525+00:00", "lastSyncTime": "2026-11-13T01:44:03.974684+00:00", "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6737, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2171252206, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1080632832, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:ms-swift", "custom_tag:LoRA"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 2171252206, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 2171252206, "repositoryOnDiskBytes": 2171252206}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T17:40:08.473751+00:00", "targetGpu": "MetaX_c-500", "taskId": "6164797", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T06:03:58.180906+00:00", "lastSyncTime": "2026-11-13T06:04:01.574819+00:00", "modelId": "cyankiwi/Ornith-1.0-35B-AWQ-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38073808064, "estimatedRequiredGiB": 42.59, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 38108913596, "modelscopeLicense": "mit", "modelscopeParams": 35107181936, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 38108913596, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:6578657f98bf7c9c", "recursiveRepositoryBytes": 38108913596, "repositoryOnDiskBytes": 38108913596}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T17:40:08.812589+00:00", "targetGpu": "Ascend_910-b3", "taskId": "6164762", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T00:10:13.458725+00:00", "lastSyncTime": "2026-11-13T01:48:46.328438+00:00", "modelId": "primitive-ai/Ripple-65B-Preview-FP8", "modelProfile": {"architectures": ["RicursiveForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 65848872576, "estimatedRequiredGiB": 73.6, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ricursive", "modelscopeFileSize": 65856257465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 64782689360, "modelscopeTags": ["license:apache-2.0", "model_type:ricursive", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:ricursive", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 65856257465, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:1235d2030b85a3b9", "recursiveRepositoryBytes": 65856257465, "repositoryOnDiskBytes": 65856257465}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T17:46:28.347415+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "6164869", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T08:43:02.269845+00:00", "lastSyncTime": "2026-11-13T08:43:05.757502+00:00", "modelId": "primitive-ai/Ripple-65B-Preview-FP8", "modelProfile": {"architectures": ["RicursiveForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 65848872576, "estimatedRequiredGiB": 73.6, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ricursive", "modelscopeFileSize": 65856257465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 64782689360, "modelscopeTags": ["license:apache-2.0", "model_type:ricursive", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:ricursive", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 65856257465, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:1235d2030b85a3b9", "recursiveRepositoryBytes": 65856257465, "repositoryOnDiskBytes": 65856257465}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T17:46:28.347415+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "6164869", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T01:03:25.000239+00:00", "lastSyncTime": "2026-11-13T01:48:46.328028+00:00", "modelId": "Axion1-0/Axion-1.0-35B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 70214494128, "estimatedRequiredGiB": 78.493, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 70234598619, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:reproduction", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:scientific-reasoning", "custom_tag:moe", "custom_tag:arxiv:2611.03233"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 70234598619, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 70234598619, "repositoryOnDiskBytes": 70234598619}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T17:46:28.348725+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "6164870", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T03:14:15.868915+00:00", "lastSyncTime": "2026-11-13T03:14:19.080896+00:00", "modelId": "RedHatAI/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 65827374264, "estimatedRequiredGiB": 73.588, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 65845709151, "modelscopeLicense": "other", "modelscopeParams": 32913266240, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 65845709151, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 65845709151, "repositoryOnDiskBytes": 65845709151}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T17:46:28.352131+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "6164872", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T01:17:22.164360+00:00", "lastSyncTime": "2026-11-13T01:48:46.328306+00:00", "modelId": "DavidAU/ERNIE-4.5-37B-A3B-Thinking-Brainstorm20x", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 74371252464, "estimatedRequiredGiB": 83.131, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 74384704412, "modelscopeLicense": "apache-2.0", "modelscopeParams": 37185044864, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:programming", "custom_tag:code generation", "custom_tag:code", "custom_tag:coding", "custom_tag:coder", "custom_tag:chat", "custom_tag:brainstorm 20x", "custom_tag:creative", "custom_tag:all uses cases", "custom_tag:benchmarks", "custom_tag:128k context", "custom_tag:creative writing", "custom_tag:fiction", "custom_tag:finetune", "custom_tag:thinking", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 74384704412, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 74384704412, "repositoryOnDiskBytes": 74384704412}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T17:46:28.353539+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "6164871", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -1148,7 +1148,7 @@
|
||||
{"agentVersion": "2026.11.12.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "df792a9eb3b7af5f6bfe", "lastOutcomeReconcileAt": "2026-11-13T02:28:48.938866+00:00", "lastSyncTime": "2026-11-13T04:48:33.763071+00:00", "modelId": "MNN/MNN-Pocket-0.3B", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 723137248, "estimatedRequiredGiB": 0.827, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 739624210, "modelscopeLicense": "apache-2.0", "modelscopeParams": 361551232, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:mnn", "custom_tag:mnn-pocket", "custom_tag:on-device", "custom_tag:edge", "custom_tag:qwen3", "custom_tag:int4"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 739624210, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 739624210, "repositoryOnDiskBytes": 739624210}, "outcome": "pending", "status": "waiting", "strategyId": "d9ca0811-d8a7-4b84-9644-9a76114def55", "submitTime": "2026-11-11T20:44:00.894728+00:00", "targetGpu": "Ascend_910-b3", "taskId": "6167472", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.11.12.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "df792a9eb3b7af5f6bfe", "lastOutcomeReconcileAt": "2026-11-13T00:32:08.287525+00:00", "lastSyncTime": "2026-11-13T04:48:33.763152+00:00", "modelId": "speakleash/Bielik-11B-v3.1-Instruct", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22337646064, "estimatedRequiredGiB": 24.967, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 22340131538, "modelscopeLicense": "apache-2.0", "modelscopeParams": 11168796672, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 22340131538, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 22340131538, "repositoryOnDiskBytes": 22340131538}, "outcome": "pending", "status": "waiting", "strategyId": "d9ca0811-d8a7-4b84-9644-9a76114def55", "submitTime": "2026-11-11T20:47:48.315114+00:00", "targetGpu": "Ascend_910-b3", "taskId": "6167512", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.11.12.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "df792a9eb3b7af5f6bfe", "lastOutcomeReconcileAt": "2026-11-13T00:32:08.287525+00:00", "lastSyncTime": "2026-11-13T05:14:37.673495+00:00", "modelId": "speakleash/Bielik-11B-v3.1-Instruct", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22337646064, "estimatedRequiredGiB": 24.967, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 22340131538, "modelscopeLicense": "apache-2.0", "modelscopeParams": 11168796672, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 22340131538, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 22340131538, "repositoryOnDiskBytes": 22340131538}, "outcome": "pending", "status": "waiting", "strategyId": "d9ca0811-d8a7-4b84-9644-9a76114def55", "submitTime": "2026-11-11T21:11:54.148938+00:00", "targetGpu": "Vastai_va16", "taskId": "6167899", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.11.12.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "df792a9eb3b7af5f6bfe", "lastOutcomeReconcileAt": "2026-11-13T02:42:51.719049+00:00", "lastSyncTime": "2026-11-13T08:38:30.970222+00:00", "modelId": "ReadyArt/gemma-4-31B-it-scotoma-2", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 62546338264, "estimatedRequiredGiB": 69.938, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 62579334938, "modelscopeLicense": "apache-2.0", "modelscopeParams": 31273088876, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 62579334938, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 62579334938, "repositoryOnDiskBytes": 62579334938}, "outcome": "pending", "status": "waiting", "strategyId": "d9ca0811-d8a7-4b84-9644-9a76114def55", "submitTime": "2026-11-12T04:42:16.927719+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "6175702", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.11.12.1", "failReason": null, "framework": "llamacpp", "instanceId": "df792a9eb3b7af5f6bfe", "lastOutcomeReconcileAt": "2026-11-13T01:12:40.516721+00:00", "lastSyncTime": "2026-11-13T08:38:30.970115+00:00", "modelId": "speakleash/Bielik-Minitron-7B-v3.0-Instruct-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "88887392536caac504983465af24046fe87672e0005b073681ee4a04fe2ff4fa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7946804256, "estimatedRequiredGiB": 26.686, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 23878193716, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7477727232, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:finetuned", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23878193716, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 23878193716, "repositoryOnDiskBytes": 23878193716}, "outcome": "pending", "status": "waiting", "strategyId": "d9ca0811-d8a7-4b84-9644-9a76114def55", "submitTime": "2026-11-12T07:40:49.836990+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "6178271", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.11.12.1", "failReason": null, "framework": "llamacpp", "instanceId": "df792a9eb3b7af5f6bfe", "lastOutcomeReconcileAt": "2026-11-13T06:09:12.363491+00:00", "lastSyncTime": "2026-11-13T08:38:30.970256+00:00", "modelId": "MiMouse/MiMouseEdgeLLM", "modelProfile": {"architectures": [], "configFingerprint": "cadea9b9404f483d273d225bb814842664573f2f56e2d5cf291713c3b7b0f535", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 229093184, "estimatedRequiredGiB": 28.259, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 25285638831, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 9400279040, "modelscopeTags": ["license:Apache License 2.0", "library:gguf", "library:other", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 25285638831, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 25285638831, "repositoryOnDiskBytes": 25285638831}, "outcome": "pending", "status": "waiting", "strategyId": "d9ca0811-d8a7-4b84-9644-9a76114def55", "submitTime": "2026-11-12T09:38:35.656078+00:00", "targetGpu": "Ascend_910-b3", "taskId": "6180024", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.11.12.1", "failReason": null, "framework": "llamacpp", "instanceId": "df792a9eb3b7af5f6bfe", "lastOutcomeReconcileAt": "2026-11-13T06:09:12.363491+00:00", "lastSyncTime": "2026-11-13T08:38:30.970030+00:00", "modelId": "MiMouse/MiMouseEdgeLLM", "modelProfile": {"architectures": [], "configFingerprint": "ae398026f5656cfd4301ce87fc25100cad06a6ff1079be74680599f8c3c8d771", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 229093184, "estimatedRequiredGiB": 28.259, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 25285638831, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 9400279040, "modelscopeTags": ["license:Apache License 2.0", "library:gguf", "library:other", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 25285638831, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 25285638831, "repositoryOnDiskBytes": 25285638831}, "outcome": "pending", "status": "waiting", "strategyId": "d9ca0811-d8a7-4b84-9644-9a76114def55", "submitTime": "2026-11-12T09:38:47.148598+00:00", "targetGpu": "Ascend_910-b4", "taskId": "6180037", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.11.12.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "df792a9eb3b7af5f6bfe", "lastOutcomeReconcileAt": "2026-11-13T02:42:51.719049+00:00", "lastSyncTime": "2026-11-13T08:43:05.757228+00:00", "modelId": "ReadyArt/gemma-4-31B-it-scotoma-2", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 62546338264, "estimatedRequiredGiB": 69.938, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 62579334938, "modelscopeLicense": "apache-2.0", "modelscopeParams": 31273088876, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 62579334938, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 62579334938, "repositoryOnDiskBytes": 62579334938}, "outcome": "pending", "status": "waiting", "strategyId": "d9ca0811-d8a7-4b84-9644-9a76114def55", "submitTime": "2026-11-12T04:42:16.927719+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "6175702", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.11.12.1", "failReason": null, "framework": "llamacpp", "instanceId": "df792a9eb3b7af5f6bfe", "lastOutcomeReconcileAt": "2026-11-13T01:12:40.516721+00:00", "lastSyncTime": "2026-11-13T08:43:05.757318+00:00", "modelId": "speakleash/Bielik-Minitron-7B-v3.0-Instruct-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "88887392536caac504983465af24046fe87672e0005b073681ee4a04fe2ff4fa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7946804256, "estimatedRequiredGiB": 26.686, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 23878193716, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7477727232, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:finetuned", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23878193716, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 23878193716, "repositoryOnDiskBytes": 23878193716}, "outcome": "pending", "status": "waiting", "strategyId": "d9ca0811-d8a7-4b84-9644-9a76114def55", "submitTime": "2026-11-12T07:40:49.836990+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "6178271", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.11.12.1", "failReason": null, "framework": "llamacpp", "instanceId": "df792a9eb3b7af5f6bfe", "lastOutcomeReconcileAt": "2026-11-13T06:09:12.363491+00:00", "lastSyncTime": "2026-11-13T08:43:05.757366+00:00", "modelId": "MiMouse/MiMouseEdgeLLM", "modelProfile": {"architectures": [], "configFingerprint": "cadea9b9404f483d273d225bb814842664573f2f56e2d5cf291713c3b7b0f535", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 229093184, "estimatedRequiredGiB": 28.259, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 25285638831, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 9400279040, "modelscopeTags": ["license:Apache License 2.0", "library:gguf", "library:other", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 25285638831, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 25285638831, "repositoryOnDiskBytes": 25285638831}, "outcome": "pending", "status": "waiting", "strategyId": "d9ca0811-d8a7-4b84-9644-9a76114def55", "submitTime": "2026-11-12T09:38:35.656078+00:00", "targetGpu": "Ascend_910-b3", "taskId": "6180024", "taskType": "text-generation", "verifyResult": null}
|
||||
{"agentVersion": "2026.11.12.1", "failReason": null, "framework": "llamacpp", "instanceId": "df792a9eb3b7af5f6bfe", "lastOutcomeReconcileAt": "2026-11-13T06:09:12.363491+00:00", "lastSyncTime": "2026-11-13T08:43:05.757457+00:00", "modelId": "MiMouse/MiMouseEdgeLLM", "modelProfile": {"architectures": [], "configFingerprint": "ae398026f5656cfd4301ce87fc25100cad06a6ff1079be74680599f8c3c8d771", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 229093184, "estimatedRequiredGiB": 28.259, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 25285638831, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 9400279040, "modelscopeTags": ["license:Apache License 2.0", "library:gguf", "library:other", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 25285638831, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 25285638831, "repositoryOnDiskBytes": 25285638831}, "outcome": "pending", "status": "waiting", "strategyId": "d9ca0811-d8a7-4b84-9644-9a76114def55", "submitTime": "2026-11-12T09:38:47.148598+00:00", "targetGpu": "Ascend_910-b4", "taskId": "6180037", "taskType": "text-generation", "verifyResult": null}
|
||||
Reference in new issue
Block a user