state: generation 31337 (cycle)

This commit is contained in:
CoolBoy committed 2026-11-13 09:01:39 +00:00
1 parent 34796567ba
commit afb89a4674
7 files changed
+872 -872

No files matched your search

+10 -10
View File
@@ -147,7 +147,7 @@
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T02:20:11.302769+00:00", "lastSyncTime": "2026-11-13T02:20:14.177364+00:00", "modelId": "LiquidAI/LFM2.5-230M-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "4577672", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T07:26:16.846302+00:00", "lastSyncTime": "2026-11-13T07:26:20.576136+00:00", "modelId": "logic65/Qwen3.8-p44w75-16.8B-unrepaired", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "4560065", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T02:51:30.796858+00:00", "lastSyncTime": "2026-11-13T02:51:34.050869+00:00", "modelId": "OsaurusAI/MiniMax-M2.7-JANGTQ", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "4560060", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T00:28:04.379676+00:00", "lastSyncTime": "2026-11-13T00:28:07.361029+00:00", "modelId": "siliconflow/Qwen2.5-72B-Instruct-fp8", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "4353195", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T09:01:15.323662+00:00", "lastSyncTime": "2026-11-13T09:01:18.667833+00:00", "modelId": "siliconflow/Qwen2.5-72B-Instruct-fp8", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "4353195", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T06:32:05.633898+00:00", "lastSyncTime": "2026-11-13T06:32:09.259449+00:00", "modelId": "empero-ai/Qwen3.8-2B-Distill-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "4347180", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T03:18:13.350471+00:00", "lastSyncTime": "2026-11-13T03:18:16.569872+00:00", "modelId": "RedHatAI/gemma-4-31B-it-FP8-Dynamic", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "4203916", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T06:22:32.551047+00:00", "lastSyncTime": "2026-11-13T06:22:36.578811+00:00", "modelId": "cyankiwi/command-a-reasoning-08-2025-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "5795170", "taskType": "text-generation", "verifyResult": null}
@@ -836,7 +836,7 @@
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T03:54:28.684705+00:00", "lastSyncTime": "2026-11-13T03:54:32.176970+00:00", "modelId": "bartowski/MiniCPM5-2B-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Mthreads_s4000", "taskId": "4754660", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T02:11:23.807447+00:00", "lastSyncTime": "2026-11-13T02:11:27.139883+00:00", "modelId": "JANGQ-AI/MiniMax-M2.7-JANGTQ_K", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "4746456", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T08:47:48.125937+00:00", "lastSyncTime": "2026-11-13T08:47:51.228729+00:00", "modelId": "prithivMLmods/MiniCPM5-2B-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Mthreads_s4000", "taskId": "4730579", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T00:28:04.379676+00:00", "lastSyncTime": "2026-11-13T00:28:07.361022+00:00", "modelId": "siliconflow/Hunyuan-A13B-Instruct-SF-FP8", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "4729534", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T09:01:15.323662+00:00", "lastSyncTime": "2026-11-13T09:01:18.667827+00:00", "modelId": "siliconflow/Hunyuan-A13B-Instruct-SF-FP8", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "4729534", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T07:26:16.846302+00:00", "lastSyncTime": "2026-11-13T07:26:20.576143+00:00", "modelId": "mlx-community/Hy3-OptiQ-2bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Kunlunxin_p-800", "taskId": "4729532", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T03:31:36.543653+00:00", "lastSyncTime": "2026-11-13T03:31:40.062228+00:00", "modelId": "XHToken/Spark-X2.5-4B-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "4692145", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T02:24:15.416080+00:00", "lastSyncTime": "2026-11-13T02:24:18.881425+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Iluvatar_bi-150", "taskId": "4650543", "taskType": "text-generation", "verifyResult": null}
@@ -988,7 +988,7 @@
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T02:20:11.302769+00:00", "lastSyncTime": "2026-11-13T02:20:14.177417+00:00", "modelId": "LiquidAI/LFM2.5-24B-A2B-FP8", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24747107856, "estimatedRequiredGiB": 27.679, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 24766905921, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:moe", "custom_tag:fp8"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 24766905921, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:c423bce491c6ff6d", "recursiveRepositoryBytes": 24766905921, "repositoryOnDiskBytes": 24766905921}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-29T21:44:11.671090+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5897657", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T02:51:30.796858+00:00", "lastSyncTime": "2026-11-13T02:51:34.050905+00:00", "modelId": "PleIAs/Baguettotron-MoE", "modelProfile": {"architectures": ["BaguettotronMoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26581256560, "estimatedRequiredGiB": 29.713, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "baguettotron_moe", "modelscopeFileSize": 26586426092, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:baguettotron_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:moe", "custom_tag:mixtral", "custom_tag:reasoning", "custom_tag:synthetic-data", "custom_tag:custom_code"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 26586426092, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 26586426092, "repositoryOnDiskBytes": 26586426092}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-29T21:44:11.736236+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5897653", "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": "2026-11-13T01:17:25.776482+00:00", "modelId": "DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16680151504, "estimatedRequiredGiB": 18.647, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 16685193382, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:lfm2_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:finetune", "custom_tag:unsloth", "custom_tag:mixture of experts", "custom_tag:sparse moe", "custom_tag:moe", "custom_tag:heretic", "custom_tag:uncensored", "custom_tag:aliterated", "custom_tag:all use cases", "custom_tag:coder", "custom_tag:creative", "custom_tag:creative writing", "custom_tag:fiction writing", "custom_tag:plot generation", "custom_tag:sub-plot generation", "custom_tag:story generation", "custom_tag:scene continue", "custom_tag:storytelling", "custom_tag:fiction story", "custom_tag:science fiction", "custom_tag:romance", "custom_tag:all genres", "custom_tag:story", "custom_tag:writing", "custom_tag:vivid prosing", "custom_tag:vivid writing", "custom_tag:fiction", "custom_tag:roleplaying", "custom_tag:bfloat16"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 16685193382, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 16685193382, "repositoryOnDiskBytes": 16685193382}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-29T21:44:11.730094+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5897654", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T00:28:04.379676+00:00", "lastSyncTime": "2026-11-13T00:28:07.360995+00:00", "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165329828, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 27200059979, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1144510513, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 27200059979, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e986acf74893086a", "recursiveRepositoryBytes": 27200059979, "repositoryOnDiskBytes": 27200059979}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-29T21:44:11.737418+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5897651", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T09:01:15.323662+00:00", "lastSyncTime": "2026-11-13T09:01:18.667806+00:00", "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165329828, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 27200059979, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1144510513, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 27200059979, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e986acf74893086a", "recursiveRepositoryBytes": 27200059979, "repositoryOnDiskBytes": 27200059979}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-29T21:44:11.737418+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5897651", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T03:22:56.839935+00:00", "lastSyncTime": "2026-11-13T03:23:00.183865+00:00", "modelId": "StartLuxAI/gdn-1.3b-isp-hybrid-3to1-50b", "modelProfile": {"architectures": ["GatedDeltaNetForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5729353240, "estimatedRequiredGiB": 6.407, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gated_deltanet", "modelscopeFileSize": 5732907231, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:gated_deltanet", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:fla", "custom_tag:gated-deltanet", "custom_tag:hybrid-linear-attention", "custom_tag:linear-attention", "custom_tag:massive-activations", "custom_tag:safetensors"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 5732907231, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 5732907231, "repositoryOnDiskBytes": 5732907231}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-29T21:44:11.733863+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5897650", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T06:45:29.606038+00:00", "lastSyncTime": "2026-11-13T06:45:32.180564+00:00", "modelId": "groxaxo/Qwen3.5-4B-Tmux-Pocket-Mini-AutoRound-AWQ-W4A16", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3127680424, "estimatedRequiredGiB": 3.518, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 3147776572, "modelscopeLicense": "apache-2.0", "modelscopeParams": 838985568, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen3.5", "custom_tag:text-only", "custom_tag:awq", "custom_tag:auto-round", "custom_tag:4-bit", "custom_tag:tmux-pocket"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 3147776572, "quantizationMethod": "awq", "quantizationSignature": "awq:c96b7e02d0a02d5e", "recursiveRepositoryBytes": 3147776572, "repositoryOnDiskBytes": 3147776572}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-30T07:54:23.473189+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5905150", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T03:00:05.385951+00:00", "lastSyncTime": "2026-11-13T03:00:08.964505+00:00", "modelId": "RWKV/RWKV7-G1k-1.5B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3055417000, "estimatedRequiredGiB": 3.417, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 3057516623, "modelscopeLicense": "apache-2.0", "modelscopeParams": 134217728, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 3057516623, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 3057516623, "repositoryOnDiskBytes": 3057516623}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-30T11:50:40.946937+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5908957", "taskType": "text-generation", "verifyResult": null}
@@ -1020,8 +1020,8 @@
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T06:45:29.606038+00:00", "lastSyncTime": "2026-11-13T06:45:32.180556+00:00", "modelId": "groxaxo/Qwen3.5-4B-Tmux-Pocket-Mini-AutoRound-AWQ-W4A16", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3127680424, "estimatedRequiredGiB": 3.518, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 3147776572, "modelscopeLicense": "apache-2.0", "modelscopeParams": 838985568, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen3.5", "custom_tag:text-only", "custom_tag:awq", "custom_tag:auto-round", "custom_tag:4-bit", "custom_tag:tmux-pocket"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 3147776572, "quantizationMethod": "awq", "quantizationSignature": "awq:c96b7e02d0a02d5e", "recursiveRepositoryBytes": 3147776572, "repositoryOnDiskBytes": 3147776572}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-02T02:03:10.495435+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5959362", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T02:20:11.302769+00:00", "lastSyncTime": "2026-11-13T02:20:14.177410+00:00", "modelId": "LiquidAI/LFM2.5-24B-A2B-FP8", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24747107856, "estimatedRequiredGiB": 27.679, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 24766905921, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:moe", "custom_tag:fp8"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 24766905921, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:c423bce491c6ff6d", "recursiveRepositoryBytes": 24766905921, "repositoryOnDiskBytes": 24766905921}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-02T02:03:15.707483+00:00", "targetGpu": "Vastai_va16", "taskId": "5959364", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T02:51:30.796858+00:00", "lastSyncTime": "2026-11-13T02:51:34.050911+00:00", "modelId": "PleIAs/Baguettotron-MoE", "modelProfile": {"architectures": ["BaguettotronMoeForCausalLM"], "configFingerprint": "2e07651654804a2ff443a05f385d50efe684c1da60752ae047be5c2e295242b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26581256560, "estimatedRequiredGiB": 29.713, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "baguettotron_moe", "modelscopeFileSize": 26586426092, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:baguettotron_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:moe", "custom_tag:mixtral", "custom_tag:reasoning", "custom_tag:synthetic-data", "custom_tag:custom_code"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 26586426092, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 26586426092, "repositoryOnDiskBytes": 26586426092}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-02T02:03:19.505672+00:00", "targetGpu": "Vastai_va16", "taskId": "5959365", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T00:28:04.379676+00:00", "lastSyncTime": "2026-11-13T00:28:07.361004+00:00", "modelId": "shisa-ai/shisa-de-2.1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165276348, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 27200017856, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6046852151, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 27200017856, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e986acf74893086a", "recursiveRepositoryBytes": 27200017856, "repositoryOnDiskBytes": 27200017856}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-02T02:03:24.061655+00:00", "targetGpu": "Vastai_va16", "taskId": "5959366", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T00:28:04.379676+00:00", "lastSyncTime": "2026-11-13T00:28:07.360987+00:00", "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165329828, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 27200059979, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1144510513, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 27200059979, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e986acf74893086a", "recursiveRepositoryBytes": 27200059979, "repositoryOnDiskBytes": 27200059979}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-02T02:03:28.162885+00:00", "targetGpu": "Vastai_va16", "taskId": "5959367", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T09:01:15.323662+00:00", "lastSyncTime": "2026-11-13T09:01:18.667821+00:00", "modelId": "shisa-ai/shisa-de-2.1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165276348, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 27200017856, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6046852151, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 27200017856, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e986acf74893086a", "recursiveRepositoryBytes": 27200017856, "repositoryOnDiskBytes": 27200017856}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-02T02:03:24.061655+00:00", "targetGpu": "Vastai_va16", "taskId": "5959366", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T09:01:15.323662+00:00", "lastSyncTime": "2026-11-13T09:01:18.667797+00:00", "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165329828, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 27200059979, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1144510513, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 27200059979, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e986acf74893086a", "recursiveRepositoryBytes": 27200059979, "repositoryOnDiskBytes": 27200059979}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-02T02:03:28.162885+00:00", "targetGpu": "Vastai_va16", "taskId": "5959367", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T03:00:05.385951+00:00", "lastSyncTime": "2026-11-13T03:00:08.964498+00:00", "modelId": "RWKV/RWKV7-G1k-1.5B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3055417000, "estimatedRequiredGiB": 3.417, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 3057516623, "modelscopeLicense": "apache-2.0", "modelscopeParams": 134217728, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 3057516623, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 3057516623, "repositoryOnDiskBytes": 3057516623}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-02T02:03:32.435054+00:00", "targetGpu": "Vastai_va16", "taskId": "5959368", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T01:21:28.948521+00:00", "lastSyncTime": "2026-11-13T01:21:32.070406+00:00", "modelId": "DavidAU/LFM2-8B-A1B-Instruct-Quantum-IQ1C-Qwen3.6-35B-A3B-DISTILL2", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16680151504, "estimatedRequiredGiB": 18.647, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 16685226991, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3344509440, "modelscopeTags": ["license:apache-2.0", "model_type:lfm2_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:distill", "custom_tag:finetune", "custom_tag:unsloth", "custom_tag:moe", "custom_tag:mixture of experts"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 16685226991, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 16685226991, "repositoryOnDiskBytes": 16685226991}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-02T02:03:36.572899+00:00", "targetGpu": "Vastai_va16", "taskId": "5959369", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T04:48:30.698259+00:00", "lastSyncTime": "2026-11-13T04:48:33.763262+00:00", "modelId": "cyankiwi/Agents-A1-AWQ-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926870808, "estimatedRequiredGiB": 26.791, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23972444278, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:vlm", "custom_tag:vision", "custom_tag:agentic"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23972444278, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:9bae5222b55fce6e", "recursiveRepositoryBytes": 23972444278, "repositoryOnDiskBytes": 23972444278}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-02T02:03:40.575244+00:00", "targetGpu": "Vastai_va16", "taskId": "5959370", "taskType": "text-generation", "verifyResult": null}
@@ -1059,7 +1059,7 @@
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T03:14:15.868915+00:00", "lastSyncTime": "2026-11-13T03:14:19.080918+00:00", "modelId": "RedHatAI/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-FP8", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 32293788600, "estimatedRequiredGiB": 36.112, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 32312682980, "modelscopeLicense": null, "modelscopeParams": 31577940288, "modelscopeTags": ["model_type:nemotron_h", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor", "custom_tag:nemotron-3.5", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 32312682980, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:f1a7feea183fba72", "recursiveRepositoryBytes": 32312682980, "repositoryOnDiskBytes": 32312682980}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-10T15:35:33.568955+00:00", "targetGpu": "Ascend_910-b3", "taskId": "6143668", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T03:40:27.455874+00:00", "lastSyncTime": "2026-11-13T03:40:30.749321+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B-w8a8", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35150826024, "estimatedRequiredGiB": 39.292, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 35157551596, "modelscopeLicense": null, "modelscopeParams": 31270466080, "modelscopeTags": ["model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 35157551596, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 35157551596, "repositoryOnDiskBytes": 35157551596}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T03:00:26.003590+00:00", "targetGpu": "MetaX_c-500", "taskId": "6151554", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T07:48:43.597512+00:00", "lastSyncTime": "2026-11-13T07:48:47.028312+00:00", "modelId": "nanbeige/Nanbeige4.3-33B-INT8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35992806936, "estimatedRequiredGiB": 40.249, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 36014177528, "modelscopeLicense": "apache-2.0", "modelscopeParams": 33118977024, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 36014177528, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:1d6de1e98552edcc", "recursiveRepositoryBytes": 36014177528, "repositoryOnDiskBytes": 36014177528}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T07:58:40.792909+00:00", "targetGpu": "MetaX_c-500", "taskId": "6155838", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T00:28:04.379676+00:00", "lastSyncTime": "2026-11-13T00:28:07.361014+00:00", "modelId": "shisa-ai/shisa-de-2.1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165276348, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 27200017856, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6046852151, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 27200017856, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e986acf74893086a", "recursiveRepositoryBytes": 27200017856, "repositoryOnDiskBytes": 27200017856}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T10:24:50.828818+00:00", "targetGpu": "MetaX_c-500", "taskId": "6157714", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T09:01:15.323662+00:00", "lastSyncTime": "2026-11-13T09:01:18.667813+00:00", "modelId": "shisa-ai/shisa-de-2.1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165276348, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 27200017856, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6046852151, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 27200017856, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:e986acf74893086a", "recursiveRepositoryBytes": 27200017856, "repositoryOnDiskBytes": 27200017856}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T10:24:50.828818+00:00", "targetGpu": "MetaX_c-500", "taskId": "6157714", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T03:22:56.839935+00:00", "lastSyncTime": "2026-11-13T03:23:00.183837+00:00", "modelId": "ShenRen1231/Spark-1.7B-DeepSeek-v4.1-Flash-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "92c9e514ac335a5c1ce5f4a6b3f86a14a806ff20573bb41bc4df2cd47cf2ef14", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820112640, "estimatedRequiredGiB": 3.272, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 2927578486, "modelscopeLicense": "MIT License", "modelscopeParams": 1707657216, "modelscopeTags": ["license:MIT License", "library:lora", "library:peft", "library:gguf", "task:text-generation", "custom_tag:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5", "custom_tag:lora", "custom_tag:peft", "custom_tag:instruction-tuned", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:agent"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 2927578486, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 2927578486, "repositoryOnDiskBytes": 2927578486}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T11:37:38.626083+00:00", "targetGpu": "Ascend_910-b3", "taskId": "6158798", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T04:03:09.547203+00:00", "lastSyncTime": "2026-11-13T04:03:13.061957+00:00", "modelId": "bytkim/Qwen3.8-27B-pi-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 34715684264, "estimatedRequiredGiB": 38.825, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 34739621865, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:speculative-decoding", "custom_tag:vision", "custom_tag:image", "custom_tag:multimodal", "custom_tag:image-text-to-text", "custom_tag:text-generation-inference", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:qwen38", "custom_tag:27b", "custom_tag:pi", "custom_tag:coding", "custom_tag:coder", "custom_tag:code-generation", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:reasoning", "custom_tag:conversational", "custom_tag:sft", "custom_tag:grpo", "custom_tag:reinforcement-learning", "custom_tag:fp8", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 34739621865, "quantizationMethod": "fp8", "quantizationSignature": "fp8:a8794dc9a10580bc", "recursiveRepositoryBytes": 34739621865, "repositoryOnDiskBytes": 34739621865}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T12:51:58.794805+00:00", "targetGpu": "MetaX_c-500", "taskId": "6159867", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T02:01:59.269090+00:00", "lastSyncTime": "2026-11-13T02:02:03.529140+00:00", "modelId": "IFM/K2-Horizon-32B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37350407624, "estimatedRequiredGiB": 41.768, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 37372966182, "modelscopeLicense": "apache-2.0", "modelscopeParams": 34779304960, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:32b", "custom_tag:dense", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 37372966182, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:36e15c6d014ede20", "recursiveRepositoryBytes": 37372966182, "repositoryOnDiskBytes": 37372966182}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-11-11T12:51:58.796095+00:00", "targetGpu": "MetaX_c-500", "taskId": "6159868", "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": "2026-11-13T08:56:01.458875+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": "2026-11-13T08:56:01.458999+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": "2026-11-13T08:56:01.459036+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": "2026-11-13T08:56:01.458978+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": "2026-11-13T09:01:18.667541+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": "2026-11-13T09:01:18.667741+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": "2026-11-13T09:01:18.667603+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": "2026-11-13T09:01:18.667653+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}