state: generation 31724 (cycle)

This commit is contained in:
CoolBoy committed 2026-11-13 18:28:43 +00:00
1 parent 499306bdce
commit da2cd12266
7 files changed
+872 -873

No files matched your search

+8 -8
View File
@@ -383,7 +383,7 @@
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T17:49:33.328601+00:00", "lastSyncTime": "2026-11-13T17:49:36.252500+00:00", "modelId": "AtomicChat/Qwen3.5-9B-DFlash-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "hygon_k100-ai", "taskId": "5699676", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T13:40:02.145873+00:00", "lastSyncTime": "2026-11-13T13:40:03.435743+00:00", "modelId": "cyankiwi/Jan-v1-4B-AWQ-8bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5698916", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:49:32.259200+00:00", "lastSyncTime": "2026-11-13T14:49:35.328404+00:00", "modelId": "cyankiwi/Trinity-Mini-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5697424", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T10:08:21.279912+00:00", "lastSyncTime": "2026-11-13T10:08:24.570717+00:00", "modelId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5694815", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T18:28:22.924369+00:00", "lastSyncTime": "2026-11-13T18:28:25.882891+00:00", "modelId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5694815", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T15:32:06.143071+00:00", "lastSyncTime": "2026-11-13T15:32:09.161614+00:00", "modelId": "incoai/Muse-Glimmer-30B-DFlash2-GGUF", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "hygon_k100-ai", "taskId": "5691062", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T15:23:37.688192+00:00", "lastSyncTime": "2026-11-13T15:23:39.976545+00:00", "modelId": "hf/esatapedico-MiniCPM-V-4.7-35B-A3B-NVFP4", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5645467", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T12:35:05.807761+00:00", "lastSyncTime": "2026-11-13T12:35:09.445959+00:00", "modelId": "castorini/gaggle-nanochat-pretrained-climbmix-20260924", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5572093", "taskType": "text-generation", "verifyResult": null}
@@ -586,7 +586,7 @@
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:23:16.606323+00:00", "lastSyncTime": "2026-11-13T14:23:19.962497+00:00", "modelId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5716393", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:15:26.936414+00:00", "lastSyncTime": "2026-11-13T14:15:30.083783+00:00", "modelId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5716024", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:01:55.430162+00:00", "lastSyncTime": "2026-11-13T14:01:58.441135+00:00", "modelId": "cyankiwi/MiroThinker-v1.0-30B-AWQ-8bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "MetaX_c-500", "taskId": "5701875", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T10:08:21.279912+00:00", "lastSyncTime": "2026-11-13T10:08:24.570711+00:00", "modelId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5697435", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T18:28:22.924369+00:00", "lastSyncTime": "2026-11-13T18:28:25.882898+00:00", "modelId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5697435", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T14:27:46.341486+00:00", "lastSyncTime": "2026-11-13T14:27:49.855357+00:00", "modelId": "cyankiwi/OmniCoder-9B-AWQ-BF16-INT4", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5697423", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T13:05:39.111734+00:00", "lastSyncTime": "2026-11-13T13:05:42.174423+00:00", "modelId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b4", "taskId": "5688915", "taskType": "text-generation", "verifyResult": null}
{"framework": null, "lastOutcomeReconcileAt": "2026-11-13T11:16:00.136088+00:00", "lastSyncTime": "2026-11-13T11:16:03.349973+00:00", "modelId": "OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark-gguf", "modelProfile": {}, "outcome": "pending", "status": "waiting", "submitTime": null, "targetGpu": "Ascend_910-b3", "taskId": "5687537", "taskType": "text-generation", "verifyResult": null}
@@ -955,12 +955,12 @@
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T13:57:28.135778+00:00", "lastSyncTime": "2026-11-13T13:57:31.851596+00:00", "modelId": "cyankiwi/Llama-3_3-Nemotron-Super-49B-v1_5-AWQ-4bit", "modelProfile": {"architectures": ["DeciLMForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29020319488, "estimatedRequiredGiB": 32.453, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_nas", "modelscopeFileSize": 29038369021, "modelscopeLicense": "other", "modelscopeParams": 49867145216, "modelscopeTags": ["license:other", "model_type:nemotron_nas", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:llama-3", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 29038369021, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 29038369021, "repositoryOnDiskBytes": 29038369021}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T10:49:59.501022+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5844817", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T12:04:35.754546+00:00", "lastSyncTime": "2026-11-13T12:04:38.374358+00:00", "modelId": "XHToken/Spark-X2.6-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "1d153f006310de4a64f8c5ec9c0a4875a6af2dfc403b09509ed2b227a47b4002", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820113440, "estimatedRequiredGiB": 7.834, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 7010046444, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 7010046444, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7010046444, "repositoryOnDiskBytes": 7010046444}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T13:34:09.462874+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5847555", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T12:04:35.754546+00:00", "lastSyncTime": "2026-11-13T12:04:38.374352+00:00", "modelId": "XHToken/Spark-X2.6-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "ee7d3f741e15635edb6a7aaff8a36f09b08e64fc64c26a9e83971ebf3d3ac190", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820113440, "estimatedRequiredGiB": 7.834, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 7010046444, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 7010046444, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7010046444, "repositoryOnDiskBytes": 7010046444}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T13:49:57.249364+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5847754", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T10:08:21.279912+00:00", "lastSyncTime": "2026-11-13T10:08:24.570698+00:00", "modelId": "Haodong07/Qwen3-14B-TwinQuant-W4A4", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12610178368, "estimatedRequiredGiB": 14.106, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 10550492288, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 12621681247, "repositoryOnDiskBytes": 12621681247}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:05:45.083117+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5847970", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T10:13:04.279162+00:00", "lastSyncTime": "2026-11-13T10:13:07.982462+00:00", "modelId": "Haodong07/Qwen3-8B-TwinQuant-W4A4", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7490808664, "estimatedRequiredGiB": 8.384, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 7502305637, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5970162816, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 7502305637, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7502305637, "repositoryOnDiskBytes": 7502305637}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:05:45.084902+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5847969", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T10:08:21.279912+00:00", "lastSyncTime": "2026-11-13T10:08:24.570684+00:00", "modelId": "Haodong07/Llama-3.1-8B-Instruct-TwinQuant-W4A4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7150927928, "estimatedRequiredGiB": 8.011, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "llama3.1", "modelscopeParams": 5823795328, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "task:text-generation", "custom_tag:llama", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7168201505, "repositoryOnDiskBytes": 7168201505}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:21:39.090816+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5848463", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T10:08:21.279912+00:00", "lastSyncTime": "2026-11-13T10:08:24.570705+00:00", "modelId": "Haodong07/Qwen3-14B-TwinQuant-W4A4", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12610178368, "estimatedRequiredGiB": 14.106, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 10550492288, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 12621681247, "repositoryOnDiskBytes": 12621681247}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:21:39.092587+00:00", "targetGpu": "Vastai_va16", "taskId": "5848462", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T10:13:04.279162+00:00", "lastSyncTime": "2026-11-13T10:13:07.982469+00:00", "modelId": "Haodong07/Qwen3-8B-TwinQuant-W4A4", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7490808664, "estimatedRequiredGiB": 8.384, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 7502305637, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5970162816, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 7502305637, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7502305637, "repositoryOnDiskBytes": 7502305637}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:21:39.081188+00:00", "targetGpu": "Vastai_va16", "taskId": "5848461", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T10:08:21.279912+00:00", "lastSyncTime": "2026-11-13T10:08:24.570691+00:00", "modelId": "Haodong07/Llama-3.1-8B-Instruct-TwinQuant-W4A4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7150927928, "estimatedRequiredGiB": 8.011, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "llama3.1", "modelscopeParams": 5823795328, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "task:text-generation", "custom_tag:llama", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7168201505, "repositoryOnDiskBytes": 7168201505}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:37:27.556834+00:00", "targetGpu": "Vastai_va16", "taskId": "5848878", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T18:28:22.924369+00:00", "lastSyncTime": "2026-11-13T18:28:25.882876+00:00", "modelId": "Haodong07/Qwen3-14B-TwinQuant-W4A4", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12610178368, "estimatedRequiredGiB": 14.106, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 10550492288, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 12621681247, "repositoryOnDiskBytes": 12621681247}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:05:45.083117+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5847970", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T18:28:22.924369+00:00", "lastSyncTime": "2026-11-13T18:28:25.882913+00:00", "modelId": "Haodong07/Qwen3-8B-TwinQuant-W4A4", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7490808664, "estimatedRequiredGiB": 8.384, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 7502305637, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5970162816, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 7502305637, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7502305637, "repositoryOnDiskBytes": 7502305637}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:05:45.084902+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5847969", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm-mlu", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T18:28:22.924369+00:00", "lastSyncTime": "2026-11-13T18:28:25.882868+00:00", "modelId": "Haodong07/Llama-3.1-8B-Instruct-TwinQuant-W4A4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7150927928, "estimatedRequiredGiB": 8.011, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "llama3.1", "modelscopeParams": 5823795328, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "task:text-generation", "custom_tag:llama", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7168201505, "repositoryOnDiskBytes": 7168201505}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:21:39.090816+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5848463", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T18:28:22.924369+00:00", "lastSyncTime": "2026-11-13T18:28:25.882884+00:00", "modelId": "Haodong07/Qwen3-14B-TwinQuant-W4A4", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12610178368, "estimatedRequiredGiB": 14.106, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 10550492288, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 12621681247, "repositoryOnDiskBytes": 12621681247}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:21:39.092587+00:00", "targetGpu": "Vastai_va16", "taskId": "5848462", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T18:28:22.924369+00:00", "lastSyncTime": "2026-11-13T18:28:25.882906+00:00", "modelId": "Haodong07/Qwen3-8B-TwinQuant-W4A4", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7490808664, "estimatedRequiredGiB": 8.384, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 7502305637, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5970162816, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 7502305637, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7502305637, "repositoryOnDiskBytes": 7502305637}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:21:39.081188+00:00", "targetGpu": "Vastai_va16", "taskId": "5848461", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T18:28:22.924369+00:00", "lastSyncTime": "2026-11-13T18:28:25.882848+00:00", "modelId": "Haodong07/Llama-3.1-8B-Instruct-TwinQuant-W4A4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7150927928, "estimatedRequiredGiB": 8.011, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "llama3.1", "modelscopeParams": 5823795328, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "task:text-generation", "custom_tag:llama", "custom_tag:twinquant", "custom_tag:quantization", "custom_tag:int4", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 7168201505, "repositoryOnDiskBytes": 7168201505}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:37:27.556834+00:00", "targetGpu": "Vastai_va16", "taskId": "5848878", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_fix_tokenizer", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T13:45:06.109466+00:00", "lastSyncTime": "2026-11-13T13:45:09.684735+00:00", "modelId": "cyankiwi/KAT-V1-40B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23382751128, "estimatedRequiredGiB": 26.15, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 23398883677, "modelscopeLicense": "other", "modelscopeParams": 40565560320, "modelscopeTags": ["license:other", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23398883677, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 23398883677, "repositoryOnDiskBytes": 23398883677}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T14:53:18.503287+00:00", "targetGpu": "Vastai_va16", "taskId": "5849746", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "vllm_tokenizer_patch", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T13:45:06.109466+00:00", "lastSyncTime": "2026-11-13T13:45:09.684742+00:00", "modelId": "cyankiwi/KAT-V1-40B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23382751128, "estimatedRequiredGiB": 26.15, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 23398883677, "modelscopeLicense": "other", "modelscopeParams": 40565560320, "modelscopeTags": ["license:other", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 23398883677, "quantizationMethod": "compressed-tensors", "quantizationSignature": "compressed-tensors:506a2c18748fc260", "recursiveRepositoryBytes": 23398883677, "repositoryOnDiskBytes": 23398883677}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T15:33:50.799119+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5850377", "taskType": "text-generation", "verifyResult": null}
{"agentVersion": "2026.10.28.1", "failReason": null, "framework": "llamacpp", "instanceId": "87a9405264eb816066a7", "lastOutcomeReconcileAt": "2026-11-13T17:49:33.328601+00:00", "lastSyncTime": "2026-11-13T17:49:36.252524+00:00", "modelId": "AtomicChat/gemma-4-E2B-it-assistant-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "40dcc0aedc42018347616f1d86a660896e0a6c687386f177ae81a2b5bf197a7e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 97817696, "estimatedRequiredGiB": 0.558, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 499499907, "modelscopeLicense": "apache-2.0", "modelscopeParams": 77207300, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:atomic-chat", "custom_tag:gemma", "custom_tag:gemma4", "custom_tag:google", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:quantized", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 499499907, "quantizationMethod": null, "quantizationSignature": "none:44136fa355b3678a", "recursiveRepositoryBytes": 499499907, "repositoryOnDiskBytes": 499499907}, "outcome": "pending", "status": "waiting", "strategyId": "9ace80d0-6764-4b98-89c8-4f744ac60080", "submitTime": "2026-10-28T17:29:23.456146+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5852178", "taskType": "text-generation", "verifyResult": null}