From e7bb007fd59296f353f06172cd62bad9e2648dc4 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Wed, 21 Oct 2026 16:14:42 +0000 Subject: [PATCH] state: generation 27261 (intent) --- .../architecture_compatibility_blacklist.json | 2 +- .modelhub_state/market_intelligence.json | 2 +- .modelhub_state/official_capabilities.json | 36 +++--- .modelhub_state/outcome_checkpoint.json | 112 +++++++++++++----- .modelhub_state/recent_outcomes.jsonl | 2 +- .modelhub_state/recovery_intents.jsonl | 12 ++ manifest.json | 20 ++-- outcomes/submissions.jsonl | 3 +- 8 files changed, 122 insertions(+), 67 deletions(-) diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 121de41ea3..a0c4198600 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -829,7 +829,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-21T16:13:00.660445+00:00", + "generatedAt": "2026-10-21T16:14:40.730609+00:00", "summary": { "activeBlockCount": 40, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index 6efe1814b2..f95c0a7ed3 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-21T16:13:00.774233+00:00", + "generatedAt": "2026-10-21T16:14:40.864808+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index 13b2a453d3..e3a89d2712 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-21T16:13:00.774233+00:00", + "catalogUpdatedAt": "2026-10-21T16:14:40.864808+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-21T16:13:01.835324+00:00", + "generatedAt": "2026-10-21T16:14:41.556389+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -1862,14 +1862,11 @@ ], "updatedAt": "2026-10-21T15:18:18.256369+00:00" }, - "https://modelscope.cn/models/agentionai/Qwen3.8-Flash-Next-ROCmFP4-FAST-imatrix-GGUF|2026-10-20T15:14:38+00:00|Iluvatar_mrv-100": { + "https://modelscope.cn/models/agentionai/Qwen3.8-Flash-Next-ROCmFP4-FAST-imatrix-GGUF|2026-10-20T15:14:38+00:00|Kunlunxin_p-800": { "taskTypes": [ - "asr", - "text-generation", - "text-to-image-generation", - "visual-multi-modal" + "text-generation" ], - "updatedAt": "2026-10-21T15:16:18.060964+00:00" + "updatedAt": "2026-10-21T16:14:41.554348+00:00" }, "https://modelscope.cn/models/agentionai/Qwen3.8-Flash-Next-ROCmFP4-FAST-imatrix-GGUF|2026-10-20T15:14:38+00:00|MetaX_c-500": { "taskTypes": [ @@ -3404,14 +3401,11 @@ ], "updatedAt": "2026-10-21T15:18:18.452173+00:00" }, - "https://modelscope.cn/models/cyankiwi/GLM-5.3-AWQ-INT4|2026-10-20T14:35:45+00:00|Iluvatar_mrv-100": { + "https://modelscope.cn/models/cyankiwi/GLM-5.3-AWQ-INT4|2026-10-20T14:35:45+00:00|Kunlunxin_p-800": { "taskTypes": [ - "asr", - "text-generation", - "text-to-image-generation", - "visual-multi-modal" + "text-generation" ], - "updatedAt": "2026-10-21T15:16:18.069533+00:00" + "updatedAt": "2026-10-21T16:14:41.555251+00:00" }, "https://modelscope.cn/models/cyankiwi/GLM-5.3-AWQ-INT4|2026-10-20T14:35:45+00:00|MetaX_c-500": { "taskTypes": [ @@ -3522,6 +3516,12 @@ ], "updatedAt": "2026-10-21T16:13:01.535711+00:00" }, + "https://modelscope.cn/models/cyankiwi/Hy3-AWQ-NVFP4|2026-10-20T14:28:53+00:00|Kunlunxin_p-800": { + "taskTypes": [ + "text-generation" + ], + "updatedAt": "2026-10-21T16:14:41.556389+00:00" + }, "https://modelscope.cn/models/cyankiwi/Jan-v1-4B-AWQ-4bit|2026-10-21T15:27:56+00:00|Ascend_910-b3": { "taskTypes": [ "text-generation", @@ -4687,12 +4687,6 @@ ], "updatedAt": "2026-10-21T15:16:18.182845+00:00" }, - "https://modelscope.cn/models/ggml-org/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF|2026-10-20T14:33:47+00:00|Kunlunxin_p-800": { - "taskTypes": [ - "text-generation" - ], - "updatedAt": "2026-10-21T15:16:18.078551+00:00" - }, "https://modelscope.cn/models/ggml-org/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF|2026-10-20T14:33:47+00:00|MetaX_c-500": { "taskTypes": [ "feature_emb", @@ -7219,6 +7213,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-21T16:13:00.774233+00:00", + "taskTreeUpdatedAt": "2026-10-21T16:14:40.864808+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index d26866e2bc..5da178c98f 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-21T16:11:21.400758+00:00", - "lastSyncTime": "2026-10-21T16:11:20.642704+00:00", + "generatedAt": "2026-10-21T16:14:40.618021+00:00", + "lastSyncTime": "2026-10-21T16:14:40.355809+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -2426,24 +2426,24 @@ "decisionSuccessRate": 0.2759, "decisionTotal": 58, "failureBreakdown": { - "ambiguous_runtime": 14, + "ambiguous_runtime": 15, "framework_architecture_unsupported": 35, "model_load": 5, "tokenizer_compatibility": 2, "参数/模板问题": 23 }, - "failureCount": 79, - "failureRate": 0.8316, + "failureCount": 80, + "failureRate": 0.8333, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 16, - "successRate": 0.1684, + "successRate": 0.1667, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", - "total": 95, - "unresolvedFailureCount": 37 + "total": 96, + "unresolvedFailureCount": 38 }, "Kunlunxin_p-800|unknown|text-generation": { "attributableFailureCount": 1, @@ -3562,7 +3562,7 @@ "decisionSuccessRate": 0.0291, "decisionTotal": 3819, "failureBreakdown": { - "ambiguous_runtime": 1607, + "ambiguous_runtime": 1608, "architecture_compatibility": 112, "attention_backend": 3, "backend_operator": 98, @@ -3576,15 +3576,15 @@ "tokenizer_compatibility": 425, "参数/模板问题": 90 }, - "failureCount": 6293, + "failureCount": 6294, "failureRate": 0.9827, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 888, "successCount": 111, "successRate": 0.0173, - "total": 6404, - "unresolvedFailureCount": 1697 + "total": 6405, + "unresolvedFailureCount": 1698 }, "vllm-customized": { "attributableFailureCount": 16, @@ -3734,7 +3734,7 @@ "unresolvedFailureCount": 339 } }, - "generatedAt": "2026-10-21T16:11:21.383102+00:00", + "generatedAt": "2026-10-21T16:14:40.602773+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 132, @@ -3936,7 +3936,7 @@ "decisionSuccessRate": 0.1514, "decisionTotal": 1169, "failureBreakdown": { - "ambiguous_runtime": 354, + "ambiguous_runtime": 355, "architecture_compatibility": 47, "backend_operator": 1, "context_length": 77, @@ -3951,15 +3951,15 @@ "日志缺失": 6, "验证失败": 47 }, - "failureCount": 1764, - "failureRate": 0.9088, + "failureCount": 1765, + "failureRate": 0.9089, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 7, "successCount": 177, - "successRate": 0.0912, - "total": 1941, - "unresolvedFailureCount": 765 + "successRate": 0.0911, + "total": 1942, + "unresolvedFailureCount": 766 }, "Kunlunxin_p-800": { "attributableFailureCount": 99, @@ -16764,9 +16764,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 1 + "ambiguous_runtime": 2 }, - "failureCount": 1, + "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", @@ -16778,8 +16778,8 @@ "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 1 + "total": 2, + "unresolvedFailureCount": 2 }, "Iluvatar_mrv-100|vllm|text-generation|sse_swa_moba|none": { "attributableFailureCount": 0, @@ -25474,10 +25474,11 @@ "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { + "ambiguous_runtime": 1, "framework_architecture_unsupported": 2, "model_load": 1, "tokenizer_compatibility": 1, - "参数/模板问题": 16 + "参数/模板问题": 15 }, "failureCount": 20, "failureRate": 1.0, @@ -26609,6 +26610,31 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Iluvatar_mrv-100|vllm|text-generation|spark2_5|torchao": { + "attributableFailureCount": 0, + "consecutiveFailures": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm", + "lastTerminalAt": "2026-10-21T16:14:40.355809+00:00", + "modelType": "spark2_5", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "torchao", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Iluvatar_mrv-100", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|k2_horizon|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -46559,6 +46585,30 @@ "total": 1, "unresolvedFailureCount": 0 }, + "Iluvatar_mrv-100|vllm|text-generation|spark2_5|torchao|31": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm", + "loadSizeLog2Bucket": 31, + "modelType": "spark2_5", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "torchao", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Iluvatar_mrv-100", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Iluvatar_mrv-100|vllm|text-generation|spark2_5|torchao|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, @@ -59456,15 +59506,15 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 17933, - "totalRecords": 18463, + "terminalRecords": 17934, + "totalRecords": 18464, "totals": { "attributableFailureCount": 6346, "decisionFailureRate": 0.8655, "decisionSuccessRate": 0.1345, "decisionTotal": 7332, "failureBreakdown": { - "ambiguous_runtime": 4657, + "ambiguous_runtime": 4658, "architecture_compatibility": 212, "attention_backend": 3, "backend_operator": 135, @@ -59480,15 +59530,15 @@ "日志缺失": 719, "验证失败": 676 }, - "failureCount": 16947, + "failureCount": 16948, "failureRate": 0.945, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 971, "successCount": 986, "successRate": 0.055, - "total": 17933, - "unresolvedFailureCount": 9630 + "total": 17934, + "unresolvedFailureCount": 9631 }, "warnings": [ "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", @@ -59551,6 +59601,6 @@ ] }, "storageMode": "decision_state_only", - "summarizedRecords": 18463, + "summarizedRecords": 18464, "version": 1 } diff --git a/.modelhub_state/recent_outcomes.jsonl b/.modelhub_state/recent_outcomes.jsonl index ac0efe2c24..35739b2603 100644 --- a/.modelhub_state/recent_outcomes.jsonl +++ b/.modelhub_state/recent_outcomes.jsonl @@ -194,6 +194,7 @@ {"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-10-21T16:11:20.642704+00:00", "modelId": "ProCreations/BetterWright-K2-Horizon-7B-Uno", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19395158128, "estimatedRequiredGiB": 21.699, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 19416072650, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4022513664, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:betterwright", "custom_tag:browser-agent", "custom_tag:web-agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:diffusion-language-model", "custom_tag:uno", "custom_tag:k2-horizon", "custom_tag:full-finetune"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19416072650}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:47:42.151731+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321068", "taskType": "text-generation", "verifyResult": -1} {"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-10-11T05:28:07.648769+00:00", "modelId": "cyankiwi/Spark-X2.5-4B-AWQ-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2856860040, "estimatedRequiredGiB": 3.21, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2872281308, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2872281308}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:47:42.147712+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321065", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-08T11:54:51.560561+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:47:42.073173+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321066", "taskType": "text-generation", "verifyResult": null} +{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-10-21T16:14:40.355809+00:00", "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2938633112, "estimatedRequiredGiB": 3.296, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2948792004, "modelscopeLicense": "apache-2.0", "modelscopeParams": 935831040, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:int4", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 2948792004}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:47:41.958543+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321063", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-08T11:54:51.560495+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:47:41.955032+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321061", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-08T11:54:51.560505+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block1-v1_D", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:47:41.757839+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321053", "taskType": "text-generation", "verifyResult": null} {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["lfm2"], "framework": "vllm", "lastSyncTime": "2026-10-10T01:23:27.856116+00:00", "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 467369015}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:47:41.656436+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321055", "taskType": "text-generation", "verifyResult": -1} @@ -297,4 +298,3 @@ {"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T12:22:04.159110+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:50:49.262829+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319938", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T12:22:04.159146+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:50:49.261247+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319939", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T14:31:58.345504+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:50:49.259138+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319937", "taskType": "text-generation", "verifyResult": null} -{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T12:22:04.159219+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:50:49.252246+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319933", "taskType": "text-generation", "verifyResult": null} diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 7aa79f7237..9ccb749022 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3674,6 +3674,18 @@ {"batchId": "5c0a4f79bd0d49e1b0444e12976e79e7", "completedAt": "2026-10-21T14:50:49.366074+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T14:50:35.095772+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b84316343e8d46af88b3738e929476a2", "lastModified": "2026-10-21T14:18:30+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Orchestrator-8B-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-21T16:13:08.131576+00:00", "repoId": "cyankiwi/Orchestrator-8B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5696188", "taskType": "text-generation"} {"batchId": "5c0a4f79bd0d49e1b0444e12976e79e7", "completedAt": "2026-10-21T14:50:49.366090+00:00", "configFingerprint": "228b6bc2745650abd95687d8da71c138b5e7b7e9cbd7ff60115887f5ff13ac2c", "configSource": "modelhub_live", "createdAt": "2026-10-21T14:50:35.095882+00:00", "framework": "llamacpp", "intentId": "61493e6f9a1c416fbf4295e168b4314a", "lastModified": "2026-10-15T11:37:55+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/DeepSeek-BlackRoot-R1-Distill-Llama-3.1-8B-GGUF", "reason": null, "reconciledAt": "2026-10-21T16:13:08.131579+00:00", "repoId": "DavidAU/DeepSeek-BlackRoot-R1-Distill-Llama-3.1-8B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "5696187", "taskType": "text-generation"} {"batchId": "87b8205a0cad4334aea39cd9f6b287ea", "completedAt": "2026-10-21T15:09:15.232215+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T15:09:12.711331+00:00", "framework": "vllm_tokenizer_patch", "intentId": "14380ef73bad420db90a200999cc9a3b", "lastModified": "2026-10-21T14:41:08+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Report-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-21T16:13:08.130600+00:00", "repoId": "cyankiwi/AgentCPM-Report-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5696505", "taskType": "text-generation"} +{"batchId": "01f2e54b38dd485395e512d494d4a325", "configFingerprint": "6227ad7464202af2fd72ed7ba47d960a6db14697bf850d85ff2e90b31777e3a8", "configSource": "modelhub_live", "createdAt": "2026-10-21T16:14:42.019600+00:00", "framework": "llamacpp", "intentId": "d206c82a5b2844cab0c10b1b227a94c2", "lastModified": "2026-10-21T03:15:59+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.6-4B-GGUF", "repoId": "XHToken/Spark-X2.6-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"} +{"batchId": "01f2e54b38dd485395e512d494d4a325", "configFingerprint": "0810a8dbec6a5bb8330373d71363e8e47f5ab88e5ca0b04cee0d7bb4fc33e81f", "configSource": "modelhub_live", "createdAt": "2026-10-21T16:14:42.019719+00:00", "framework": "llamacpp", "intentId": "d1ba9967379f4f328cf807f18dbc1339", "lastModified": "2026-10-20T13:54:35+00:00", "modelAddress": "https://modelscope.cn/models/incoai/Muse-Glimmer-30B-DFlash2-GGUF", "repoId": "incoai/Muse-Glimmer-30B-DFlash2-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "01f2e54b38dd485395e512d494d4a325", "configFingerprint": "e6a494afe49de43cfe2b51111d8b2495fcc9c2b24f0b475f84ce14dcdff5b462", "configSource": "modelhub_live", "createdAt": "2026-10-21T16:14:42.019779+00:00", "framework": "llamacpp", "intentId": "ca468c03b6ec44a0a8007faa2991fa32", "lastModified": "2026-10-20T05:58:12+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.7-1B-DSpark-gguf", "repoId": "OpenBMB/MiniCPM-V-4.7-1B-DSpark-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "01f2e54b38dd485395e512d494d4a325", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T16:14:42.019834+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a2f1aaa249b94dac84e58f45bfb7bd76", "lastModified": "2026-10-21T15:32:58+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/OmniCoder-9B-AWQ-BF16-INT4", "repoId": "cyankiwi/OmniCoder-9B-AWQ-BF16-INT4", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "01f2e54b38dd485395e512d494d4a325", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T16:14:42.019887+00:00", "framework": "vllm_tokenizer_patch", "intentId": "fb79394d1c184173bb29176b2b32a540", "lastModified": "2026-10-21T14:17:13+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiroThinker-v1.0-30B-AWQ-4bit", "repoId": "cyankiwi/MiroThinker-v1.0-30B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "01f2e54b38dd485395e512d494d4a325", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T16:14:42.019937+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0a9bd2cf16f74cdcb57efa8234d0cc11", "lastModified": "2026-10-21T14:24:21+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Explore-AWQ-4bit", "repoId": "cyankiwi/AgentCPM-Explore-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "01f2e54b38dd485395e512d494d4a325", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T16:14:42.019987+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0d079137520743498f568dec2bd7532b", "lastModified": "2026-10-20T08:50:37+00:00", "modelAddress": "https://modelscope.cn/models/Haodong07/Qwen3-32B-TwinQuant-W4A4", "repoId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "01f2e54b38dd485395e512d494d4a325", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T16:14:42.020035+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1fcf102320724df181c21246792e147a", "lastModified": "2026-10-21T15:40:57+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Explore-AWQ-8bit", "repoId": "cyankiwi/AgentCPM-Explore-AWQ-8bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "01f2e54b38dd485395e512d494d4a325", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T16:14:42.020084+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3513485c97db43ee8225dd434bf6a8bc", "lastModified": "2026-10-21T15:59:12+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "01f2e54b38dd485395e512d494d4a325", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T16:14:42.020133+00:00", "framework": "vllm_tokenizer_patch", "intentId": "53974c3e54234f84ac61a30ca3c724fa", "lastModified": "2026-10-21T14:42:38+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Jan-v1-4B-AWQ-8bit", "repoId": "cyankiwi/Jan-v1-4B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "01f2e54b38dd485395e512d494d4a325", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T16:14:42.020194+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f34cb07adab045f6af0f1e9df3f7a24d", "lastModified": "2026-10-21T15:04:03+00:00", "modelAddress": "https://modelscope.cn/models/hf/BennyDaBall-Mistral-44B-MoE-Patched-MLX-4bit-G64", "repoId": "hf/BennyDaBall-Mistral-44B-MoE-Patched-MLX-4bit-G64", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "01f2e54b38dd485395e512d494d4a325", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T16:14:42.020247+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c6d7f9f8520b44ac9d9bf36b2bbc82ec", "lastModified": "2026-10-21T14:56:09+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Trinity-Mini-AWQ-4bit", "repoId": "cyankiwi/Trinity-Mini-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} {"batchId": "d2fa6ce5d46d4dbb8606566c0872ab99", "completedAt": "2026-10-21T16:13:05.021915+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T16:13:02.103241+00:00", "framework": "vllm_tokenizer_patch", "intentId": "106070a9dcdf469984a069aff653fd8a", "repoId": "cyankiwi/Trinity-Mini-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "d2fa6ce5d46d4dbb8606566c0872ab99", "completedAt": "2026-10-21T16:13:05.021912+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T16:13:02.103191+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ca81cd148b0d46aebc2840ee16052bd0", "repoId": "hf/BennyDaBall-Mistral-44B-MoE-Patched-MLX-4bit-G64", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "d2fa6ce5d46d4dbb8606566c0872ab99", "completedAt": "2026-10-21T16:13:05.021909+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T16:13:02.103130+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b39c8085c5c2445e8333743a72a94a74", "repoId": "cyankiwi/Jan-v1-4B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index ba47bf813c..dc9d7f046e 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "b2a64a90c0d60b5aba3558414ce198fc3ad8d6aa397c9dbd92d308ef115dded3", - ".modelhub_state/architecture_compatibility_blacklist.json": "178514522f408d92a115446d167d9051dc493cbc26e1f9d67540208200bb458f", + ".modelhub_state/architecture_compatibility_blacklist.json": "a7adf8d08af2378715010430ce4be33a41869a2e4ab4957bf21a0e2c849341d5", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "f434b52040fcf1aaf635c7913eaf13d918be4b67b2c2084f1bba4cedd42b5964", - ".modelhub_state/official_capabilities.json": "1dad4935b962cee51b6eb0f0a6f59fb68c4ca3634ff1d9cbb4ab653f6f7e722a", - ".modelhub_state/outcome_checkpoint.json": "8eb6ae64e4e002f7420e46e3b02762168c971cd44f075ab93ceab40ed7bb9dbd", + ".modelhub_state/market_intelligence.json": "7febbe59926a4743d00f549c9c16c4079d18c14c97dd22a647f6ad0dc0fbf6df", + ".modelhub_state/official_capabilities.json": "e4f214837387d63b1753bb1ee02df2ead66445ec375a174b977fe6b6dcf92625", + ".modelhub_state/outcome_checkpoint.json": "a76bef20958cab969622ea94c9b949a302d42fdd45561e073763bc656245ed06", ".modelhub_state/queue_cleanup_latest.json": "0131c45f935ae58a0e843431a8540fec0cd040d818446150772f2c922327038b", - ".modelhub_state/recent_outcomes.jsonl": "3d598c558f1ab4a724f4bc7717cfecdb356d587918c0dd9596294b4413aedc47", + ".modelhub_state/recent_outcomes.jsonl": "a8537200c5a8edc6ff68cf81f4d430de7dba473e0b5ff46c40f3a0f6981287c9", ".modelhub_state/recovery_active_tasks.jsonl": "046a42a0736b87ac83491b74741e6913a65ca1ff2ccfc101510def51d188b28c", - ".modelhub_state/recovery_intents.jsonl": "c9e678cffefe13edb77dd8b53716ade916d8d2bf26122e96ab3211d526569971", + ".modelhub_state/recovery_intents.jsonl": "ea4bff71682c43b5d2fc70361fb4fffc38e0cdbf48bdc6dbeae8648cdf2bd879", ".modelhub_state/routing_intelligence.json": "0cbaa847c72486bbe72e7b584afe4dd09fd3d5c3f820a65507efac6a5dec5e95", ".modelhub_state/submission_exclusions.jsonl": "07b0cf531e208c0d6ecfffb156a0cb39a09636bee94976f2a8a2e3b767cf06cc", ".modelhub_state/worker_crashes.jsonl": "d46c42c2991f2fda703c2ba17f2b6a21afa8e1453bf67666f1bc0ff3bb99e2e9", "ledger/submissions.jsonl": "8d4f883b91b0714535e9b8086e47468bcb8be9c24590b1a92373c923297d9334", - "outcomes/submissions.jsonl": "3ab1f525c6788dcdcabda3cd21a8ceb7cfb671f2b22c3b5b00e1adf2931945c1" + "outcomes/submissions.jsonl": "cd3ffc2508c325bd8dcebbea380ff87cfd25364a7c5c1d85e0e76c82d86a0014" }, - "generation": 27260, - "phase": "cycle", + "generation": 27261, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-21T16:13:08.364058+00:00", + "updatedAt": "2026-10-21T16:14:42.257975+00:00", "writerId": "f9d6ac09a4c14ca19fc241d193853c55" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 89dcfe5c22..d1d34eefd4 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -495,7 +495,6 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952941+00:00", "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 1784320455, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:finance", "custom_tag:plamo", "custom_tag:japanese"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1784320455}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.756287+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321052", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952394+00:00", "modelId": "OsaurusAI/Raptor-0.6-4B-JANG_4M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2635323720, "estimatedRequiredGiB": 2.962, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2650224659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2650224659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.751476+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321056", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.951927+00:00", "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "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": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.967785+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321060", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952823+00:00", "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2938633112, "estimatedRequiredGiB": 3.296, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2948792004, "modelscopeLicense": "apache-2.0", "modelscopeParams": 935831040, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:int4", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 2948792004}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.958543+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321063", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952720+00:00", "modelId": "burtenshaw/nanochat", "modelProfile": {"architectures": ["NanoChatForCausalLM"], "configFingerprint": "785069d14d27b828ee50a34932a2fa1917fd842d075189f20fc7defd52ef2db4", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8583142248, "estimatedRequiredGiB": 9.603, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanochat", "modelscopeFileSize": 8592610065, "modelscopeLicense": "mit", "modelscopeParams": 161546240, "modelscopeTags": ["license:mit", "model_type:nanochat", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8592610065}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.855732+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321058", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952389+00:00", "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6737, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2171252206, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1080632832, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:ms-swift", "custom_tag:LoRA"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2171252206}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.075531+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321064", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952714+00:00", "modelId": "IFM/K2-Horizon-32B-NVFP4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23253718728, "estimatedRequiredGiB": 26.013, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 23275790433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 34779305408, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:k2-horizon", "custom_tag:32b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23275790433}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.150650+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321070", "taskType": "text-generation", "verifyResult": null} @@ -1082,7 +1081,7 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-21T15:07:26.070090+00:00", "modelId": "cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["SeedOssForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21000825520, "estimatedRequiredGiB": 23.484, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "seed_oss", "modelscopeFileSize": 21013103805, "modelscopeLicense": "apache-2.0", "modelscopeParams": 36151104512, "modelscopeTags": ["license:apache-2.0", "model_type:seed_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 21013103805}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T07:05:46.531823+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5690178", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-21T15:23:24.077806+00:00", "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19282103457, "estimatedRequiredGiB": 21.582, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19310950017, "modelscopeLicense": "other", "modelscopeParams": 5321729392, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:5-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19310950017}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T07:22:26.160574+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5690393", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-21T16:11:20.642680+00:00", "modelId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-NVFP4", "modelProfile": {"architectures": ["DoryForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3202498032, "estimatedRequiredGiB": 3.6, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "dory", "modelscopeFileSize": 3221457919, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:dory", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-labs", "custom_tag:dory"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 3221457919}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T08:10:47.947488+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5691022", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "incoai/Muse-Glimmer-30B-DFlash2-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "b8a926f4d98c4c17ed728affade2dfee1910e905840c16a7c6d35cdf073f1b9a", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2959518912, "estimatedRequiredGiB": 11.359, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10163561932, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:dflash2", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10163561932}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T08:13:50.255199+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5691062", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-21T16:14:40.355786+00:00", "modelId": "incoai/Muse-Glimmer-30B-DFlash2-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "b8a926f4d98c4c17ed728affade2dfee1910e905840c16a7c6d35cdf073f1b9a", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2959518912, "estimatedRequiredGiB": 11.359, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10163561932, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:dflash2", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10163561932}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-21T08:13:50.255199+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5691062", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cpatonn-mirror/Qwen3-Next-80B-A3B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3NextForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 49231450912, "estimatedRequiredGiB": 55.063, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_next", "modelscopeFileSize": 49269386372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 81324862720, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_next", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 49269386372}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T09:52:13.230435+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5692453", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "iluvatar-corex/Qwen3-8B-W8A8", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9441379272, "estimatedRequiredGiB": 10.569, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 9457348916, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9457348916}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T10:03:53.143948+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5692570", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cpatonn-mirror/Qwen3-30B-A3B-Thinking-2507-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064333187, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 33064333187}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-21T12:05:06.542231+00:00", "targetGpu": "MetaX_c-500", "taskId": "5694040", "taskType": "text-generation", "verifyResult": null}