diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index ee390a9376..7e602da148 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -506,7 +506,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-23T21:26:42.857456+00:00", + "generatedAt": "2026-10-23T21:28:24.933922+00:00", "summary": { "activeBlockCount": 25, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index 17f0bdbcaf..588cb35561 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-23T21:26:42.957789+00:00", + "generatedAt": "2026-10-23T21:28:25.055348+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index b87389e0d5..cc1a07d105 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-23T21:26:42.957789+00:00", + "catalogUpdatedAt": "2026-10-23T21:28:25.055348+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-23T21:26:42.957789+00:00", + "generatedAt": "2026-10-23T21:28:25.055348+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6466,6 +6466,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-23T21:26:42.957789+00:00", + "taskTreeUpdatedAt": "2026-10-23T21:28:25.055348+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index 08b1bdb04a..8fb352c89d 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-23T20:04:44.521662+00:00", - "lastSyncTime": "2026-10-23T20:04:44.274551+00:00", + "generatedAt": "2026-10-23T21:28:24.829744+00:00", + "lastSyncTime": "2026-10-23T21:28:24.747670+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -2102,20 +2102,20 @@ "framework_architecture_unsupported": 38, "model_load": 5, "tokenizer_compatibility": 2, - "参数/模板问题": 24 + "参数/模板问题": 25 }, - "failureCount": 85, - "failureRate": 0.8416, + "failureCount": 86, + "failureRate": 0.8431, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 16, - "successRate": 0.1584, + "successRate": 0.1569, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", - "total": 101, - "unresolvedFailureCount": 40 + "total": 102, + "unresolvedFailureCount": 41 }, "Kunlunxin_p-800|unknown|text-generation": { "attributableFailureCount": 1, @@ -3248,17 +3248,17 @@ "repository_structure": 470, "runtime_memory": 66, "tokenizer_compatibility": 425, - "参数/模板问题": 101 + "参数/模板问题": 102 }, - "failureCount": 6317, + "failureCount": 6318, "failureRate": 0.9827, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 888, "successCount": 111, "successRate": 0.0173, - "total": 6428, - "unresolvedFailureCount": 1711 + "total": 6429, + "unresolvedFailureCount": 1712 }, "vllm-customized": { "attributableFailureCount": 16, @@ -3408,7 +3408,7 @@ "unresolvedFailureCount": 341 } }, - "generatedAt": "2026-10-23T20:04:44.507825+00:00", + "generatedAt": "2026-10-23T21:28:24.813411+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 133, @@ -3621,19 +3621,19 @@ "repository_structure": 133, "runtime_memory": 1, "tokenizer_compatibility": 118, - "参数/模板问题": 361, + "参数/模板问题": 362, "日志缺失": 6, "验证失败": 47 }, - "failureCount": 1772, + "failureCount": 1773, "failureRate": 0.9092, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 7, "successCount": 177, "successRate": 0.0908, - "total": 1949, - "unresolvedFailureCount": 770 + "total": 1950, + "unresolvedFailureCount": 771 }, "Kunlunxin_p-800": { "attributableFailureCount": 99, @@ -25890,18 +25890,18 @@ "unresolvedFailureCount": 20 }, "Iluvatar_mrv-100|vllm|text-generation": { - "attributableFailureCount": 6, - "consecutiveFailures": 6, + "attributableFailureCount": 5, + "consecutiveFailures": 5, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, - "decisionTotal": 6, + "decisionTotal": 5, "failureBreakdown": { "ambiguous_runtime": 2, - "framework_architecture_unsupported": 4, + "framework_architecture_unsupported": 3, "model_load": 1, "tokenizer_compatibility": 1, - "参数/模板问题": 12 + "参数/模板问题": 13 }, "failureCount": 20, "failureRate": 1.0, @@ -25916,7 +25916,7 @@ "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 20, - "unresolvedFailureCount": 14 + "unresolvedFailureCount": 15 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 0, @@ -25970,18 +25970,17 @@ "unresolvedFailureCount": 11 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation": { - "attributableFailureCount": 3, - "consecutiveFailures": 3, + "attributableFailureCount": 2, + "consecutiveFailures": 2, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, - "decisionTotal": 3, + "decisionTotal": 2, "failureBreakdown": { "backend_operator": 2, - "model_load": 1, "参数/模板问题": 5 }, - "failureCount": 8, + "failureCount": 7, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastPlatformFailureAt": null, @@ -25993,7 +25992,7 @@ "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", - "total": 8, + "total": 7, "unresolvedFailureCount": 5 }, "MetaX_c-500|vllm|text-generation": { @@ -27586,31 +27585,6 @@ "total": 1, "unresolvedFailureCount": 1 }, - "MetaX_c-500|vllm_tokenizer_patch|text-generation|gpt_oss|none": { - "attributableFailureCount": 1, - "consecutiveFailures": 1, - "decisionFailureRate": 1.0, - "decisionSuccessRate": 0.0, - "decisionTotal": 1, - "failureBreakdown": { - "model_load": 1 - }, - "failureCount": 1, - "failureRate": 1.0, - "framework": "vllm_tokenizer_patch", - "lastTerminalAt": "2026-10-07T06:27:34.062566+00:00", - "modelType": "gpt_oss", - "pendingCount": 0, - "pendingRate": 0.0, - "platformFailureCount": 0, - "quantizationMethod": "none", - "successCount": 0, - "successRate": 0.0, - "targetGpu": "MetaX_c-500", - "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 0 - }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3|compressed-tensors": { "attributableFailureCount": 1, "consecutiveFailures": 1, @@ -61176,8 +61150,8 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 17997, - "totalRecords": 18541, + "terminalRecords": 17998, + "totalRecords": 18542, "totals": { "attributableFailureCount": 6372, "decisionFailureRate": 0.866, @@ -61196,19 +61170,19 @@ "repository_structure": 742, "runtime_memory": 101, "tokenizer_compatibility": 698, - "参数/模板问题": 3599, + "参数/模板问题": 3600, "日志缺失": 719, "验证失败": 676 }, - "failureCount": 17011, + "failureCount": 17012, "failureRate": 0.9452, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 972, "successCount": 986, "successRate": 0.0548, - "total": 17997, - "unresolvedFailureCount": 9667 + "total": 17998, + "unresolvedFailureCount": 9668 }, "warnings": [ "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", @@ -61263,14 +61237,14 @@ "组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Biren_166m|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x4|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Cambricon_mlu-370-x4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_mrv-100|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Kunlunxin_p-800|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。" + "组合 Kunlunxin_p-800|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Cambricon_mlu-370-x4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。" ] }, "storageMode": "decision_state_only", - "summarizedRecords": 18541, + "summarizedRecords": 18542, "version": 1 } diff --git a/.modelhub_state/recent_outcomes.jsonl b/.modelhub_state/recent_outcomes.jsonl index 69a938ead3..04c3b62979 100644 --- a/.modelhub_state/recent_outcomes.jsonl +++ b/.modelhub_state/recent_outcomes.jsonl @@ -226,6 +226,7 @@ {"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": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-23T21:28:24.747670+00:00", "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:47:41.964098+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321059", "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} @@ -297,4 +298,3 @@ {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T09:26:43.784451+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409915, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409915}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:27.159752+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320008", "taskType": "text-generation", "verifyResult": -1} {"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_fix_tokenizer", "lastSyncTime": "2026-10-21T21:16:24.481190+00:00", "modelId": "juspay/Xor-26B-A4B-NVFP4", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18788485588, "estimatedRequiredGiB": 21.039, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 18825737204, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14386943566, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:gemma4", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 18825737204}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:27.158144+00:00", "targetGpu": "Biren_166m", "taskId": "5320010", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T14:09:53.041515+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:52:26.657696+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319990", "taskType": "text-generation", "verifyResult": null} -{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T06:27:34.062566+00:00", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11623702006, "estimatedRequiredGiB": 13.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 11651702017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3982569024, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:openai", "custom_tag:gpt-oss", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:optiq", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11651702017}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:26.475735+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319987", "taskType": "text-generation", "verifyResult": -1} diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 663c56b38b..0e684238cd 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3733,6 +3733,18 @@ {"batchId": "4ba40262d41d4141871a82e2c8ef7e3d", "completedAt": "2026-10-23T09:25:25.190554+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T09:25:22.571790+00:00", "framework": "vllm_tokenizer_patch", "intentId": "16d775d2d9e84b2c9f96cd48661d178c", "lastModified": "2026-10-21T19:08:10+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-23T21:26:52.920995+00:00", "repoId": "cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5735872", "taskType": "text-generation"} {"batchId": "3240b9dc6ea34cfa957079f469e9ae4b", "completedAt": "2026-10-23T11:15:29.377844+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T11:15:26.821111+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3d111b54d33a4ad6a01ce40afe6240df", "lastModified": "2026-10-22T01:37:07+00:00", "modelAddress": "https://modelscope.cn/models/RecursiveSI/flint-int4", "reason": null, "reconciledAt": "2026-10-23T21:26:52.921210+00:00", "repoId": "RecursiveSI/flint-int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5737151", "taskType": "text-generation"} {"batchId": "3d8c0e91978f43e09b0ff79b372b0077", "completedAt": "2026-10-23T13:28:14.742077+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-23T13:27:58.482566+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2bbf1c38663f4f2a91f1f3c5a47eb79f", "lastModified": "2026-10-21T16:38:25+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-23T21:26:52.920256+00:00", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5738981", "taskType": "text-generation"} +{"batchId": "9bceb13734314f209e19eb6c976dcada", "configFingerprint": "705b8b3614c86a1ac722c97f43e177e84ca20282e9799fffb1b890510d641728", "configSource": "modelhub_live", "createdAt": "2026-10-23T21:28:25.710885+00:00", "framework": "llamacpp", "intentId": "58e59ebf02dc426b8cbe94c455f39fce", "lastModified": "2026-10-21T18:16:46+00:00", "modelAddress": "https://modelscope.cn/models/AtomicChat/Qwen3.5-9B-DFlash-GGUF", "repoId": "AtomicChat/Qwen3.5-9B-DFlash-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "9bceb13734314f209e19eb6c976dcada", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T21:28:25.710999+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ec26dcb8a36b413b8a98bdd8a69c4ebc", "lastModified": "2026-10-21T16:33:24+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-4B-Instruct-2507-AWQ-4bit", "repoId": "cyankiwi/Qwen3-4B-Instruct-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "9bceb13734314f209e19eb6c976dcada", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T21:28:25.711055+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d5155e5f7c0f4b03a7ccaa41773af67f", "lastModified": "2026-10-21T16:31:51+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-4bit", "repoId": "cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "9bceb13734314f209e19eb6c976dcada", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T21:28:25.711118+00:00", "framework": "vllm_tokenizer_patch", "intentId": "660d5dcfd8e5427c81f3297310251353", "lastModified": "2026-10-23T13:17:05+00:00", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-4bit-MLX", "repoId": "ukisai/Swift-1.5-4bit-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "9bceb13734314f209e19eb6c976dcada", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T21:28:25.711187+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8fbc4b102fd54defb20395b82a175c53", "lastModified": "2026-10-21T17:21:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/OmniCoder-9B-AWQ-BF16-INT8", "repoId": "cyankiwi/OmniCoder-9B-AWQ-BF16-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "9bceb13734314f209e19eb6c976dcada", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T21:28:25.711252+00:00", "framework": "vllm_tokenizer_patch", "intentId": "aa2ab29c9ebb4cdd82b3c8a34019d1e1", "lastModified": "2026-10-21T17:03:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiniCPM-SALA-AWQ-4bit", "repoId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "9bceb13734314f209e19eb6c976dcada", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T21:28:25.711316+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9c118b9617404aada49a3f2f84ddad4c", "lastModified": "2026-10-21T16:19:52+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "repoId": "cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "9bceb13734314f209e19eb6c976dcada", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T21:28:25.711381+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c7119b0e19b84851adcb7d65b5494f79", "lastModified": "2026-10-22T14:14:09+00:00", "modelAddress": "https://modelscope.cn/models/InternScience/Sage-A1.5-FP8", "repoId": "InternScience/Sage-A1.5-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "9bceb13734314f209e19eb6c976dcada", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T21:28:25.711445+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d53b5630cac4437f938cea9de56664f8", "lastModified": "2026-10-23T13:09:59+00:00", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-5bit-MLX", "repoId": "ukisai/Swift-1.5-5bit-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "9bceb13734314f209e19eb6c976dcada", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T21:28:25.711508+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8191da900f894d9b8751269653e290f8", "lastModified": "2026-10-21T17:18:20+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiroThinker-v1.5-30B-AWQ-8bit", "repoId": "cyankiwi/MiroThinker-v1.5-30B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "9bceb13734314f209e19eb6c976dcada", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T21:28:25.711573+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ccad9606e6b1433ca6622267d03428d6", "lastModified": "2026-10-21T16:56:28+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "repoId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "9bceb13734314f209e19eb6c976dcada", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T21:28:25.711636+00:00", "framework": "vllm_tokenizer_patch", "intentId": "64a8921a56834cb7b93bb20f1439fb8e", "lastModified": "2026-10-21T16:21:36+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Report-AWQ-8bit", "repoId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} {"batchId": "bc58f50ca60841148d7b86a337fdfe35", "completedAt": "2026-10-23T21:26:46.562088+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T21:26:43.712573+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3ed76446af4446e2a3461c8d531ea9bf", "repoId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} {"batchId": "bc58f50ca60841148d7b86a337fdfe35", "completedAt": "2026-10-23T21:26:46.562085+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T21:26:43.712505+00:00", "framework": "vllm_tokenizer_patch", "intentId": "78b828f8c86249e3abcf965d8f95ddda", "repoId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} {"batchId": "bc58f50ca60841148d7b86a337fdfe35", "completedAt": "2026-10-23T21:26:46.562081+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T21:26:43.712436+00:00", "framework": "vllm_tokenizer_patch", "intentId": "46add8ca353742a1bd31971000a20c11", "repoId": "cyankiwi/MiroThinker-v1.5-30B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index 48a7713893..1bda51e26d 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "dc6b73ea23f7b03b9376c1a5ae2a6c8d7dcc1153b6b215e924e8a2d7c7f3c43d", - ".modelhub_state/architecture_compatibility_blacklist.json": "df56b6b222dab567bc7a1950688937e690f6d4fba6ad33d0f0d503a2974dbd69", + ".modelhub_state/architecture_compatibility_blacklist.json": "7bb53b79eda0815f63e1876378efcf715690d468852884c4e13c324e03d1e9b0", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "6203763e7ce62027d7ed72b7392e9c98efb15177865b3037841375baa8615193", - ".modelhub_state/official_capabilities.json": "150f7e1e6053694d58f5822b187393524c637e53b3be3bb3a8b58938bded46e3", - ".modelhub_state/outcome_checkpoint.json": "8f237f5957428445cd16863ccd2f05403d2fdae78bacc66b1a90deb374cfe203", + ".modelhub_state/market_intelligence.json": "1c01a92a13db2cc8ea7f0c3e28de6ee74381269658b06dbd176a000e26348815", + ".modelhub_state/official_capabilities.json": "c12155d96e597fbcceea87f2e7a03ff6134e75314a88989ad6032bab6e711280", + ".modelhub_state/outcome_checkpoint.json": "975aca991daf3a83cbce3798fdf80cdda0a441d794616d1b05ff570663cf26ce", ".modelhub_state/queue_cleanup_latest.json": "b9f4ab6b802f11fba1eac4aab36681bb1c55ca9ec453f998ff165c36b204bca4", - ".modelhub_state/recent_outcomes.jsonl": "4e9ea96530129301fd28fce2a2553a0c3ac736a88199c5f646c5d1f197302806", + ".modelhub_state/recent_outcomes.jsonl": "c86864152c81680d9b52f2d8dd585fb6b34855b70cf47c5ce1024b7c37e05c03", ".modelhub_state/recovery_active_tasks.jsonl": "131c8ef7b9f0790c6e3ba1dc4d0efd59b2f2ceea8f4b2cae38561c36e1fc6fbb", - ".modelhub_state/recovery_intents.jsonl": "f5155c479fe8169ed5aec84c8a299d39f4a0a26b4ae94f45a686dd318786be53", + ".modelhub_state/recovery_intents.jsonl": "813616754da7f01674fc741c2b9bc7eeef9a4ee560a71263aa49660114b030bd", ".modelhub_state/routing_intelligence.json": "86d7d8bc5b563c97e38a11d721593de6f68328c0db0381e1ba49e41bee3df159", ".modelhub_state/submission_exclusions.jsonl": "3bb99a0a703cee6767cdaeed2e3d26480ebf6d1cb44552f40bf65c94d9ed58b1", ".modelhub_state/worker_crashes.jsonl": "0e675b1c3ea5c2ab436cf083668db8830733f3e9d03420e10a8563a589acb517", "ledger/submissions.jsonl": "3d8aa5d757abc53e8fdef68f6355847de0058d65dbfcb8917138cabc8e4b65b5", - "outcomes/submissions.jsonl": "59f840fa423e739697479b980d75af215cc2490dc1fba9ecc661203df75c1a71" + "outcomes/submissions.jsonl": "18b5252b3f3289da170771aecfcbc71349d7dcb7e553df0a460efa68e2157b31" }, - "generation": 32344, - "phase": "cycle", + "generation": 32345, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-23T21:26:53.143042+00:00", + "updatedAt": "2026-10-23T21:28:25.892547+00:00", "writerId": "6cd7cbd5a7014f838149942b3e5927f7" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 3b39985c9a..e3af332549 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1087,4 +1087,4 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-23T14:46:53.252365+00:00", "modelId": "cyankiwi/Nemotron-Cascade-8B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921096, "estimatedRequiredGiB": 15.786, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 14125281593, "modelscopeLicense": "other", "modelscopeParams": 8190735360, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:Nemotron-Cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-22T11:48:09.066588+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 14125281593}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-23T06:45:26.950299+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5733468", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-23T17:40:01.945822+00:00", "modelId": "cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-8bit", "modelProfile": {"architectures": ["KimiLinearForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54087705936, "estimatedRequiredGiB": 60.459, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kimi_linear", "modelscopeFileSize": 54097373275, "modelscopeLicense": "mit", "modelscopeParams": 49122681728, "modelscopeTags": ["license:mit", "model_type:kimi_linear", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 54097373275}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-23T09:25:23.728480+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5735872", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-23T19:15:40.473459+00:00", "modelId": "RecursiveSI/flint-int4", "modelProfile": {"architectures": ["FlintForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22568912600, "estimatedRequiredGiB": 25.235, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "flint", "modelscopeFileSize": 22580274594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3572482016, "modelscopeTags": ["license:apache-2.0", "model_type:flint", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:int4", "custom_tag:safetensors"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22580274594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-23T11:15:27.958590+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5737151", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14278393080, "estimatedRequiredGiB": 15.973, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 14292651057, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14292651057}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-23T13:28:00.360187+00:00", "targetGpu": "MetaX_c-500", "taskId": "5738981", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-23T21:28:24.747626+00:00", "modelId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14278393080, "estimatedRequiredGiB": 15.973, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 14292651057, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14292651057}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-23T13:28:00.360187+00:00", "targetGpu": "MetaX_c-500", "taskId": "5738981", "taskType": "text-generation", "verifyResult": null}