diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 283c9b9c7d..6f18e328de 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -2871,7 +2871,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-09-21T23:53:01.756493+00:00", + "generatedAt": "2026-09-21T23:54:31.199181+00:00", "summary": { "activeBlockCount": 144, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index 18d4bb9809..2d84aabd24 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -434,7 +434,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-09-21T23:50:54.685305+00:00", + "generatedAt": "2026-09-21T23:54:41.767263+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index 182b446bb3..571f7be185 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-09-21T23:50:54.685305+00:00", + "catalogUpdatedAt": "2026-09-21T23:54:41.767263+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-09-21T23:50:54.685305+00:00", + "generatedAt": "2026-09-21T23:54:41.767263+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6819,6 +6819,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-09-21T23:50:54.685305+00:00", + "taskTreeUpdatedAt": "2026-09-21T23:54:41.767263+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index 7c43c94479..3419664aff 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-09-21T23:49:31.238696+00:00", - "lastSyncTime": "2026-09-21T23:49:30.866198+00:00", + "generatedAt": "2026-09-21T23:54:31.127689+00:00", + "lastSyncTime": "2026-09-21T23:54:30.855927+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -3887,13 +3887,13 @@ "decisionSuccessRate": 0.0, "decisionTotal": 26, "failureBreakdown": { - "ambiguous_runtime": 9, + "ambiguous_runtime": 10, "framework_architecture_unsupported": 7, "memory_capacity": 5, "model_load": 2, "tokenizer_compatibility": 12 }, - "failureCount": 35, + "failureCount": 36, "failureRate": 1.0, "framework": "transformers", "pendingCount": 0, @@ -3903,8 +3903,8 @@ "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", - "total": 35, - "unresolvedFailureCount": 9 + "total": 36, + "unresolvedFailureCount": 10 }, "Iluvatar_bi-150|unknown|asr": { "attributableFailureCount": 0, @@ -5479,21 +5479,21 @@ "decisionSuccessRate": 0.0, "decisionTotal": 27, "failureBreakdown": { - "ambiguous_runtime": 61, + "ambiguous_runtime": 62, "framework_architecture_unsupported": 8, "memory_capacity": 5, "model_load": 2, "tokenizer_compatibility": 12 }, - "failureCount": 88, + "failureCount": 89, "failureRate": 1.0, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, - "total": 88, - "unresolvedFailureCount": 61 + "total": 89, + "unresolvedFailureCount": 62 }, "unknown": { "attributableFailureCount": 1860, @@ -5700,7 +5700,7 @@ "unresolvedFailureCount": 121 } }, - "generatedAt": "2026-09-21T23:49:31.228042+00:00", + "generatedAt": "2026-09-21T23:54:31.116699+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 99, @@ -5868,7 +5868,7 @@ "decisionSuccessRate": 0.1656, "decisionTotal": 900, "failureBreakdown": { - "ambiguous_runtime": 625, + "ambiguous_runtime": 626, "architecture_compatibility": 15, "backend_operator": 12, "context_length": 29, @@ -5883,15 +5883,15 @@ "日志缺失": 155, "验证失败": 30 }, - "failureCount": 1902, + "failureCount": 1903, "failureRate": 0.9274, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 21, "successCount": 149, "successRate": 0.0726, - "total": 2051, - "unresolvedFailureCount": 1130 + "total": 2052, + "unresolvedFailureCount": 1131 }, "Iluvatar_mrv-100": { "attributableFailureCount": 968, @@ -11517,6 +11517,29 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Iluvatar_bi-150|transformers|text-generation|gemma2|compressed-tensors": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "transformers", + "modelType": "gemma2", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "compressed-tensors", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Iluvatar_bi-150", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Iluvatar_bi-150|transformers|text-generation|gemma4_unified|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -18179,15 +18202,15 @@ "unresolvedFailureCount": 17 }, "Iluvatar_bi-150|transformers|text-generation": { - "attributableFailureCount": 15, - "consecutiveFailures": 15, + "attributableFailureCount": 14, + "consecutiveFailures": 14, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, - "decisionTotal": 15, + "decisionTotal": 14, "failureBreakdown": { - "ambiguous_runtime": 5, - "framework_architecture_unsupported": 6, + "ambiguous_runtime": 6, + "framework_architecture_unsupported": 5, "memory_capacity": 1, "tokenizer_compatibility": 8 }, @@ -18195,7 +18218,7 @@ "failureRate": 1.0, "framework": "transformers", "lastPlatformFailureAt": null, - "lastTerminalAt": "2026-09-21T22:33:35.352083+00:00", + "lastTerminalAt": "2026-09-21T23:54:30.855927+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, @@ -18204,7 +18227,7 @@ "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 20, - "unresolvedFailureCount": 5 + "unresolvedFailureCount": 6 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": { "attributableFailureCount": 3, @@ -19878,31 +19901,6 @@ "total": 1, "unresolvedFailureCount": 1 }, - "Cambricon_mlu-370-x8|vllm|text-generation|llama|none": { - "attributableFailureCount": 0, - "consecutiveFailures": 0, - "decisionFailureRate": 0.0, - "decisionSuccessRate": 0.0, - "decisionTotal": 0, - "failureBreakdown": { - "ambiguous_runtime": 1 - }, - "failureCount": 1, - "failureRate": 1.0, - "framework": "vllm", - "lastTerminalAt": "2026-09-21T04:51:55.164837+00:00", - "modelType": "llama", - "pendingCount": 0, - "pendingRate": 0.0, - "platformFailureCount": 0, - "quantizationMethod": "none", - "successCount": 0, - "successRate": 0.0, - "targetGpu": "Cambricon_mlu-370-x8", - "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 1 - }, "Cambricon_mlu-370-x8|vllm|text-generation|mistral3|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, @@ -20278,6 +20276,31 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Iluvatar_bi-150|transformers|text-generation|gemma2|compressed-tensors": { + "attributableFailureCount": 0, + "consecutiveFailures": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "transformers", + "lastTerminalAt": "2026-09-21T23:54:30.855927+00:00", + "modelType": "gemma2", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "compressed-tensors", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Iluvatar_bi-150", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Iluvatar_bi-150|transformers|text-generation|gemma4_unified|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, @@ -29505,6 +29528,30 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Iluvatar_bi-150|transformers|text-generation|gemma2|compressed-tensors|32": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "transformers", + "loadSizeLog2Bucket": 32, + "modelType": "gemma2", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "compressed-tensors", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Iluvatar_bi-150", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Iluvatar_bi-150|transformers|text-generation|gemma4_unified|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -38693,15 +38740,15 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 16443, - "totalRecords": 16637, + "terminalRecords": 16444, + "totalRecords": 16638, "totals": { "attributableFailureCount": 5925, "decisionFailureRate": 0.8619, "decisionSuccessRate": 0.1381, "decisionTotal": 6874, "failureBreakdown": { - "ambiguous_runtime": 4056, + "ambiguous_runtime": 4057, "architecture_compatibility": 212, "attention_backend": 1, "backend_operator": 105, @@ -38717,31 +38764,31 @@ "日志缺失": 719, "验证失败": 674 }, - "failureCount": 15494, + "failureCount": 15495, "failureRate": 0.9423, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 925, "successCount": 949, "successRate": 0.0577, - "total": 16443, - "unresolvedFailureCount": 8644 + "total": 16444, + "unresolvedFailureCount": 8645 }, "warnings": [ "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", "组合 Iluvatar_bi-150|vllm|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 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 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", @@ -38781,6 +38828,6 @@ ] }, "storageMode": "decision_state_only", - "summarizedRecords": 16637, + "summarizedRecords": 16638, "version": 1 } diff --git a/.modelhub_state/recent_outcomes.jsonl b/.modelhub_state/recent_outcomes.jsonl index 678d2fbce9..1046cc83c5 100644 --- a/.modelhub_state/recent_outcomes.jsonl +++ b/.modelhub_state/recent_outcomes.jsonl @@ -1,6 +1,7 @@ {"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": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-21T16:50:30.559368+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T16:39:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610379", "taskType": "text-generation", "verifyResult": -1} {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-21T16:50:30.559274+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T16:37:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4332638", "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": "", "lastSyncTime": "2026-09-21T15:58:04.749250+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T15:57:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4332444", "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", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-21T23:54:30.855927+00:00", "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615496, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615496}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T15:40:17.175718+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5003113", "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": "", "lastSyncTime": "2026-09-21T15:14:12.874625+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T15:11:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610383", "taskType": "text-generation", "verifyResult": -1} {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-21T15:02:24.876304+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T14:47:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4586965", "taskType": "text-generation", "verifyResult": -1} {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-21T14:32:55.759858+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T14:23:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4584252", "taskType": "text-generation", "verifyResult": -1} @@ -297,4 +298,3 @@ {"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": ["zaya"], "framework": "vllm", "lastSyncTime": "2026-09-20T17:09:45.266103+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463197, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463197}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.346171+00:00", "targetGpu": "Biren_166m", "taskId": "4970445", "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", "lastSyncTime": "2026-09-21T04:51:55.164906+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109841981, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109841981}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.344449+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970441", "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", "lastSyncTime": "2026-09-20T22:27:36.960842+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.342540+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970435", "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", "lastSyncTime": "2026-09-21T04:51:55.164837+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426233716, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426233716}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.341085+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970438", "taskType": "text-generation", "verifyResult": -1} diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index b26c1739fb..3929915901 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2341,6 +2341,7 @@ {"batchId": "94374b3b2b264c97bef257444587acaa", "completedAt": "2026-09-21T23:46:26.029171+00:00", "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configSource": "modelhub_live", "createdAt": "2026-09-21T23:46:23.532484+00:00", "framework": "vllm", "intentId": "d7e170e8db2a4d5b907bf392562fd3ce", "lastModified": "2026-09-21T20:13:14+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-64-v2", "reason": null, "reconciledAt": "2026-09-21T23:53:15.619551+00:00", "repoId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5009122", "taskType": "text-generation"} {"batchId": "8e56ee5e993148539afedf340419216a", "completedAt": "2026-09-21T23:50:56.286851+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-21T23:50:55.193839+00:00", "framework": "vllm-mlu", "intentId": "558c0744988944c2bc9c537fb43f8e88", "lastModified": "2026-09-21T18:34:41+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "reason": null, "reconciledAt": "2026-09-21T23:53:15.617408+00:00", "repoId": "nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5009164", "taskType": "text-generation"} {"batchId": "8e56ee5e993148539afedf340419216a", "completedAt": "2026-09-21T23:50:56.286873+00:00", "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configSource": "modelhub_live", "createdAt": "2026-09-21T23:50:55.193948+00:00", "framework": "vllm", "intentId": "c81bca32e7b04b129042e7b5d0fcabab", "lastModified": "2026-09-21T18:42:39+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "reason": null, "reconciledAt": "2026-09-21T23:53:15.619295+00:00", "repoId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5009165", "taskType": "text-generation"} +{"batchId": "42d9d4c9dbe642b2b8bcb041a4502552", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-21T23:54:42.085677+00:00", "framework": "vllm", "intentId": "1ed5b82e591e4822b000359f429c22a2", "lastModified": "2026-09-21T18:43:38+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g2-v2_C", "repoId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"} {"batchId": "24082fb4e4bc48b988e1e4deac30068b", "completedAt": "2026-09-21T20:36:17.828196+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T20:36:00.461127+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7ef98d8672514b6cb8bcf83850090ffe", "repoId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} {"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691781+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.137064+00:00", "framework": "vllm", "intentId": "64b834dd640742a0b32535bde02b94ad", "repoId": "CohereLabs/tiny-aya-base-32K", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691779+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.137007+00:00", "framework": "vllm", "intentId": "d6229ef4ac9942078baa35e312133d9d", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index 2111dadcf7..6fffd1cdc9 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.20.2", "checksums": { ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1", - ".modelhub_state/architecture_compatibility_blacklist.json": "2e25f18eb3cd0ed26b75755145cc1902f2d215c6cb3b7c6ae9ed670c84f27b3c", + ".modelhub_state/architecture_compatibility_blacklist.json": "872ea63db6c3c8a1c74fbf40f9eaf4b8a3d114af64395da41b71152a30a8773f", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "6f0ce4dd7db0c479076326a694974797896731b96c979e2f48886b3b7334325d", - ".modelhub_state/official_capabilities.json": "bd4db4ae3be3723487562dff38dbc63645c2c2b5493449f6b01dc157c5749f9b", - ".modelhub_state/outcome_checkpoint.json": "86c6dbb6328e22eec9b3583c6188536151a67e50008a15fc6243ca3386ca233e", + ".modelhub_state/market_intelligence.json": "faa714fcd87e0a080201ce239b53208113580882a7dcd0705f6d3ab2d73cd9eb", + ".modelhub_state/official_capabilities.json": "904ec8d5e3bcd7d2f619458d2bce0c5550315f3b908aa191ebff903b8c239b66", + ".modelhub_state/outcome_checkpoint.json": "02051da0c76a25789dba8da19bc7890c766cde79d33305d300308123c93b6e18", ".modelhub_state/queue_cleanup_latest.json": "14282fb49e9aa62e07b6a07250bcf51916a4d783e09664c80d1fa965b4d48615", - ".modelhub_state/recent_outcomes.jsonl": "2e158008b8f4a3f2ef56cf1aa7c85c596ab2f546fbcbf0f909cfe4b7798db031", + ".modelhub_state/recent_outcomes.jsonl": "87f6a308bd6e4b3dfa57c36ba83c72646bc3f33362fe7046df3cd7305e215c4b", ".modelhub_state/recovery_active_tasks.jsonl": "53ccb84fa3ebce3e13134a01902b12de7b2dfcfbf4c097ac099c4c43db596f3d", - ".modelhub_state/recovery_intents.jsonl": "bcaae18ceacd91f57f3ab42b76dde8738ad3637fe0bea296d8e7f476610603be", + ".modelhub_state/recovery_intents.jsonl": "e5ec27416987bbceb824898ed6ad3723d98feb21e34553a2275a0a4bd04f18ac", ".modelhub_state/routing_intelligence.json": "e308eb3010388f2101ddddd70dfc5bcef8dee96dde639992c8c80c509234a007", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", "ledger/submissions.jsonl": "983baf06456ad0b2a54c19405e1da7bbf8e64a5f569c038fb36804163c318597", - "outcomes/submissions.jsonl": "54f8c77e87b48897a05c1b29b126dbefc64fc93679c22d6da7bf19a1b584c481" + "outcomes/submissions.jsonl": "f267f97775ae7d881f0aa8dbac2c1b38f44e3aec9b5422e15d177df4655fff85" }, - "generation": 11929, - "phase": "cycle_no_slots", + "generation": 11930, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-09-21T23:53:15.796912+00:00", + "updatedAt": "2026-09-21T23:54:42.254445+00:00", "writerId": "8b35139af6674067a339a670222d4b67" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 902944e554..0161c9b7cc 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -1004,7 +1004,6 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T22:48:12.757454+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T14:48:11.805114+00:00", "targetGpu": "Biren_166m", "taskId": "5002503", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T22:48:12.757482+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T14:48:11.795290+00:00", "targetGpu": "Biren_166m", "taskId": "5002497", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T23:38:02.064803+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a8", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4385522016, "estimatedRequiredGiB": 4.926, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 4407346443, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4407346443}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T15:37:01.383959+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5003018", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "transformers", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-2b-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6746735136, "estimatedRequiredGiB": 7.565, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 6768615496, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6768615496}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T15:40:17.175718+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5003113", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-21T23:47:09.753970+00:00", "modelId": "RedHatAI/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7855165704, "estimatedRequiredGiB": 8.783, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7858540940, "modelscopeLicense": "other", "modelscopeParams": 7400416256, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7858540940}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T15:43:55.761793+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5003178", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-21T23:47:09.753948+00:00", "modelId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3SmallForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8630134648, "estimatedRequiredGiB": 9.647, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3small", "modelscopeFileSize": 8632060880, "modelscopeLicense": "mit", "modelscopeParams": 7803314176, "modelscopeTags": ["license:mit", "model_type:phi3small", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8632060880}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T15:44:10.499526+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5003181", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T23:49:30.866162+00:00", "modelId": "aisingapore/SEA-LION-v1-7B", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008115847, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008115847}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T15:46:08.955762+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5003203", "taskType": "text-generation", "verifyResult": null}