diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 041eda5d00..8dea8a4d2b 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -546,7 +546,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-26T02:01:19.842655+00:00", + "generatedAt": "2026-10-26T02:03:00.516497+00:00", "summary": { "activeBlockCount": 27, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index 17211cedb7..487a39595e 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-26T02:01:19.962609+00:00", + "generatedAt": "2026-10-26T02:03:00.636762+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index 155472bd4b..8c2e01512f 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-26T02:01:19.962609+00:00", + "catalogUpdatedAt": "2026-10-26T02:03:00.636762+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-26T02:01:21.748224+00:00", + "generatedAt": "2026-10-26T02:03:01.245036+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -1565,6 +1565,19 @@ ], "updatedAt": "2026-10-26T01:51:14.893950+00:00" }, + "https://modelscope.cn/models/SargeDev/Solar-Decision-JEV-27B-GGUF|2026-10-23T13:33:04+00:00|Iluvatar_bi-150": { + "taskTypes": [ + "asr", + "question_answering", + "reinforcement_learning", + "text-generation", + "text-to-image-generation", + "text_classification", + "vision_classification", + "visual-multi-modal" + ], + "updatedAt": "2026-10-26T02:03:01.143999+00:00" + }, "https://modelscope.cn/models/SargeDev/Solar-Decision-JEV-27B-GGUF|2026-10-23T13:33:04+00:00|Kunlunxin_p-800": { "taskTypes": [ "text-generation" @@ -1577,7 +1590,7 @@ "text-generation", "visual-multi-modal" ], - "updatedAt": "2026-10-26T01:40:56.397831+00:00" + "updatedAt": "2026-10-26T02:03:01.245036+00:00" }, "https://modelscope.cn/models/SargeDev/Solar-Decision-JEV-27B-GGUF|2026-10-23T13:33:04+00:00|Vastai_va16": { "taskTypes": [ @@ -1585,6 +1598,14 @@ ], "updatedAt": "2026-10-26T01:51:14.980606+00:00" }, + "https://modelscope.cn/models/SargeDev/Solar-Decision-JEV-27B-GGUF|2026-10-23T13:33:04+00:00|hygon_k100-ai": { + "taskTypes": [ + "text-generation", + "text-to-image-generation", + "visual-multi-modal" + ], + "updatedAt": "2026-10-26T02:03:01.209592+00:00" + }, "https://modelscope.cn/models/SargeDev/Solar-JEV-27B-GGUF|2026-10-23T13:53:07+00:00|Ascend_910-b3": { "taskTypes": [ "text-generation", @@ -1648,48 +1669,37 @@ ], "updatedAt": "2026-10-26T01:51:15.113171+00:00" }, - "https://modelscope.cn/models/SargeDev/Solar-JEV-27B-R32-GGUF|2026-10-23T13:11:10+00:00|Ascend_910-b4": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-10-26T01:40:56.373296+00:00" - }, "https://modelscope.cn/models/SargeDev/Solar-JEV-27B-R32-GGUF|2026-10-23T13:11:10+00:00|Biren_166m": { "taskTypes": [ "text-generation" ], "updatedAt": "2026-10-26T01:51:15.079164+00:00" }, + "https://modelscope.cn/models/SargeDev/Solar-JEV-27B-R32-GGUF|2026-10-23T13:11:10+00:00|Iluvatar_bi-150": { + "taskTypes": [ + "asr", + "question_answering", + "reinforcement_learning", + "text-generation", + "text-to-image-generation", + "text_classification", + "vision_classification", + "visual-multi-modal" + ], + "updatedAt": "2026-10-26T02:03:01.149765+00:00" + }, "https://modelscope.cn/models/SargeDev/Solar-JEV-27B-R32-GGUF|2026-10-23T13:11:10+00:00|Kunlunxin_p-800": { "taskTypes": [ "text-generation" ], "updatedAt": "2026-10-26T01:51:15.031195+00:00" }, - "https://modelscope.cn/models/SargeDev/Solar-JEV-27B-R32-GGUF|2026-10-23T13:11:10+00:00|MetaX_c-500": { - "taskTypes": [ - "feature_emb", - "text-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-10-26T01:40:56.446204+00:00" - }, "https://modelscope.cn/models/SargeDev/Solar-JEV-27B-R32-GGUF|2026-10-23T13:11:10+00:00|Vastai_va16": { "taskTypes": [ "text-generation" ], "updatedAt": "2026-10-26T01:51:15.173722+00:00" }, - "https://modelscope.cn/models/SargeDev/Solar-JEV-27B-R32-GGUF|2026-10-23T13:11:10+00:00|hygon_k100-ai": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-10-26T01:40:56.410452+00:00" - }, "https://modelscope.cn/models/XingChen-AGI/Xing4.0-29B-A4B-GGUF|2026-10-26T01:24:52+00:00|Ascend_910-b3": { "taskTypes": [ "text-generation", @@ -6811,6 +6821,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-26T02:01:19.962609+00:00", + "taskTreeUpdatedAt": "2026-10-26T02:03:00.636762+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index 4f20255a95..0fa041fdde 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-26T01:22:17.047770+00:00", - "lastSyncTime": "2026-10-26T01:22:16.738778+00:00", + "generatedAt": "2026-10-26T02:03:00.408344+00:00", + "lastSyncTime": "2026-10-26T02:03:00.157922+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -2210,10 +2210,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 204, + "ambiguous_runtime": 205, "参数/模板问题": 16 }, - "failureCount": 220, + "failureCount": 221, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "pendingCount": 0, @@ -2223,8 +2223,8 @@ "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", - "total": 220, - "unresolvedFailureCount": 220 + "total": 221, + "unresolvedFailureCount": 221 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": { "attributableFailureCount": 61, @@ -3400,7 +3400,7 @@ "decisionSuccessRate": 0.0348, "decisionTotal": 201, "failureBreakdown": { - "ambiguous_runtime": 452, + "ambiguous_runtime": 453, "backend_operator": 11, "framework_architecture_unsupported": 59, "memory_capacity": 11, @@ -3409,15 +3409,15 @@ "tokenizer_compatibility": 100, "参数/模板问题": 50 }, - "failureCount": 732, + "failureCount": 733, "failureRate": 0.9905, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 36, "successCount": 7, "successRate": 0.0095, - "total": 739, - "unresolvedFailureCount": 502 + "total": 740, + "unresolvedFailureCount": 503 }, "vllm_tokenizer_patch": { "attributableFailureCount": 181, @@ -3448,7 +3448,7 @@ "unresolvedFailureCount": 366 } }, - "generatedAt": "2026-10-26T01:22:17.033757+00:00", + "generatedAt": "2026-10-26T02:03:00.388412+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 134, @@ -3681,7 +3681,7 @@ "decisionSuccessRate": 0.066, "decisionTotal": 106, "failureBreakdown": { - "ambiguous_runtime": 293, + "ambiguous_runtime": 294, "backend_operator": 23, "framework_architecture_unsupported": 37, "memory_capacity": 3, @@ -3694,15 +3694,15 @@ "日志缺失": 1, "验证失败": 23 }, - "failureCount": 477, - "failureRate": 0.9855, + "failureCount": 478, + "failureRate": 0.9856, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 7, - "successRate": 0.0145, - "total": 484, - "unresolvedFailureCount": 377 + "successRate": 0.0144, + "total": 485, + "unresolvedFailureCount": 378 }, "Kunlunxin_r-200-8f": { "attributableFailureCount": 0, @@ -17567,6 +17567,29 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|bananaall|none": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_fix_tokenizer", + "modelType": "bananaall", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Kunlunxin_p-800", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|cagliostro|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, @@ -26969,10 +26992,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 12, + "ambiguous_runtime": 13, "参数/模板问题": 5 }, - "failureCount": 17, + "failureCount": 18, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastPlatformFailureAt": null, @@ -26984,8 +27007,8 @@ "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", - "total": 17, - "unresolvedFailureCount": 17 + "total": 18, + "unresolvedFailureCount": 18 }, "MetaX_c-500|unknown|text-generation": { "attributableFailureCount": 0, @@ -27252,9 +27275,9 @@ "decisionTotal": 2, "failureBreakdown": { "model_load": 2, - "参数/模板问题": 6 + "参数/模板问题": 5 }, - "failureCount": 8, + "failureCount": 7, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "lastPlatformFailureAt": null, @@ -27266,8 +27289,8 @@ "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", - "total": 8, - "unresolvedFailureCount": 6 + "total": 7, + "unresolvedFailureCount": 5 }, "hygon_k100-ai|vllm|text-generation": { "attributableFailureCount": 1, @@ -28527,6 +28550,31 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|bananaall|none": { + "attributableFailureCount": 0, + "consecutiveFailures": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_fix_tokenizer", + "lastTerminalAt": "2026-10-26T02:03:00.157922+00:00", + "modelType": "bananaall", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Kunlunxin_p-800", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|cagliostro|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -29361,10 +29409,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { - "model_load": 1, - "参数/模板问题": 1 + "model_load": 1 }, - "failureCount": 2, + "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "lastTerminalAt": "2026-10-25T06:30:02.980564+00:00", @@ -29377,8 +29424,8 @@ "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", - "total": 2, - "unresolvedFailureCount": 1 + "total": 1, + "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|gemma4|compressed-tensors": { "attributableFailureCount": 0, @@ -50287,6 +50334,30 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|bananaall|none|12": { + "attributableFailureCount": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_fix_tokenizer", + "loadSizeLog2Bucket": 12, + "modelType": "bananaall", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "none", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Kunlunxin_p-800", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|cagliostro|none|28": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, @@ -64087,15 +64158,15 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 18114, - "totalRecords": 18658, + "terminalRecords": 18115, + "totalRecords": 18659, "totals": { "attributableFailureCount": 6389, "decisionFailureRate": 0.8663, "decisionSuccessRate": 0.1337, "decisionTotal": 7375, "failureBreakdown": { - "ambiguous_runtime": 4706, + "ambiguous_runtime": 4707, "architecture_compatibility": 212, "attention_backend": 3, "backend_operator": 137, @@ -64111,15 +64182,15 @@ "日志缺失": 719, "验证失败": 676 }, - "failureCount": 17128, + "failureCount": 17129, "failureRate": 0.9456, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 972, "successCount": 986, "successRate": 0.0544, - "total": 18114, - "unresolvedFailureCount": 9767 + "total": 18115, + "unresolvedFailureCount": 9768 }, "warnings": [ "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", @@ -64171,17 +64242,17 @@ "组合 Biren_166m|unknown|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|vllm-customized|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 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 MetaX_c-500|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 MetaX_c-500|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 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。", "组合 Vastai_va16|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 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 Mthreads_s4000|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 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-x8|vllm-mlu|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": 18658, + "summarizedRecords": 18659, "version": 1 } diff --git a/.modelhub_state/recent_outcomes.jsonl b/.modelhub_state/recent_outcomes.jsonl index bfcb6c9122..229dc2e818 100644 --- a/.modelhub_state/recent_outcomes.jsonl +++ b/.modelhub_state/recent_outcomes.jsonl @@ -144,6 +144,7 @@ {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-10T09:26:43.784435+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T20:21:22.460114+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5361078", "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_fix_tokenizer", "lastSyncTime": "2026-10-21T02:39:23.457372+00:00", "modelId": "ProCreations/BetterWright-K2-Horizon-7B-Uno", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19395158128, "estimatedRequiredGiB": 21.699, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-10-07T19:46:36.063213+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5360850", "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": "2026-10-25T04:12:56.440398+00:00", "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "failed", "status": "success", "submitTime": "2026-10-07T19:42:09.894375+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5360601", "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": "2026-10-26T02:03:00.157922+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": 36069420, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "failed", "status": "success", "submitTime": "2026-10-07T19:40:33.477836+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5360515", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-24T15:31:00.652172+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077974096, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11077974096}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T19:40:33.455736+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5360516", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557028+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T19:30:30.071008+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360316", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557151+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T19:30:30.057671+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360317", "taskType": "text-generation", "verifyResult": null} @@ -297,4 +298,3 @@ {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164611+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:46.356016+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320886", "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-patch-tokenizer", "lastSyncTime": "2026-10-07T13:20:53.257507+00:00", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": "2026-10-06T09:35:46.170338+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320879", "taskType": "text-generation", "verifyResult": -1} {"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-patch-tokenizer", "lastSyncTime": "2026-10-25T06:30:02.980564+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4749242120, "estimatedRequiredGiB": 5.332, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 4771310100, "modelscopeLicense": "apache-2.0", "modelscopeParams": 641597440, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4771310100}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:35:46.168164+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320881", "taskType": "text-generation", "verifyResult": -1} -{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-24T18:37:46.581732+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8122473440, "estimatedRequiredGiB": 9.103, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 8145035684, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1605333250, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8145035684}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:46.165208+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320880", "taskType": "text-generation", "verifyResult": null} diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 8062c1837c..c1b76fa5b5 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3887,6 +3887,18 @@ {"batchId": "39db3005c8f04577b15cb0dc1617a704", "completedAt": "2026-10-25T23:11:08.828661+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-25T23:11:05.685574+00:00", "framework": "vllm_fix_tokenizer", "intentId": "93ce57f9e5ba449b9a40439a6eb35841", "lastModified": "2026-10-21T16:18:34+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-30B-A3B-Thinking-2507-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-26T02:01:28.297765+00:00", "repoId": "cyankiwi/Qwen3-30B-A3B-Thinking-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5791777", "taskType": "text-generation"} {"batchId": "5605ea6fd3c84e608741fad3fc948ba9", "completedAt": "2026-10-26T00:29:09.400428+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T00:28:55.374763+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8b7015b86e2a4a539c8170b8a5936477", "lastModified": "2026-10-21T15:32:58+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/OmniCoder-9B-AWQ-BF16-INT4", "reason": null, "reconciledAt": "2026-10-26T02:01:28.300448+00:00", "repoId": "cyankiwi/OmniCoder-9B-AWQ-BF16-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5793176", "taskType": "text-generation"} {"batchId": "ab19adb3f44947b892d37aabd450908b", "completedAt": "2026-10-26T00:31:55.372589+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T00:31:52.250065+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f20ddb33693c40259d65106b1bd16ac0", "lastModified": "2026-10-21T19:08:45+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-5bit", "reason": null, "reconciledAt": "2026-10-26T02:01:28.297116+00:00", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5793229", "taskType": "text-generation"} +{"batchId": "ad2791fe80504084bac83363907ad2ab", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-26T02:03:02.278099+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2d360248b39348b59b685ba81227ebe6", "lastModified": "2026-10-21T16:38:25+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"} +{"batchId": "ad2791fe80504084bac83363907ad2ab", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T02:03:02.278216+00:00", "framework": "vllm_fix_tokenizer", "intentId": "547638cfa8524ce4b8eb98a478632bd1", "lastModified": "2026-10-21T16:56:28+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/GLM-4.7-Flash-AWQ-4bit", "repoId": "cyankiwi/GLM-4.7-Flash-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "ad2791fe80504084bac83363907ad2ab", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T02:03:02.278314+00:00", "framework": "vllm_fix_tokenizer", "intentId": "513151bbb4394472b26b3bacc30c17e4", "lastModified": "2026-10-25T14:40:45+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": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "ad2791fe80504084bac83363907ad2ab", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T02:03:02.278361+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6801c75c4a9e49979b2e9d9541587692", "lastModified": "2026-10-25T13:17:58+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": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "ad2791fe80504084bac83363907ad2ab", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T02:03:02.278404+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8da706c7df764fc18b4145cc75231f31", "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": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "ad2791fe80504084bac83363907ad2ab", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T02:03:02.278448+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c1ced97c826d4c84b0a4f7c09611ea4b", "lastModified": "2026-10-21T16:19:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "ad2791fe80504084bac83363907ad2ab", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T02:03:02.278492+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1a67348995fb4d6aa6103c3005325557", "lastModified": "2026-10-21T16:38:24+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-4B-Instruct-2507-AWQ-8bit", "repoId": "cyankiwi/Qwen3-4B-Instruct-2507-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "ad2791fe80504084bac83363907ad2ab", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T02:03:02.278537+00:00", "framework": "vllm_fix_tokenizer", "intentId": "433a2f0c91fe4664b3cf712518aabbb1", "lastModified": "2026-10-21T17:19:00+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Hermes-4.3-36B-AWQ-4bit", "repoId": "cyankiwi/Hermes-4.3-36B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "ad2791fe80504084bac83363907ad2ab", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T02:03:02.278581+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a8bfa158b2a34135ba6d7d5f9ee59ff6", "lastModified": "2026-10-25T15:32:31+00:00", "modelAddress": "https://modelscope.cn/models/IFM/Jais-3-7B-FP8", "repoId": "IFM/Jais-3-7B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "ad2791fe80504084bac83363907ad2ab", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T02:03:02.278624+00:00", "framework": "vllm_fix_tokenizer", "intentId": "70a5644679494374abf600c2c9439e9f", "lastModified": "2026-10-21T17:12:48+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-4B-Thinking-2507-AWQ-4bit", "repoId": "cyankiwi/Qwen3-4B-Thinking-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "ad2791fe80504084bac83363907ad2ab", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T02:03:02.278668+00:00", "framework": "vllm_fix_tokenizer", "intentId": "62e720c6d7cf4285b667776300c1ef41", "lastModified": "2026-10-21T19:08:38+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-4bit", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} +{"batchId": "ad2791fe80504084bac83363907ad2ab", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T02:03:02.278712+00:00", "framework": "vllm_fix_tokenizer", "intentId": "42425d45d1364d949c4a85e4f1a5ee5e", "lastModified": "2026-10-21T16:18:09+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Orchestrator-8B-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Orchestrator-8B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Vastai_va16", "taskType": "text-generation"} {"batchId": "8a083e2975ec4aefb80a50122f8e7dd8", "completedAt": "2026-10-26T02:01:26.041569+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T02:01:23.496519+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6e5d84f5ca1948a5bc7988b39f1c7481", "repoId": "cyankiwi/Nemotron-Orchestrator-8B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "8a083e2975ec4aefb80a50122f8e7dd8", "completedAt": "2026-10-26T02:01:26.041566+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T02:01:23.496476+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0182fd118024494ba5fde1fb5620ff29", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} {"batchId": "8a083e2975ec4aefb80a50122f8e7dd8", "completedAt": "2026-10-26T02:01:26.041563+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-10-26T02:01:23.496432+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b99b44e5d3e4452ab7239b0709c298c8", "repoId": "cyankiwi/Qwen3-4B-Thinking-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Vastai_va16", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index 9fe7797a6a..b1cfd1f8f2 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "5ac9d0bab549d188271a45c116d434645b88442ba7bdcc94f99b33de6b12736d", - ".modelhub_state/architecture_compatibility_blacklist.json": "9d9c032dc1e4b05f2e4b164def49af1dae6ff0fe49cddb5d382d41fb14529396", + ".modelhub_state/architecture_compatibility_blacklist.json": "0849707b0f14a1c04b4fb9f07718803dfb6d0abc6bcff2d7d0bbd4313b932439", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "c9fc31c7e4e84eea47a4be9cec7f3057b1f702516cd30646119f1c8ea1aec762", - ".modelhub_state/official_capabilities.json": "a297fc871a4420c9e75eb431a14d975b16f9771b08d09eb462c04aca0f10e270", - ".modelhub_state/outcome_checkpoint.json": "78f0c65540fbf21fe1ae8bad7a2798d66a771b4e7f2b1accda35a49c56d10632", + ".modelhub_state/market_intelligence.json": "2b38b2bc3726ad2683a602eab03c43e26950506078ccdb5b27db6f53634ac3d3", + ".modelhub_state/official_capabilities.json": "08e5e62753b85bbc66ebdcf34975571f873c4328760c4810d11cac4b41e9405a", + ".modelhub_state/outcome_checkpoint.json": "ff797dbca8727365cf1623d4a0b27feed6f8253afebf7eab299081be5386a6f5", ".modelhub_state/queue_cleanup_latest.json": "afa5b060b35e56131a96b0b6445e0224c7f659d33e025194ba1d935844257d77", - ".modelhub_state/recent_outcomes.jsonl": "de78df1dcf7a50c62c09f73e937186eea5c4a11e1cfe34c2d680a3fc99d6eddc", + ".modelhub_state/recent_outcomes.jsonl": "1ac1cee7b5eb9bf9cdec2f467bfb9785b758992928be2dfbd5781ca23737a23f", ".modelhub_state/recovery_active_tasks.jsonl": "59f098262f3987be0b7f227d26968373ccc5ee67fa000738bec1bb086016b06d", - ".modelhub_state/recovery_intents.jsonl": "ca167214895ab55b3069b8e215255a713f5eec70b581f1fcc933db12d3492a85", + ".modelhub_state/recovery_intents.jsonl": "806ea5ee5f37badabed2750bc1f0b65dd996a938d6e72bbbe5691bf33a2d4f0d", ".modelhub_state/routing_intelligence.json": "7496564a79e427ec194badff406ba849b3fe111f86b5b6b436a6c44e22811bd3", ".modelhub_state/submission_exclusions.jsonl": "3db506f4d37bc78a9069d6022969e3718fa3eb1dad129907c99f63d5a7300ba1", ".modelhub_state/worker_crashes.jsonl": "2a418db914481d815151923dc46f4e4ad1154d9195fad06fee6275702f33c0b9", "ledger/submissions.jsonl": "fb62c95c52c7eae37fe9d7039285e4107711498f221c13596d7806c22d9e2d84", - "outcomes/submissions.jsonl": "adc78ffefb70be4c1d370f09d3284c1a3e85a49505ac737a8c7ae4f68ebc3e43" + "outcomes/submissions.jsonl": "c8aa41afdc1b10b3261e169945e8e80e6dde2b8ebae483b7b7b19e4fcc748446" }, - "generation": 37616, - "phase": "cycle", + "generation": 37617, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-26T02:01:28.525112+00:00", + "updatedAt": "2026-10-26T02:03:02.469403+00:00", "writerId": "dffce16061d848e398e5b5b22f649ccc" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 33b15f195a..a55dffefcf 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -505,7 +505,6 @@ {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T03:44:24.154826+00:00", "modelId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "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": 7120900461, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1915564544, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:qwen3.5", "custom_tag:reasoning", "custom_tag:long-context", "custom_tag:function-calling", "custom_tag:tool-use", "custom_tag:agentic", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7120900461}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T19:30:29.962927+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360314", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T03:44:24.154936+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242696, "estimatedRequiredGiB": 2.46, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2201523288, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2201523288}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T19:40:33.532208+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5360509", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T03:44:24.154768+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033920112, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199304207, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199304207}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T19:40:33.474378+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5360511", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T03:44:24.154685+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": 36069420, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T19:40:33.477836+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5360515", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T03:44:24.154715+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1932905544, "estimatedRequiredGiB": 2.313, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2070028245, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2070028245}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T19:40:33.529054+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5360512", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T03:44:24.154676+00:00", "modelId": "NovelAI/clio-v1-legacy", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6358779576, "estimatedRequiredGiB": 27.418, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 24533499859, "modelscopeLicense": "gpl-2.0", "modelscopeParams": 3043786240, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24533499859}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T19:40:33.458312+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5360507", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T03:44:24.154833+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033754200, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199119539, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199119539}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T19:40:33.530333+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5360513", "taskType": "text-generation", "verifyResult": null} @@ -1085,7 +1084,7 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-26T00:02:37.269992+00:00", "modelId": "ychy7001/Qwen3.6-35B-A3B-W4A8-SSZ-MTP-310P", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24604826824, "estimatedRequiredGiB": 27.524, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 24628378073, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20349011824, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:ascend", "custom_tag:ascend310p", "custom_tag:w4a8", "custom_tag:mtp", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24628378073}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T16:01:21.336737+00:00", "targetGpu": "Vastai_va16", "taskId": "5785610", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-26T00:02:37.269967+00:00", "modelId": "cyankiwi/DASD-4B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3600063736, "estimatedRequiredGiB": 4.041, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 3615964391, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3615964391}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T16:02:30.573113+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5785631", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-26T01:25:06.540487+00:00", "modelId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18094507352, "estimatedRequiredGiB": 20.246, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 18115815143, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 18115815143}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T17:23:32.266960+00:00", "targetGpu": "Vastai_va16", "taskId": "5786730", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/DASD-4B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5416721872, "estimatedRequiredGiB": 6.072, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 5432701212, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5432701212}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T18:02:29.661531+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5787259", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-26T02:03:00.157892+00:00", "modelId": "cyankiwi/DASD-4B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5416721872, "estimatedRequiredGiB": 6.072, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 5432701212, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4411424256, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5432701212}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-25T18:02:29.661531+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5787259", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9261250624, "estimatedRequiredGiB": 10.359, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm", "modelscopeFileSize": 9269343620, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8185253888, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:agent"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9269343620}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T18:53:19.459268+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5788011", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6691066608, "estimatedRequiredGiB": 7.498, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 6709196808, "modelscopeLicense": "other", "modelscopeParams": 2381547248, "modelscopeTags": ["license:other", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6709196808}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T19:02:18.636734+00:00", "targetGpu": "Vastai_va16", "taskId": "5788201", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/Hermes-4-14B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17150429576, "estimatedRequiredGiB": 19.185, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 17166417170, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14768307200, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:Qwen-3-14B", "custom_tag:instruct", "custom_tag:finetune", "custom_tag:reasoning", "custom_tag:hybrid-mode", "custom_tag:chatml", "custom_tag:function calling", "custom_tag:tool use", "custom_tag:json mode", "custom_tag:structured outputs", "custom_tag:atropos", "custom_tag:dataforge", "custom_tag:long context", "custom_tag:roleplaying", "custom_tag:chat"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17166417170}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-25T19:18:03.733127+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5788454", "taskType": "text-generation", "verifyResult": null}