From 82a6d852d8927cb8c01c023389511b1c1ed58485 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Sat, 24 Oct 2026 23:18:42 +0000 Subject: [PATCH] state: generation 34889 (intent) --- .../architecture_compatibility_blacklist.json | 2 +- .modelhub_state/market_intelligence.json | 2 +- .modelhub_state/official_capabilities.json | 6 +- .modelhub_state/outcome_checkpoint.json | 118 +++++++----------- .modelhub_state/recent_outcomes.jsonl | 2 +- .modelhub_state/recovery_intents.jsonl | 12 ++ manifest.json | 20 +-- outcomes/submissions.jsonl | 3 +- 8 files changed, 75 insertions(+), 90 deletions(-) diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 1cb3fdcf3a..70bb467cfe 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -483,7 +483,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-24T23:17:02.537012+00:00", + "generatedAt": "2026-10-24T23:18:41.032241+00:00", "summary": { "activeBlockCount": 24, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index dc965d5a6f..3088928d13 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -452,7 +452,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-24T23:17:02.663333+00:00", + "generatedAt": "2026-10-24T23:18:41.156697+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index baf93dc3cb..723a718e88 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-24T23:17:02.663333+00:00", + "catalogUpdatedAt": "2026-10-24T23:18:41.156697+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-24T23:17:02.663333+00:00", + "generatedAt": "2026-10-24T23:18:41.156697+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6708,6 +6708,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-24T23:17:02.663333+00:00", + "taskTreeUpdatedAt": "2026-10-24T23:18:41.156697+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index 25a5a7e0aa..032085d3dc 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-24T22:58:36.048626+00:00", - "lastSyncTime": "2026-10-24T22:58:35.840735+00:00", + "generatedAt": "2026-10-24T23:18:40.928780+00:00", + "lastSyncTime": "2026-10-24T23:18:40.667328+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -1752,7 +1752,7 @@ "decisionSuccessRate": 0.2533, "decisionTotal": 75, "failureBreakdown": { - "ambiguous_runtime": 36, + "ambiguous_runtime": 37, "backend_operator": 6, "framework_architecture_unsupported": 31, "memory_capacity": 1, @@ -1760,18 +1760,18 @@ "runtime_memory": 10, "参数/模板问题": 27 }, - "failureCount": 119, - "failureRate": 0.8623, + "failureCount": 120, + "failureRate": 0.8633, "framework": "vllm_0_17_0_corex_4_4_0", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 19, - "successRate": 0.1377, + "successRate": 0.1367, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", - "total": 138, - "unresolvedFailureCount": 63 + "total": 139, + "unresolvedFailureCount": 64 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 9, @@ -3312,7 +3312,7 @@ "decisionSuccessRate": 0.2533, "decisionTotal": 75, "failureBreakdown": { - "ambiguous_runtime": 36, + "ambiguous_runtime": 37, "backend_operator": 6, "framework_architecture_unsupported": 31, "memory_capacity": 1, @@ -3320,15 +3320,15 @@ "runtime_memory": 10, "参数/模板问题": 27 }, - "failureCount": 119, - "failureRate": 0.8623, + "failureCount": 120, + "failureRate": 0.8633, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 19, - "successRate": 0.1377, - "total": 138, - "unresolvedFailureCount": 63 + "successRate": 0.1367, + "total": 139, + "unresolvedFailureCount": 64 }, "vllm_fix_tokenizer": { "attributableFailureCount": 194, @@ -3384,7 +3384,7 @@ "unresolvedFailureCount": 350 } }, - "generatedAt": "2026-10-24T22:58:36.033457+00:00", + "generatedAt": "2026-10-24T23:18:40.910407+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 133, @@ -3555,7 +3555,7 @@ "decisionSuccessRate": 0.1625, "decisionTotal": 923, "failureBreakdown": { - "ambiguous_runtime": 670, + "ambiguous_runtime": 671, "architecture_compatibility": 15, "backend_operator": 12, "context_length": 29, @@ -3570,15 +3570,15 @@ "日志缺失": 155, "验证失败": 30 }, - "failureCount": 1998, + "failureCount": 1999, "failureRate": 0.9302, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 21, "successCount": 150, "successRate": 0.0698, - "total": 2148, - "unresolvedFailureCount": 1204 + "total": 2149, + "unresolvedFailureCount": 1205 }, "Iluvatar_mrv-100": { "attributableFailureCount": 995, @@ -14247,10 +14247,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 2, + "ambiguous_runtime": 3, "参数/模板问题": 2 }, - "failureCount": 4, + "failureCount": 5, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "k2_horizon", @@ -14262,8 +14262,8 @@ "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", - "total": 4, - "unresolvedFailureCount": 4 + "total": 5, + "unresolvedFailureCount": 5 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|lfm2|none": { "attributableFailureCount": 2, @@ -25973,10 +25973,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 1, "参数/模板问题": 1 }, - "failureCount": 2, + "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastPlatformFailureAt": null, @@ -25988,8 +25987,8 @@ "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", - "total": 2, - "unresolvedFailureCount": 2 + "total": 1, + "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|unknown|text-generation": { "attributableFailureCount": 0, @@ -26127,9 +26126,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { - "ambiguous_runtime": 3, + "ambiguous_runtime": 4, "framework_architecture_unsupported": 2, - "参数/模板问题": 15 + "参数/模板问题": 14 }, "failureCount": 20, "failureRate": 1.0, @@ -26639,31 +26638,6 @@ "total": 1, "unresolvedFailureCount": 0 }, - "Biren_166m|vllm_fix_tokenizer|text-generation|gpt_oss|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": "2026-10-06T19:00:42.266417+00:00", - "modelType": "gpt_oss", - "pendingCount": 0, - "pendingRate": 0.0, - "platformFailureCount": 0, - "quantizationMethod": "none", - "successCount": 0, - "successRate": 0.0, - "targetGpu": "Biren_166m", - "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 1 - }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -27071,10 +27045,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 1, + "ambiguous_runtime": 2, "参数/模板问题": 2 }, - "failureCount": 3, + "failureCount": 4, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastTerminalAt": "2026-10-24T21:54:31.454355+00:00", @@ -27087,8 +27061,8 @@ "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", - "total": 3, - "unresolvedFailureCount": 3 + "total": 4, + "unresolvedFailureCount": 4 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|lfm2|none": { "attributableFailureCount": 0, @@ -44546,10 +44520,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 1, + "ambiguous_runtime": 2, "参数/模板问题": 1 }, - "failureCount": 2, + "failureCount": 3, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 32, @@ -44562,8 +44536,8 @@ "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", - "total": 2, - "unresolvedFailureCount": 2 + "total": 3, + "unresolvedFailureCount": 3 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|k2_horizon|compressed-tensors|33": { "attributableFailureCount": 0, @@ -62096,15 +62070,15 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 18041, - "totalRecords": 18585, + "terminalRecords": 18042, + "totalRecords": 18586, "totals": { "attributableFailureCount": 6374, "decisionFailureRate": 0.866, "decisionSuccessRate": 0.134, "decisionTotal": 7360, "failureBreakdown": { - "ambiguous_runtime": 4675, + "ambiguous_runtime": 4676, "architecture_compatibility": 212, "attention_backend": 3, "backend_operator": 137, @@ -62120,21 +62094,20 @@ "日志缺失": 719, "验证失败": 676 }, - "failureCount": 17055, + "failureCount": 17056, "failureRate": 0.9453, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 972, "successCount": 986, "successRate": 0.0547, - "total": 18041, - "unresolvedFailureCount": 9709 + "total": 18042, + "unresolvedFailureCount": 9710 }, "warnings": [ "GPU Ascend_910-b4 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 Cambricon_mlu-370-x8 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 Kunlunxin_p-800 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 Mthreads_s4000 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。", @@ -62142,8 +62115,9 @@ "GPU Biren_166m 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 Cambricon_mlu-370-x4 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 Kunlunxin_p-800 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 Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "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 Biren_166m|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", @@ -62191,6 +62165,6 @@ ] }, "storageMode": "decision_state_only", - "summarizedRecords": 18585, + "summarizedRecords": 18586, "version": 1 } diff --git a/.modelhub_state/recent_outcomes.jsonl b/.modelhub_state/recent_outcomes.jsonl index 7a7301f728..9e82e53493 100644 --- a/.modelhub_state/recent_outcomes.jsonl +++ b/.modelhub_state/recent_outcomes.jsonl @@ -140,6 +140,7 @@ {"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", "failureUnsupportedArchitectures": ["CagliostroForCausalLM"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-21T14:48:45.557072+00:00", "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "17a693aa8ae65d96fb0c459d2e1f98ce1d8b2f8933e06b75903df1a5b48287eb", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": 1556071699, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "failed", "status": "success", "submitTime": "2026-10-07T19:30:29.971308+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360311", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557090+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-standard-v1", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T19:30:29.945877+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360309", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-24T21:54:31.454355+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6343991648, "estimatedRequiredGiB": 7.115, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6366013051, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1716764160, "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": 6366013051}, "outcome": "failed", "status": "success", "submitTime": "2026-10-07T19:30:29.889751+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360308", "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": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-24T23:18:40.667328+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4749242120, "estimatedRequiredGiB": 5.332, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 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": "2026-10-07T19:30:29.859208+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360305", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-24T18:37:46.581645+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8122473440, "estimatedRequiredGiB": 9.103, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 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": "2026-10-07T19:30:29.851218+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360304", "taskType": "text-generation", "verifyResult": null} {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-10T00:51:39.858999+00:00", "modelId": "cyankiwi/Spark-X2.5-4B-AWQ-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2856860040, "estimatedRequiredGiB": 3.21, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2872281308, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2872281308}, "outcome": "failed", "status": "success", "submitTime": "2026-10-07T19:30:29.757524+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360301", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.556965+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T19:30:29.751419+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360302", "taskType": "text-generation", "verifyResult": null} @@ -297,4 +298,3 @@ {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164473+00:00", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:15:22.866391+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320518", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164580+00:00", "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:15:22.761540+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320515", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-24T08:34:54.442474+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20443542279, "estimatedRequiredGiB": 22.881, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20473981021, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5678320880, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:qwen3", "custom_tag:qwen", "custom_tag:mtplx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 20473981021}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:15:22.650807+00:00", "targetGpu": "Biren_166m", "taskId": "5320513", "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": "2026-10-06T19:00:42.266417+00:00", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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": "2026-10-06T09:15:22.648982+00:00", "targetGpu": "Biren_166m", "taskId": "5320514", "taskType": "text-generation", "verifyResult": -1} diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 3082ef61ce..ae42d12ae4 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3802,6 +3802,18 @@ {"batchId": "ed55759503cd47e68b79d8c6dd4d61ed", "completedAt": "2026-10-24T23:12:06.041039+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-24T23:12:04.017371+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1b6848fb81da47219577132a7c975569", "lastModified": "2026-10-22T01:37:07+00:00", "modelAddress": "https://modelscope.cn/models/RecursiveSI/flint-int4", "reason": null, "reconciledAt": "2026-10-24T23:17:09.305426+00:00", "repoId": "RecursiveSI/flint-int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5768504", "taskType": "text-generation"} {"batchId": "b3082168f08a41d79c64de1eeaf1dc9f", "completedAt": "2026-10-24T23:12:59.480574+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-24T23:12:57.307345+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ab738eeec65843a0b187cb87be456acb", "lastModified": "2026-10-21T16:19:52+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-24T23:17:09.305424+00:00", "repoId": "cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5768526", "taskType": "text-generation"} {"batchId": "b3082168f08a41d79c64de1eeaf1dc9f", "completedAt": "2026-10-24T23:12:59.480580+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-24T23:12:57.307432+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d1bba9aa234e4998aeb8c73c7dccc6ed", "lastModified": "2026-10-21T15:40:57+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Explore-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-24T23:17:09.307659+00:00", "repoId": "cyankiwi/AgentCPM-Explore-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5768525", "taskType": "text-generation"} +{"batchId": "b85e5c82b4b34cc1a5bcd4c65c5dddc2", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-24T23:18:42.309756+00:00", "framework": "vllm-mlu", "intentId": "b2805493fb454ae5acd9425e0ab5e4e2", "lastModified": "2026-10-21T16:56:28+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "repoId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "b85e5c82b4b34cc1a5bcd4c65c5dddc2", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-24T23:18:42.309868+00:00", "framework": "vllm-mlu", "intentId": "3b1df38e6d384d438d50a92aba2e409a", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "b85e5c82b4b34cc1a5bcd4c65c5dddc2", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-24T23:18:42.309923+00:00", "framework": "vllm-mlu", "intentId": "a8b8094e106c41faa3b9661c55f7d52b", "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": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "b85e5c82b4b34cc1a5bcd4c65c5dddc2", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-24T23:18:42.309973+00:00", "framework": "vllm-mlu", "intentId": "62830f9d86b042fe9a1e4fcb90aecd07", "lastModified": "2026-10-21T17:09:55+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "b85e5c82b4b34cc1a5bcd4c65c5dddc2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-24T23:18:42.310023+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dd1fb23e2cb64bc0bfc13fc431653947", "lastModified": "2026-10-21T19:51:23+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/NVIDIA-Nemotron-3-Super-120B-A12B-AWQ-4bit", "repoId": "cyankiwi/NVIDIA-Nemotron-3-Super-120B-A12B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "b85e5c82b4b34cc1a5bcd4c65c5dddc2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-24T23:18:42.310069+00:00", "framework": "vllm_fix_tokenizer", "intentId": "014b10a65056441e8fbac9e3a0385106", "lastModified": "2026-10-21T17:03:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiniCPM-SALA-AWQ-4bit", "repoId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "b85e5c82b4b34cc1a5bcd4c65c5dddc2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-24T23:18:42.310113+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0d31343b95b140a49a3f9a96fa8731cb", "lastModified": "2026-10-22T14:13:07+00:00", "modelAddress": "https://modelscope.cn/models/InternScience/Sage-A1.5", "repoId": "InternScience/Sage-A1.5", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "b85e5c82b4b34cc1a5bcd4c65c5dddc2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-24T23:18:42.310155+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b7090a9af42b40e8839221cf3df33f3e", "lastModified": "2026-10-21T17:18:20+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiroThinker-v1.5-30B-AWQ-8bit", "repoId": "cyankiwi/MiroThinker-v1.5-30B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "b85e5c82b4b34cc1a5bcd4c65c5dddc2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-24T23:18:42.310214+00:00", "framework": "vllm_fix_tokenizer", "intentId": "caf536479b9f457e8f513a0ae6f47718", "lastModified": "2026-10-21T16:06:54+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/GLM-4.5-Air-Derestricted-AWQ-4bit", "repoId": "cyankiwi/GLM-4.5-Air-Derestricted-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "b85e5c82b4b34cc1a5bcd4c65c5dddc2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-24T23:18:42.310257+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d8d2284b68eb456080e605739f7e7da2", "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": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "b85e5c82b4b34cc1a5bcd4c65c5dddc2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-24T23:18:42.310300+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5170f0f368cb4548888d88531df0f15e", "lastModified": "2026-10-24T12:01:13+00:00", "modelAddress": "https://modelscope.cn/models/kakarotter/calix", "repoId": "kakarotter/calix", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} +{"batchId": "b85e5c82b4b34cc1a5bcd4c65c5dddc2", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-24T23:18:42.310342+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c94e3d02344d43788f7ccee4ae33b297", "lastModified": "2026-10-21T16:56:31+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "repoId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"} {"batchId": "fb0b8efb8a9c4f12b6821842c126e726", "completedAt": "2026-10-24T23:17:06.972741+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-24T23:17:03.929205+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9f4636d0487c46b8b50eb44920e94129", "repoId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "fb0b8efb8a9c4f12b6821842c126e726", "completedAt": "2026-10-24T23:17:06.972737+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-24T23:17:03.929122+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9c85050032d84918816e80f91f4309de", "repoId": "kakarotter/calix", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "fb0b8efb8a9c4f12b6821842c126e726", "completedAt": "2026-10-24T23:17:06.972733+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-24T23:17:03.929053+00:00", "framework": "vllm_fix_tokenizer", "intentId": "dfd2464f0eec4866a3903d7146d19042", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index a3821fcff7..7bc894e9e5 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "9feaf646a9bf485f24b93b43e34c59676ba58911e7c87ae4aa7fa98920adc451", - ".modelhub_state/architecture_compatibility_blacklist.json": "a00a1c00d6881a5bf72c5c9b7e1055a4d4e7a471fb08b1fea31a83779c091ed6", + ".modelhub_state/architecture_compatibility_blacklist.json": "cb8350c2b54942fb4dd27af48be309b0aa4856a2408266a9ed8398a7c59123f4", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "8e2d918271239bf0727555f2a6d8f486b1def5dd162716cb2c884011f45cc4a2", - ".modelhub_state/official_capabilities.json": "865e121456d39d0e82e693efba0642bbc375b673e2230eeff3c49c8e5b55de36", - ".modelhub_state/outcome_checkpoint.json": "e0bab1228628eaa13f964a2cb3cba0bd15b3feaa8340015d4be066e928b210da", + ".modelhub_state/market_intelligence.json": "516ac8d4ff425dafdaa178ce3e416455deb133d640a36a8c55247b68221b9cc6", + ".modelhub_state/official_capabilities.json": "298f45d3ce97deace23ce942115b3b138fb8b470fa035140b9c735e4232a9f88", + ".modelhub_state/outcome_checkpoint.json": "83d4a6045de07dbf88c780b354004944dabdaa7e86f0a414d646ff4530dcd46f", ".modelhub_state/queue_cleanup_latest.json": "a30e98033b88700cd96f638ef2c2591616caffa0561a97f365d5149f40b06a3c", - ".modelhub_state/recent_outcomes.jsonl": "36013b333c7c719ea921476bd9d32591a9b976e5ddc10f4350fe7fa81a041820", + ".modelhub_state/recent_outcomes.jsonl": "f2370e8e47978edec21440450a9b0ae639647b92c6593f0a83420a9fb7349690", ".modelhub_state/recovery_active_tasks.jsonl": "69f7e646c8d01330cb81e80fb5bdac9a0f0582750baa57fc8b5cb2ddc8ee3cff", - ".modelhub_state/recovery_intents.jsonl": "7058e472d944e67716a2b018c8ba6d0edb4ddce5baa9e20572a5b07f273264eb", + ".modelhub_state/recovery_intents.jsonl": "6bed5981b1d1d35eb781ea66b418d396ec186935dc240ada81dcaf8e2dfbd435", ".modelhub_state/routing_intelligence.json": "3445eeda0e64eacd252a8b2ab1ef53fbb1d2e46f1a163dc9063698568c826407", ".modelhub_state/submission_exclusions.jsonl": "ec0164a066e590a129ed69be5c4279284ccf1a85230e402be88754b03203581d", ".modelhub_state/worker_crashes.jsonl": "e436652d39bca5bcba31822ff9fb949a9d7ff0b7f509c170e258a53d7e01ce9a", "ledger/submissions.jsonl": "4aaf1b244893cdaad46f94a0da384b22a44722fe7879949e66a3fb1609e62416", - "outcomes/submissions.jsonl": "2c76da45a4c75c45ea926dca6f948b887fa132b6ac9473a5140d1a6c500093bd" + "outcomes/submissions.jsonl": "6efb3b203836c3f6554f4341655eaa7f97f40dbed8f64c1f2e3630aaff9ddb56" }, - "generation": 34888, - "phase": "cycle", + "generation": 34889, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-24T23:17:09.491694+00:00", + "updatedAt": "2026-10-24T23:18:42.541600+00:00", "writerId": "5c9906c400e2442789cb0c734d70dc03" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 0cd64baa8b..8cd79b9c1f 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -561,7 +561,6 @@ {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T03:44:24.154788+00:00", "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2092366914, "estimatedRequiredGiB": 2.351, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2103475788, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:apple-silicon", "custom_tag:oq", "custom_tag:llama", "custom_tag:minicpm", "custom_tag:imatrix", "custom_tag:long-context", "custom_tag:coding", "custom_tag:sharp-template", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2103475788}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T19:30:29.844294+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360307", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T03:44:24.154949+00:00", "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "df879293d64bd4eef168b273fb4b6ac51b0bec98b1555859d64582b13249914c", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": 281591196, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T19:30:29.942926+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360312", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T03:44:24.154879+00:00", "modelId": "Akahsizrr/Cyber-Prime-1.1-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427432, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412809492, "modelscopeLicense": "other", "modelscopeParams": 209741824, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412809492}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T19:30:29.849363+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360306", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T03:44:24.154707+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4749242120, "estimatedRequiredGiB": 5.332, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 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": "pending", "status": "waiting", "submitTime": "2026-10-07T19:30:29.859208+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360305", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T03:44:24.154903+00:00", "modelId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.638, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:thinking", "custom_tag:fable5", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:agentic", "custom_tag:coding", "custom_tag:instruction-following", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5045067151}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T19:30:29.951189+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360313", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T03:44:24.154782+00:00", "modelId": "danish-foundation-models/DFM-Mimir-v1.5", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3573566200, "estimatedRequiredGiB": 4.03, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 3606214195, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1786775040, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:danish", "custom_tag:english", "custom_tag:hrm-text", "custom_tag:instruction-tuned", "custom_tag:prefix-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3606214195}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T19:30:29.977755+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360315", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T03:44:24.154800+00:00", "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11771374457, "estimatedRequiredGiB": 13.184, "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": 11796740983, "modelscopeLicense": "other", "modelscopeParams": 301338560, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:3-bit", "custom_tag:affine", "custom_tag:text-only", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11796740983}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T19:30:29.957803+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360310", "taskType": "text-generation", "verifyResult": null} @@ -1087,7 +1086,7 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-24T18:37:46.581696+00:00", "modelId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "modelProfile": {"architectures": ["Olmo3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19609154304, "estimatedRequiredGiB": 21.926, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "olmo3", "modelscopeFileSize": 19619096698, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32233522176, "modelscopeTags": ["license:apache-2.0", "model_type:olmo3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 19619096698}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T10:37:33.135140+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5758988", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-24T21:56:10.438236+00:00", "modelId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "modelProfile": {"architectures": ["Olmo3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19609154304, "estimatedRequiredGiB": 21.926, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "olmo3", "modelscopeFileSize": 19619082384, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32233522176, "modelscopeTags": ["license:apache-2.0", "model_type:olmo3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 19619082384}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T13:54:41.633452+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5761466", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-24T23:00:13.556835+00:00", "modelId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10544400664, "estimatedRequiredGiB": 16.539, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 14798414872, "modelscopeLicense": "other", "modelscopeParams": 14768307200, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:nemotron-cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-22T11:48:09.066588+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 14798414872}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T14:58:43.739473+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5762276", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-8bit", "modelProfile": {"architectures": ["IQuestLoopCoderForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 43020541704, "estimatedRequiredGiB": 48.082, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "iquestloopcoder", "modelscopeFileSize": 43022744508, "modelscopeLicense": "other", "modelscopeParams": 39794696320, "modelscopeTags": ["license:other", "model_type:iquestloopcoder", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 43022744508}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T15:18:38.633307+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5762557", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-24T23:18:40.667302+00:00", "modelId": "cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-8bit", "modelProfile": {"architectures": ["IQuestLoopCoderForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 43020541704, "estimatedRequiredGiB": 48.082, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "iquestloopcoder", "modelscopeFileSize": 43022744508, "modelscopeLicense": "other", "modelscopeParams": 39794696320, "modelscopeTags": ["license:other", "model_type:iquestloopcoder", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 43022744508}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T15:18:38.633307+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5762557", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/Hermes-4-70B-AWQ-4bit", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 42709261480, "estimatedRequiredGiB": 47.751, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 42726705598, "modelscopeLicense": "llama3", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:Llama-3.1", "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": 42726705598}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T16:04:12.435598+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5763295", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17150429576, "estimatedRequiredGiB": 23.921, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 21404443971, "modelscopeLicense": "other", "modelscopeParams": 14768307200, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:nemotron-cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 21404443971}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T16:06:45.349812+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5763338", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6691066608, "estimatedRequiredGiB": 7.498, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-10-24T16:12:09.964702+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5763434", "taskType": "text-generation", "verifyResult": null}