From 94261cf8423875b0e44c44d62eda14fc0350b31e Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Mon, 21 Sep 2026 23:42:58 +0000 Subject: [PATCH] state: generation 11912 (intent) --- .../architecture_compatibility_blacklist.json | 10 +- .modelhub_state/market_intelligence.json | 2 +- .modelhub_state/official_capabilities.json | 47 +++--- .modelhub_state/outcome_checkpoint.json | 143 ++++++++---------- .modelhub_state/recent_outcomes.jsonl | 2 +- .modelhub_state/recovery_intents.jsonl | 4 + manifest.json | 20 +-- outcomes/submissions.jsonl | 1 - 8 files changed, 105 insertions(+), 124 deletions(-) diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 50a6b9363a..e6b07d746c 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -1010,7 +1010,7 @@ "cambricon_mlu-370-x8|vllm|text-generation|model_type:gemma4": { "architectureSignature": "model_type:gemma4", "architectures": [], - "evidenceCount": 1, + "evidenceCount": 2, "expiresAt": "2026-10-20T04:26:51.246271+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T04:26:51.246271+00:00", @@ -1018,10 +1018,12 @@ "matchType": "model_type", "modelType": "gemma4", "sourceModelIds": [ - "mlx-community/gemma-4-e4b-it-OptiQ-4bit" + "mlx-community/gemma-4-e4b-it-OptiQ-4bit", + "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit" ], "sourceTaskIds": [ - "4970731" + "4970731", + "4970619" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" @@ -2869,7 +2871,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-09-21T23:39:40.062516+00:00", + "generatedAt": "2026-09-21T23:42:47.688464+00:00", "summary": { "activeBlockCount": 144, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index a80faec6c5..4b07f85648 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -434,7 +434,7 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-09-21T23:41:37.864402+00:00", + "generatedAt": "2026-09-21T23:42:57.231629+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index 139dfc3c9f..eb079fbe97 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-09-21T23:41:37.864402+00:00", + "catalogUpdatedAt": "2026-09-21T23:42:57.231629+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-09-21T23:41:37.864402+00:00", + "generatedAt": "2026-09-21T23:42:58.153462+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -1812,12 +1812,6 @@ ], "updatedAt": "2026-09-21T18:49:59.733562+00:00" }, - "https://modelscope.cn/models/aisingapore/Apertus-SEA-LION-v4-8B-IT-GGUF|2026-08-25T12:47:35+00:00|MetaX_c-500": { - "taskTypes": [ - "text-generation" - ], - "updatedAt": "2026-09-21T18:49:59.694609+00:00" - }, "https://modelscope.cn/models/amd/Qwen3.6-35B-A3B-w4a16-llmcompressor|2026-09-21T15:48:16+00:00|Sunrise_pt-200-x1": { "taskTypes": [ "text-generation" @@ -2312,6 +2306,14 @@ ], "updatedAt": "2026-09-21T19:05:25.099915+00:00" }, + "https://modelscope.cn/models/facebook/OMol25|2026-09-21T12:23:47+00:00|Cambricon_mlu-370-x4": { + "taskTypes": [ + "text-generation", + "text-to-image-generation", + "visual-multi-modal" + ], + "updatedAt": "2026-09-21T23:42:57.856775+00:00" + }, "https://modelscope.cn/models/facebook/OMol25|2026-09-21T12:23:47+00:00|Cambricon_mlu-370-x8": { "taskTypes": [ "text-generation", @@ -2363,6 +2365,18 @@ ], "updatedAt": "2026-09-21T19:05:24.616307+00:00" }, + "https://modelscope.cn/models/facebook/OMol25|2026-09-21T12:23:47+00:00|Sunrise_pt-200-x1": { + "taskTypes": [ + "text-generation" + ], + "updatedAt": "2026-09-21T23:42:58.123689+00:00" + }, + "https://modelscope.cn/models/facebook/OMol25|2026-09-21T12:23:47+00:00|Vastai_va16": { + "taskTypes": [ + "text-generation" + ], + "updatedAt": "2026-09-21T23:42:58.153462+00:00" + }, "https://modelscope.cn/models/facebook/OMol25|2026-09-21T12:23:47+00:00|hygon_k100-ai": { "taskTypes": [ "text-generation", @@ -6123,21 +6137,6 @@ "visual-multi-modal" ], "updatedAt": "2026-09-21T19:05:29.540983+00:00" - }, - "https://modelscope.cn/models/z-lab/Qwen3.8-27B-DFlash2-GGUF|2026-08-25T14:22:45+00:00|Biren_166m": { - "taskTypes": [ - "text-generation" - ], - "updatedAt": "2026-09-21T18:49:59.657356+00:00" - }, - "https://modelscope.cn/models/z-lab/Qwen3.8-27B-DFlash2-GGUF|2026-08-25T14:22:45+00:00|Iluvatar_mrv-100": { - "taskTypes": [ - "asr", - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-09-21T18:49:59.687435+00:00" } }, "taskTree": [ @@ -6820,6 +6819,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-09-21T23:41:37.864402+00:00", + "taskTreeUpdatedAt": "2026-09-21T23:42:57.231629+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index 8f4b341bec..c0e0b5d96c 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-09-21T23:35:10.930892+00:00", - "lastSyncTime": "2026-09-21T23:35:10.664127+00:00", + "generatedAt": "2026-09-21T23:42:47.613650+00:00", + "lastSyncTime": "2026-09-21T23:42:47.252222+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -1014,7 +1014,7 @@ "cambricon_mlu-370-x8|vllm|text-generation|model_type:gemma4": { "architectureSignature": "model_type:gemma4", "architectures": [], - "evidenceCount": 1, + "evidenceCount": 2, "expiresAt": "2026-10-20T04:26:51.246271+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T04:26:51.246271+00:00", @@ -1022,10 +1022,12 @@ "matchType": "model_type", "modelType": "gemma4", "sourceModelIds": [ - "mlx-community/gemma-4-e4b-it-OptiQ-4bit" + "mlx-community/gemma-4-e4b-it-OptiQ-4bit", + "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit" ], "sourceTaskIds": [ - "4970731" + "4970731", + "4970619" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" @@ -3568,17 +3570,17 @@ "unresolvedFailureCount": 43 }, "Cambricon_mlu-370-x8|vllm|text-generation": { - "attributableFailureCount": 21, + "attributableFailureCount": 22, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, - "decisionTotal": 21, + "decisionTotal": 22, "failureBreakdown": { "ambiguous_runtime": 20, - "framework_architecture_unsupported": 20, + "framework_architecture_unsupported": 21, "memory_capacity": 1, "参数/模板问题": 12 }, - "failureCount": 53, + "failureCount": 54, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, @@ -3588,7 +3590,7 @@ "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", - "total": 53, + "total": 54, "unresolvedFailureCount": 32 }, "Iluvatar_bi-100|transformers|text-generation": { @@ -5525,17 +5527,17 @@ "unresolvedFailureCount": 6446 }, "vllm": { - "attributableFailureCount": 3546, + "attributableFailureCount": 3547, "decisionFailureRate": 0.9758, "decisionSuccessRate": 0.0242, - "decisionTotal": 3634, + "decisionTotal": 3635, "failureBreakdown": { "ambiguous_runtime": 1499, "architecture_compatibility": 112, "attention_backend": 1, "backend_operator": 84, "context_length": 161, - "framework_architecture_unsupported": 1312, + "framework_architecture_unsupported": 1313, "memory_capacity": 722, "model_load": 208, "platform_infrastructure": 865, @@ -5544,14 +5546,14 @@ "tokenizer_compatibility": 412, "参数/模板问题": 46 }, - "failureCount": 5956, + "failureCount": 5957, "failureRate": 0.9854, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 865, "successCount": 88, "successRate": 0.0146, - "total": 6044, + "total": 6045, "unresolvedFailureCount": 1545 }, "vllm-customized": { @@ -5698,7 +5700,7 @@ "unresolvedFailureCount": 120 } }, - "generatedAt": "2026-09-21T23:35:10.920230+00:00", + "generatedAt": "2026-09-21T23:42:47.602690+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 99, @@ -5814,27 +5816,27 @@ "unresolvedFailureCount": 774 }, "Cambricon_mlu-370-x8": { - "attributableFailureCount": 52, - "decisionFailureRate": 0.7879, - "decisionSuccessRate": 0.2121, - "decisionTotal": 66, + "attributableFailureCount": 53, + "decisionFailureRate": 0.791, + "decisionSuccessRate": 0.209, + "decisionTotal": 67, "failureBreakdown": { "ambiguous_runtime": 110, - "framework_architecture_unsupported": 43, + "framework_architecture_unsupported": 44, "memory_capacity": 4, "model_load": 3, "tokenizer_compatibility": 2, "参数/模板问题": 34, "验证失败": 22 }, - "failureCount": 218, - "failureRate": 0.9397, + "failureCount": 219, + "failureRate": 0.9399, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 14, - "successRate": 0.0603, - "total": 232, + "successRate": 0.0601, + "total": 233, "unresolvedFailureCount": 166 }, "Iluvatar_bi-100": { @@ -10711,14 +10713,14 @@ "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|gemma4|none": { - "attributableFailureCount": 1, + "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, - "decisionTotal": 1, + "decisionTotal": 2, "failureBreakdown": { - "framework_architecture_unsupported": 1 + "framework_architecture_unsupported": 2 }, - "failureCount": 1, + "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma4", @@ -10730,7 +10732,7 @@ "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", - "total": 1, + "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|hrm_text|none": { @@ -18078,15 +18080,15 @@ "unresolvedFailureCount": 6 }, "Cambricon_mlu-370-x8|vllm|text-generation": { - "attributableFailureCount": 7, - "consecutiveFailures": 7, + "attributableFailureCount": 8, + "consecutiveFailures": 8, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, - "decisionTotal": 7, + "decisionTotal": 8, "failureBreakdown": { - "ambiguous_runtime": 12, - "framework_architecture_unsupported": 6, + "ambiguous_runtime": 11, + "framework_architecture_unsupported": 7, "memory_capacity": 1, "参数/模板问题": 1 }, @@ -18103,7 +18105,7 @@ "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 20, - "unresolvedFailureCount": 13 + "unresolvedFailureCount": 12 }, "Iluvatar_bi-100|transformers|text-generation": { "attributableFailureCount": 0, @@ -19682,15 +19684,15 @@ "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|gemma4|none": { - "attributableFailureCount": 1, - "consecutiveFailures": 1, + "attributableFailureCount": 2, + "consecutiveFailures": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, - "decisionTotal": 1, + "decisionTotal": 2, "failureBreakdown": { - "framework_architecture_unsupported": 1 + "framework_architecture_unsupported": 2 }, - "failureCount": 1, + "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-21T19:58:46.051796+00:00", @@ -19703,7 +19705,7 @@ "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", - "total": 1, + "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|lfm2_moe|none": { @@ -21033,31 +21035,6 @@ "total": 2, "unresolvedFailureCount": 2 }, - "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|nemotron_h|modelopt": { - "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": "2026-09-20T12:21:49.902137+00:00", - "modelType": "nemotron_h", - "pendingCount": 0, - "pendingRate": 0.0, - "platformFailureCount": 0, - "quantizationMethod": "modelopt", - "successCount": 0, - "successRate": 0.0, - "targetGpu": "Iluvatar_bi-150", - "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 1 - }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|nemotron_h|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -28427,14 +28404,14 @@ "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|gemma4|none|32": { - "attributableFailureCount": 1, + "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, - "decisionTotal": 1, + "decisionTotal": 2, "failureBreakdown": { - "framework_architecture_unsupported": 1 + "framework_architecture_unsupported": 2 }, - "failureCount": 1, + "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, @@ -28447,7 +28424,7 @@ "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", - "total": 1, + "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|hrm_text|none|31": { @@ -38574,20 +38551,20 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 16438, - "totalRecords": 16632, + "terminalRecords": 16439, + "totalRecords": 16633, "totals": { - "attributableFailureCount": 5924, + "attributableFailureCount": 5925, "decisionFailureRate": 0.8619, "decisionSuccessRate": 0.1381, - "decisionTotal": 6873, + "decisionTotal": 6874, "failureBreakdown": { "ambiguous_runtime": 4052, "architecture_compatibility": 212, "attention_backend": 1, "backend_operator": 105, "context_length": 321, - "framework_architecture_unsupported": 2095, + "framework_architecture_unsupported": 2096, "memory_capacity": 1199, "model_load": 500, "platform_infrastructure": 925, @@ -38598,31 +38575,31 @@ "日志缺失": 719, "验证失败": 674 }, - "failureCount": 15489, + "failureCount": 15490, "failureRate": 0.9423, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 925, "successCount": 949, "successRate": 0.0577, - "total": 16438, + "total": 16439, "unresolvedFailureCount": 8640 }, "warnings": [ "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU MetaX_c-500 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。", "组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", @@ -38662,6 +38639,6 @@ ] }, "storageMode": "decision_state_only", - "summarizedRecords": 16632, + "summarizedRecords": 16633, "version": 1 } diff --git a/.modelhub_state/recent_outcomes.jsonl b/.modelhub_state/recent_outcomes.jsonl index e1c02c5dd4..7210b72c26 100644 --- a/.modelhub_state/recent_outcomes.jsonl +++ b/.modelhub_state/recent_outcomes.jsonl @@ -259,6 +259,7 @@ {"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": "2026-09-20T12:46:14.462946+00:00", "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelProfile": {"architectures": ["Mistral3ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17367755740, "estimatedRequiredGiB": 19.429, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral3", "modelscopeFileSize": 17385072379, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4929899520, "modelscopeTags": ["license:apache-2.0", "model_type:mistral3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:mistral", "custom_tag:mistral3", "custom_tag:devstral"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17385072379}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:26:45.153348+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970732", "taskType": "text-generation", "verifyResult": -1} {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["gemma4_unified"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:46:14.462967+00:00", "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9003966484, "estimatedRequiredGiB": 10.099, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 9036402901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2463563824, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9036402901}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:26:45.138158+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970728", "taskType": "text-generation", "verifyResult": -1} {"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 24.0, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-21T17:22:47.256921+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:19:00.606791+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970641", "taskType": "text-generation", "verifyResult": -1} +{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["gemma4"], "framework": "vllm", "lastSyncTime": "2026-09-21T23:42:47.252222+00:00", "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5222073830, "estimatedRequiredGiB": 5.872, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5254590634, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1140034851, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5254590634}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:15:37.035881+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970619", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm-customized", "lastSyncTime": "2026-09-21T06:41:38.663980+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-20T04:15:36.979619+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970617", "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-mlu", "lastSyncTime": "2026-09-21T08:44:09.587559+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663396475}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:15:36.970472+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970618", "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": "2026-09-20T12:34:29.856403+00:00", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8674988799, "estimatedRequiredGiB": 9.718, "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": 8695119291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2415484144, "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:qwen", "custom_tag:qwen3", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:qwen3-5", "custom_tag:9b", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8695119291}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:15:36.958375+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970614", "taskType": "text-generation", "verifyResult": -1} @@ -297,4 +298,3 @@ {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T22:27:36.960871+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.338954+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970440", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T10:57:20.777292+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.337459+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970434", "taskType": "text-generation", "verifyResult": -1} {"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 32.0, "failureScope": "model_gpu", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-20T12:21:49.901701+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:02:45.335178+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970437", "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_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.902137+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21561882284, "estimatedRequiredGiB": 24.122, "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": 21583784354, "modelscopeLicense": "other", "modelscopeParams": 17820210764, "modelscopeTags": ["license:other", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21583784354}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:58:41.340891+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970366", "taskType": "text-generation", "verifyResult": -1} diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index 6734627961..53c97161bb 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2333,6 +2333,10 @@ {"batchId": "dd6b1a097b3f40c391eadc79550f9c5b", "completedAt": "2026-09-21T23:34:26.866699+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-21T23:34:25.803118+00:00", "framework": "vllm-mlu", "intentId": "72ad66be9d4245eba3cf2590a476a19a", "lastModified": "2026-09-21T18:39:37+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "reason": null, "reconciledAt": "2026-09-21T23:39:54.269197+00:00", "repoId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5008980", "taskType": "text-generation"} {"batchId": "573474397dbd48f29ed54d976de51b7d", "completedAt": "2026-09-21T23:38:54.792504+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-21T23:38:53.850981+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1a4908b75bdc41298729c6ac176f00aa", "lastModified": "2026-09-21T18:44:33+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block6-v1_C", "reason": null, "reconciledAt": "2026-09-21T23:39:54.265521+00:00", "repoId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5009025", "taskType": "text-generation"} {"batchId": "573474397dbd48f29ed54d976de51b7d", "completedAt": "2026-09-21T23:38:54.792522+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-21T23:38:53.851103+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0eadc022194c41548cda6765d776f028", "lastModified": "2026-09-21T18:43:38+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g2-v2_C", "reason": null, "reconciledAt": "2026-09-21T23:39:54.269431+00:00", "repoId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5009026", "taskType": "text-generation"} +{"batchId": "1d6648fc018c4bfab422b0b9b5d57c21", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-21T23:42:58.208018+00:00", "framework": "vllm-mlu", "intentId": "bf86e5191ce740d4bf382bfbf66788d7", "lastModified": "2026-09-21T18:24:38+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block2-v1_B", "repoId": "nkkbr/Mini-K3-1H-attnres-block2-v1_B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "1d6648fc018c4bfab422b0b9b5d57c21", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-21T23:42:58.208125+00:00", "framework": "vllm-mlu", "intentId": "58dc4015785f468cad27836422f38c97", "lastModified": "2026-09-21T18:38:06+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-standard-v1_B", "repoId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "1d6648fc018c4bfab422b0b9b5d57c21", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-21T23:42:58.208179+00:00", "framework": "vllm-mlu", "intentId": "eeb88a18eec64f86933c8895ba44def5", "lastModified": "2026-09-21T18:27:54+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g1-v2_B", "repoId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "1d6648fc018c4bfab422b0b9b5d57c21", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-21T23:42:58.208230+00:00", "framework": "vllm-mlu", "intentId": "c2599e4f122d441591da94dd134b0c71", "lastModified": "2026-09-21T18:27:55+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g32-v2_C", "repoId": "nkkbr/Mini-K3-1H-decay-g32-v2_C", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} {"batchId": "24082fb4e4bc48b988e1e4deac30068b", "completedAt": "2026-09-21T20:36:17.828196+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T20:36:00.461127+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7ef98d8672514b6cb8bcf83850090ffe", "repoId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} {"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691781+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.137064+00:00", "framework": "vllm", "intentId": "64b834dd640742a0b32535bde02b94ad", "repoId": "CohereLabs/tiny-aya-base-32K", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "f8d3f1991720478ea905a5ecf7d43601", "completedAt": "2026-09-21T19:05:00.691779+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T19:00:55.137007+00:00", "framework": "vllm", "intentId": "d6229ef4ac9942078baa35e312133d9d", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "age_policy_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index 14f00f076c..8b751e9345 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.20.2", "checksums": { ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1", - ".modelhub_state/architecture_compatibility_blacklist.json": "4c9c61537771c850134397bdd5c37c18d8abf7f87284c165a6845ccdcb889b88", + ".modelhub_state/architecture_compatibility_blacklist.json": "24391188d56239222982cad5c74b2a2987e4b433118004ee41ad1ff1b3fe155e", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "449b2f88e3b5a11432bae0369639b1ffb5d87a8b8da7e19ebf14b456c15acd2a", - ".modelhub_state/official_capabilities.json": "b8e72b2c39d31bafba6cde00eb06428054c39b228cc7ec4e883b3f569fc98e13", - ".modelhub_state/outcome_checkpoint.json": "13856bae9dd4923ad3603bd400fe9550b4d6cedd5b46ee22bff78b1fc652146d", + ".modelhub_state/market_intelligence.json": "f9fed279b98219131f3eab422d847f457f3b4ac4c3b6868b6a19300bfb2c7574", + ".modelhub_state/official_capabilities.json": "bda24fe2d86a60fb1006564da8ceda40c9273eec24f4d64cde8f5b2d803df807", + ".modelhub_state/outcome_checkpoint.json": "4f7c673fcc766d016406aec793fbd3cf696186c8e63085898305486876a025f8", ".modelhub_state/queue_cleanup_latest.json": "14282fb49e9aa62e07b6a07250bcf51916a4d783e09664c80d1fa965b4d48615", - ".modelhub_state/recent_outcomes.jsonl": "d532366bd98a9a0563ee0a2b0282e238acc915f6b665670ee87caa0a49abae61", + ".modelhub_state/recent_outcomes.jsonl": "3b50817f00b85c123039bd0070ea7f7a8283b2bd3a4ffb5f726294223daa4630", ".modelhub_state/recovery_active_tasks.jsonl": "a2d9f074c20c12d9b7bb78f7c3deae983c39fe2b62b725305f43ece7bc4dfd43", - ".modelhub_state/recovery_intents.jsonl": "3a729e2084a73167cb3a505ff09d7a8ec59bc77c6fafe42a3497263c397c06d2", + ".modelhub_state/recovery_intents.jsonl": "6b71302513fc1e5bc218dcec7cfcf34c08d879903eb68ad07c59e8086c9cd924", ".modelhub_state/routing_intelligence.json": "032699d470cac575aef9968cb8be2b22c4623c307ca8649d7fda7a24e19568ce", ".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989", ".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7", "ledger/submissions.jsonl": "0c6f921aa1660bb5631798128deb1a35f1cd4820ca26440d6e7d308c11adccc0", - "outcomes/submissions.jsonl": "9455a29d20989ba612856b61c49a3a6c588575eea942deadad754345bbe15c6f" + "outcomes/submissions.jsonl": "66867e51744f9f3f13e329ca38e194f7e77cfc85b945ca7e7aac3f8c347c48b3" }, - "generation": 11911, - "phase": "cycle", + "generation": 11912, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-09-21T23:41:46.471849+00:00", + "updatedAt": "2026-09-21T23:42:58.361106+00:00", "writerId": "8b35139af6674067a339a670222d4b67" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 8c648bf208..8f009e69d0 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -566,7 +566,6 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:21:49.901918+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:42.093442+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970600", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:21:49.901615+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663867, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788663867}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:42.090996+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970597", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901870+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:15:36.946953+00:00", "targetGpu": "Vastai_va16", "taskId": "4970616", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:21:49.902111+00:00", "modelId": "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5222073830, "estimatedRequiredGiB": 5.872, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5254590634, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1140034851, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5254590634}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:15:37.035881+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970619", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T12:21:49.901693+00:00", "modelId": "RedHatAI/Llama-3.2-1B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2024670536, "estimatedRequiredGiB": 2.273, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033824831, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2033824831}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:19:00.650992+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4970642", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:34:29.856332+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293356304, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295851911, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295851911}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:26:45.136463+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4970727", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:34:29.856383+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:26:45.109939+00:00", "targetGpu": "Vastai_va16", "taskId": "4970729", "taskType": "text-generation", "verifyResult": null}