CoolBoy/submmit
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

state: generation 10673 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-20 15:32:28 +00:00
parent 94f10cfbd8
commit 993bfd3853
9 changed files with 1798 additions and 1730 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -236,7 +236,7 @@
"ascend_910-b3|vllm|text-generation|model_type:rwkv7": {
"architectureSignature": "model_type:rwkv7",
"architectures": [],
"evidenceCount": 2,
"evidenceCount": 1,
"expiresAt": "2026-10-14T23:57:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-14T23:57:21+00:00",
@@ -244,12 +244,10 @@
"matchType": "model_type",
"modelType": "rwkv7",
"sourceModelIds": [
"RWKV/RWKV7-7.2B-20260805",
"RWKV/RWKV7-13.3B-20260805"
"RWKV/RWKV7-7.2B-20260805"
],
"sourceTaskIds": [
"4591876",
"4582655"
"4591876"
],
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation"
@@ -1954,7 +1952,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-20T15:28:56.556770+00:00",
"generatedAt": "2026-09-20T15:32:19.726582+00:00",
"summary": {
"activeBlockCount": 95,
"byGpuFramework": {

2
.modelhub_state/market_intelligence.json
View File

@@ -425,7 +425,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-20T15:31:18.329940+00:00",
"generatedAt": "2026-09-20T15:32:27.644108+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

6
.modelhub_state/official_capabilities.json
View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-09-20T15:31:18.329940+00:00",
"catalogUpdatedAt": "2026-09-20T15:32:27.644108+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-09-20T15:31:18.329940+00:00",
"generatedAt": "2026-09-20T15:32:27.644108+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6422,6 +6422,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-09-20T15:31:18.329940+00:00",
"taskTreeUpdatedAt": "2026-09-20T15:32:27.644108+00:00",
"version": 1
}

171
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-20T15:25:29.241097+00:00",
"lastSyncTime": "2026-09-20T15:25:28.950050+00:00",
"generatedAt": "2026-09-20T15:32:19.669979+00:00",
"lastSyncTime": "2026-09-20T15:32:19.355892+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -240,7 +240,7 @@
"ascend_910-b3|vllm|text-generation|model_type:rwkv7": {
"architectureSignature": "model_type:rwkv7",
"architectures": [],
"evidenceCount": 2,
"evidenceCount": 1,
"expiresAt": "2026-10-14T23:57:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-14T23:57:21+00:00",
@@ -248,12 +248,10 @@
"matchType": "model_type",
"modelType": "rwkv7",
"sourceModelIds": [
"RWKV/RWKV7-7.2B-20260805",
"RWKV/RWKV7-13.3B-20260805"
"RWKV/RWKV7-7.2B-20260805"
],
"sourceTaskIds": [
"4591876",
"4582655"
"4591876"
],
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation"
@@ -2373,27 +2371,27 @@
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 35,
"decisionFailureRate": 0.7,
"decisionSuccessRate": 0.3,
"decisionTotal": 50,
"attributableFailureCount": 36,
"decisionFailureRate": 0.7059,
"decisionSuccessRate": 0.2941,
"decisionTotal": 51,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 27,
"model_load": 7,
"model_load": 8,
"tokenizer_compatibility": 1
},
"failureCount": 36,
"failureRate": 0.7059,
"failureCount": 37,
"failureRate": 0.7115,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 15,
"successRate": 0.2941,
"successRate": 0.2885,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 51,
"total": 52,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -4471,10 +4469,10 @@
"unresolvedFailureCount": 6405
},
"vllm": {
"attributableFailureCount": 3475,
"attributableFailureCount": 3476,
"decisionFailureRate": 0.9778,
"decisionSuccessRate": 0.0222,
"decisionTotal": 3554,
"decisionTotal": 3555,
"failureBreakdown": {
"ambiguous_runtime": 1434,
"architecture_compatibility": 112,
@@ -4483,21 +4481,21 @@
"context_length": 161,
"framework_architecture_unsupported": 1261,
"memory_capacity": 720,
"model_load": 198,
"model_load": 199,
"platform_infrastructure": 864,
"repository_structure": 470,
"runtime_memory": 60,
"tokenizer_compatibility": 408,
"参数/模板问题": 40
},
"failureCount": 5813,
"failureCount": 5814,
"failureRate": 0.9866,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 864,
"successCount": 79,
"successRate": 0.0134,
"total": 5892,
"total": 5893,
"unresolvedFailureCount": 1474
},
"vllm-customized": {
@@ -4631,7 +4629,7 @@
"unresolvedFailureCount": 24
}
},
"generatedAt": "2026-09-20T15:25:29.233684+00:00",
"generatedAt": "2026-09-20T15:32:19.661307+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 75,
@@ -4687,17 +4685,17 @@
"unresolvedFailureCount": 588
},
"Biren_166m": {
"attributableFailureCount": 173,
"decisionFailureRate": 0.8737,
"decisionSuccessRate": 0.1263,
"decisionTotal": 198,
"attributableFailureCount": 174,
"decisionFailureRate": 0.8744,
"decisionSuccessRate": 0.1256,
"decisionTotal": 199,
"failureBreakdown": {
"ambiguous_runtime": 131,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 114,
"memory_capacity": 1,
"model_load": 18,
"model_load": 19,
"platform_infrastructure": 2,
"repository_structure": 18,
"runtime_memory": 2,
@@ -4706,14 +4704,14 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 609,
"failureCount": 610,
"failureRate": 0.9606,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.0394,
"total": 634,
"total": 635,
"unresolvedFailureCount": 434
},
"Cambricon_mlu-370-x4": {
@@ -5816,6 +5814,29 @@
"total": 5,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|mistral|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "mistral",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|muse_glimmer|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -11284,28 +11305,29 @@
"unresolvedFailureCount": 5
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 2,
"consecutiveFailures": 1,
"attributableFailureCount": 3,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.3333,
"decisionTotal": 3,
"decisionFailureRate": 0.75,
"decisionSuccessRate": 0.25,
"decisionTotal": 4,
"failureBreakdown": {
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 2,
"model_load": 1
},
"failureCount": 2,
"failureRate": 0.6667,
"failureCount": 3,
"failureRate": 0.75,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T15:25:28.950050+00:00",
"lastTerminalAt": "2026-09-20T15:32:19.355892+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.3333,
"successRate": 0.25,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 3,
"total": 4,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -11964,6 +11986,31 @@
"total": 3,
"unresolvedFailureCount": 3
},
"Biren_166m|vllm|text-generation|mistral|compressed-tensors": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-20T15:32:19.355892+00:00",
"modelType": "mistral",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|nemotron_h|modelopt": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -14361,6 +14408,30 @@
"total": 4,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|mistral|compressed-tensors|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "mistral",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|muse_glimmer|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -22405,13 +22476,13 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 15877,
"totalRecords": 15982,
"terminalRecords": 15878,
"totalRecords": 15983,
"totals": {
"attributableFailureCount": 5756,
"attributableFailureCount": 5757,
"decisionFailureRate": 0.8613,
"decisionSuccessRate": 0.1387,
"decisionTotal": 6683,
"decisionTotal": 6684,
"failureBreakdown": {
"ambiguous_runtime": 3770,
"architecture_compatibility": 212,
@@ -22420,7 +22491,7 @@
"context_length": 318,
"framework_architecture_unsupported": 1986,
"memory_capacity": 1195,
"model_load": 478,
"model_load": 479,
"platform_infrastructure": 922,
"repository_structure": 734,
"runtime_memory": 78,
@@ -22429,14 +22500,14 @@
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 14950,
"failureCount": 14951,
"failureRate": 0.9416,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 927,
"successRate": 0.0584,
"total": 15877,
"total": 15878,
"unresolvedFailureCount": 8272
},
"warnings": [
@@ -22482,12 +22553,12 @@
"组合 Cambricon_mlu-370-x4|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-150|transformers|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|vllm|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。",
"组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
"组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 15982,
"summarizedRecords": 15983,
"version": 1
}

2
.modelhub_state/recent_outcomes.jsonl
View File

@@ -38,6 +38,7 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-20T14:34:57.856723+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504850, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504850}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:14:41.848764+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970580", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-20T12:34:29.856361+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955963132, "modelscopeLicense": "other", "modelscopeParams": 256113408, "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", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955963132}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:14:41.846486+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970590", "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": "2026-09-20T12:58:28.353096+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "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": 17788663591, "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": 17788663591}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:09:56.550329+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970503", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-20T15:32:19.355892+00:00", "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221588, "modelscopeLicense": "llama2", "modelscopeParams": 12247782400, "modelscopeTags": ["license:llama2", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8338221588}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:09:56.548188+00:00", "targetGpu": "Biren_166m", "taskId": "4970505", "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": "2026-09-20T12:34:29.856396+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-Research", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "17a693aa8ae65d96fb0c459d2e1f98ce1d8b2f8933e06b75903df1a5b48287eb", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008118474, "modelscopeLicense": "cc-by-nc-sa-4.0", "modelscopeParams": 7501651968, "modelscopeTags": ["license:cc-by-nc-sa-4.0", "model_type:mpt", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008118474}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:09:56.540284+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970507", "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": "2026-09-20T12:34:29.856340+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T04:09:56.493446+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970510", "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}
@@ -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": "", "lastSyncTime": "2026-09-14T04:51:03.045568+00:00", "modelId": "siliconflow/gpt-oss-20b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T04:45:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610351", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-14T03:38:15.505403+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T03:35:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4596909", "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": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-14T02:51:59.045472+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T02:47:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4493314", "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": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-14T02:14:40.319417+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T02:13:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4582655", "taskType": "text-generation", "verifyResult": -1}

1332
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1982
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff