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

state: generation 11421 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-21 11:35:14 +00:00
parent c31c558fe4
commit dce15c60d4
9 changed files with 2066 additions and 1972 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -2671,7 +2671,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-21T11:15:45.200155+00:00",
"generatedAt": "2026-09-21T11:35:05.724592+00:00",
"summary": {
"activeBlockCount": 134,
"byGpuFramework": {

2
.modelhub_state/market_intelligence.json
View File

@@ -434,7 +434,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-21T11:34:01.446001+00:00",
"generatedAt": "2026-09-21T11:35:13.046035+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

6
.modelhub_state/official_capabilities.json
View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-09-21T11:34:01.446001+00:00",
"catalogUpdatedAt": "2026-09-21T11:35:13.046035+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-09-21T11:34:01.446001+00:00",
"generatedAt": "2026-09-21T11:35:13.046035+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6510,6 +6510,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-09-21T11:34:01.446001+00:00",
"taskTreeUpdatedAt": "2026-09-21T11:35:13.046035+00:00",
"version": 1
}

262
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T11:16:32.135781+00:00",
"lastSyncTime": "2026-09-21T11:16:32.032065+00:00",
"generatedAt": "2026-09-21T11:35:05.656601+00:00",
"lastSyncTime": "2026-09-21T11:35:03.480283+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4227,27 +4227,27 @@
"unresolvedFailureCount": 57
},
"Iluvatar_mrv-100|vllm|text-generation": {
"attributableFailureCount": 16,
"decisionFailureRate": 0.5517,
"decisionSuccessRate": 0.4483,
"decisionTotal": 29,
"attributableFailureCount": 17,
"decisionFailureRate": 0.5667,
"decisionSuccessRate": 0.4333,
"decisionTotal": 30,
"failureBreakdown": {
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 15,
"ambiguous_runtime": 6,
"framework_architecture_unsupported": 16,
"model_load": 1
},
"failureCount": 21,
"failureRate": 0.6176,
"failureCount": 23,
"failureRate": 0.6389,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.3824,
"successRate": 0.3611,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 34,
"unresolvedFailureCount": 5
"total": 36,
"unresolvedFailureCount": 6
},
"Kunlunxin_p-800|unknown|text-generation": {
"attributableFailureCount": 1,
@@ -4962,20 +4962,21 @@
"failureBreakdown": {
"ambiguous_runtime": 14,
"framework_architecture_unsupported": 10,
"model_load": 2
"model_load": 2,
"参数/模板问题": 4
},
"failureCount": 26,
"failureRate": 0.8387,
"failureCount": 30,
"failureRate": 0.8571,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 5,
"successRate": 0.1613,
"successRate": 0.1429,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 31,
"unresolvedFailureCount": 14
"total": 35,
"unresolvedFailureCount": 18
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 430,
@@ -5318,17 +5319,17 @@
"unresolvedFailureCount": 6445
},
"vllm": {
"attributableFailureCount": 3527,
"attributableFailureCount": 3528,
"decisionFailureRate": 0.9762,
"decisionSuccessRate": 0.0238,
"decisionTotal": 3613,
"decisionTotal": 3614,
"failureBreakdown": {
"ambiguous_runtime": 1481,
"ambiguous_runtime": 1482,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
"context_length": 161,
"framework_architecture_unsupported": 1297,
"framework_architecture_unsupported": 1298,
"memory_capacity": 720,
"model_load": 207,
"platform_infrastructure": 865,
@@ -5337,15 +5338,15 @@
"tokenizer_compatibility": 411,
"参数/模板问题": 41
},
"failureCount": 5914,
"failureCount": 5916,
"failureRate": 0.9857,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 865,
"successCount": 86,
"successRate": 0.0143,
"total": 6000,
"unresolvedFailureCount": 1522
"total": 6002,
"unresolvedFailureCount": 1523
},
"vllm-customized": {
"attributableFailureCount": 4,
@@ -5451,17 +5452,17 @@
"model_load": 2,
"platform_infrastructure": 17,
"tokenizer_compatibility": 82,
"参数/模板问题": 9
"参数/模板问题": 13
},
"failureCount": 302,
"failureRate": 0.9837,
"failureCount": 306,
"failureRate": 0.9839,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 17,
"successCount": 5,
"successRate": 0.0163,
"total": 307,
"unresolvedFailureCount": 164
"successRate": 0.0161,
"total": 311,
"unresolvedFailureCount": 168
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 67,
@@ -5490,7 +5491,7 @@
"unresolvedFailureCount": 86
}
},
"generatedAt": "2026-09-21T11:16:32.082238+00:00",
"generatedAt": "2026-09-21T11:35:05.645850+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 94,
@@ -5684,16 +5685,16 @@
"unresolvedFailureCount": 1122
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 966,
"decisionFailureRate": 0.8474,
"decisionSuccessRate": 0.1526,
"decisionTotal": 1140,
"attributableFailureCount": 967,
"decisionFailureRate": 0.8475,
"decisionSuccessRate": 0.1525,
"decisionTotal": 1141,
"failureBreakdown": {
"ambiguous_runtime": 345,
"ambiguous_runtime": 346,
"architecture_compatibility": 47,
"backend_operator": 1,
"context_length": 77,
"framework_architecture_unsupported": 287,
"framework_architecture_unsupported": 288,
"memory_capacity": 219,
"model_load": 85,
"platform_infrastructure": 7,
@@ -5704,15 +5705,15 @@
"日志缺失": 6,
"验证失败": 47
},
"failureCount": 1687,
"failureRate": 0.9065,
"failureCount": 1689,
"failureRate": 0.9066,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 7,
"successCount": 174,
"successRate": 0.0935,
"total": 1861,
"unresolvedFailureCount": 714
"successRate": 0.0934,
"total": 1863,
"unresolvedFailureCount": 715
},
"Kunlunxin_p-800": {
"attributableFailureCount": 15,
@@ -5858,19 +5859,19 @@
"platform_infrastructure": 14,
"repository_structure": 57,
"tokenizer_compatibility": 12,
"参数/模板问题": 238,
"参数/模板问题": 242,
"日志缺失": 124,
"验证失败": 130
},
"failureCount": 1764,
"failureRate": 0.9687,
"failureCount": 1768,
"failureRate": 0.9688,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 14,
"successCount": 57,
"successRate": 0.0313,
"total": 1821,
"unresolvedFailureCount": 1306
"successRate": 0.0312,
"total": 1825,
"unresolvedFailureCount": 1310
},
"hygon_k100-ai": {
"attributableFailureCount": 699,
@@ -12162,6 +12163,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|gemma3|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "gemma3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|vllm|text-generation|hrm_text|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -12370,14 +12394,14 @@
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|none": {
"attributableFailureCount": 4,
"attributableFailureCount": 5,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 5,
"failureBreakdown": {
"framework_architecture_unsupported": 4
"framework_architecture_unsupported": 5
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
@@ -12389,7 +12413,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 4,
"total": 5,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3|none": {
@@ -16298,11 +16322,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 3,
"memory_capacity": 2
},
"failureCount": 6,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -16314,7 +16337,32 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 6,
"total": 5,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T11:35:03.480257+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -19592,10 +19640,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 1
},
"failureCount": 2,
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-20T11:30:54.600137+00:00",
@@ -19608,8 +19655,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 1
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 1,
@@ -19711,6 +19758,31 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|gemma3|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-21T11:35:03.480257+00:00",
"modelType": "gemma3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma4|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -28867,6 +28939,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|gemma3|compressed-tensors|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "gemma3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|vllm|text-generation|hrm_text|none|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -29200,14 +29296,14 @@
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|none|33": {
"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": 33,
@@ -29220,7 +29316,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|none|34": {
@@ -34444,55 +34540,55 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16251,
"totalRecords": 16435,
"terminalRecords": 16257,
"totalRecords": 16441,
"totals": {
"attributableFailureCount": 5877,
"decisionFailureRate": 0.8617,
"decisionSuccessRate": 0.1383,
"decisionTotal": 6820,
"attributableFailureCount": 5878,
"decisionFailureRate": 0.8618,
"decisionSuccessRate": 0.1382,
"decisionTotal": 6821,
"failureBreakdown": {
"ambiguous_runtime": 3933,
"ambiguous_runtime": 3934,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 102,
"context_length": 320,
"framework_architecture_unsupported": 2067,
"framework_architecture_unsupported": 2068,
"memory_capacity": 1197,
"model_load": 497,
"platform_infrastructure": 925,
"repository_structure": 736,
"runtime_memory": 85,
"tokenizer_compatibility": 660,
"参数/模板问题": 3180,
"参数/模板问题": 3184,
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15308,
"failureCount": 15314,
"failureRate": 0.942,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 943,
"successRate": 0.058,
"total": 16251,
"unresolvedFailureCount": 8506
"total": 16257,
"unresolvedFailureCount": 8511
},
"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。",
@@ -34532,6 +34628,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16435,
"summarizedRecords": 16441,
"version": 1
}

2
.modelhub_state/recent_outcomes.jsonl
View File

@@ -244,6 +244,7 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671190+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794426, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4205751296, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794426}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.160353+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4970010", "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": "2026-09-20T17:09:45.266141+00:00", "modelId": "OpenBMB/BitCPM-CANN-8B", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16370604914, "estimatedRequiredGiB": 18.305, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm", "modelscopeFileSize": 16378634956, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm", "library:pytorch", "library:transformer", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16378634956}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.155389+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970012", "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", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-20T22:43:47.754917+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430847031, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430847031}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.149678+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970015", "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": "2026-09-21T11:35:03.480257+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.145647+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4970009", "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": "2026-09-20T16:51:24.761950+00:00", "modelId": "sapientinc/HRM-Text-1B", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2365606568, "estimatedRequiredGiB": 2.651, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 2371660433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1182795264, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:hrm", "custom_tag:hierarchical-reasoning", "custom_tag:prefix-lm", "custom_tag:pre-alignment", "custom_tag:non-chat", "custom_tag:non-instruction-tuned"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2371660433}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.140281+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970016", "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", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-20T16:47:50.886473+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.138985+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970013", "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", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-20T16:47:50.886464+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8239718268, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8239718268}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:41:49.135089+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4970008", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"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", "lastSyncTime": "2026-09-20T11:30:54.599890+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25593158704, "estimatedRequiredGiB": 28.626, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 25613691403, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7626590448, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25613691403}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:19.097857+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969393", "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", "lastSyncTime": "2026-09-20T11:30:54.600245+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22263760648, "estimatedRequiredGiB": 24.908, "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": 22286993822, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6019449856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22286993822}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:19.091891+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969394", "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", "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600137+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:19.090425+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969392", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.600306+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "ac4b2845ddd4bdce478dd2b65134ee3ab3d259a119afe6841bf068b135fd4892", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:19.045622+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4969391", "taskType": "text-generation", "verifyResult": -1}

1710
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

2030
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff