state: generation 4911 (cycle)

This commit is contained in:
2026-09-10 02:43:08 +00:00
parent 74a56ddb53
commit 756f81ff47
9 changed files with 2169 additions and 2171 deletions

View File

@@ -1306,7 +1306,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T02:39:44.189528+00:00",
"generatedAt": "2026-09-10T02:43:07.607454+00:00",
"summary": {
"activeBlockCount": 65,
"byGpuFramework": {

View File

@@ -75,7 +75,7 @@
"7": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 349,
"listingErrors": 350,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0,
"mode": "incremental_decision_only",
"nextAccountIndex": 7,
"nextAccountIndex": 8,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-10T02:39:44.165237+00:00",
"updatedAt": "2026-09-10T02:43:07.583518+00:00",
"version": 1
}

View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-09-10T02:23:42.128088+00:00",
"communityAttemptedAt": "2026-09-10T02:40:54.299569+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-09-10T02:23:42.128088+00:00",
"communityUpdatedAt": "2026-09-10T02:40:54.299569+00:00",
"frameworkAttemptedAt": "2026-09-10T00:33:23.734278+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T02:38:14.747399+00:00",
"generatedAt": "2026-09-10T02:40:54.299569+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-10T02:32:07.743588+00:00",
"lastSyncTime": "2026-09-10T02:32:07.501704+00:00",
"generatedAt": "2026-09-10T02:40:45.261552+00:00",
"lastSyncTime": "2026-09-10T02:40:44.943974+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1540,24 +1540,24 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 16,
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 75,
"failureRate": 0.974,
"failureCount": 76,
"failureRate": 0.9744,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.026,
"successRate": 0.0256,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 77,
"unresolvedFailureCount": 55
"total": 78,
"unresolvedFailureCount": 56
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 7,
@@ -1786,29 +1786,29 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 65,
"decisionFailureRate": 0.8784,
"decisionSuccessRate": 0.1216,
"decisionTotal": 74,
"attributableFailureCount": 67,
"decisionFailureRate": 0.8701,
"decisionSuccessRate": 0.1299,
"decisionTotal": 77,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 43,
"framework_architecture_unsupported": 44,
"memory_capacity": 1,
"model_load": 21,
"model_load": 22,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 131,
"failureRate": 0.9357,
"failureCount": 133,
"failureRate": 0.9301,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.0643,
"successCount": 10,
"successRate": 0.0699,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 140,
"total": 143,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2284,29 +2284,29 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 117,
"decisionFailureRate": 0.7134,
"decisionSuccessRate": 0.2866,
"decisionTotal": 164,
"attributableFailureCount": 119,
"decisionFailureRate": 0.7126,
"decisionSuccessRate": 0.2874,
"decisionTotal": 167,
"failureBreakdown": {
"ambiguous_runtime": 100,
"ambiguous_runtime": 101,
"backend_operator": 2,
"framework_architecture_unsupported": 84,
"framework_architecture_unsupported": 85,
"memory_capacity": 5,
"model_load": 23,
"model_load": 24,
"tokenizer_compatibility": 3,
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 946,
"failureRate": 0.9527,
"failureCount": 949,
"failureRate": 0.9519,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 47,
"successRate": 0.0473,
"total": 993,
"unresolvedFailureCount": 829
"successCount": 48,
"successRate": 0.0481,
"total": 997,
"unresolvedFailureCount": 830
},
"vllm": {
"attributableFailureCount": 227,
@@ -2436,7 +2436,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T02:32:07.739281+00:00",
"generatedAt": "2026-09-10T02:40:45.256871+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2516,21 +2516,21 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 16,
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 75,
"failureRate": 0.974,
"failureCount": 76,
"failureRate": 0.9744,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.026,
"total": 77,
"unresolvedFailureCount": 55
"successRate": 0.0256,
"total": 78,
"unresolvedFailureCount": 56
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 17,
@@ -2599,26 +2599,26 @@
"unresolvedFailureCount": 41
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 65,
"decisionFailureRate": 0.8784,
"decisionSuccessRate": 0.1216,
"decisionTotal": 74,
"attributableFailureCount": 67,
"decisionFailureRate": 0.8701,
"decisionSuccessRate": 0.1299,
"decisionTotal": 77,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 43,
"framework_architecture_unsupported": 44,
"memory_capacity": 1,
"model_load": 21,
"model_load": 22,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 131,
"failureRate": 0.9357,
"failureCount": 133,
"failureRate": 0.9301,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.0643,
"total": 140,
"successCount": 10,
"successRate": 0.0699,
"total": 143,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800": {
@@ -4044,24 +4044,24 @@
"decisionSuccessRate": 0.3333,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 3,
"ambiguous_runtime": 4,
"framework_architecture_unsupported": 3,
"tokenizer_compatibility": 1
},
"failureCount": 7,
"failureRate": 0.7778,
"failureCount": 8,
"failureRate": 0.8,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T02:32:07.501704+00:00",
"lastTerminalAt": "2026-09-10T02:40:44.943974+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.2222,
"successRate": 0.2,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 9,
"unresolvedFailureCount": 3
"total": 10,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 4,
@@ -4217,19 +4217,18 @@
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 6,
"backend_operator": 2,
"framework_architecture_unsupported": 2,
"runtime_memory": 1
"framework_architecture_unsupported": 2
},
"failureCount": 11,
"failureCount": 10,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4241,35 +4240,35 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 11,
"total": 10,
"unresolvedFailureCount": 6
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 15,
"consecutiveFailures": 6,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8824,
"decisionSuccessRate": 0.1176,
"decisionTotal": 17,
"decisionFailureRate": 0.8333,
"decisionSuccessRate": 0.1667,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 3,
"framework_architecture_unsupported": 9,
"model_load": 6
"ambiguous_runtime": 2,
"framework_architecture_unsupported": 8,
"model_load": 7
},
"failureCount": 18,
"failureRate": 0.9,
"failureCount": 17,
"failureRate": 0.85,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T02:23:37.132500+00:00",
"lastTerminalAt": "2026-09-10T02:40:44.943952+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.1,
"successCount": 3,
"successRate": 0.15,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 3
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -6765,19 +6764,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1484,
"totalRecords": 1568,
"terminalRecords": 1488,
"totalRecords": 1572,
"totals": {
"attributableFailureCount": 391,
"decisionFailureRate": 0.8907,
"decisionSuccessRate": 0.1093,
"decisionTotal": 439,
"attributableFailureCount": 393,
"decisionFailureRate": 0.8891,
"decisionSuccessRate": 0.1109,
"decisionTotal": 442,
"failureBreakdown": {
"ambiguous_runtime": 276,
"ambiguous_runtime": 277,
"backend_operator": 25,
"framework_architecture_unsupported": 267,
"framework_architecture_unsupported": 268,
"memory_capacity": 11,
"model_load": 45,
"model_load": 46,
"platform_infrastructure": 2,
"repository_structure": 5,
"runtime_memory": 5,
@@ -6785,21 +6784,21 @@
"参数/模板问题": 94,
"验证失败": 673
},
"failureCount": 1436,
"failureRate": 0.9677,
"failureCount": 1439,
"failureRate": 0.9671,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 48,
"successRate": 0.0323,
"total": 1484,
"unresolvedFailureCount": 1043
"successCount": 49,
"successRate": 0.0329,
"total": 1488,
"unresolvedFailureCount": 1044
},
"warnings": [
"GPU Cambricon_mlu-370-x8 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 Iluvatar_mrv-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 Iluvatar_bi-150 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 Vastai_va16 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。",
@@ -6807,7 +6806,7 @@
"GPU hygon_k100-ai 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 Mthreads_s4000 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Biren_166m|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -6828,6 +6827,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1568,
"summarizedRecords": 1572,
"version": 1
}

View File

@@ -1,3 +1,7 @@
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-10T02:40:44.943952+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-10T02:37:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4483083", "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": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-10T02:40:44.943965+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:37:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4483082", "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": "2026-09-10T02:40:44.943974+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:35:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496938", "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": "", "lastSyncTime": "2026-09-10T02:40:44.943909+00:00", "modelId": "neuralmagic/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:33:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4505137", "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": "2026-09-10T02:32:07.501704+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:29:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496940", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T02:32:07.501688+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:25:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505091", "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": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-10T02:23:37.132500+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:19:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4483081", "taskType": "text-generation", "verifyResult": -1}
@@ -294,7 +298,3 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-07T07:41:41.205155+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T07:25:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4461223", "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", "lastSyncTime": "2026-09-07T07:41:41.205219+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T07:09:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4462454", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-07T07:06:44.706649+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-07T06:49:22+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4461327", "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": ["qwen3_vl"], "framework": "", "lastSyncTime": "2026-09-07T06:07:37.712044+00:00", "modelId": "TRNGT/cosmos3-nano-reasoner-fp8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T06:05:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4112282", "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": "2026-09-07T06:07:37.712062+00:00", "modelId": "AI-ModelScope/HackIDLE-NIST-Coder-MLX-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T06:01:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080003", "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": "", "lastSyncTime": "2026-09-07T06:07:37.712028+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T05:57:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080856", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "runtime_memory", "failureAction": "lower_memory_risk_or_reject_combination", "failureCategory": "runtime_memory", "failureClassificationReason": "structured_device_oom", "failureCode": "DEVICE_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-07T05:45:22.903421+00:00", "modelId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T05:43:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4461506", "taskType": "text-generation", "verifyResult": -1}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "62f170b05b71dd3aa167f7ad2de97554032d1b8f7b2780ed625643b3435d8149",
".modelhub_state/architecture_history_backfill.json": "68e16f399c08438dd7960153006c898c3544fd71676226aaa0b6797ceaf526e1",
".modelhub_state/market_intelligence.json": "2ce017bc0ab5ec99121cc38344b681061e8837c0a58594b9f7ac07d41c6fdb99",
".modelhub_state/official_capabilities.json": "d2eeaeb664aa48bada081b3166824718c4ba07be0643551a36b7151556c6d858",
".modelhub_state/outcome_checkpoint.json": "90be78f7c44eaa3829f98e45ec0fa3982431b76904ac599aeae7c67346ec18fd",
".modelhub_state/architecture_compatibility_blacklist.json": "8c8a549a62b87ca3b0cb6bfb1b19ea5040c02e41d256e60d9af3361c33b4ead5",
".modelhub_state/architecture_history_backfill.json": "75148b8957950dfc74216eea36baeca0ff4737fb9307dd34b72bd757d95efa73",
".modelhub_state/market_intelligence.json": "d262216857064dead5c74ef9ac4fe87279d9d1e690226c68b56c4ac335efe2ef",
".modelhub_state/official_capabilities.json": "06122dada1368aaa16bf83cdd53b74cf072f6c090c2efbf273b88f2714d48611",
".modelhub_state/outcome_checkpoint.json": "ac0353427edef1545dcbb1f08137eac5a0602613b527249bd0c8b9a3a732dd20",
".modelhub_state/queue_cleanup_latest.json": "1ff9cf1dcc1b2c2557b532394e1e76da55fa710317d6832581664c56c6ecc7b3",
".modelhub_state/recent_outcomes.jsonl": "9863bdbefbef04e14ac3e1578ca87fa3f1d850c18458c818ba3c6014b13524cf",
".modelhub_state/recovery_active_tasks.jsonl": "93abb99c7e47b4a7a412477b1dd60c5c3e9a9a3edde359f77e50855605ed4f22",
".modelhub_state/recovery_intents.jsonl": "a039f332cbb0de573f47b92b35eaf0441621e04fcc97bbd067c32abeda2ccef1",
".modelhub_state/recent_outcomes.jsonl": "0fb15bca34e7b5f483d04fae8ac20b0e13f58c22111d8116b7b176ca2e6288a2",
".modelhub_state/recovery_active_tasks.jsonl": "20dc43166e965862c06fd9df9cb8f485a1aff97f13646acb29b8b81e2fe7288f",
".modelhub_state/recovery_intents.jsonl": "a11e1e072f133e7b1df4a12b1d33e45b795461cc19807d721406a878bbdb0799",
".modelhub_state/routing_intelligence.json": "289584603011b6a895f3ab1c0b743c174293ab94ad8d2f1f5a3531e01a72207b",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "d242179d528ce949e36ac1834a20e4f46e6d5194c7a834b19b8e1b58d9a1bea6",
"outcomes/submissions.jsonl": "aa4777b88adb640cc19bee1b1611d6a4701b470fc709ec54f48c2db876528cb5"
},
"generation": 4910,
"generation": 4911,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T02:39:44.270944+00:00",
"updatedAt": "2026-09-10T02:43:08.208543+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}