state: generation 5857 (cycle)

This commit is contained in:
2026-09-11 20:05:32 +00:00
parent 7a37d04686
commit 434905af3e
9 changed files with 2154 additions and 2154 deletions

View File

@@ -1307,7 +1307,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-11T20:02:22.766204+00:00",
"generatedAt": "2026-09-11T20:05:31.652113+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -35,7 +35,7 @@
"2": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 419,
"listingErrors": 420,
"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": 2,
"nextAccountIndex": 3,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-11T20:02:22.742126+00:00",
"updatedAt": "2026-09-11T20:05:31.626568+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-11T19:57:58.483765+00:00",
"generatedAt": "2026-09-11T20:03:30.992962+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": "2026-09-11T18:23:30.542558+00:00",
"lastSyncTime": "2026-09-11T18:23:30.509203+00:00",
"generatedAt": "2026-09-11T20:03:23.747278+00:00",
"lastSyncTime": "2026-09-11T20:03:23.495341+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1762,18 +1762,18 @@
"unresolvedFailureCount": 4
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 14,
"attributableFailureCount": 15,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 14,
"decisionTotal": 15,
"failureBreakdown": {
"ambiguous_runtime": 7,
"backend_operator": 2,
"framework_architecture_unsupported": 7,
"framework_architecture_unsupported": 8,
"model_load": 3,
"runtime_memory": 2
},
"failureCount": 21,
"failureCount": 22,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -1783,7 +1783,7 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 21,
"total": 22,
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
@@ -2316,14 +2316,14 @@
"unresolvedFailureCount": 860
},
"vllm": {
"attributableFailureCount": 241,
"decisionFailureRate": 0.9877,
"decisionSuccessRate": 0.0123,
"decisionTotal": 244,
"attributableFailureCount": 242,
"decisionFailureRate": 0.9878,
"decisionSuccessRate": 0.0122,
"decisionTotal": 245,
"failureBreakdown": {
"ambiguous_runtime": 195,
"backend_operator": 33,
"framework_architecture_unsupported": 169,
"framework_architecture_unsupported": 170,
"memory_capacity": 6,
"model_load": 18,
"platform_infrastructure": 1,
@@ -2332,14 +2332,14 @@
"tokenizer_compatibility": 4,
"参数/模板问题": 24
},
"failureCount": 461,
"failureCount": 462,
"failureRate": 0.9935,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.0065,
"total": 464,
"total": 465,
"unresolvedFailureCount": 219
},
"vllm-mlu": {
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-11T18:23:30.538892+00:00",
"generatedAt": "2026-09-11T20:03:23.743013+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2582,27 +2582,27 @@
"unresolvedFailureCount": 26
},
"Iluvatar_bi-150": {
"attributableFailureCount": 19,
"decisionFailureRate": 0.7037,
"decisionSuccessRate": 0.2963,
"decisionTotal": 27,
"attributableFailureCount": 20,
"decisionFailureRate": 0.7143,
"decisionSuccessRate": 0.2857,
"decisionTotal": 28,
"failureBreakdown": {
"ambiguous_runtime": 12,
"backend_operator": 5,
"framework_architecture_unsupported": 8,
"framework_architecture_unsupported": 9,
"model_load": 4,
"runtime_memory": 2,
"参数/模板问题": 1,
"验证失败": 30
},
"failureCount": 62,
"failureRate": 0.8857,
"failureCount": 63,
"failureRate": 0.8873,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 8,
"successRate": 0.1143,
"total": 70,
"successRate": 0.1127,
"total": 71,
"unresolvedFailureCount": 43
},
"Iluvatar_mrv-100": {
@@ -4240,14 +4240,14 @@
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 3,
"backend_operator": 2,
"framework_architecture_unsupported": 1
"backend_operator": 1,
"framework_architecture_unsupported": 2
},
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-09T19:18:48.711664+00:00",
"lastTerminalAt": "2026-09-11T20:03:23.495341+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -6960,17 +6960,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1663,
"totalRecords": 1750,
"terminalRecords": 1664,
"totalRecords": 1751,
"totals": {
"attributableFailureCount": 439,
"decisionFailureRate": 0.8887,
"decisionSuccessRate": 0.1113,
"decisionTotal": 494,
"attributableFailureCount": 440,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 495,
"failureBreakdown": {
"ambiguous_runtime": 393,
"backend_operator": 40,
"framework_architecture_unsupported": 274,
"framework_architecture_unsupported": 275,
"memory_capacity": 11,
"model_load": 61,
"platform_infrastructure": 4,
@@ -6980,31 +6980,30 @@
"参数/模板问题": 99,
"验证失败": 673
},
"failureCount": 1608,
"failureCount": 1609,
"failureRate": 0.9669,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 55,
"successRate": 0.0331,
"total": 1663,
"total": 1664,
"unresolvedFailureCount": 1165
},
"warnings": [
"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 Iluvatar_mrv-100 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 Mthreads_s4000 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 MetaX_c-500 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 Iluvatar_bi-150 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 Cambricon_mlu-370-x8 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 Ascend_910-b4 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 Cambricon_mlu-370-x4 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-x4|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 Mthreads_s4000|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。",
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7019,10 +7018,11 @@
"组合 hygon_k100-ai|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|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 Vastai_va16|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-x4|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 hygon_k100-ai|vllm-patch-tokenizer|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": 1750,
"summarizedRecords": 1751,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"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": "2026-09-11T20:03:23.495341+00:00", "modelId": "amd/Qwen2.5-7B-Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T19:59:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079943", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-11T18:23:30.509203+00:00", "modelId": "LiquidAI/LFM2-2.6B-Transcript-GGUF", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-11T18:21:22+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079227", "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": "2026-09-11T17:04:58.435558+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T16:55:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523307", "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": "", "lastSyncTime": "2026-09-11T14:13:29.151029+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T14:11:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523303", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-08T10:53:19.117664+00:00", "modelId": "mlx-community/Ornith-1.0-9B-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T10:39:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4080189", "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, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-08T10:53:19.117686+00:00", "modelId": "ModelCloud.AI/Qwen2.5-0.5B-Instruct-gptqmodel-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T10:35:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080017", "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": "2026-09-08T10:53:19.117711+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T10:33:22+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4488350", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T10:53:19.117696+00:00", "modelId": "cyankiwi/Ornith-1.0-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T10:27:22+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079920", "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": "1873486f0169f5f278df6757468f54c9caad3786942daa6f2254ddae4e10f87e",
".modelhub_state/architecture_history_backfill.json": "4b7c4d7b0d7de850094d01b5a0e1b70ad362697f41a50413943b808f9e2dd85a",
".modelhub_state/market_intelligence.json": "440000c4e049f28b0e1f6cfa96053964baaca40a7705849c3e9c147b5f09e354",
".modelhub_state/official_capabilities.json": "c8db80bfdf516659f62e6492afc5e5cedeae73b6524d8d684e414b375c61e664",
".modelhub_state/outcome_checkpoint.json": "7d7e3c03435077d702aeac7fea7a39c89cd8c03ced3888612787ab1187604132",
".modelhub_state/architecture_compatibility_blacklist.json": "22f023027a0d9b71f65edd861bfdc31a06ff0ec7c74523992a071594d64c97f1",
".modelhub_state/architecture_history_backfill.json": "bde2c512ca1e96ca96a11285fa8e094f5e65a8ca9520e1c40f7ea5ca89185ab0",
".modelhub_state/market_intelligence.json": "fe0ab3b056e5a4613b09832eab731bea6e87c6fd9ab292fa4e24f25649f5eaa9",
".modelhub_state/official_capabilities.json": "753ce6beb730832c9e1dc085757c137d78c69065a80eed4578ba1d08d6c2b0c5",
".modelhub_state/outcome_checkpoint.json": "55e86664164c52562629967d441a15ba87e9d1d26627448fcb3f574079fd4236",
".modelhub_state/queue_cleanup_latest.json": "aef9d56345e6e6b2c6e9bcc5c224abe9dc0699f57e994e20e663ac3e21dd4b56",
".modelhub_state/recent_outcomes.jsonl": "696c8282e40144a5f62605843b8cc373d73561026952367ea15b6978238ff0df",
".modelhub_state/recovery_active_tasks.jsonl": "f50b50805fea09ed5bca7f47d64aafca5344ee840bd80be4aa9283c6b7abaa92",
".modelhub_state/recovery_intents.jsonl": "4b8e7b3f7eff63ea081fb003ebfbff15247f5722f80ab38b11abbedffe1999c4",
".modelhub_state/recent_outcomes.jsonl": "5ba980b328a3422cdee04766611633e0e0b2ee853a92b1161308dccf348d098a",
".modelhub_state/recovery_active_tasks.jsonl": "8985f450a5856f370538f58287821370421ac67884878b645238efbd3b07df2b",
".modelhub_state/recovery_intents.jsonl": "cb933ed542e0e0168a6599ff99eced2ba3ba422d7724ff84c3645aba65455715",
".modelhub_state/routing_intelligence.json": "2da3713196ca1e91894849ef085aa23e7bbbe62f73e4798de45905af36ff3d02",
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
"ledger/submissions.jsonl": "3ab3b5a7948321363483df7e744cbfbeffd1d760cd4f71f95cc60aff52bdf233",
"outcomes/submissions.jsonl": "7c95d20dc8045bece4b2a76fc32adf6b921687d867ac930b1920289c4b9b4510"
},
"generation": 5856,
"generation": 5857,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-11T20:02:22.844020+00:00",
"updatedAt": "2026-09-11T20:05:32.334443+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42"
}