state: generation 5860 (cycle)

This commit is contained in:
2026-09-11 20:16:48 +00:00
parent 2b1e80104f
commit 3a55ee3876
9 changed files with 2144 additions and 2144 deletions

View File

@@ -1307,7 +1307,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-11T20:13:34.848080+00:00",
"generatedAt": "2026-09-11T20:16:47.729497+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -59,7 +59,7 @@
"5": {
"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": 5,
"nextAccountIndex": 6,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-11T20:13:34.786737+00:00",
"updatedAt": "2026-09-11T20:16:47.707137+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-11T20:09:36.802651+00:00",
"generatedAt": "2026-09-11T20:14:42.115892+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": "2026-09-11T20:03:23.747278+00:00",
"lastSyncTime": "2026-09-11T20:03:23.495341+00:00",
"generatedAt": "2026-09-11T20:14:35.806830+00:00",
"lastSyncTime": "2026-09-11T20:14:35.600665+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1637,9 +1637,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5
"ambiguous_runtime": 6
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "transformers",
"pendingCount": 0,
@@ -1649,8 +1649,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 5
"total": 6,
"unresolvedFailureCount": 6
},
"Iluvatar_bi-100|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -2277,17 +2277,17 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5
"ambiguous_runtime": 6
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 5,
"unresolvedFailureCount": 5
"total": 6,
"unresolvedFailureCount": 6
},
"unknown": {
"attributableFailureCount": 141,
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-11T20:03:23.743013+00:00",
"generatedAt": "2026-09-11T20:14:35.802524+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2568,18 +2568,18 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 6,
"ambiguous_runtime": 7,
"验证失败": 20
},
"failureCount": 26,
"failureCount": 27,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 26,
"unresolvedFailureCount": 26
"total": 27,
"unresolvedFailureCount": 27
},
"Iluvatar_bi-150": {
"attributableFailureCount": 20,
@@ -4191,13 +4191,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "transformers",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-08T21:43:22.342466+00:00",
"lastTerminalAt": "2026-09-11T20:14:35.600665+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4205,8 +4205,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-150|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -6960,15 +6960,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1664,
"totalRecords": 1751,
"terminalRecords": 1665,
"totalRecords": 1752,
"totals": {
"attributableFailureCount": 440,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 495,
"failureBreakdown": {
"ambiguous_runtime": 393,
"ambiguous_runtime": 394,
"backend_operator": 40,
"framework_architecture_unsupported": 275,
"memory_capacity": 11,
@@ -6980,30 +6980,31 @@
"参数/模板问题": 99,
"验证失败": 673
},
"failureCount": 1609,
"failureRate": 0.9669,
"failureCount": 1610,
"failureRate": 0.967,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 55,
"successRate": 0.0331,
"total": 1664,
"unresolvedFailureCount": 1165
"successRate": 0.033,
"total": 1665,
"unresolvedFailureCount": 1166
},
"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 Iluvatar_bi-150 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 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 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。",
"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。",
@@ -7018,11 +7019,10 @@
"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": 1751,
"summarizedRecords": 1752,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"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": "2026-09-11T20:14:35.600665+00:00", "modelId": "amd/Qwen2.5-7B-Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T20:07:21+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4080034", "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": "2026-09-11T20:03:23.495341+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}
@@ -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": "2026-09-08T10:53:19.117704+00:00", "modelId": "BAAI/AquilaDense-7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T10:51:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079198", "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": "2026-09-08T10:53:19.117664+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}

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": "b0012d351e49ac3ce7b52ae0aafde1b17921457c7ddc47bc0aeda3c98d64b784",
".modelhub_state/architecture_history_backfill.json": "164ad5c2b80e0827d238aa632cc0448d4e7d61fb1f83a16cd42940615d5df573",
".modelhub_state/market_intelligence.json": "d241dc1402475f67d5a8fe92ac2f925c64b452c818385be3587c177b9164ad71",
".modelhub_state/official_capabilities.json": "cebaebe412d7653ab9cd59ca75d245bf1119be08210491ff4d915011e6e640c2",
".modelhub_state/outcome_checkpoint.json": "55e86664164c52562629967d441a15ba87e9d1d26627448fcb3f574079fd4236",
".modelhub_state/architecture_compatibility_blacklist.json": "20c7c2c8c8e1ab457bfadd19da625f7ca54855706fcf1a9631bf2306a7763030",
".modelhub_state/architecture_history_backfill.json": "9270eceb58e760de4d14530359d2c27a940b307060f11373a92d9e3be64745e8",
".modelhub_state/market_intelligence.json": "659554b0e324ef43f669943d5acc2d86020c15f32e4912d63693b4aea318d9d0",
".modelhub_state/official_capabilities.json": "5001f857ca1b0aa3c26a90fa165f5ee8c3bd1eb8e25090570a103ab0aaf2a499",
".modelhub_state/outcome_checkpoint.json": "014f8a2455be0cfd1a8501719da688ca7ca1d104664da85485f2d525e886f4cd",
".modelhub_state/queue_cleanup_latest.json": "aef9d56345e6e6b2c6e9bcc5c224abe9dc0699f57e994e20e663ac3e21dd4b56",
".modelhub_state/recent_outcomes.jsonl": "5ba980b328a3422cdee04766611633e0e0b2ee853a92b1161308dccf348d098a",
".modelhub_state/recovery_active_tasks.jsonl": "8985f450a5856f370538f58287821370421ac67884878b645238efbd3b07df2b",
".modelhub_state/recovery_intents.jsonl": "cb933ed542e0e0168a6599ff99eced2ba3ba422d7724ff84c3645aba65455715",
".modelhub_state/recent_outcomes.jsonl": "0c0089683190e9c3458f7155e642dec540718ef12e799fb0a9fef3506152743c",
".modelhub_state/recovery_active_tasks.jsonl": "2f7c646c3f7a608a95aedde015a2eb8f7f328e9a6f90bc3c20d280847d9da007",
".modelhub_state/recovery_intents.jsonl": "540684915e40231f3faa69756128e8502bf15fa1588adf0d555d256362067cf0",
".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": 5859,
"generation": 5860,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-11T20:13:34.989819+00:00",
"updatedAt": "2026-09-11T20:16:48.330238+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42"
}