state: generation 5702 (cycle)

This commit is contained in:
2026-09-11 13:20:26 +00:00
parent 8f27106d12
commit 7e39f1f45e
9 changed files with 2142 additions and 2143 deletions

View File

@@ -1307,7 +1307,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-11T13:17:33.109768+00:00",
"generatedAt": "2026-09-11T13:20:26.007785+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -27,7 +27,7 @@
"11": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 408,
"listingErrors": 409,
"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": 11,
"nextAccountIndex": 0,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-11T13:17:33.086260+00:00",
"updatedAt": "2026-09-11T13:20:25.983391+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-11T13:15:45.375777+00:00",
"generatedAt": "2026-09-11T13:18:43.511178+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": "2026-09-11T13:09:08.434430+00:00",
"lastSyncTime": "2026-09-11T13:09:08.149747+00:00",
"generatedAt": "2026-09-11T13:18:34.185095+00:00",
"lastSyncTime": "2026-09-11T13:18:33.951636+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1787,30 +1787,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 83,
"decisionFailureRate": 0.8925,
"decisionSuccessRate": 0.1075,
"decisionTotal": 93,
"attributableFailureCount": 84,
"decisionFailureRate": 0.8936,
"decisionSuccessRate": 0.1064,
"decisionTotal": 94,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 34,
"model_load": 35,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 151,
"failureRate": 0.9379,
"failureCount": 152,
"failureRate": 0.9383,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0621,
"successRate": 0.0617,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 161,
"total": 162,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2290,29 +2290,29 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 137,
"decisionFailureRate": 0.7405,
"decisionSuccessRate": 0.2595,
"decisionTotal": 185,
"attributableFailureCount": 138,
"decisionFailureRate": 0.7419,
"decisionSuccessRate": 0.2581,
"decisionTotal": 186,
"failureBreakdown": {
"ambiguous_runtime": 129,
"backend_operator": 4,
"framework_architecture_unsupported": 89,
"memory_capacity": 5,
"model_load": 36,
"model_load": 37,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 57,
"验证失败": 673
},
"failureCount": 997,
"failureCount": 998,
"failureRate": 0.9541,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.0459,
"total": 1045,
"total": 1046,
"unresolvedFailureCount": 859
},
"vllm": {
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-11T13:09:08.430453+00:00",
"generatedAt": "2026-09-11T13:18:34.181402+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2606,27 +2606,27 @@
"unresolvedFailureCount": 43
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 83,
"decisionFailureRate": 0.8925,
"decisionSuccessRate": 0.1075,
"decisionTotal": 93,
"attributableFailureCount": 84,
"decisionFailureRate": 0.8936,
"decisionSuccessRate": 0.1064,
"decisionTotal": 94,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 34,
"model_load": 35,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 151,
"failureRate": 0.9379,
"failureCount": 152,
"failureRate": 0.9383,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0621,
"total": 161,
"successRate": 0.0617,
"total": 162,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800": {
@@ -4237,22 +4237,22 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 17,
"consecutiveFailures": 16,
"consecutiveFailures": 17,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.9444,
"decisionSuccessRate": 0.0556,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 5,
"model_load": 12,
"framework_architecture_unsupported": 4,
"model_load": 13,
"platform_infrastructure": 1
},
"failureCount": 19,
"failureRate": 0.95,
"framework": "unknown",
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-11T13:09:08.149747+00:00",
"lastTerminalAt": "2026-09-11T13:18:33.951636+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -6937,19 +6937,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1656,
"totalRecords": 1743,
"terminalRecords": 1657,
"totalRecords": 1744,
"totals": {
"attributableFailureCount": 435,
"decisionFailureRate": 0.8914,
"decisionSuccessRate": 0.1086,
"decisionTotal": 488,
"attributableFailureCount": 436,
"decisionFailureRate": 0.8916,
"decisionSuccessRate": 0.1084,
"decisionTotal": 489,
"failureBreakdown": {
"ambiguous_runtime": 392,
"backend_operator": 40,
"framework_architecture_unsupported": 273,
"memory_capacity": 11,
"model_load": 58,
"model_load": 59,
"platform_infrastructure": 4,
"repository_structure": 5,
"runtime_memory": 6,
@@ -6957,31 +6957,30 @@
"参数/模板问题": 99,
"验证失败": 673
},
"failureCount": 1603,
"failureCount": 1604,
"failureRate": 0.968,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 53,
"successRate": 0.032,
"total": 1656,
"total": 1657,
"unresolvedFailureCount": 1164
},
"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。",
@@ -6996,10 +6995,11 @@
"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": 1743,
"summarizedRecords": 1744,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"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": "2026-09-11T13:18:33.951636+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T13:11:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523312", "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": "2026-09-11T13:09:08.149747+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T13:07:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523311", "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": "2026-09-11T12:59:52.253401+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T12:59:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4531547", "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": "2026-09-11T12:50:33.752023+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T12:47:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523324", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"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": "2026-09-08T10:00:15.603843+00:00", "modelId": "amd/Qwen2.5-Coder-7B-Instruct-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T09:59:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080012", "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": "2026-09-08T10:00:15.603861+00:00", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T09:57:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080861", "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": "2026-09-08T10:00:15.603853+00:00", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T09:43:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4268342", "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"], "framework": "", "lastSyncTime": "2026-09-08T09:34:21.991823+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T09:21:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332983", "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": "2159364d2d52d3be266ef06aa308f74a53f2a828b158e03881fd76cb6be852b8",
".modelhub_state/architecture_history_backfill.json": "d81041412706ec45e901d3b53a9dd9fa55cfe8dc6d59bcf5ca757fbf78f00623",
".modelhub_state/market_intelligence.json": "462e3021201bce8642c5fc7f9932c88f848c05e19a99a071a80ed27514744b9d",
".modelhub_state/official_capabilities.json": "55bd2b33f23338aabc7566c81077a4df5a0e1e6ef9918820247bae4489098ce3",
".modelhub_state/outcome_checkpoint.json": "fa2160f53ecffc3c528f8efb9365d52bb20df7bf3a1dee9e6e6aad6119ea15d7",
".modelhub_state/architecture_compatibility_blacklist.json": "ab86ba3ef4309173ce00187594d53e3b9e7087deec17955269c369f381d63c06",
".modelhub_state/architecture_history_backfill.json": "d7eb7c8ed912a9cf0eb6871f6dcaa7680dafbb30b2e65ae0008a2c4c4e426839",
".modelhub_state/market_intelligence.json": "ae9fb78b2d4c9ec7c1b915aa4282c5487aa4865c1d3b2275b03d25e8db265cc7",
".modelhub_state/official_capabilities.json": "d270dfd17ed13994d9276db41641338e21af2ad99a4e7bbb9655ad9af9ad95a0",
".modelhub_state/outcome_checkpoint.json": "977810ce19fd052161ef4a2a1efef0d76aedd19ea0da9c9024fd420fb88b7152",
".modelhub_state/queue_cleanup_latest.json": "9092a0b045d21453d0210c81bf56fa209d341915359e8357a6e260c821f48c9b",
".modelhub_state/recent_outcomes.jsonl": "87422de52ccdf1fb67e8d4341ed10d2fd565df8d441f90c7386ce8b681973f48",
".modelhub_state/recovery_active_tasks.jsonl": "83d2a9f5f6a1372f68c352076db2e6d93add8d89a2ad77c5afb218e89b8ad5b7",
".modelhub_state/recovery_intents.jsonl": "185fa3987aa0eee9dd3f017c5b7f7f3da45f2971016fa89a80636c2a5a3c2665",
".modelhub_state/recent_outcomes.jsonl": "f11a53d4b90ec23ba00e975f7de4a6bb40a6de18daa4a39dda008cdda5a42e3a",
".modelhub_state/recovery_active_tasks.jsonl": "4af397ace44d9c4faef510f6efb01dd8fe0009c4fd234f361e6636aac3a39b3a",
".modelhub_state/recovery_intents.jsonl": "5dbf927d5ac5d7877a82fe1950d4ab388a8a02c68453d2ceb39844b99445dc4d",
".modelhub_state/routing_intelligence.json": "01755a7ae15e8408cf0586a62b0684ec4e7e2d46c2715b9b2bfe968c7d40353e",
".modelhub_state/submission_exclusions.jsonl": "3790b5c148f222a4de26d50a3d8afc58891c8da251a82d20dbaf4fc35e6dbd89",
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
"ledger/submissions.jsonl": "0f2922a5f34c5777fcbb7e7ea1512bd1784eed2b74f5d6c3f05103cb3bbea37e",
"outcomes/submissions.jsonl": "9b436339a59d073250c1f14e08f71c1148a29e5b3db2301e39b71ed36893e02b"
},
"generation": 5701,
"generation": 5702,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-11T13:17:33.188419+00:00",
"updatedAt": "2026-09-11T13:20:26.835261+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42"
}