state: generation 5693 (cycle)

This commit is contained in:
2026-09-11 12:52:37 +00:00
parent 19ac7409f6
commit 79ee103fe8
9 changed files with 2352 additions and 2354 deletions

View File

@@ -1307,7 +1307,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-11T12:49:32.827691+00:00",
"generatedAt": "2026-09-11T12:52:37.052119+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -35,7 +35,7 @@
"2": {
"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": 2,
"nextAccountIndex": 3,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-11T12:49:32.805463+00:00",
"updatedAt": "2026-09-11T12:52:37.015188+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-11T12:47:40.384786+00:00",
"generatedAt": "2026-09-11T12:50:45.178443+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": "2026-09-11T11:19:08.559808+00:00",
"lastSyncTime": "2026-09-11T11:19:08.306651+00:00",
"generatedAt": "2026-09-11T12:50:33.981130+00:00",
"lastSyncTime": "2026-09-11T12:50:33.752023+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1787,30 +1787,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 81,
"decisionFailureRate": 0.8901,
"decisionSuccessRate": 0.1099,
"decisionTotal": 91,
"attributableFailureCount": 82,
"decisionFailureRate": 0.8913,
"decisionSuccessRate": 0.1087,
"decisionTotal": 92,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 32,
"model_load": 33,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 149,
"failureRate": 0.9371,
"failureCount": 150,
"failureRate": 0.9375,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0629,
"successRate": 0.0625,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 159,
"total": 160,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2290,29 +2290,29 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 135,
"decisionFailureRate": 0.7377,
"decisionSuccessRate": 0.2623,
"decisionTotal": 183,
"attributableFailureCount": 136,
"decisionFailureRate": 0.7391,
"decisionSuccessRate": 0.2609,
"decisionTotal": 184,
"failureBreakdown": {
"ambiguous_runtime": 128,
"backend_operator": 4,
"framework_architecture_unsupported": 89,
"memory_capacity": 5,
"model_load": 34,
"model_load": 35,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 57,
"验证失败": 673
},
"failureCount": 994,
"failureRate": 0.9539,
"failureCount": 995,
"failureRate": 0.954,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.0461,
"total": 1042,
"successRate": 0.046,
"total": 1043,
"unresolvedFailureCount": 858
},
"vllm": {
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-11T11:19:08.555805+00:00",
"generatedAt": "2026-09-11T12:50:33.976285+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2606,27 +2606,27 @@
"unresolvedFailureCount": 43
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 81,
"decisionFailureRate": 0.8901,
"decisionSuccessRate": 0.1099,
"decisionTotal": 91,
"attributableFailureCount": 82,
"decisionFailureRate": 0.8913,
"decisionSuccessRate": 0.1087,
"decisionTotal": 92,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 32,
"model_load": 33,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 149,
"failureRate": 0.9371,
"failureCount": 150,
"failureRate": 0.9375,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0629,
"total": 159,
"successRate": 0.0625,
"total": 160,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800": {
@@ -4210,18 +4210,18 @@
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 3,
"backend_operator": 2,
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 1
},
"failureCount": 7,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4233,27 +4233,27 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 7,
"total": 6,
"unresolvedFailureCount": 3
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 17,
"consecutiveFailures": 14,
"consecutiveFailures": 15,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.9444,
"decisionSuccessRate": 0.0556,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 6,
"model_load": 11,
"framework_architecture_unsupported": 5,
"model_load": 12,
"platform_infrastructure": 1
},
"failureCount": 19,
"failureRate": 0.95,
"framework": "unknown",
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-11T07:33:47.206168+00:00",
"lastTerminalAt": "2026-09-11T12:50:33.752023+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -6938,19 +6938,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1653,
"totalRecords": 1740,
"terminalRecords": 1654,
"totalRecords": 1741,
"totals": {
"attributableFailureCount": 433,
"decisionFailureRate": 0.8909,
"decisionSuccessRate": 0.1091,
"decisionTotal": 486,
"attributableFailureCount": 434,
"decisionFailureRate": 0.8912,
"decisionSuccessRate": 0.1088,
"decisionTotal": 487,
"failureBreakdown": {
"ambiguous_runtime": 391,
"backend_operator": 40,
"framework_architecture_unsupported": 273,
"memory_capacity": 11,
"model_load": 56,
"model_load": 57,
"platform_infrastructure": 4,
"repository_structure": 5,
"runtime_memory": 6,
@@ -6958,30 +6958,31 @@
"参数/模板问题": 99,
"验证失败": 673
},
"failureCount": 1600,
"failureRate": 0.9679,
"failureCount": 1601,
"failureRate": 0.968,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 53,
"successRate": 0.0321,
"total": 1653,
"successRate": 0.032,
"total": 1654,
"unresolvedFailureCount": 1163
},
"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。",
@@ -6996,11 +6997,10 @@
"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": 1740,
"summarizedRecords": 1741,
"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": "2026-09-11T12:50:33.752023+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}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-11T11:19:08.306651+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T11:13:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4578314", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-11T11:19:08.306628+00:00", "modelId": "nm-testing/SmolLM-135M-Instruct-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T11:09:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457980", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-11T11:08:14.809954+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T11:05:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457994", "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", "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}
{"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": "2026-09-08T09:05:31.097966+00:00", "modelId": "amd/Qwen2.5-Coder-1.5B-Instruct-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T08:59:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079918", "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": "2026-09-08T08:12:43.104884+00:00", "modelId": "nv-community/Qwen3-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T08:03:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079088", "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": "2026-09-08T08:12:43.104862+00:00", "modelId": "amd/Qwen2.5_3B_Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T08:01:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079942", "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": "0e1a9c7226eba8382a739143af78e4f48d5d73b0f8e78eb797c1064b8684601a",
".modelhub_state/architecture_history_backfill.json": "0e60bb78d6bcbf299b172cc88692f349a33db5035a4b521c7089fbdbf27794ed",
".modelhub_state/market_intelligence.json": "8b63fb51a6fd6537e7c9c3c059abe15c676bae17a5ba908810475073b7fec1c6",
".modelhub_state/official_capabilities.json": "1b1613fe5ba28d4b610fe71477c04047b0864c32695084c4b33cebed55034d0c",
".modelhub_state/outcome_checkpoint.json": "c2d11f8fa2c54c709b06c66c02bba10ff3f4ee109ea7db2ce3a39a44c139fc1f",
".modelhub_state/architecture_compatibility_blacklist.json": "d44c33c7e1d8ecfcbbea2a73838933638a859aca827eead66eeacc611d4b8fa9",
".modelhub_state/architecture_history_backfill.json": "54edc7a6c481d1ca2cbd16544aa6fd56cbc79de0fe509a98df53c2ecc3ad7d99",
".modelhub_state/market_intelligence.json": "6f8d83d1eccdf0b36cd097676c62159a451f048aa0d802e3442b6125d1c38890",
".modelhub_state/official_capabilities.json": "b4114a1c49c2c4f066c1b193e1c9a492ec295e00377756328c778f9c064bcdde",
".modelhub_state/outcome_checkpoint.json": "53ebe66afa934975d2a4207edcd2c0f7dde6df13ef7e42d9be3dec631f961154",
".modelhub_state/queue_cleanup_latest.json": "9092a0b045d21453d0210c81bf56fa209d341915359e8357a6e260c821f48c9b",
".modelhub_state/recent_outcomes.jsonl": "84a846ee1c2269ec077c25ffd0d77f9ca4fe2b3bb5a6ed6f689cb0f45756f8cb",
".modelhub_state/recovery_active_tasks.jsonl": "5d558342fec61827f03fde7c309df3c4ac4680d7d40326487b74cd17644875a2",
".modelhub_state/recovery_intents.jsonl": "821157970d595f1becb0b06b686fdb2847062d2840973d974261b0e36a6f33b6",
".modelhub_state/recent_outcomes.jsonl": "b8d8e0b8bd0359a3e4a51d5ed0462beb114f22e565ce6087128d91d229780b46",
".modelhub_state/recovery_active_tasks.jsonl": "62610261aafec5c3758b820f3f0210aa03b2a6733733d4e91c2e2e5a59700b16",
".modelhub_state/recovery_intents.jsonl": "1fc0aa67da15ff7c32cfe74f5b5bd7ecd3384d6e3035b055b314b3529e785aa2",
".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": 5692,
"generation": 5693,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-11T12:49:32.905005+00:00",
"updatedAt": "2026-09-11T12:52:37.934161+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42"
}