state: generation 9222 (cycle)

This commit is contained in:
2026-09-18 11:38:06 +00:00
parent c37673add4
commit 7abcacd6f2
9 changed files with 1859 additions and 1859 deletions

View File

@@ -1745,7 +1745,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-18T11:35:11.181253+00:00",
"generatedAt": "2026-09-18T11:38:05.594666+00:00",
"summary": {
"activeBlockCount": 84,
"byGpuFramework": {

View File

@@ -11,7 +11,7 @@
"1": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 673,
"listingErrors": 674,
"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": 1,
"nextAccountIndex": 2,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-18T11:35:11.156665+00:00",
"updatedAt": "2026-09-18T11:38:05.568407+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-18T11:33:38.718078+00:00",
"generatedAt": "2026-09-18T11:36:19.365263+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": "2026-09-18T11:18:54.959201+00:00",
"lastSyncTime": "2026-09-18T11:18:54.918111+00:00",
"generatedAt": "2026-09-18T11:36:12.168347+00:00",
"lastSyncTime": "2026-09-18T11:36:11.987002+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2286,7 +2286,7 @@
"decisionSuccessRate": 0.1615,
"decisionTotal": 130,
"failureBreakdown": {
"ambiguous_runtime": 23,
"ambiguous_runtime": 24,
"framework_architecture_unsupported": 64,
"memory_capacity": 1,
"model_load": 43,
@@ -2295,18 +2295,18 @@
"参数/模板问题": 3,
"验证失败": 47
},
"failureCount": 183,
"failureRate": 0.8971,
"failureCount": 184,
"failureRate": 0.8976,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 21,
"successRate": 0.1029,
"successRate": 0.1024,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 204,
"unresolvedFailureCount": 73
"total": 205,
"unresolvedFailureCount": 74
},
"Iluvatar_mrv-100|vllm|text-generation": {
"attributableFailureCount": 11,
@@ -2821,7 +2821,7 @@
"decisionSuccessRate": 0.2685,
"decisionTotal": 257,
"failureBreakdown": {
"ambiguous_runtime": 163,
"ambiguous_runtime": 164,
"backend_operator": 4,
"framework_architecture_unsupported": 126,
"memory_capacity": 5,
@@ -2832,15 +2832,15 @@
"参数/模板问题": 73,
"验证失败": 673
},
"failureCount": 1098,
"failureCount": 1099,
"failureRate": 0.9409,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 69,
"successRate": 0.0591,
"total": 1167,
"unresolvedFailureCount": 909
"total": 1168,
"unresolvedFailureCount": 910
},
"vllm": {
"attributableFailureCount": 412,
@@ -2979,7 +2979,7 @@
"unresolvedFailureCount": 17
}
},
"generatedAt": "2026-09-18T11:18:54.953778+00:00",
"generatedAt": "2026-09-18T11:36:12.163120+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 58,
@@ -3151,7 +3151,7 @@
"decisionSuccessRate": 0.1549,
"decisionTotal": 142,
"failureBreakdown": {
"ambiguous_runtime": 25,
"ambiguous_runtime": 26,
"framework_architecture_unsupported": 74,
"memory_capacity": 1,
"model_load": 44,
@@ -3160,15 +3160,15 @@
"参数/模板问题": 3,
"验证失败": 47
},
"failureCount": 196,
"failureRate": 0.8991,
"failureCount": 197,
"failureRate": 0.8995,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 22,
"successRate": 0.1009,
"total": 218,
"unresolvedFailureCount": 75
"successRate": 0.1005,
"total": 219,
"unresolvedFailureCount": 76
},
"Kunlunxin_p-800": {
"attributableFailureCount": 1,
@@ -7653,19 +7653,19 @@
"unresolvedFailureCount": 2
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 10,
"consecutiveFailures": 10,
"attributableFailureCount": 9,
"consecutiveFailures": 9,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 10,
"decisionTotal": 9,
"failureBreakdown": {
"backend_operator": 1,
"framework_architecture_unsupported": 5,
"model_load": 3,
"model_load": 2,
"repository_structure": 1
},
"failureCount": 10,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -7677,19 +7677,19 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 10,
"total": 9,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 13,
"attributableFailureCount": 12,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.6842,
"decisionSuccessRate": 0.3158,
"decisionTotal": 19,
"decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.3333,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 11,
"model_load": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 1
},
@@ -7697,7 +7697,7 @@
"failureRate": 0.7,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-17T14:39:04.244134+00:00",
"lastTerminalAt": "2026-09-18T11:36:11.987002+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -7706,7 +7706,7 @@
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 1
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -14337,15 +14337,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2248,
"totalRecords": 2351,
"terminalRecords": 2249,
"totalRecords": 2352,
"totals": {
"attributableFailureCount": 731,
"decisionFailureRate": 0.8431,
"decisionSuccessRate": 0.1569,
"decisionTotal": 867,
"failureBreakdown": {
"ambiguous_runtime": 564,
"ambiguous_runtime": 565,
"backend_operator": 55,
"framework_architecture_unsupported": 482,
"memory_capacity": 12,
@@ -14357,15 +14357,15 @@
"参数/模板问题": 133,
"验证失败": 673
},
"failureCount": 2112,
"failureCount": 2113,
"failureRate": 0.9395,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 11,
"successCount": 136,
"successRate": 0.0605,
"total": 2248,
"unresolvedFailureCount": 1370
"total": 2249,
"unresolvedFailureCount": 1371
},
"warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
@@ -14405,6 +14405,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2351,
"summarizedRecords": 2352,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"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": "2026-09-18T11:36:11.987002+00:00", "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-18T11:29:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4610408", "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", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-18T08:57:11.697973+00:00", "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-18T08:51:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4490562", "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": "2026-09-18T05:37:23.595667+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-18T05:33:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458008", "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": "2026-09-18T04:07:34.207962+00:00", "modelId": "BAAI/Aerospace-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-18T03:59:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471933", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"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": "2026-09-12T02:48:11.158114+00:00", "modelId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:43:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458009", "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": "2026-09-12T02:39:29.219599+00:00", "modelId": "RedHatAI/Qwen2.5-3B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:39:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4100876", "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_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["mellum"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T02:39:29.219629+00:00", "modelId": "JetBrains/Mellum2-12B-A2.5B-Thinking", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:35:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4152611", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T02:30:20.417896+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-2507-Gemini-3-Pro-Preview-High-Reasoning-Distill-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:27:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079970", "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": "ff1779e6801878e6a892951cf5028cb1238ac35275fad3efdc0f06c672635b5b",
".modelhub_state/architecture_history_backfill.json": "b66c9280f0e4a38705e42e7efcf73eb6c6f4141557965a40d1d07b07dbf1218f",
".modelhub_state/market_intelligence.json": "5c93342aeb7d94ee4c0b7eaf96c2053e01190cf5805bdc9057573efe44fbf20a",
".modelhub_state/official_capabilities.json": "e7df3011e04c609b1e9da389041fe751f60f736a561a3910ed7f4ac0626f97b9",
".modelhub_state/outcome_checkpoint.json": "e1540fa5516e7d0eee414081bf1cd36bf55e42a966c267fcd699ab46779ed3ed",
".modelhub_state/architecture_compatibility_blacklist.json": "38e5ec4a971596e007f4f0d74300db41a266d3162306b46867863541301ac280",
".modelhub_state/architecture_history_backfill.json": "5da72065229e543b303e2bae710c171306d7951bc2084552fe9e36bcd5aad9b0",
".modelhub_state/market_intelligence.json": "8d228e9702f5b46558bef3deec3ba84b0e35a4e8364386e91eb113c4e9a01150",
".modelhub_state/official_capabilities.json": "ffc8a1e6dea890813263321e7215fe018238fc0acc27273526aad102dd9f7ffc",
".modelhub_state/outcome_checkpoint.json": "3b22ec10268cef835ccb99c119fe9cd578941421337db59264e7637496e8c039",
".modelhub_state/queue_cleanup_latest.json": "54b0840bc2b48f9e843dbc6cd12416fea7092c8eb00f4572dd0223938b47b3ea",
".modelhub_state/recent_outcomes.jsonl": "767c985ed59510e3687730ca9ac6d7d36f203f216d70ba53bfac8119d3f1c78f",
".modelhub_state/recovery_active_tasks.jsonl": "2765163b62670ed688beaa13e15ed3e4b64636c24074806b4540467a870de27f",
".modelhub_state/recovery_intents.jsonl": "2528d19c8262f14a3ca43617373d1904738534a16f7bcad43d2318ab63b2daad",
".modelhub_state/recent_outcomes.jsonl": "b2ba223133452b30e9fe574bccbf89880138a05df5540e015acb737e07181e73",
".modelhub_state/recovery_active_tasks.jsonl": "9b641316b1e36fa1784af0ef8dc073790133ddae7a504c821cfa799798c6d044",
".modelhub_state/recovery_intents.jsonl": "5b0fcca8ec0ecb246710535a92c2d2d162d0c8944b08105e246c316222522ff5",
".modelhub_state/routing_intelligence.json": "6e3e3cec2e19fa831fc5172cb8a106b3edcbcecbf32bd92e366e46b0e92f93f8",
".modelhub_state/submission_exclusions.jsonl": "97f5961c6b5663f29d9de57c0c9ebe69b2db497d02e39fc863a7942e652cdf07",
".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
"ledger/submissions.jsonl": "63562b7b8506187307f5dde7a98da8cd721d577ae94f543353f232f289896927",
"outcomes/submissions.jsonl": "d619df9b2d4bdccece911ecb2d1d9092236de50169447b59ee3e968ce3b5815e"
},
"generation": 9221,
"generation": 9222,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-18T11:35:11.326589+00:00",
"updatedAt": "2026-09-18T11:38:06.090884+00:00",
"writerId": "217f1806b49c401894bed7ce18be9095"
}