state: generation 8224 (cycle)

This commit is contained in:
2026-09-16 14:15:12 +00:00
parent 187f23dd23
commit b89b7be36f
9 changed files with 1999 additions and 1999 deletions

View File

@@ -1693,7 +1693,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-16T14:11:59.471255+00:00",
"generatedAt": "2026-09-16T14:15:12.043298+00:00",
"summary": {
"activeBlockCount": 82,
"byGpuFramework": {

View File

@@ -75,7 +75,7 @@
"7": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 600,
"listingErrors": 601,
"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": 7,
"nextAccountIndex": 8,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-16T14:11:59.445823+00:00",
"updatedAt": "2026-09-16T14:15:12.018952+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-16T14:10:16.073903+00:00",
"generatedAt": "2026-09-16T14:13:09.508895+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": "2026-09-16T14:03:39.987499+00:00",
"lastSyncTime": "2026-09-16T14:03:38.007248+00:00",
"generatedAt": "2026-09-16T14:13:02.349916+00:00",
"lastSyncTime": "2026-09-16T14:13:00.205420+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1948,29 +1948,29 @@
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 28,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 32,
"attributableFailureCount": 29,
"decisionFailureRate": 0.8788,
"decisionSuccessRate": 0.1212,
"decisionTotal": 33,
"failureBreakdown": {
"ambiguous_runtime": 38,
"framework_architecture_unsupported": 25,
"framework_architecture_unsupported": 26,
"memory_capacity": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 1,
"验证失败": 39
},
"failureCount": 106,
"failureRate": 0.9636,
"failureCount": 107,
"failureRate": 0.964,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 4,
"successRate": 0.0364,
"successRate": 0.036,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 110,
"total": 111,
"unresolvedFailureCount": 78
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
@@ -2758,14 +2758,14 @@
"unresolvedFailureCount": 8
},
"unknown": {
"attributableFailureCount": 181,
"decisionFailureRate": 0.7479,
"decisionSuccessRate": 0.2521,
"decisionTotal": 242,
"attributableFailureCount": 182,
"decisionFailureRate": 0.749,
"decisionSuccessRate": 0.251,
"decisionTotal": 243,
"failureBreakdown": {
"ambiguous_runtime": 157,
"backend_operator": 4,
"framework_architecture_unsupported": 121,
"framework_architecture_unsupported": 122,
"memory_capacity": 5,
"model_load": 46,
"platform_infrastructure": 1,
@@ -2773,14 +2773,14 @@
"参数/模板问题": 66,
"验证失败": 673
},
"failureCount": 1078,
"failureRate": 0.9464,
"failureCount": 1079,
"failureRate": 0.9465,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 61,
"successRate": 0.0536,
"total": 1139,
"successRate": 0.0535,
"total": 1140,
"unresolvedFailureCount": 896
},
"vllm": {
@@ -2918,7 +2918,7 @@
"unresolvedFailureCount": 5
}
},
"generatedAt": "2026-09-16T14:03:39.980991+00:00",
"generatedAt": "2026-09-16T14:13:02.343645+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 49,
@@ -2994,26 +2994,26 @@
"unresolvedFailureCount": 59
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 28,
"decisionFailureRate": 0.875,
"decisionSuccessRate": 0.125,
"decisionTotal": 32,
"attributableFailureCount": 29,
"decisionFailureRate": 0.8788,
"decisionSuccessRate": 0.1212,
"decisionTotal": 33,
"failureBreakdown": {
"ambiguous_runtime": 41,
"framework_architecture_unsupported": 25,
"framework_architecture_unsupported": 26,
"memory_capacity": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 1,
"验证失败": 39
},
"failureCount": 109,
"failureRate": 0.9646,
"failureCount": 110,
"failureRate": 0.9649,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 4,
"successRate": 0.0354,
"total": 113,
"successRate": 0.0351,
"total": 114,
"unresolvedFailureCount": 81
},
"Cambricon_mlu-370-x8": {
@@ -6253,15 +6253,15 @@
"unresolvedFailureCount": 6
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 8,
"consecutiveFailures": 1,
"attributableFailureCount": 9,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 10,
"decisionFailureRate": 0.8182,
"decisionSuccessRate": 0.1818,
"decisionTotal": 11,
"failureBreakdown": {
"ambiguous_runtime": 9,
"framework_architecture_unsupported": 7,
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 8,
"tokenizer_compatibility": 1,
"参数/模板问题": 1
},
@@ -6269,7 +6269,7 @@
"failureRate": 0.9,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-16T00:58:27.147335+00:00",
"lastTerminalAt": "2026-09-16T14:13:00.205420+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -6278,7 +6278,7 @@
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 10
"unresolvedFailureCount": 9
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 1,
@@ -10896,17 +10896,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2018,
"totalRecords": 2112,
"terminalRecords": 2019,
"totalRecords": 2113,
"totals": {
"attributableFailureCount": 648,
"decisionFailureRate": 0.8913,
"decisionSuccessRate": 0.1087,
"decisionTotal": 727,
"attributableFailureCount": 649,
"decisionFailureRate": 0.8915,
"decisionSuccessRate": 0.1085,
"decisionTotal": 728,
"failureBreakdown": {
"ambiguous_runtime": 491,
"backend_operator": 45,
"framework_architecture_unsupported": 424,
"framework_architecture_unsupported": 425,
"memory_capacity": 12,
"model_load": 84,
"platform_infrastructure": 10,
@@ -10916,14 +10916,14 @@
"参数/模板问题": 117,
"验证失败": 673
},
"failureCount": 1939,
"failureCount": 1940,
"failureRate": 0.9609,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 10,
"successCount": 79,
"successRate": 0.0391,
"total": 2018,
"total": 2019,
"unresolvedFailureCount": 1281
},
"warnings": [
@@ -10931,14 +10931,14 @@
"GPU Iluvatar_mrv-100 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 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 Biren_166m 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 hygon_k100-ai 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 Cambricon_mlu-370-x4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b3 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 Vastai_va16 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。",
"组合 Biren_166m|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 Biren_166m|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_fix_tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -10963,6 +10963,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2112,
"summarizedRecords": 2113,
"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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-16T14:13:00.205420+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-16T14:11:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4579947", "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": "2026-09-16T13:55:11.492824+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-16T13:51:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4591816", "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": "2026-09-16T13:55:11.492860+00:00", "modelId": "callmezcc/Qwen3.8-27B-GPTQ-W4A16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-16T13:51:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4609083", "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": "2026-09-16T11:50:54.111136+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-16T11:43:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4590402", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T13:55:40.785120+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T13:47:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610380", "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": "2026-09-10T13:30:05.632388+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T13:23:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496944", "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": "2026-09-10T13:23:06.708419+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T13:19:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496965", "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": "2026-09-10T12:40:42.405633+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:37:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523210", "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": "03c977c2c7629fe35ffa98f20639d3e21d6426c8f7107b9c9da23e43834c3eb4",
".modelhub_state/architecture_history_backfill.json": "129e8206f9b7077594fd196a090418d5ed4cb7c706a78dd898574106789ffe16",
".modelhub_state/market_intelligence.json": "1576fdc7a32031316291c55f68abd24f22aa990d4cb336a1c977724ebe68d687",
".modelhub_state/official_capabilities.json": "ab24424131c599d5cadb9303f6eaa0e58c9b382c73b54c3a0208b255c8ba0f7b",
".modelhub_state/outcome_checkpoint.json": "91edade3ed851e6aeb768d6104b4b711ff5c4cb8c7845e49515c325fd377f9bb",
".modelhub_state/architecture_compatibility_blacklist.json": "cb57ed69bacd710978bde49c4efa746207e8effdec991951ca852c235d9c7760",
".modelhub_state/architecture_history_backfill.json": "ecaaec9634b76e09c55010be3626d7d37dc12ad48c6a5843b67b724dfea9b2f2",
".modelhub_state/market_intelligence.json": "59cc9b02c9f9ac3e25006635d6572a7e84b7463bccbf7cbdbdb7bc40d8130ec5",
".modelhub_state/official_capabilities.json": "1234ac14135fba4b68f1cfb56198285d3e4ba2b698a21314da64fd362d893e0c",
".modelhub_state/outcome_checkpoint.json": "c045be2e7609fd3b269bb28be0ae649fb73688bed508b8cfbf226b1124429a72",
".modelhub_state/queue_cleanup_latest.json": "057079282bc277b3a97c1805915c45464c12312f8ee3ba54d0366d05f34f4466",
".modelhub_state/recent_outcomes.jsonl": "1c47953c8848f46a5d7f000dd779708a08016689c75a99bd80ecff0d8fcc669b",
".modelhub_state/recovery_active_tasks.jsonl": "e26cb3b940df04e297c3ffbc4ddfa643de273fd5d087a5303a6e467a1f9e3457",
".modelhub_state/recovery_intents.jsonl": "88e9d87e194a325c35a997db4dcf5f3272aadb5671c6ee821fb1b793df5c9f77",
".modelhub_state/recent_outcomes.jsonl": "026cae23eddb0e9717516c063b2835d5a1a4628e460282f8d85937166990c107",
".modelhub_state/recovery_active_tasks.jsonl": "efb377b80b478d7ed27724cf027049f1a76cb23f7a663670f61633d7c5d67c15",
".modelhub_state/recovery_intents.jsonl": "de7c538f3c466a52956f159fa376a21e2bc87f343d19e6e9e9f1bc15214f2dff",
".modelhub_state/routing_intelligence.json": "6eb0869a3775dab84161e373d7a23bd67d2843b691074760b256dca93142d124",
".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
"ledger/submissions.jsonl": "1a49861c72001064b378e98b55269416e82d59164cbdff44740b3a41cd51b00e",
"outcomes/submissions.jsonl": "ca14c26ce5c7d7b172905c62fb42591fad0f19eb29c4b63f8333d9c1cf96ad86"
},
"generation": 8223,
"generation": 8224,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-16T14:11:59.576857+00:00",
"updatedAt": "2026-09-16T14:15:12.538879+00:00",
"writerId": "eccb3e0018f640d19e578c271a207b5c"
}