state: generation 6191 (cycle)

This commit is contained in:
2026-09-12 12:19:17 +00:00
parent 34f76dd221
commit af980128bc
9 changed files with 2228 additions and 2229 deletions

View File

@@ -1383,7 +1383,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-12T12:16:16.575760+00:00",
"generatedAt": "2026-09-12T12:19:16.343986+00:00",
"summary": {
"activeBlockCount": 70,
"byGpuFramework": {

View File

@@ -27,7 +27,7 @@
"11": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 445,
"listingErrors": 446,
"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": "2026-09-12T12:16:16.548766+00:00",
"updatedAt": "2026-09-12T12:19:16.321563+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-12T12:14:24.431862+00:00",
"generatedAt": "2026-09-12T12:17:26.491462+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": "2026-09-12T11:59:10.224777+00:00",
"lastSyncTime": "2026-09-12T11:59:10.019448+00:00",
"generatedAt": "2026-09-12T12:17:17.618280+00:00",
"lastSyncTime": "2026-09-12T12:17:17.415709+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2001,30 +2001,30 @@
"unresolvedFailureCount": 56
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 50,
"decisionFailureRate": 0.9434,
"decisionSuccessRate": 0.0566,
"decisionTotal": 53,
"attributableFailureCount": 51,
"decisionFailureRate": 0.9444,
"decisionSuccessRate": 0.0556,
"decisionTotal": 54,
"failureBreakdown": {
"ambiguous_runtime": 8,
"backend_operator": 27,
"framework_architecture_unsupported": 15,
"memory_capacity": 1,
"model_load": 6,
"model_load": 7,
"repository_structure": 1,
"参数/模板问题": 9
},
"failureCount": 67,
"failureRate": 0.9571,
"failureCount": 68,
"failureRate": 0.9577,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.0429,
"successRate": 0.0423,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 70,
"total": 71,
"unresolvedFailureCount": 17
},
"Mthreads_s4000|llamacpp|text-generation": {
@@ -2417,30 +2417,30 @@
"unresolvedFailureCount": 865
},
"vllm": {
"attributableFailureCount": 270,
"decisionFailureRate": 0.989,
"decisionSuccessRate": 0.011,
"decisionTotal": 273,
"attributableFailureCount": 271,
"decisionFailureRate": 0.9891,
"decisionSuccessRate": 0.0109,
"decisionTotal": 274,
"failureBreakdown": {
"ambiguous_runtime": 200,
"backend_operator": 34,
"framework_architecture_unsupported": 185,
"memory_capacity": 6,
"model_load": 25,
"model_load": 26,
"platform_infrastructure": 1,
"repository_structure": 8,
"runtime_memory": 6,
"tokenizer_compatibility": 6,
"参数/模板问题": 24
},
"failureCount": 495,
"failureCount": 496,
"failureRate": 0.994,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 3,
"successRate": 0.006,
"total": 498,
"total": 499,
"unresolvedFailureCount": 224
},
"vllm-mlu": {
@@ -2545,7 +2545,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-12T11:59:10.220753+00:00",
"generatedAt": "2026-09-12T12:17:17.613681+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2754,28 +2754,28 @@
"unresolvedFailureCount": 91
},
"MetaX_c-500": {
"attributableFailureCount": 50,
"decisionFailureRate": 0.8065,
"decisionSuccessRate": 0.1935,
"decisionTotal": 62,
"attributableFailureCount": 51,
"decisionFailureRate": 0.8095,
"decisionSuccessRate": 0.1905,
"decisionTotal": 63,
"failureBreakdown": {
"ambiguous_runtime": 8,
"backend_operator": 27,
"framework_architecture_unsupported": 15,
"memory_capacity": 1,
"model_load": 6,
"model_load": 7,
"repository_structure": 1,
"参数/模板问题": 17,
"验证失败": 48
},
"failureCount": 123,
"failureRate": 0.9111,
"failureCount": 124,
"failureRate": 0.9118,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 12,
"successRate": 0.0889,
"total": 135,
"successRate": 0.0882,
"total": 136,
"unresolvedFailureCount": 73
},
"Mthreads_s4000": {
@@ -4403,17 +4403,16 @@
"unresolvedFailureCount": 20
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 15,
"tokenizer_compatibility": 1
"ambiguous_runtime": 15
},
"failureCount": 16,
"failureCount": 15,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
@@ -4425,7 +4424,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 16,
"total": 15,
"unresolvedFailureCount": 15
},
"Iluvatar_bi-100|transformers|text-generation": {
@@ -4585,23 +4584,23 @@
"unresolvedFailureCount": 19
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 2,
"model_load": 2,
"model_load": 3,
"repository_structure": 1
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T11:41:06.016003+00:00",
"lastTerminalAt": "2026-09-12T12:17:17.415709+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4609,7 +4608,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 6,
"total": 7,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|llamacpp|text-generation": {
@@ -7256,19 +7255,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1718,
"totalRecords": 1805,
"terminalRecords": 1719,
"totalRecords": 1806,
"totals": {
"attributableFailureCount": 480,
"decisionFailureRate": 0.8939,
"decisionSuccessRate": 0.1061,
"decisionTotal": 537,
"attributableFailureCount": 481,
"decisionFailureRate": 0.8941,
"decisionSuccessRate": 0.1059,
"decisionTotal": 538,
"failureBreakdown": {
"ambiguous_runtime": 403,
"backend_operator": 42,
"framework_architecture_unsupported": 294,
"memory_capacity": 11,
"model_load": 71,
"model_load": 72,
"platform_infrastructure": 4,
"repository_structure": 8,
"runtime_memory": 6,
@@ -7276,21 +7275,20 @@
"参数/模板问题": 101,
"验证失败": 673
},
"failureCount": 1661,
"failureCount": 1662,
"failureRate": 0.9668,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 57,
"successRate": 0.0332,
"total": 1718,
"total": 1719,
"unresolvedFailureCount": 1177
},
"warnings": [
"GPU Ascend_910-b3 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 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。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
@@ -7299,6 +7297,7 @@
"GPU MetaX_c-500 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 Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"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。",
"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 Ascend_910-b4|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7320,6 +7319,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1805,
"summarizedRecords": 1806,
"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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T12:17:17.415709+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-Apollo-V0.1-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T12:13:22+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079266", "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": "2026-09-12T11:41:06.016003+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Lite-Preview-Distill-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T11:37:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079092", "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": "2026-09-12T11:23:23.155704+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T11:17:22+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4543768", "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", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-12T10:56:57.011705+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T10:55:22+00:00", "targetGpu": "Vastai_va16", "taskId": "4554931", "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": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-08T21:43:22.342466+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T21:41:21+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4477978", "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": "2026-09-08T21:43:22.342491+00:00", "modelId": "neuralmagic/Mistral-7B-Instruct-v0.3-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T21:37:22+00:00", "targetGpu": "Vastai_va16", "taskId": "4080288", "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_mtp"], "framework": "", "lastSyncTime": "2026-09-08T21:18:07.599932+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-bf16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T21:15:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332706", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "", "lastSyncTime": "2026-09-08T20:58:55.412682+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T20:57:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481650", "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": "388c9b8c92cd145d40cd7d91a6415810b0edb85d899e1fddee55644e9f161ec8",
".modelhub_state/architecture_history_backfill.json": "e1412fc2515487cbc0d1b02b501278822ee1a9051ec1bfcb499f295de4381251",
".modelhub_state/market_intelligence.json": "c271f472f64cd5d7e20a8caf2e33b61e97a0a17ea98db810c3f6a6371e6cfbf1",
".modelhub_state/official_capabilities.json": "e2133bd845af18091df0c6835bf5af5f96880cce9b054ce25b9beefdca20925b",
".modelhub_state/outcome_checkpoint.json": "07f80607100ed5f4e35737d457405a49c06fe0c03fd6c8111bfd99a1210a2800",
".modelhub_state/architecture_compatibility_blacklist.json": "69d8eae5edec081f49c97196ba22a28d891094ef60f53378839eba68b0c9f711",
".modelhub_state/architecture_history_backfill.json": "b7e18aeb0f4f71966ffbeb5117ffd4a8828f45a90e9b84c0246598e471b23ba3",
".modelhub_state/market_intelligence.json": "fb6d975c2692bb478a77c4b7907f4cea714adfa5a5cc5eaf6861c6153849f6df",
".modelhub_state/official_capabilities.json": "72b620d75624006c8c0646126057e687afb74284312abcaa40e5cf6a5a95eed0",
".modelhub_state/outcome_checkpoint.json": "3657ec027841428715a925f9743884cb5dc5cc64d36a3cf3aa9cd581be2fabc2",
".modelhub_state/queue_cleanup_latest.json": "34b932df05032ee1048c1de50e1c38b8398a18e633d931a757b3bcfc8c50609c",
".modelhub_state/recent_outcomes.jsonl": "3a503824f1ebae887db1aaf7de243f716ffdf5d0245d40f615c32cfa47083e9b",
".modelhub_state/recovery_active_tasks.jsonl": "bf1baa1730541507039426b8811eb1b256a3091875181441fe8abf22c3e8614d",
".modelhub_state/recovery_intents.jsonl": "80a7afac9acb1371c01c8256cbe87fa5da9a489998f0dcb1e42cafb1c1193a9f",
".modelhub_state/recent_outcomes.jsonl": "4bc2b3beca30e786115c0cbdca6c9de06e27fc184666682245e4ddb98e1f7a7c",
".modelhub_state/recovery_active_tasks.jsonl": "543bf6c14a00b70d2a193cc9739acce28822b4d33b9131e5f6235d09d6050fdf",
".modelhub_state/recovery_intents.jsonl": "8661ba928f698167f5475703d0b82f7637110fbaa8646b74b36efb1597cd8817",
".modelhub_state/routing_intelligence.json": "a85a6a865f741b30ed352b033dd21f087adf76d42ad1dafaeaa7ef4b20a26734",
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
"ledger/submissions.jsonl": "eaae6410b44d2a2c7ac0145ff8e6b0d2965f1078cc1044298a0e496dd78627b3",
"outcomes/submissions.jsonl": "43d6e86b1edb700dbbde13f080c1eefb36870d380fd74e7a33df3bbf0502968f"
},
"generation": 6190,
"generation": 6191,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-12T12:16:16.726816+00:00",
"updatedAt": "2026-09-12T12:19:16.998204+00:00",
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
}