state: generation 7449 (cycle)

This commit is contained in:
2026-09-15 00:33:36 +00:00
parent 719363dae4
commit b54aff5061
9 changed files with 1991 additions and 1992 deletions

View File

@@ -1556,7 +1556,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-15T00:30:27.622858+00:00",
"generatedAt": "2026-09-15T00:33:35.043848+00:00",
"summary": {
"activeBlockCount": 77,
"byGpuFramework": {

View File

@@ -51,7 +51,7 @@
"4": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 540,
"listingErrors": 541,
"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": 4,
"nextAccountIndex": 5,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-15T00:30:27.597534+00:00",
"updatedAt": "2026-09-15T00:33:35.008440+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-15T00:28:33.024840+00:00",
"generatedAt": "2026-09-15T00:31:52.291307+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": "2026-09-15T00:22:04.571941+00:00",
"lastSyncTime": "2026-09-15T00:22:04.249561+00:00",
"generatedAt": "2026-09-15T00:31:35.057561+00:00",
"lastSyncTime": "2026-09-15T00:31:34.841419+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2098,11 +2098,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 42,
"ambiguous_runtime": 43,
"memory_capacity": 1,
"验证失败": 22
},
"failureCount": 65,
"failureCount": 66,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
@@ -2112,8 +2112,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 65,
"unresolvedFailureCount": 64
"total": 66,
"unresolvedFailureCount": 65
},
"Kunlunxin_p-800|unknown|visual-multi-modal": {
"attributableFailureCount": 0,
@@ -2577,7 +2577,7 @@
"decisionSuccessRate": 0.2569,
"decisionTotal": 218,
"failureBreakdown": {
"ambiguous_runtime": 152,
"ambiguous_runtime": 153,
"backend_operator": 4,
"framework_architecture_unsupported": 104,
"memory_capacity": 5,
@@ -2587,15 +2587,15 @@
"参数/模板问题": 66,
"验证失败": 673
},
"failureCount": 1054,
"failureRate": 0.9495,
"failureCount": 1055,
"failureRate": 0.9496,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 56,
"successRate": 0.0505,
"total": 1110,
"unresolvedFailureCount": 891
"successRate": 0.0504,
"total": 1111,
"unresolvedFailureCount": 892
},
"vllm": {
"attributableFailureCount": 325,
@@ -2730,7 +2730,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-15T00:22:04.564736+00:00",
"generatedAt": "2026-09-15T00:31:35.050322+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 38,
@@ -2925,20 +2925,20 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 83,
"ambiguous_runtime": 84,
"memory_capacity": 1,
"参数/模板问题": 2,
"验证失败": 23
},
"failureCount": 109,
"failureCount": 110,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 109,
"unresolvedFailureCount": 108
"total": 110,
"unresolvedFailureCount": 109
},
"MetaX_c-500": {
"attributableFailureCount": 56,
@@ -5564,13 +5564,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 10
"ambiguous_runtime": 11
},
"failureCount": 10,
"failureCount": 11,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-14T21:47:28.713808+00:00",
"lastTerminalAt": "2026-09-15T00:31:34.841419+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -5578,8 +5578,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 10,
"unresolvedFailureCount": 10
"total": 11,
"unresolvedFailureCount": 11
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -9010,15 +9010,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1880,
"totalRecords": 1973,
"terminalRecords": 1881,
"totalRecords": 1974,
"totals": {
"attributableFailureCount": 570,
"decisionFailureRate": 0.9005,
"decisionSuccessRate": 0.0995,
"decisionTotal": 633,
"failureBreakdown": {
"ambiguous_runtime": 452,
"ambiguous_runtime": 453,
"backend_operator": 44,
"framework_architecture_unsupported": 365,
"memory_capacity": 12,
@@ -9030,15 +9030,15 @@
"参数/模板问题": 116,
"验证失败": 673
},
"failureCount": 1817,
"failureCount": 1818,
"failureRate": 0.9665,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 6,
"successCount": 63,
"successRate": 0.0335,
"total": 1880,
"unresolvedFailureCount": 1241
"total": 1881,
"unresolvedFailureCount": 1242
},
"warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
@@ -9076,6 +9076,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1973,
"summarizedRecords": 1974,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"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": "2026-09-15T00:31:34.841419+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T00:31:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4597481", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-15T00:22:04.249561+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T00:19:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4592892", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-15T00:22:04.249539+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T00:17:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4595877", "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": "2026-09-15T00:03:42.210358+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T00:03:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4592744", "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": ["nemotron_h"], "framework": "", "lastSyncTime": "2026-09-10T02:50:12.317748+00:00", "modelId": "nota-ai/Nemotron-3.5-Lightning-30B-A3B-NVFP4-Global-Pruned-15", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:41:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4271675", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-10T02:40:44.943952+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-10T02:37:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4483083", "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_moe"], "framework": "", "lastSyncTime": "2026-09-10T02:40:44.943965+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:37:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4483082", "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": "2026-09-10T02:40:44.943974+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:35:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496938", "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": "52dc579834485a207e5cf17b5b2a8070160445d881c69e68b33ad5f9aa931c85",
".modelhub_state/architecture_history_backfill.json": "7ff767857978952dcd59e5ca7bd6a9f70396bc5b570c4246aacf174ab4ab0fec",
".modelhub_state/market_intelligence.json": "cc5d0d4c1e62eb9f393b0acc54362038774d338d415e2770c0a193d9eadfbff3",
".modelhub_state/official_capabilities.json": "3197fadc71e8d52b5937d34d4d86f560fcbbbb23ed69ceb03f0550eb60f9b029",
".modelhub_state/outcome_checkpoint.json": "7f6774b01534b40e8a3bcc1c37bff301522dddd9f6541a56749fc27fcbcc6faf",
".modelhub_state/architecture_compatibility_blacklist.json": "3294669c527377856d8fe1b4b8efcc5aa03b575d118f9a4ed37f15c685e63f2e",
".modelhub_state/architecture_history_backfill.json": "7e089e74abd60ad047bec1a9d0502fb4b0923d099baae984aaf71db7801bc821",
".modelhub_state/market_intelligence.json": "97f5fb28d315bf22433db6a15f8ff41de4e412ae440ce5eff9d6b6b77d237758",
".modelhub_state/official_capabilities.json": "d4033645e4915471c5717d0aca3a834afa1a204b4b8d77d07cbb452039c6e7a7",
".modelhub_state/outcome_checkpoint.json": "80cb6deb7dd43830c9020c29914fb51c66b6f5d9d12474b4e7f5df9f70a45e8b",
".modelhub_state/queue_cleanup_latest.json": "31192efe87aeb0abfa466af5f4610a5ee2c42cd23042e3754ec5250cd5b2517d",
".modelhub_state/recent_outcomes.jsonl": "76ce990037b9e3cd014c21d801612325dc0ded295b8e0f04fc41eba5d5b6f814",
".modelhub_state/recovery_active_tasks.jsonl": "0a25a98019efc7918013615eab12b014c3dcd9687eb4c07d7d2d824c3e4454c2",
".modelhub_state/recovery_intents.jsonl": "eae622f71d495a54a42bc7a7dffc0fec66cca7ae8eeeda5b27876584ceefe842",
".modelhub_state/recent_outcomes.jsonl": "59311290219bde96abe5f9934fc43b618791159f640421f805b88e67cedabbad",
".modelhub_state/recovery_active_tasks.jsonl": "690342c936ad3b8d31f4b71e20a14e4815d11c36a28626a169dd5ef7b9c9d14d",
".modelhub_state/recovery_intents.jsonl": "b1e34b01866da7f5c14efc127a7b1702535cf86e96e7215128e188be62e7df5f",
".modelhub_state/routing_intelligence.json": "5f7939a4bcc0cd3361fb3c8b9e46d01882b7482b42018a697367e830f28b1f09",
".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
".modelhub_state/worker_crashes.jsonl": "53505d335313446ff7094bcb58658b561de55799302fa7bfb49e418e414eebad",
"ledger/submissions.jsonl": "b8563512d893ae2a4f8a4d65881d0eab34d0b8d937550ac1fd54cdbaddb9db2b",
"outcomes/submissions.jsonl": "8fb1bca3e421116716deccb3142261e8474705ab5a5757dca848881a4970c52a"
},
"generation": 7448,
"generation": 7449,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-15T00:30:27.717652+00:00",
"updatedAt": "2026-09-15T00:33:36.060467+00:00",
"writerId": "69701e73196b4ac2b3fad0f412335168"
}