state: generation 5589 (cycle)

This commit is contained in:
2026-09-11 07:36:01 +00:00
parent 6776ae9231
commit 2f912f8b2e
9 changed files with 2239 additions and 2234 deletions

View File

@@ -1307,7 +1307,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-11T07:32:46.341700+00:00",
"generatedAt": "2026-09-11T07:36:00.445134+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -83,7 +83,7 @@
"8": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 399,
"listingErrors": 400,
"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": 8,
"nextAccountIndex": 9,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-11T07:32:46.318512+00:00",
"updatedAt": "2026-09-11T07:36:00.422542+00:00",
"version": 1
}

View File

@@ -387,7 +387,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-11T07:30:58.163131+00:00",
"generatedAt": "2026-09-11T07:34:00.615138+00:00",
"gpuStats": {
"Ascend_910-b4": {
"available": true,

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-11T07:24:30.424566+00:00",
"lastSyncTime": "2026-09-11T07:24:30.143494+00:00",
"generatedAt": "2026-09-11T07:33:47.456861+00:00",
"lastSyncTime": "2026-09-11T07:33:47.206168+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1787,30 +1787,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 80,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 90,
"attributableFailureCount": 81,
"decisionFailureRate": 0.8901,
"decisionSuccessRate": 0.1099,
"decisionTotal": 91,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 31,
"model_load": 32,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 148,
"failureRate": 0.9367,
"failureCount": 149,
"failureRate": 0.9371,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0633,
"successRate": 0.0629,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 158,
"total": 159,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2288,29 +2288,29 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 134,
"decisionFailureRate": 0.7363,
"decisionSuccessRate": 0.2637,
"decisionTotal": 182,
"attributableFailureCount": 135,
"decisionFailureRate": 0.7377,
"decisionSuccessRate": 0.2623,
"decisionTotal": 183,
"failureBreakdown": {
"ambiguous_runtime": 128,
"backend_operator": 4,
"framework_architecture_unsupported": 89,
"memory_capacity": 5,
"model_load": 33,
"model_load": 34,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 992,
"failureRate": 0.9538,
"failureCount": 993,
"failureRate": 0.9539,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.0462,
"total": 1040,
"successRate": 0.0461,
"total": 1041,
"unresolvedFailureCount": 857
},
"vllm": {
@@ -2441,7 +2441,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-11T07:24:30.420386+00:00",
"generatedAt": "2026-09-11T07:33:47.451941+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2604,27 +2604,27 @@
"unresolvedFailureCount": 43
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 80,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 90,
"attributableFailureCount": 81,
"decisionFailureRate": 0.8901,
"decisionSuccessRate": 0.1099,
"decisionTotal": 91,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 31,
"model_load": 32,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 148,
"failureRate": 0.9367,
"failureCount": 149,
"failureRate": 0.9371,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0633,
"total": 158,
"successRate": 0.0629,
"total": 159,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800": {
@@ -4236,7 +4236,7 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 17,
"consecutiveFailures": 13,
"consecutiveFailures": 14,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.9444,
"decisionSuccessRate": 0.0556,
@@ -4251,7 +4251,7 @@
"failureRate": 0.95,
"framework": "unknown",
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-11T07:24:30.143494+00:00",
"lastTerminalAt": "2026-09-11T07:33:47.206168+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -4543,20 +4543,19 @@
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 4,
"model_load": 1,
"repository_structure": 1,
"runtime_memory": 1
},
"failureCount": 19,
"failureCount": 18,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4568,7 +4567,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 19,
"total": 18,
"unresolvedFailureCount": 12
}
},
@@ -6911,19 +6910,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1648,
"totalRecords": 1735,
"terminalRecords": 1649,
"totalRecords": 1736,
"totals": {
"attributableFailureCount": 429,
"decisionFailureRate": 0.89,
"decisionSuccessRate": 0.11,
"decisionTotal": 482,
"attributableFailureCount": 430,
"decisionFailureRate": 0.8903,
"decisionSuccessRate": 0.1097,
"decisionTotal": 483,
"failureBreakdown": {
"ambiguous_runtime": 391,
"backend_operator": 40,
"framework_architecture_unsupported": 273,
"memory_capacity": 11,
"model_load": 55,
"model_load": 56,
"platform_infrastructure": 4,
"repository_structure": 5,
"runtime_memory": 6,
@@ -6931,30 +6930,31 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1595,
"failureRate": 0.9678,
"failureCount": 1596,
"failureRate": 0.9679,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 53,
"successRate": 0.0322,
"total": 1648,
"successRate": 0.0321,
"total": 1649,
"unresolvedFailureCount": 1162
},
"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。",
@@ -6969,11 +6969,10 @@
"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": 1735,
"summarizedRecords": 1736,
"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": "2026-09-11T07:33:47.206168+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T07:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523220", "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": "2026-09-11T07:24:30.143494+00:00", "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T07:21:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4505135", "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": "2026-09-11T07:05:27.006934+00:00", "modelId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T06:57:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523318", "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": "2026-09-11T05:08:00.009961+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T05:05:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477832", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"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": "2026-09-08T08:12:43.104903+00:00", "modelId": "nightmedia/Mistral-Nemo-Instruct-2407-12B-Thinking-M-Claude-Opus-High-Reasoning-mxfp4-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T07:55:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080014", "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": "2026-09-08T07:47:20.009376+00:00", "modelId": "ModelCloud.AI/Marin-32B-Base-GPTQMODEL-W4A16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T07:41:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079069", "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": "2026-09-08T07:47:20.009326+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T07:39:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4478473", "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": "2026-09-08T07:22:29.130684+00:00", "modelId": "nightmedia/Mistral-Nemo-Instruct-2407-12B-Thinking-M-Claude-Opus-High-Reasoning-mxfp4-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T07:19:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079225", "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": "bda8a5abdf571c77ef01012ffcb2c2e3c618aaf25bdd32074a73125ba76fe834",
".modelhub_state/architecture_history_backfill.json": "ac8f3fcd94fdfaf648232f9e68a5cbf94fc49a33180c8ee2130e722ddaca586f",
".modelhub_state/market_intelligence.json": "bc1329821708cf69a62daac745e26539d73b94669cdede7f53a9be33db7a4b2b",
".modelhub_state/official_capabilities.json": "1036501f31262a79c5c54c735281344ac19ffdbc28f7ddb819c09aba620716b9",
".modelhub_state/outcome_checkpoint.json": "7e43dee88fc6f3f6998a08d56d90db0b259d19538e88f5cc03eeae527d5b9410",
".modelhub_state/architecture_compatibility_blacklist.json": "361f4d7abac481aae40d2a0628514054e9e6a07c501108ded8e7bb181425b7c2",
".modelhub_state/architecture_history_backfill.json": "076801a090f3949795eb08324e821cb36cfb61edbeae7d5776e9f895a0beedc8",
".modelhub_state/market_intelligence.json": "bef0eaee8ba176d8f9df4a031b6431386c1ed59db7d63e990090dfd2b5cb97b6",
".modelhub_state/official_capabilities.json": "9b112ad61ad44e4bd84a38df92a43cb61c9c14b4e729e95818bdfb8650f4a7cf",
".modelhub_state/outcome_checkpoint.json": "7318be4ba0700e9528490aa4ad7ef282bdf6ba24ca891dc63206b51a7ac1ffda",
".modelhub_state/queue_cleanup_latest.json": "757bb52cd4c1e398d565b25c01e1a394e97727dc87500e4184be2784f229ae2a",
".modelhub_state/recent_outcomes.jsonl": "90c73f011c6f100a1bffdb2b100768813d9127d89581a76bb9911a22d4043822",
".modelhub_state/recovery_active_tasks.jsonl": "6d41c769f8b34fe2f0f07363af09dad56412f93ca564926a558d41bee54cacd0",
".modelhub_state/recovery_intents.jsonl": "6fcd09d3eb095a585837d1506c000d17ca5a9ec05f7f056437dbadcf110fbe1a",
".modelhub_state/recent_outcomes.jsonl": "10dfebed82cec3858ac6201ef9534aa32d3c72bf7454aaab3f63d9e49fef3446",
".modelhub_state/recovery_active_tasks.jsonl": "9f72027789641e2c1e6462cf21cffef2244f85cda00c009f4d7d69c1d2d8f79b",
".modelhub_state/recovery_intents.jsonl": "9590d59523c98a40065dbe89e7ecf0186d070328e6a33ab869f871a786dd2552",
".modelhub_state/routing_intelligence.json": "a7d892e1ccda118f72a13ee212ed5aad3be9d65cdbf4c8218d696761745235b0",
".modelhub_state/submission_exclusions.jsonl": "a07e1a02840754257cdff556f0bbb75a93364d6fc493705741531a86b71b768e",
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
"ledger/submissions.jsonl": "369d50ba323fae299168a3afc0597ce8bc04a737b67af19154a569c0c08db4aa",
"outcomes/submissions.jsonl": "e73ee02e18c7cb77e8d2a8a683d96a85963b8bb5e720d1be855002e1480be466"
},
"generation": 5588,
"generation": 5589,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-11T07:32:46.419516+00:00",
"updatedAt": "2026-09-11T07:36:01.132640+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42"
}