state: generation 5592 (cycle)

This commit is contained in:
2026-09-11 07:45:05 +00:00
parent 13a3966b99
commit 9165b532d9
9 changed files with 2126 additions and 2100 deletions

View File

@@ -1307,7 +1307,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-11T07:42:03.494782+00:00",
"generatedAt": "2026-09-11T07:45:04.115330+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -27,7 +27,7 @@
"11": {
"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": 11,
"nextAccountIndex": 0,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-11T07:42:03.470937+00:00",
"updatedAt": "2026-09-11T07:45:04.092452+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-11T07:40:17.792113+00:00",
"generatedAt": "2026-09-11T07:43:10.916167+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": "2026-09-11T07:33:47.456861+00:00",
"lastSyncTime": "2026-09-11T07:33:47.206168+00:00",
"generatedAt": "2026-09-11T07:43:04.447309+00:00",
"lastSyncTime": "2026-09-11T07:43:04.407471+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2185,9 +2185,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 1,
"验证失败": 27
},
"failureCount": 27,
"failureCount": 28,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
@@ -2197,8 +2198,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 27,
"unresolvedFailureCount": 27
"total": 28,
"unresolvedFailureCount": 28
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 3,
@@ -2300,18 +2301,18 @@
"model_load": 34,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 56,
"参数/模板问题": 57,
"验证失败": 673
},
"failureCount": 993,
"failureCount": 994,
"failureRate": 0.9539,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.0461,
"total": 1041,
"unresolvedFailureCount": 857
"total": 1042,
"unresolvedFailureCount": 858
},
"vllm": {
"attributableFailureCount": 240,
@@ -2441,7 +2442,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-11T07:33:47.451941+00:00",
"generatedAt": "2026-09-11T07:43:04.442818+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2756,18 +2757,18 @@
"model_load": 3,
"repository_structure": 3,
"runtime_memory": 2,
"参数/模板问题": 8,
"参数/模板问题": 9,
"验证失败": 27
},
"failureCount": 92,
"failureCount": 93,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 92,
"unresolvedFailureCount": 53
"total": 93,
"unresolvedFailureCount": 54
}
},
"observedGpuMemoryGiB": {
@@ -4517,6 +4518,31 @@
"total": 20,
"unresolvedFailureCount": 20
},
"hygon_k100-ai|unknown|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-11T07:43:04.407471+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -6910,8 +6936,8 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1649,
"totalRecords": 1736,
"terminalRecords": 1650,
"totalRecords": 1737,
"totals": {
"attributableFailureCount": 430,
"decisionFailureRate": 0.8903,
@@ -6927,34 +6953,33 @@
"repository_structure": 5,
"runtime_memory": 6,
"tokenizer_compatibility": 39,
"参数/模板问题": 98,
"参数/模板问题": 99,
"验证失败": 673
},
"failureCount": 1596,
"failureCount": 1597,
"failureRate": 0.9679,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 53,
"successRate": 0.0321,
"total": 1649,
"unresolvedFailureCount": 1162
"total": 1650,
"unresolvedFailureCount": 1163
},
"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 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。",
"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 Cambricon_mlu-370-x4 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。",
@@ -6969,10 +6994,11 @@
"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": 1736,
"summarizedRecords": 1737,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-11T07:43:04.407471+00:00", "modelId": "deepreinforce-ai/Ornith-1.0-35B-FP8", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-11T07:38:33+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079996", "taskType": "text-generation", "verifyResult": null}
{"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}
@@ -297,4 +298,3 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-08T08:12:43.104895+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T07:59:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4494268", "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": "2026-09-08T08:12:43.104903+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}

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": "2f25c1efd91c71e4abb80647e410de8cb508c0950530eb46e697106e220ad4ca",
".modelhub_state/architecture_history_backfill.json": "bcfaa10d862b825eb386d57ee9e18713d518d9567ebf9a01a680b069eef3af0b",
".modelhub_state/market_intelligence.json": "9ce2b2e13240e504d73b07f85be71c79ac84ccefee5accdba9884557e15f6874",
".modelhub_state/official_capabilities.json": "ded8271af47e92ae165f9df1c9226fe8bb8b1f2e3e2ca71c6c8249f6ef8d822e",
".modelhub_state/outcome_checkpoint.json": "7318be4ba0700e9528490aa4ad7ef282bdf6ba24ca891dc63206b51a7ac1ffda",
".modelhub_state/architecture_compatibility_blacklist.json": "741b226095822908d6df577098c108559281d847adea91735eab231c2feda5c3",
".modelhub_state/architecture_history_backfill.json": "e7ba620a77ac8cd293ef4a0245ff2f4ae8cfe4cb1a7894b0ef565b67e47dcd83",
".modelhub_state/market_intelligence.json": "b7c927c5b605a2e588073916761de7fdea9016fea0542c952e4883e3f16f9b48",
".modelhub_state/official_capabilities.json": "5630e3e06b03822b5040bcd75b13613ac7ab21b2be5960dd660edf85817d6a70",
".modelhub_state/outcome_checkpoint.json": "502057f7f506ac7aea6130b20a3b225f6ccc1510a86779ebe5ce5ccdc1aaef13",
".modelhub_state/queue_cleanup_latest.json": "757bb52cd4c1e398d565b25c01e1a394e97727dc87500e4184be2784f229ae2a",
".modelhub_state/recent_outcomes.jsonl": "10dfebed82cec3858ac6201ef9534aa32d3c72bf7454aaab3f63d9e49fef3446",
".modelhub_state/recovery_active_tasks.jsonl": "9f72027789641e2c1e6462cf21cffef2244f85cda00c009f4d7d69c1d2d8f79b",
".modelhub_state/recovery_intents.jsonl": "9590d59523c98a40065dbe89e7ecf0186d070328e6a33ab869f871a786dd2552",
".modelhub_state/recent_outcomes.jsonl": "a33ccc3fa6f0a8d1f1c645ff6013256fc4a07ac5401bd607a08dfae424e4f02e",
".modelhub_state/recovery_active_tasks.jsonl": "59927ed7ff394a58cacbe85ddf778a7f5351afb4f7114fcdbb78594f6760079d",
".modelhub_state/recovery_intents.jsonl": "5bd34016d4a59daae8115102a55d7dfbeb142ad1d191c28f564925f6c85935ee",
".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": 5591,
"generation": 5592,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-11T07:42:03.601896+00:00",
"updatedAt": "2026-09-11T07:45:05.242805+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42"
}