state: generation 5714 (cycle)

This commit is contained in:
2026-09-11 13:56:56 +00:00
parent cfc5dc059c
commit 0c7e5e4be3
9 changed files with 2165 additions and 2165 deletions

View File

@@ -1307,7 +1307,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-11T13:54:07.994385+00:00",
"generatedAt": "2026-09-11T13:56:55.943881+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -27,7 +27,7 @@
"11": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 409,
"listingErrors": 410,
"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": "2026-09-11T13:54:07.970694+00:00",
"updatedAt": "2026-09-11T13:56:55.920502+00:00",
"version": 1
}

View File

@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-11T13:52:17.716912+00:00",
"generatedAt": "2026-09-11T13:55:18.487677+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": "2026-09-11T13:46:06.898495+00:00",
"lastSyncTime": "2026-09-11T13:46:06.650683+00:00",
"generatedAt": "2026-09-11T13:55:09.160805+00:00",
"lastSyncTime": "2026-09-11T13:55:08.941364+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1787,30 +1787,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 85,
"decisionFailureRate": 0.8947,
"decisionSuccessRate": 0.1053,
"decisionTotal": 95,
"attributableFailureCount": 86,
"decisionFailureRate": 0.8866,
"decisionSuccessRate": 0.1134,
"decisionTotal": 97,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
"model_load": 36,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 153,
"failureRate": 0.9387,
"failureCount": 154,
"failureRate": 0.9333,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0613,
"successCount": 11,
"successRate": 0.0667,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 163,
"total": 165,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2290,14 +2290,14 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 139,
"decisionFailureRate": 0.7433,
"decisionSuccessRate": 0.2567,
"decisionTotal": 187,
"attributableFailureCount": 140,
"decisionFailureRate": 0.7407,
"decisionSuccessRate": 0.2593,
"decisionTotal": 189,
"failureBreakdown": {
"ambiguous_runtime": 129,
"backend_operator": 4,
"framework_architecture_unsupported": 89,
"framework_architecture_unsupported": 90,
"memory_capacity": 5,
"model_load": 38,
"platform_infrastructure": 1,
@@ -2305,14 +2305,14 @@
"参数/模板问题": 57,
"验证失败": 673
},
"failureCount": 999,
"failureRate": 0.9542,
"failureCount": 1000,
"failureRate": 0.9533,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.0458,
"total": 1047,
"successCount": 49,
"successRate": 0.0467,
"total": 1049,
"unresolvedFailureCount": 859
},
"vllm": {
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-11T13:46:06.894640+00:00",
"generatedAt": "2026-09-11T13:55:09.156645+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2606,27 +2606,27 @@
"unresolvedFailureCount": 43
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 85,
"decisionFailureRate": 0.8947,
"decisionSuccessRate": 0.1053,
"decisionTotal": 95,
"attributableFailureCount": 86,
"decisionFailureRate": 0.8866,
"decisionSuccessRate": 0.1134,
"decisionTotal": 97,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
"model_load": 36,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 153,
"failureRate": 0.9387,
"failureCount": 154,
"failureRate": 0.9333,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0613,
"total": 163,
"successCount": 11,
"successRate": 0.0667,
"total": 165,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800": {
@@ -4236,28 +4236,28 @@
"unresolvedFailureCount": 3
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 18,
"consecutiveFailures": 18,
"attributableFailureCount": 17,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionFailureRate": 0.9444,
"decisionSuccessRate": 0.0556,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 4,
"framework_architecture_unsupported": 3,
"model_load": 14,
"platform_infrastructure": 1
},
"failureCount": 20,
"failureRate": 1.0,
"failureCount": 19,
"failureRate": 0.95,
"framework": "unknown",
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-11T13:46:06.650683+00:00",
"lastTerminalAt": "2026-09-11T13:55:08.941364+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"successCount": 1,
"successRate": 0.05,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 20,
@@ -6937,17 +6937,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1658,
"totalRecords": 1745,
"terminalRecords": 1660,
"totalRecords": 1747,
"totals": {
"attributableFailureCount": 437,
"decisionFailureRate": 0.8918,
"decisionSuccessRate": 0.1082,
"decisionTotal": 490,
"attributableFailureCount": 438,
"decisionFailureRate": 0.8902,
"decisionSuccessRate": 0.1098,
"decisionTotal": 492,
"failureBreakdown": {
"ambiguous_runtime": 392,
"backend_operator": 40,
"framework_architecture_unsupported": 273,
"framework_architecture_unsupported": 274,
"memory_capacity": 11,
"model_load": 60,
"platform_infrastructure": 4,
@@ -6957,31 +6957,30 @@
"参数/模板问题": 99,
"验证失败": 673
},
"failureCount": 1605,
"failureRate": 0.968,
"failureCount": 1606,
"failureRate": 0.9675,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 53,
"successRate": 0.032,
"total": 1658,
"successCount": 54,
"successRate": 0.0325,
"total": 1660,
"unresolvedFailureCount": 1164
},
"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。",
@@ -6996,10 +6995,11 @@
"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": 1745,
"summarizedRecords": 1747,
"version": 1
}

View File

@@ -1,3 +1,5 @@
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-11T13:55:08.941364+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-11T13:53:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523314", "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": "2026-09-11T13:55:08.941340+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T13:47:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332898", "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": "2026-09-11T13:46:06.650683+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T13:43:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523302", "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": "2026-09-11T13:18:33.951636+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T13:11:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523312", "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": "2026-09-11T13:09:08.149747+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T13:07:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523311", "taskType": "text-generation", "verifyResult": -1}
@@ -296,5 +298,3 @@
{"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", "framework": "vllm", "lastSyncTime": "2026-09-08T10:26:32.495882+00:00", "modelId": "amd/Qwen2.5_3B_Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T10:15:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4080079", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-08T10:26:32.495858+00:00", "modelId": "ModelCloud.AI/Marin-32B-Base-GPTQMODEL-W4A16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T10:07:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079252", "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": "2026-09-08T10:00:15.603821+00:00", "modelId": "ModelCloud.AI/Marin-32B-Base-GPTQMODEL-W4A16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T09:59:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079974", "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", "framework": "vllm", "lastSyncTime": "2026-09-08T10:00:15.603843+00:00", "modelId": "amd/Qwen2.5-Coder-7B-Instruct-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T09:59:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080012", "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": "2026-09-08T10:00:15.603861+00:00", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T09:57:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4080861", "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": "54a0754cb161cd2675e6087f1887c0f9152abb8a95534024fa96d45845892493",
".modelhub_state/architecture_history_backfill.json": "daba39c95144a2285761b5819af32f89067d20c9cd6ab6aacc3c956caf38140e",
".modelhub_state/market_intelligence.json": "3c7e79f7d203d6d65cfc4783c22a0af432987ba6c1af60eb764d9521df2bcefe",
".modelhub_state/official_capabilities.json": "222a1fa6819db75145fc55f3a59066db0a20c5315ce5a90d0ee70086fc2b743d",
".modelhub_state/outcome_checkpoint.json": "92e680a3284f3a1148e6c15ce586f10c315dcce41fcda4c30e74affada398dab",
".modelhub_state/architecture_compatibility_blacklist.json": "320a128c8c595b0d1c7845d1651a9f35e777249b8a6927652d8393a73f19e6ce",
".modelhub_state/architecture_history_backfill.json": "d9688cdde5c03e5d67bd030f16372f060d722b0de7817378a2d54c85fb81f96f",
".modelhub_state/market_intelligence.json": "c958b7b10142c608e0e33d4d6dc0e4ad319b5b525a8a9911c3452949a5e5a1c6",
".modelhub_state/official_capabilities.json": "c24f2872e0efae1a2050b97cd603cf2b5c446bc5acb7fd0523634074f7c63436",
".modelhub_state/outcome_checkpoint.json": "647455760c8596dccd6c2b8e5cc62e668e84142084d2d6703ed11291a9715de7",
".modelhub_state/queue_cleanup_latest.json": "9092a0b045d21453d0210c81bf56fa209d341915359e8357a6e260c821f48c9b",
".modelhub_state/recent_outcomes.jsonl": "1c2d83489cc5f37e7b2ad8f3d8099d5e0d1bcf2813f1db347bf27119a70f057f",
".modelhub_state/recovery_active_tasks.jsonl": "31f9d0767eca2882a08d22f2ac51e3a6aea66fee896384ad86f54ca1fa4c6e8b",
".modelhub_state/recovery_intents.jsonl": "5853868e32ce707fcf5a78a52bdfe7a53ce9ee678d013f1868f77e36653d183d",
".modelhub_state/recent_outcomes.jsonl": "520cfcb8d2676632a8af1cc3c530a71e976bf7ce75f013ab6b5dde24170f7d33",
".modelhub_state/recovery_active_tasks.jsonl": "789e7030763d610e808e5d1195add2f1cf62127bb99c11328c04782989200d4d",
".modelhub_state/recovery_intents.jsonl": "b24d998761cd285fafda46285bdfeca6e37cee4edaabdfc18d4679c08d24acf1",
".modelhub_state/routing_intelligence.json": "01755a7ae15e8408cf0586a62b0684ec4e7e2d46c2715b9b2bfe968c7d40353e",
".modelhub_state/submission_exclusions.jsonl": "3790b5c148f222a4de26d50a3d8afc58891c8da251a82d20dbaf4fc35e6dbd89",
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
"ledger/submissions.jsonl": "0f2922a5f34c5777fcbb7e7ea1512bd1784eed2b74f5d6c3f05103cb3bbea37e",
"outcomes/submissions.jsonl": "9b436339a59d073250c1f14e08f71c1148a29e5b3db2301e39b71ed36893e02b"
},
"generation": 5713,
"generation": 5714,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-11T13:54:08.058321+00:00",
"updatedAt": "2026-09-11T13:56:56.682392+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42"
}