state: generation 5586 (cycle)

This commit is contained in:
2026-09-11 07:26:39 +00:00
parent 42eb26dc91
commit 1b2ee70a03
9 changed files with 2035 additions and 2060 deletions

View File

@@ -1307,7 +1307,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-11T07:23:29.364250+00:00",
"generatedAt": "2026-09-11T07:26:38.001259+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -59,7 +59,7 @@
"5": {
"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": 5,
"nextAccountIndex": 6,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-11T07:23:29.340035+00:00",
"updatedAt": "2026-09-11T07:26:37.977056+00:00",
"version": 1
}

View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-09-11T07:09:20.471394+00:00",
"communityAttemptedAt": "2026-09-11T07:24:40.292193+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-09-11T07:09:20.471394+00:00",
"communityUpdatedAt": "2026-09-11T07:24:40.292193+00:00",
"frameworkAttemptedAt": "2026-09-11T02:36:24.395876+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -387,7 +387,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-11T07:21:42.533306+00:00",
"generatedAt": "2026-09-11T07:24:40.292193+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": "2026-09-11T07:05:27.225930+00:00",
"lastSyncTime": "2026-09-11T07:05:27.006934+00:00",
"generatedAt": "2026-09-11T07:24:30.424566+00:00",
"lastSyncTime": "2026-09-11T07:24:30.143494+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1787,30 +1787,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 79,
"decisionFailureRate": 0.8876,
"decisionSuccessRate": 0.1124,
"decisionTotal": 89,
"attributableFailureCount": 80,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 90,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 30,
"model_load": 31,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 147,
"failureRate": 0.9363,
"failureCount": 148,
"failureRate": 0.9367,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0637,
"successRate": 0.0633,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 157,
"total": 158,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2288,29 +2288,29 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 133,
"decisionFailureRate": 0.7348,
"decisionSuccessRate": 0.2652,
"decisionTotal": 181,
"attributableFailureCount": 134,
"decisionFailureRate": 0.7363,
"decisionSuccessRate": 0.2637,
"decisionTotal": 182,
"failureBreakdown": {
"ambiguous_runtime": 128,
"backend_operator": 4,
"framework_architecture_unsupported": 89,
"memory_capacity": 5,
"model_load": 32,
"model_load": 33,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 991,
"failureCount": 992,
"failureRate": 0.9538,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.0462,
"total": 1039,
"total": 1040,
"unresolvedFailureCount": 857
},
"vllm": {
@@ -2441,7 +2441,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-11T07:05:27.222026+00:00",
"generatedAt": "2026-09-11T07:24:30.420386+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2604,27 +2604,27 @@
"unresolvedFailureCount": 43
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 79,
"decisionFailureRate": 0.8876,
"decisionSuccessRate": 0.1124,
"decisionTotal": 89,
"attributableFailureCount": 80,
"decisionFailureRate": 0.8889,
"decisionSuccessRate": 0.1111,
"decisionTotal": 90,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 30,
"model_load": 31,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 147,
"failureRate": 0.9363,
"failureCount": 148,
"failureRate": 0.9367,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0637,
"total": 157,
"successRate": 0.0633,
"total": 158,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800": {
@@ -4182,31 +4182,6 @@
"total": 15,
"unresolvedFailureCount": 14
},
"Cambricon_mlu-370-x8|vllm|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": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-08T23:42:27.831495+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-100|transformers|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -4261,22 +4236,22 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 17,
"consecutiveFailures": 12,
"consecutiveFailures": 13,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.9444,
"decisionSuccessRate": 0.0556,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 7,
"model_load": 10,
"framework_architecture_unsupported": 6,
"model_load": 11,
"platform_infrastructure": 1
},
"failureCount": 19,
"failureRate": 0.95,
"framework": "unknown",
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-11T07:05:27.006934+00:00",
"lastTerminalAt": "2026-09-11T07:24:30.143494+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -6936,19 +6911,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1647,
"totalRecords": 1734,
"terminalRecords": 1648,
"totalRecords": 1735,
"totals": {
"attributableFailureCount": 428,
"decisionFailureRate": 0.8898,
"decisionSuccessRate": 0.1102,
"decisionTotal": 481,
"attributableFailureCount": 429,
"decisionFailureRate": 0.89,
"decisionSuccessRate": 0.11,
"decisionTotal": 482,
"failureBreakdown": {
"ambiguous_runtime": 391,
"backend_operator": 40,
"framework_architecture_unsupported": 273,
"memory_capacity": 11,
"model_load": 54,
"model_load": 55,
"platform_infrastructure": 4,
"repository_structure": 5,
"runtime_memory": 6,
@@ -6956,31 +6931,30 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1594,
"failureCount": 1595,
"failureRate": 0.9678,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 53,
"successRate": 0.0322,
"total": 1647,
"total": 1648,
"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 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。",
@@ -6995,10 +6969,11 @@
"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": 1734,
"summarizedRecords": 1735,
"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": "2026-09-11T07:24:30.143494+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}
{"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": "2026-09-11T03:33:48.898214+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T03:29:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497066", "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": "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}
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831495+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.934706+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712836", "taskType": "text-generation", "verifyResult": null}

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": "53c447f51d5da4ee61d5b6085df56b6d8caa0956b84ec59927d5fd9f3342d641",
".modelhub_state/architecture_history_backfill.json": "4b3d5c310373b3f828d9cc274ebddbc730437e77eb6e1a7fc5890de9f35826fb",
".modelhub_state/market_intelligence.json": "39ae4440e6a308913d72d7e408c57e8c130a903bacd099df877c244c6165ebb0",
".modelhub_state/official_capabilities.json": "4493ed4e33d5672aa22149ae0a94d725ec5e0447e90e36b6da56d681703484f3",
".modelhub_state/outcome_checkpoint.json": "19ce09da372093a638920952e034c98e6eaad3a9bca9403076f195ec4bf9d432",
".modelhub_state/architecture_compatibility_blacklist.json": "56d57dac01be024692274ef59ac69b6288ae09fdd15134bbf93bcc505a5547da",
".modelhub_state/architecture_history_backfill.json": "58270e4e7e17839059e6bfbc2a6e144707b606da6bf0737afd2b716326e9a6d8",
".modelhub_state/market_intelligence.json": "5fa7c4e46ab10992613438a9cdebbc074fd741e8433fac48bccd8ce442cf4a48",
".modelhub_state/official_capabilities.json": "6f32a4369da43ce20fe828efcf6ac7f2104c0646521ba6e50edcbe5f6e72d7d5",
".modelhub_state/outcome_checkpoint.json": "7e43dee88fc6f3f6998a08d56d90db0b259d19538e88f5cc03eeae527d5b9410",
".modelhub_state/queue_cleanup_latest.json": "757bb52cd4c1e398d565b25c01e1a394e97727dc87500e4184be2784f229ae2a",
".modelhub_state/recent_outcomes.jsonl": "796c6e8d248a155b5498d9b59bedef3eceb69eb00ed8abed3b55fdf67a8756b9",
".modelhub_state/recovery_active_tasks.jsonl": "8b4177734aea8242a3486ac5c11e5a883e6c4a5f276a4b081e822b5bf35d5f1e",
".modelhub_state/recovery_intents.jsonl": "6c438404b44e6e93abc87d94a0397a423ce9196cb1edfc66a45852a3d0535066",
".modelhub_state/recent_outcomes.jsonl": "90c73f011c6f100a1bffdb2b100768813d9127d89581a76bb9911a22d4043822",
".modelhub_state/recovery_active_tasks.jsonl": "6d41c769f8b34fe2f0f07363af09dad56412f93ca564926a558d41bee54cacd0",
".modelhub_state/recovery_intents.jsonl": "6fcd09d3eb095a585837d1506c000d17ca5a9ec05f7f056437dbadcf110fbe1a",
".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": 5585,
"generation": 5586,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-11T07:23:29.441866+00:00",
"updatedAt": "2026-09-11T07:26:39.019881+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42"
}