state: generation 5711 (cycle)

This commit is contained in:
2026-09-11 13:47:57 +00:00
parent 144d0dd13d
commit 7f3ff21702
9 changed files with 1987 additions and 1983 deletions

View File

@@ -1307,7 +1307,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-11T13:45:05.926059+00:00",
"generatedAt": "2026-09-11T13:47:56.309834+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -83,7 +83,7 @@
"8": {
"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": 8,
"nextAccountIndex": 9,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-11T13:45:05.903007+00:00",
"updatedAt": "2026-09-11T13:47:56.287284+00:00",
"version": 1
}

View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-09-11T13:31:03.367598+00:00",
"communityAttemptedAt": "2026-09-11T13:46:15.127125+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-09-11T13:31:03.367598+00:00",
"communityUpdatedAt": "2026-09-11T13:46:15.127125+00:00",
"frameworkAttemptedAt": "2026-09-11T13:40:14.410581+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-11T13:43:32.813694+00:00",
"generatedAt": "2026-09-11T13:46:15.127125+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": "2026-09-11T13:18:34.185095+00:00",
"lastSyncTime": "2026-09-11T13:18:33.951636+00:00",
"generatedAt": "2026-09-11T13:46:06.898495+00:00",
"lastSyncTime": "2026-09-11T13:46:06.650683+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1787,30 +1787,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 84,
"decisionFailureRate": 0.8936,
"decisionSuccessRate": 0.1064,
"decisionTotal": 94,
"attributableFailureCount": 85,
"decisionFailureRate": 0.8947,
"decisionSuccessRate": 0.1053,
"decisionTotal": 95,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 35,
"model_load": 36,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 152,
"failureRate": 0.9383,
"failureCount": 153,
"failureRate": 0.9387,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0617,
"successRate": 0.0613,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 162,
"total": 163,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2290,29 +2290,29 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 138,
"decisionFailureRate": 0.7419,
"decisionSuccessRate": 0.2581,
"decisionTotal": 186,
"attributableFailureCount": 139,
"decisionFailureRate": 0.7433,
"decisionSuccessRate": 0.2567,
"decisionTotal": 187,
"failureBreakdown": {
"ambiguous_runtime": 129,
"backend_operator": 4,
"framework_architecture_unsupported": 89,
"memory_capacity": 5,
"model_load": 37,
"model_load": 38,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 57,
"验证失败": 673
},
"failureCount": 998,
"failureRate": 0.9541,
"failureCount": 999,
"failureRate": 0.9542,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.0459,
"total": 1046,
"successRate": 0.0458,
"total": 1047,
"unresolvedFailureCount": 859
},
"vllm": {
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-11T13:18:34.181402+00:00",
"generatedAt": "2026-09-11T13:46:06.894640+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2606,27 +2606,27 @@
"unresolvedFailureCount": 43
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 84,
"decisionFailureRate": 0.8936,
"decisionSuccessRate": 0.1064,
"decisionTotal": 94,
"attributableFailureCount": 85,
"decisionFailureRate": 0.8947,
"decisionSuccessRate": 0.1053,
"decisionTotal": 95,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 35,
"model_load": 36,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 152,
"failureRate": 0.9383,
"failureCount": 153,
"failureRate": 0.9387,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0617,
"total": 162,
"successRate": 0.0613,
"total": 163,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800": {
@@ -4236,28 +4236,28 @@
"unresolvedFailureCount": 3
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 17,
"consecutiveFailures": 17,
"attributableFailureCount": 18,
"consecutiveFailures": 18,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.9444,
"decisionSuccessRate": 0.0556,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 4,
"model_load": 13,
"model_load": 14,
"platform_infrastructure": 1
},
"failureCount": 19,
"failureRate": 0.95,
"failureCount": 20,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-11T13:18:33.951636+00:00",
"lastTerminalAt": "2026-09-11T13:46:06.650683+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 1,
"successRate": 0.05,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 20,
@@ -6937,19 +6937,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1657,
"totalRecords": 1744,
"terminalRecords": 1658,
"totalRecords": 1745,
"totals": {
"attributableFailureCount": 436,
"decisionFailureRate": 0.8916,
"decisionSuccessRate": 0.1084,
"decisionTotal": 489,
"attributableFailureCount": 437,
"decisionFailureRate": 0.8918,
"decisionSuccessRate": 0.1082,
"decisionTotal": 490,
"failureBreakdown": {
"ambiguous_runtime": 392,
"backend_operator": 40,
"framework_architecture_unsupported": 273,
"memory_capacity": 11,
"model_load": 59,
"model_load": 60,
"platform_infrastructure": 4,
"repository_structure": 5,
"runtime_memory": 6,
@@ -6957,30 +6957,31 @@
"参数/模板问题": 99,
"验证失败": 673
},
"failureCount": 1604,
"failureCount": 1605,
"failureRate": 0.968,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 53,
"successRate": 0.032,
"total": 1657,
"total": 1658,
"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 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。",
@@ -6995,11 +6996,10 @@
"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": 1744,
"summarizedRecords": 1745,
"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": "2026-09-11T13:46:06.650683+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}
{"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": "2026-09-11T12:59:52.253401+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T12:59:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4531547", "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": "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}
{"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": "2026-09-08T10:00:15.603853+00:00", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T09:43:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4268342", "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": "bff9800d29ba000edecb268fb53c5257227d53d5500eecd0cb3a1867e4e0c136",
".modelhub_state/architecture_history_backfill.json": "1abc64ee5553b0ce2e5df7f7daa31b647578b3ad01404ffc5917d785245c5907",
".modelhub_state/market_intelligence.json": "bd4a2f6bb1343c53a8ecedd226fc8b455ebcd363de467bf88d6e22ed851addaf",
".modelhub_state/official_capabilities.json": "86a7722fb207c4db74975f84535698e64b2edcd0c9e85436dfff7c9359ca7217",
".modelhub_state/outcome_checkpoint.json": "977810ce19fd052161ef4a2a1efef0d76aedd19ea0da9c9024fd420fb88b7152",
".modelhub_state/architecture_compatibility_blacklist.json": "681e6af87b082c1dcb3c319af1d952d022e3a84a068a082fc9b42acc02c37152",
".modelhub_state/architecture_history_backfill.json": "574338e30f5de39ba0352ad81b0d503db8f308e55f8de09de3d1899ee9488421",
".modelhub_state/market_intelligence.json": "8a1f933b22d13f3bbfa7af28030b92250933b4f0999b8a87ab515ba45c0973f7",
".modelhub_state/official_capabilities.json": "73de7706ef6e050005a5ab85c545e4822683446aa1ff49ed6fda214306a4f513",
".modelhub_state/outcome_checkpoint.json": "92e680a3284f3a1148e6c15ce586f10c315dcce41fcda4c30e74affada398dab",
".modelhub_state/queue_cleanup_latest.json": "9092a0b045d21453d0210c81bf56fa209d341915359e8357a6e260c821f48c9b",
".modelhub_state/recent_outcomes.jsonl": "f11a53d4b90ec23ba00e975f7de4a6bb40a6de18daa4a39dda008cdda5a42e3a",
".modelhub_state/recovery_active_tasks.jsonl": "17111fd5f71e25467753e6bf32b30297f5e39ab1b1ab32e11b8f91364f41da66",
".modelhub_state/recovery_intents.jsonl": "1bf7f6e92cd71b75268e78f41730f538857bd5d3890eb9ed9a81a38d355c123e",
".modelhub_state/recent_outcomes.jsonl": "1c2d83489cc5f37e7b2ad8f3d8099d5e0d1bcf2813f1db347bf27119a70f057f",
".modelhub_state/recovery_active_tasks.jsonl": "31f9d0767eca2882a08d22f2ac51e3a6aea66fee896384ad86f54ca1fa4c6e8b",
".modelhub_state/recovery_intents.jsonl": "5853868e32ce707fcf5a78a52bdfe7a53ce9ee678d013f1868f77e36653d183d",
".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": 5710,
"generation": 5711,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-11T13:45:05.990594+00:00",
"updatedAt": "2026-09-11T13:47:57.566021+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42"
}