state: generation 5402 (cycle)

This commit is contained in:
2026-09-10 23:13:32 +00:00
parent 8e47a0ae9f
commit 744c4f9986
9 changed files with 2144 additions and 2144 deletions

View File

@@ -1307,7 +1307,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T23:10:45.370244+00:00",
"generatedAt": "2026-09-10T23:13:32.244427+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -27,7 +27,7 @@
"11": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 384,
"listingErrors": 385,
"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": "2026-09-10T23:10:45.346787+00:00",
"updatedAt": "2026-09-10T23:13:32.219355+00:00",
"version": 1
}

View File

@@ -1,8 +1,8 @@
{
"communityAttemptedAt": "2026-09-10T22:55:33.847976+00:00",
"communityAttemptedAt": "2026-09-10T23:11:51.940836+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-09-10T22:55:33.847976+00:00",
"communityUpdatedAt": "2026-09-10T23:11:51.940836+00:00",
"frameworkAttemptedAt": "2026-09-10T21:27:33.050021+00:00",
"frameworkError": null,
"frameworkStats": {
@@ -416,7 +416,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T23:09:18.621254+00:00",
"generatedAt": "2026-09-10T23:11:51.940836+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": "2026-09-10T22:39:22.030091+00:00",
"lastSyncTime": "2026-09-10T22:39:21.821546+00:00",
"generatedAt": "2026-09-10T23:11:46.333230+00:00",
"lastSyncTime": "2026-09-10T23:11:46.109095+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1787,30 +1787,30 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 77,
"decisionFailureRate": 0.8851,
"decisionSuccessRate": 0.1149,
"decisionTotal": 87,
"attributableFailureCount": 78,
"decisionFailureRate": 0.8864,
"decisionSuccessRate": 0.1136,
"decisionTotal": 88,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 28,
"model_load": 29,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 145,
"failureRate": 0.9355,
"failureCount": 146,
"failureRate": 0.9359,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0645,
"successRate": 0.0641,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 155,
"total": 156,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2288,29 +2288,29 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 131,
"decisionFailureRate": 0.7318,
"decisionSuccessRate": 0.2682,
"decisionTotal": 179,
"attributableFailureCount": 132,
"decisionFailureRate": 0.7333,
"decisionSuccessRate": 0.2667,
"decisionTotal": 180,
"failureBreakdown": {
"ambiguous_runtime": 124,
"backend_operator": 4,
"framework_architecture_unsupported": 89,
"memory_capacity": 5,
"model_load": 30,
"model_load": 31,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 985,
"failureRate": 0.9535,
"failureCount": 986,
"failureRate": 0.9536,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.0465,
"total": 1033,
"successRate": 0.0464,
"total": 1034,
"unresolvedFailureCount": 853
},
"vllm": {
@@ -2441,7 +2441,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T22:39:22.025914+00:00",
"generatedAt": "2026-09-10T23:11:46.328987+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2604,27 +2604,27 @@
"unresolvedFailureCount": 43
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 77,
"decisionFailureRate": 0.8851,
"decisionSuccessRate": 0.1149,
"decisionTotal": 87,
"attributableFailureCount": 78,
"decisionFailureRate": 0.8864,
"decisionSuccessRate": 0.1136,
"decisionTotal": 88,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 28,
"model_load": 29,
"platform_infrastructure": 1,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 145,
"failureRate": 0.9355,
"failureCount": 146,
"failureRate": 0.9359,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 10,
"successRate": 0.0645,
"total": 155,
"successRate": 0.0641,
"total": 156,
"unresolvedFailureCount": 67
},
"Kunlunxin_p-800": {
@@ -4192,9 +4192,9 @@
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2,
"参数/模板问题": 8
"参数/模板问题": 7
},
"failureCount": 10,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4206,8 +4206,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 10,
"unresolvedFailureCount": 8
"total": 9,
"unresolvedFailureCount": 7
},
"Iluvatar_bi-100|transformers|text-generation": {
"attributableFailureCount": 0,
@@ -4263,22 +4263,22 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 17,
"consecutiveFailures": 10,
"consecutiveFailures": 11,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.9444,
"decisionSuccessRate": 0.0556,
"decisionTotal": 18,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 8,
"model_load": 9,
"framework_architecture_unsupported": 7,
"model_load": 10,
"platform_infrastructure": 1
},
"failureCount": 19,
"failureRate": 0.95,
"framework": "unknown",
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-10T20:06:18.925896+00:00",
"lastTerminalAt": "2026-09-10T23:11:46.109095+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -6988,19 +6988,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1638,
"totalRecords": 1725,
"terminalRecords": 1639,
"totalRecords": 1726,
"totals": {
"attributableFailureCount": 426,
"decisionFailureRate": 0.8894,
"decisionSuccessRate": 0.1106,
"decisionTotal": 479,
"attributableFailureCount": 427,
"decisionFailureRate": 0.8896,
"decisionSuccessRate": 0.1104,
"decisionTotal": 480,
"failureBreakdown": {
"ambiguous_runtime": 384,
"backend_operator": 40,
"framework_architecture_unsupported": 273,
"memory_capacity": 11,
"model_load": 52,
"model_load": 53,
"platform_infrastructure": 4,
"repository_structure": 5,
"runtime_memory": 6,
@@ -7008,31 +7008,30 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1585,
"failureRate": 0.9676,
"failureCount": 1586,
"failureRate": 0.9677,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 53,
"successRate": 0.0324,
"total": 1638,
"successRate": 0.0323,
"total": 1639,
"unresolvedFailureCount": 1155
},
"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。",
@@ -7047,10 +7046,11 @@
"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": 1725,
"summarizedRecords": 1726,
"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": "2026-09-10T23:11:46.109095+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T23:11:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523218", "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": "2026-09-10T22:39:21.821546+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T22:33:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532025", "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": "2026-09-10T22:32:18.404515+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T22:25:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4583642", "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": "2026-09-10T21:23:30.606595+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T21:17:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532126", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831503+00:00", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.803703+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712829", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831391+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.797429+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712830", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831425+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.795480+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712823", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831439+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.791128+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712828", "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": "e7044ec1ae43fe72bfd7c997f4741da0b36edb53cb4d72658e0acc7727089f69",
".modelhub_state/architecture_history_backfill.json": "b0f2b943668c59beeff55a4ed330e0a1f9c9a53d3786037fcee30914d70353d9",
".modelhub_state/market_intelligence.json": "71c66ecb75202189cb5df8422b4395abb1acfe89a5820cf609a4792b50fa114f",
".modelhub_state/official_capabilities.json": "a1656d93f317e41bed4d8af74b7044f643360508d5c205f27e04653057890c9d",
".modelhub_state/outcome_checkpoint.json": "f9e205f02e05a8a14a8d27fd8f0fe2628758dd4425980a543c65ca57136d41cf",
".modelhub_state/architecture_compatibility_blacklist.json": "536e74b9870e095841f37639f410514f83eec7d3b47b67afeb12a3ccc9abe311",
".modelhub_state/architecture_history_backfill.json": "d44ad7fb028bfe155afbcfb841e28ad475111391b7cc2558dae426f9172335db",
".modelhub_state/market_intelligence.json": "87e6cd6f501ec5060959bc208815ddd6682e4d4c9ab30f853dbf8a0e26314baf",
".modelhub_state/official_capabilities.json": "c2693329b415f76a61a93863c6650fc70cefb8d57a8b458485344b1b5a99b6db",
".modelhub_state/outcome_checkpoint.json": "f635e8d3113fb2d8f33751b1415ba25fd8d09fe31f8315a9f0b22802a6980f26",
".modelhub_state/queue_cleanup_latest.json": "777f4bec9250957bd6a5571440bc1d401209444f7c4aa372f2de9033886894e5",
".modelhub_state/recent_outcomes.jsonl": "fdb4c0dc058871c9d9f13be6a30a06347677fdc2e4bcc1902d9f9d0fbc63279c",
".modelhub_state/recovery_active_tasks.jsonl": "2a8caf5abcd5f09a5c172eacf43ae2ad172923408bcfa7b56566ce4802924734",
".modelhub_state/recovery_intents.jsonl": "0174d54f4ff9a8d2e1604fa020104b94371d883aafdc497b411118978080fdfc",
".modelhub_state/recent_outcomes.jsonl": "a08690c8eb7569e67990763bcad5f519d6bf5782a6553db69f4b2f973cceffc7",
".modelhub_state/recovery_active_tasks.jsonl": "56e59160b3df68fe88e839f19f18d5cd45606c476423cd429f59d1807be7cc5e",
".modelhub_state/recovery_intents.jsonl": "d01e7b397db7b7268ce108c1da98b1475802da6fc6c40b0577d36feffaf7e2c2",
".modelhub_state/routing_intelligence.json": "e3d23a5e6afd96c3481aa525fd641500a5693cc776defa488e9749eeeca78057",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
"ledger/submissions.jsonl": "70b6cae0b58ec41be21dadaa435c9a39a06725619fd8619bf24a2aeafa24a8dc",
"outcomes/submissions.jsonl": "203bc3e9ecc25bb0f7c8d801501fa4a33e75bb4ab064a318f7871658d54ca020"
},
"generation": 5401,
"generation": 5402,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T23:10:45.446421+00:00",
"updatedAt": "2026-09-10T23:13:32.893036+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42"
}