state: generation 5505 (cycle)

This commit is contained in:
2026-09-11 03:26:55 +00:00
parent ee626ddfab
commit a322f3128b
9 changed files with 2123 additions and 2124 deletions

View File

@@ -1307,7 +1307,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-11T03:24:05.140414+00:00",
"generatedAt": "2026-09-11T03:26:54.066028+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -83,7 +83,7 @@
"8": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 392,
"listingErrors": 393,
"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": "2026-09-11T03:24:05.116561+00:00",
"updatedAt": "2026-09-11T03:26:54.043161+00:00",
"version": 1
}

View File

@@ -387,7 +387,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-11T03:22:03.418295+00:00",
"generatedAt": "2026-09-11T03:25:12.935321+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": "2026-09-11T01:55:12.205153+00:00",
"lastSyncTime": "2026-09-11T01:55:11.999431+00:00",
"generatedAt": "2026-09-11T03:25:07.038041+00:00",
"lastSyncTime": "2026-09-11T03:25:05.807699+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1541,24 +1541,24 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 31,
"ambiguous_runtime": 32,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 90,
"failureRate": 0.9783,
"failureCount": 91,
"failureRate": 0.9785,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0217,
"successRate": 0.0215,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 92,
"unresolvedFailureCount": 70
"total": 93,
"unresolvedFailureCount": 71
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 7,
@@ -2293,7 +2293,7 @@
"decisionSuccessRate": 0.2667,
"decisionTotal": 180,
"failureBreakdown": {
"ambiguous_runtime": 126,
"ambiguous_runtime": 127,
"backend_operator": 4,
"framework_architecture_unsupported": 89,
"memory_capacity": 5,
@@ -2303,15 +2303,15 @@
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 988,
"failureCount": 989,
"failureRate": 0.9537,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.0463,
"total": 1036,
"unresolvedFailureCount": 855
"total": 1037,
"unresolvedFailureCount": 856
},
"vllm": {
"attributableFailureCount": 240,
@@ -2441,7 +2441,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-11T01:55:12.200841+00:00",
"generatedAt": "2026-09-11T03:25:07.033553+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2521,21 +2521,21 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 31,
"ambiguous_runtime": 32,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 90,
"failureRate": 0.9783,
"failureCount": 91,
"failureRate": 0.9785,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0217,
"total": 92,
"unresolvedFailureCount": 70
"successRate": 0.0215,
"total": 93,
"unresolvedFailureCount": 71
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 17,
@@ -4131,22 +4131,21 @@
"unresolvedFailureCount": 10
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 18,
"framework_architecture_unsupported": 1,
"ambiguous_runtime": 19,
"tokenizer_compatibility": 1
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T23:36:16.447910+00:00",
"lastTerminalAt": "2026-09-11T03:25:05.807699+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4155,7 +4154,7 @@
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 18
"unresolvedFailureCount": 19
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 1,
@@ -4192,9 +4191,9 @@
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"参数/模板问题": 4
"参数/模板问题": 3
},
"failureCount": 5,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4206,8 +4205,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 4
"total": 4,
"unresolvedFailureCount": 3
},
"Iluvatar_bi-100|transformers|text-generation": {
"attributableFailureCount": 0,
@@ -6963,15 +6962,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1643,
"totalRecords": 1730,
"terminalRecords": 1644,
"totalRecords": 1731,
"totals": {
"attributableFailureCount": 427,
"decisionFailureRate": 0.8896,
"decisionSuccessRate": 0.1104,
"decisionTotal": 480,
"failureBreakdown": {
"ambiguous_runtime": 388,
"ambiguous_runtime": 389,
"backend_operator": 40,
"framework_architecture_unsupported": 273,
"memory_capacity": 11,
@@ -6983,31 +6982,30 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1590,
"failureRate": 0.9677,
"failureCount": 1591,
"failureRate": 0.9678,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 53,
"successRate": 0.0323,
"total": 1643,
"unresolvedFailureCount": 1159
"successRate": 0.0322,
"total": 1644,
"unresolvedFailureCount": 1160
},
"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。",
@@ -7022,10 +7020,11 @@
"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": 1730,
"summarizedRecords": 1731,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"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": "2026-09-11T03:25:05.807699+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T03:23:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497054", "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": "2026-09-10T23:52:39.100972+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T23:51:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477786", "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": "2026-09-10T23:36:16.447910+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T23:33:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497061", "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": "2026-09-10T23:36:16.447873+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T23:29:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497074", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831446+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.928754+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712837", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831476+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.927161+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712835", "taskType": "text-generation", "verifyResult": null}
{"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": "vllm", "lastSyncTime": "2026-09-08T15:50:00.101653+00:00", "modelId": "EschaLabs/Qwen3.6-35B-A3B-Escha-W2", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12296952480, "estimatedRequiredGiB": 13.771, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 12322205679, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7300654928, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:mlx", "library:safetensors", "task:text-generation", "custom_tag:mixture-of-experts", "custom_tag:moe", "custom_tag:qwen3", "custom_tag:2-bit", "custom_tag:quantization", "custom_tag:eschamoe", "custom_tag:sglang", "custom_tag:zml", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:metal", "custom_tag:code", "custom_tag:reasoning", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "eschamoe", "repositoryOnDiskBytes": 12322205679}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:11.886266+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712834", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-08T23:42:27.831411+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-08T06:46:11.884676+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712833", "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": "942b9e4449c1aecf565508eb3aebd207be86cc6c568507e23d2b003c9c766702",
".modelhub_state/architecture_history_backfill.json": "7fb8d4710ea8022c100495856636d107b9a84b4e7a3cea58532efa13106f3735",
".modelhub_state/market_intelligence.json": "ab641537ef09ba044d5b757aef7ce5226949c004d9dbbca63973c1a7befd339e",
".modelhub_state/official_capabilities.json": "ed91adf00b2834ebb413160a20ca9088d28f442a958db5efe3a62eacb8c798b0",
".modelhub_state/outcome_checkpoint.json": "0746176d5d55d9305be56d7b36c8155589741ad59e859f96a3f88e2364a9855c",
".modelhub_state/architecture_compatibility_blacklist.json": "58d18736cb87422b7c877c19e59f71c73da1c5b513c65a1b276e320ad1ccd32e",
".modelhub_state/architecture_history_backfill.json": "b06e70ca3cca004ff0bb891767636a771c66bedc6df90a2a38fb498e2d6d8994",
".modelhub_state/market_intelligence.json": "55c1effbf644ea11b1b2567d2f6969ce6dfada040150422668cfeb9d119e60a3",
".modelhub_state/official_capabilities.json": "da695b428b7c84890b35e3ac453d1456d3743603f41bccd7a8f6b7891d2ebfac",
".modelhub_state/outcome_checkpoint.json": "f4a510ed675007ae3f63721d3ce3b6ae107e5469fe337fef6ca5d949bdd41e68",
".modelhub_state/queue_cleanup_latest.json": "757bb52cd4c1e398d565b25c01e1a394e97727dc87500e4184be2784f229ae2a",
".modelhub_state/recent_outcomes.jsonl": "bd5bc016203c47b78570ee529b26ca643046dc41c45df1b39bf80f63e66a248a",
".modelhub_state/recovery_active_tasks.jsonl": "ef05b28836be09401adb21cde09e5a0e2ca89a4ddfb637916ff75503be6a3c41",
".modelhub_state/recovery_intents.jsonl": "b7ac6c5855ab4b307fb1c875255817b4a0c7a2b68fb5c9b6779aacc7496ea638",
".modelhub_state/recent_outcomes.jsonl": "3db8cbb1a7cc73b42ed867fa670224e1a04c08716d86a1fa5744f1d052aa19c9",
".modelhub_state/recovery_active_tasks.jsonl": "4141fca5495c02458c74fa42d477757b4c9a2cf0da09777e2eb00d673c7b43bb",
".modelhub_state/recovery_intents.jsonl": "9d8998c0091e8676ffb78f90d15dbb2009beb0a5bbc7233a6cc727aba736b3a8",
".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": "c1c3d0d4da05824c9f827503db934bd7ce488d83abf9ec539b0907e9b7086f77"
},
"generation": 5504,
"generation": 5505,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-11T03:24:05.206663+00:00",
"updatedAt": "2026-09-11T03:26:55.488448+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42"
}