state: generation 22359 (cycle)

This commit is contained in:
2026-10-08 21:47:48 +00:00
parent c85d8b5f48
commit 48e471317b
9 changed files with 2287 additions and 2099 deletions

View File

@@ -2862,7 +2862,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-10-08T21:35:05.958014+00:00",
"generatedAt": "2026-10-08T21:44:44.316962+00:00",
"summary": {
"activeBlockCount": 143,
"byGpuFramework": {

View File

@@ -434,7 +434,7 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-08T21:43:36.374740+00:00",
"generatedAt": "2026-10-08T21:46:39.275925+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": "2026-10-08T21:09:27.989749+00:00",
"lastSyncTime": "2026-10-08T21:09:25.152964+00:00",
"generatedAt": "2026-10-08T21:44:44.239170+00:00",
"lastSyncTime": "2026-10-08T21:44:43.964193+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -4776,7 +4776,7 @@
"decisionSuccessRate": 0.039,
"decisionTotal": 666,
"failureBreakdown": {
"ambiguous_runtime": 134,
"ambiguous_runtime": 135,
"architecture_compatibility": 20,
"backend_operator": 43,
"context_length": 46,
@@ -4789,18 +4789,18 @@
"tokenizer_compatibility": 79,
"参数/模板问题": 10
},
"failureCount": 787,
"failureRate": 0.968,
"failureCount": 788,
"failureRate": 0.9681,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 26,
"successRate": 0.032,
"successRate": 0.0319,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 813,
"unresolvedFailureCount": 144
"total": 814,
"unresolvedFailureCount": 145
},
"MetaX_c-500|vllm|unknown": {
"attributableFailureCount": 1,
@@ -5598,7 +5598,7 @@
"decisionSuccessRate": 0.028,
"decisionTotal": 3791,
"failureBreakdown": {
"ambiguous_runtime": 1602,
"ambiguous_runtime": 1603,
"architecture_compatibility": 112,
"attention_backend": 3,
"backend_operator": 95,
@@ -5612,15 +5612,15 @@
"tokenizer_compatibility": 420,
"参数/模板问题": 83
},
"failureCount": 6250,
"failureCount": 6251,
"failureRate": 0.9833,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 880,
"successCount": 106,
"successRate": 0.0167,
"total": 6356,
"unresolvedFailureCount": 1685
"total": 6357,
"unresolvedFailureCount": 1686
},
"vllm-customized": {
"attributableFailureCount": 15,
@@ -5770,7 +5770,7 @@
"unresolvedFailureCount": 304
}
},
"generatedAt": "2026-10-08T21:09:27.976050+00:00",
"generatedAt": "2026-10-08T21:44:44.225477+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 125,
@@ -6050,7 +6050,7 @@
"decisionSuccessRate": 0.1778,
"decisionTotal": 827,
"failureBreakdown": {
"ambiguous_runtime": 306,
"ambiguous_runtime": 307,
"architecture_compatibility": 21,
"backend_operator": 43,
"context_length": 59,
@@ -6065,15 +6065,15 @@
"日志缺失": 15,
"验证失败": 48
},
"failureCount": 1482,
"failureCount": 1483,
"failureRate": 0.9098,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 5,
"successCount": 147,
"successRate": 0.0902,
"total": 1629,
"unresolvedFailureCount": 797
"total": 1630,
"unresolvedFailureCount": 798
},
"Mthreads_s4000": {
"attributableFailureCount": 89,
@@ -22009,6 +22009,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"MetaX_c-500|vllm|text-generation|sse_swa_moba|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "sse_swa_moba",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 7,
"decisionFailureRate": 0.875,
@@ -26381,13 +26404,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-10-08T03:44:24.154872+00:00",
"lastTerminalAt": "2026-10-08T21:44:43.964193+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -26395,8 +26419,8 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
"total": 2,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -27303,6 +27327,31 @@
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|sse_swa_moba|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-10-08T21:44:43.964193+00:00",
"modelType": "sse_swa_moba",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|qwen3_5_text|none": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
@@ -51486,6 +51535,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"MetaX_c-500|vllm|text-generation|sse_swa_moba|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "sse_swa_moba",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors|31": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
@@ -57430,15 +57503,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17735,
"totalRecords": 18222,
"terminalRecords": 17736,
"totalRecords": 18223,
"totals": {
"attributableFailureCount": 6299,
"decisionFailureRate": 0.8655,
"decisionSuccessRate": 0.1345,
"decisionTotal": 7278,
"failureBreakdown": {
"ambiguous_runtime": 4602,
"ambiguous_runtime": 4603,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 130,
@@ -57454,15 +57527,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16756,
"failureCount": 16757,
"failureRate": 0.9448,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 955,
"successCount": 979,
"successRate": 0.0552,
"total": 17735,
"unresolvedFailureCount": 9502
"total": 17736,
"unresolvedFailureCount": 9503
},
"warnings": [
"GPU Kunlunxin_p-800 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -57471,13 +57544,13 @@
"GPU Iluvatar_bi-150 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 Sunrise_pt-200-x1 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 hygon_k100-ai 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 Ascend_910-b3 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 Cambricon_mlu-370-x4 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 Vastai_va16 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。",
"组合 Sunrise_pt-200-x1|vllm|visual-multi-modal 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。",
@@ -57524,6 +57597,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 18222,
"summarizedRecords": 18223,
"version": 1
}

View File

@@ -274,6 +274,7 @@
{"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557020+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g4-v2_B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T05:54:51.550868+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5013339", "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", "failureUnsupportedArchitectures": ["SSESWAMoBAForCausalLM"], "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T14:08:43.365639+00:00", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "modelProfile": {"architectures": ["SSESWAMoBAForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11110611058, "estimatedRequiredGiB": 12.435, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sse_swa_moba", "modelscopeFileSize": 11126702266, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:sse_swa_moba", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11126702266}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:48:17.265295+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5013248", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557144+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T05:36:08.409002+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5013035", "taskType": "text-generation", "verifyResult": null}
{"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": "2026-10-08T21:44:43.964193+00:00", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "modelProfile": {"architectures": ["SSESWAMoBAForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11110611058, "estimatedRequiredGiB": 12.435, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sse_swa_moba", "modelscopeFileSize": 11126702266, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:sse_swa_moba", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11126702266}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:32:05.479742+00:00", "targetGpu": "MetaX_c-500", "taskId": "5012980", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557127+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g32-v2_C", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T05:29:49.361193+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5012953", "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"], "framework": "vllm-customized", "lastSyncTime": "2026-09-29T17:54:53.270719+00:00", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8674988799, "estimatedRequiredGiB": 9.718, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8695119291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2415484144, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:qwen3-5", "custom_tag:9b", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8695119291}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:27:11.098010+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5012909", "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": ["lfm2"], "framework": "vllm", "lastSyncTime": "2026-09-26T07:10:36.169057+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955857175}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:27:11.087107+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5012911", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +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", "failureUnsupportedModelTypes": ["mini_k3"], "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T03:44:24.154943+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "modelProfile": {"architectures": [], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2038896936, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042511760}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T02:13:58.677566+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5010811", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T04:30:44.383896+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T02:13:58.674661+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5010809", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T04:30:44.383722+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-8-v2_D", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T02:13:58.672986+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5010810", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-08T04:30:44.383795+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g32-v2_C", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T02:13:58.669421+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5010808", "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