state: generation 11332 (cycle)
This commit is contained in:
@@ -2635,7 +2635,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T08:17:31.482580+00:00",
|
||||
"generatedAt": "2026-09-21T08:22:05.179335+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 132,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -425,7 +425,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-21T08:21:01.933423+00:00",
|
||||
"generatedAt": "2026-09-21T08:22:12.096302+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-21T08:21:01.933423+00:00",
|
||||
"catalogUpdatedAt": "2026-09-21T08:22:12.096302+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-21T08:21:01.933423+00:00",
|
||||
"generatedAt": "2026-09-21T08:22:12.096302+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6553,6 +6553,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-21T08:21:01.933423+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-21T08:22:12.096302+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-21T08:17:31.351998+00:00",
|
||||
"lastSyncTime": "2026-09-21T08:17:25.672573+00:00",
|
||||
"generatedAt": "2026-09-21T08:22:05.105619+00:00",
|
||||
"lastSyncTime": "2026-09-21T08:22:03.151517+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -4463,10 +4463,10 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation": {
|
||||
"attributableFailureCount": 623,
|
||||
"decisionFailureRate": 0.9629,
|
||||
"decisionSuccessRate": 0.0371,
|
||||
"decisionTotal": 647,
|
||||
"attributableFailureCount": 624,
|
||||
"decisionFailureRate": 0.963,
|
||||
"decisionSuccessRate": 0.037,
|
||||
"decisionTotal": 648,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 129,
|
||||
"architecture_compatibility": 20,
|
||||
@@ -4474,24 +4474,24 @@
|
||||
"context_length": 46,
|
||||
"framework_architecture_unsupported": 192,
|
||||
"memory_capacity": 84,
|
||||
"model_load": 60,
|
||||
"model_load": 61,
|
||||
"platform_infrastructure": 3,
|
||||
"repository_structure": 98,
|
||||
"runtime_memory": 2,
|
||||
"tokenizer_compatibility": 78,
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 764,
|
||||
"failureRate": 0.9695,
|
||||
"failureCount": 765,
|
||||
"failureRate": 0.9696,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 24,
|
||||
"successRate": 0.0305,
|
||||
"successRate": 0.0304,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 788,
|
||||
"total": 789,
|
||||
"unresolvedFailureCount": 138
|
||||
},
|
||||
"MetaX_c-500|vllm|unknown": {
|
||||
@@ -5279,10 +5279,10 @@
|
||||
"unresolvedFailureCount": 6442
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3521,
|
||||
"attributableFailureCount": 3522,
|
||||
"decisionFailureRate": 0.9764,
|
||||
"decisionSuccessRate": 0.0236,
|
||||
"decisionTotal": 3606,
|
||||
"decisionTotal": 3607,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1474,
|
||||
"architecture_compatibility": 112,
|
||||
@@ -5291,21 +5291,21 @@
|
||||
"context_length": 161,
|
||||
"framework_architecture_unsupported": 1292,
|
||||
"memory_capacity": 720,
|
||||
"model_load": 206,
|
||||
"model_load": 207,
|
||||
"platform_infrastructure": 865,
|
||||
"repository_structure": 470,
|
||||
"runtime_memory": 64,
|
||||
"tokenizer_compatibility": 411,
|
||||
"参数/模板问题": 41
|
||||
},
|
||||
"failureCount": 5901,
|
||||
"failureCount": 5902,
|
||||
"failureRate": 0.9858,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 865,
|
||||
"successCount": 85,
|
||||
"successRate": 0.0142,
|
||||
"total": 5986,
|
||||
"total": 5987,
|
||||
"unresolvedFailureCount": 1515
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -5449,7 +5449,7 @@
|
||||
"unresolvedFailureCount": 70
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T08:17:31.340375+00:00",
|
||||
"generatedAt": "2026-09-21T08:22:05.094989+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 91,
|
||||
@@ -5716,10 +5716,10 @@
|
||||
"unresolvedFailureCount": 170
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"attributableFailureCount": 658,
|
||||
"decisionFailureRate": 0.8194,
|
||||
"decisionSuccessRate": 0.1806,
|
||||
"decisionTotal": 803,
|
||||
"attributableFailureCount": 659,
|
||||
"decisionFailureRate": 0.8197,
|
||||
"decisionSuccessRate": 0.1803,
|
||||
"decisionTotal": 804,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 301,
|
||||
"architecture_compatibility": 21,
|
||||
@@ -5727,7 +5727,7 @@
|
||||
"context_length": 59,
|
||||
"framework_architecture_unsupported": 196,
|
||||
"memory_capacity": 85,
|
||||
"model_load": 60,
|
||||
"model_load": 61,
|
||||
"platform_infrastructure": 5,
|
||||
"repository_structure": 114,
|
||||
"runtime_memory": 2,
|
||||
@@ -5736,14 +5736,14 @@
|
||||
"日志缺失": 15,
|
||||
"验证失败": 48
|
||||
},
|
||||
"failureCount": 1425,
|
||||
"failureRate": 0.9076,
|
||||
"failureCount": 1426,
|
||||
"failureRate": 0.9077,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 5,
|
||||
"successCount": 145,
|
||||
"successRate": 0.0924,
|
||||
"total": 1570,
|
||||
"successRate": 0.0923,
|
||||
"total": 1571,
|
||||
"unresolvedFailureCount": 762
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
@@ -13492,6 +13492,29 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|qwen3_moe|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "qwen3_moe",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|qwen3|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -30465,6 +30488,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|qwen3_moe|none|34": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 34,
|
||||
"modelType": "qwen3_moe",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|qwen3|none|13": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -32965,13 +33012,13 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 16184,
|
||||
"totalRecords": 16366,
|
||||
"terminalRecords": 16185,
|
||||
"totalRecords": 16367,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5860,
|
||||
"attributableFailureCount": 5861,
|
||||
"decisionFailureRate": 0.8615,
|
||||
"decisionSuccessRate": 0.1385,
|
||||
"decisionTotal": 6802,
|
||||
"decisionTotal": 6803,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3894,
|
||||
"architecture_compatibility": 212,
|
||||
@@ -32980,7 +33027,7 @@
|
||||
"context_length": 319,
|
||||
"framework_architecture_unsupported": 2056,
|
||||
"memory_capacity": 1197,
|
||||
"model_load": 494,
|
||||
"model_load": 495,
|
||||
"platform_infrastructure": 924,
|
||||
"repository_structure": 735,
|
||||
"runtime_memory": 84,
|
||||
@@ -32989,14 +33036,14 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 674
|
||||
},
|
||||
"failureCount": 15242,
|
||||
"failureCount": 15243,
|
||||
"failureRate": 0.9418,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 924,
|
||||
"successCount": 942,
|
||||
"successRate": 0.0582,
|
||||
"total": 16184,
|
||||
"total": 16185,
|
||||
"unresolvedFailureCount": 8458
|
||||
},
|
||||
"warnings": [
|
||||
@@ -33006,14 +33053,14 @@
|
||||
"GPU Biren_166m 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Iluvatar_bi-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 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 Cambricon_mlu-370-x4 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-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 Ascend_910-b4 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 Iluvatar_bi-150 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。",
|
||||
"组合 Iluvatar_bi-150|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 Sunrise_pt-200-x1|vllm_fix_tokenizer|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|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -33053,6 +33100,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 16366,
|
||||
"summarizedRecords": 16367,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user