state: generation 19244 (cycle)
This commit is contained in:
@@ -3341,7 +3341,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-01T13:37:44.819622+00:00",
|
||||
"generatedAt": "2026-10-01T13:47:43.307453+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 168,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -434,7 +434,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-10-01T13:46:40.557611+00:00",
|
||||
"generatedAt": "2026-10-01T13:49:39.690021+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-10-01T13:46:40.557611+00:00",
|
||||
"catalogUpdatedAt": "2026-10-01T13:49:39.690021+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-10-01T13:46:40.865376+00:00",
|
||||
"generatedAt": "2026-10-01T13:49:39.690021+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6636,6 +6636,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-10-01T13:46:40.557611+00:00",
|
||||
"taskTreeUpdatedAt": "2026-10-01T13:49:39.690021+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-10-01T13:37:44.736731+00:00",
|
||||
"lastSyncTime": "2026-10-01T13:37:44.450782+00:00",
|
||||
"generatedAt": "2026-10-01T13:47:43.222376+00:00",
|
||||
"lastSyncTime": "2026-10-01T13:47:42.951743+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -3927,25 +3927,25 @@
|
||||
"decisionSuccessRate": 0.3214,
|
||||
"decisionTotal": 28,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 44,
|
||||
"ambiguous_runtime": 45,
|
||||
"framework_architecture_unsupported": 16,
|
||||
"model_load": 3,
|
||||
"platform_infrastructure": 1,
|
||||
"参数/模板问题": 1,
|
||||
"验证失败": 3
|
||||
},
|
||||
"failureCount": 68,
|
||||
"failureRate": 0.8831,
|
||||
"failureCount": 69,
|
||||
"failureRate": 0.8846,
|
||||
"framework": "vllm-mlu",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 9,
|
||||
"successRate": 0.1169,
|
||||
"successRate": 0.1154,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 77,
|
||||
"unresolvedFailureCount": 48
|
||||
"total": 78,
|
||||
"unresolvedFailureCount": 49
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm|text-generation": {
|
||||
"attributableFailureCount": 25,
|
||||
@@ -6098,7 +6098,7 @@
|
||||
"decisionSuccessRate": 0.3929,
|
||||
"decisionTotal": 56,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 94,
|
||||
"ambiguous_runtime": 95,
|
||||
"framework_architecture_unsupported": 28,
|
||||
"model_load": 5,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -6106,15 +6106,15 @@
|
||||
"参数/模板问题": 4,
|
||||
"验证失败": 3
|
||||
},
|
||||
"failureCount": 136,
|
||||
"failureRate": 0.8608,
|
||||
"failureCount": 137,
|
||||
"failureRate": 0.8616,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 22,
|
||||
"successRate": 0.1392,
|
||||
"total": 158,
|
||||
"unresolvedFailureCount": 101
|
||||
"successRate": 0.1384,
|
||||
"total": 159,
|
||||
"unresolvedFailureCount": 102
|
||||
},
|
||||
"vllm-patch-tokenizer": {
|
||||
"attributableFailureCount": 59,
|
||||
@@ -6217,7 +6217,7 @@
|
||||
"unresolvedFailureCount": 225
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-01T13:37:44.723981+00:00",
|
||||
"generatedAt": "2026-10-01T13:47:43.209314+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 113,
|
||||
@@ -6310,7 +6310,7 @@
|
||||
"decisionSuccessRate": 0.0896,
|
||||
"decisionTotal": 826,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 509,
|
||||
"ambiguous_runtime": 510,
|
||||
"architecture_compatibility": 53,
|
||||
"context_length": 48,
|
||||
"framework_architecture_unsupported": 305,
|
||||
@@ -6323,15 +6323,15 @@
|
||||
"日志缺失": 13,
|
||||
"验证失败": 42
|
||||
},
|
||||
"failureCount": 1619,
|
||||
"failureCount": 1620,
|
||||
"failureRate": 0.9563,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 16,
|
||||
"successCount": 74,
|
||||
"successRate": 0.0437,
|
||||
"total": 1693,
|
||||
"unresolvedFailureCount": 851
|
||||
"total": 1694,
|
||||
"unresolvedFailureCount": 852
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"attributableFailureCount": 61,
|
||||
@@ -11672,6 +11672,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|torchao": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "torchao",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|stablelm|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -35916,6 +35939,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|torchao|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "spark2_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "torchao",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|stablelm|none|31": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -54403,15 +54450,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17201,
|
||||
"totalRecords": 17422,
|
||||
"terminalRecords": 17202,
|
||||
"totalRecords": 17423,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6169,
|
||||
"decisionFailureRate": 0.8635,
|
||||
"decisionSuccessRate": 0.1365,
|
||||
"decisionTotal": 7144,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4490,
|
||||
"ambiguous_runtime": 4491,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 128,
|
||||
@@ -54427,30 +54474,30 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16226,
|
||||
"failureCount": 16227,
|
||||
"failureRate": 0.9433,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 944,
|
||||
"successCount": 975,
|
||||
"successRate": 0.0567,
|
||||
"total": 17201,
|
||||
"unresolvedFailureCount": 9113
|
||||
"total": 17202,
|
||||
"unresolvedFailureCount": 9114
|
||||
},
|
||||
"warnings": [
|
||||
"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 Biren_166m 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 Cambricon_mlu-370-x4 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 hygon_k100-ai 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 Mthreads_s4000 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Kunlunxin_p-800 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 Sunrise_pt-200-x1 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 MetaX_c-500 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 Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Kunlunxin_p-800|vllm_tokenizer_patch|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -54495,6 +54542,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17422,
|
||||
"summarizedRecords": 17423,
|
||||
"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