state: generation 17107 (cycle)

This commit is contained in:
2026-10-31 11:08:10 +00:00
parent ce28fd650e
commit 4b7b78c192
9 changed files with 979 additions and 980 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-31T10:07:49.975522+00:00",
"lastSyncTime": "2026-10-31T10:07:49.740586+00:00",
"generatedAt": "2026-10-31T11:08:06.316752+00:00",
"lastSyncTime": "2026-10-31T11:08:06.037498+00:00",
"recentLimit": 300,
"report": {
"agentSummaries": {
@@ -29,7 +29,7 @@
"decisionSuccessRate": 0.0479,
"decisionTotal": 146,
"failureBreakdown": {
"ambiguous_runtime": 57,
"ambiguous_runtime": 58,
"backend_operator": 5,
"configuration_launch": 33,
"context_length": 5,
@@ -42,15 +42,15 @@
"任务失败_原因未确认": 146,
"参数/模板问题": 114
},
"failureCount": 456,
"failureCount": 457,
"failureRate": 0.9849,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 7,
"successRate": 0.0151,
"total": 463,
"unresolvedFailureCount": 317
"total": 464,
"unresolvedFailureCount": 318
}
},
"architectureCompatibilityBlocks": {
@@ -1403,7 +1403,7 @@
"decisionSuccessRate": 0.0697,
"decisionTotal": 1076,
"failureBreakdown": {
"ambiguous_runtime": 297,
"ambiguous_runtime": 298,
"architecture_compatibility": 11,
"context_length": 48,
"framework_architecture_unsupported": 460,
@@ -1417,7 +1417,7 @@
"参数/模板问题": 317,
"日志缺失": 12
},
"failureCount": 1644,
"failureCount": 1645,
"failureRate": 0.9564,
"framework": "unknown",
"pendingCount": 0,
@@ -1427,8 +1427,8 @@
"successRate": 0.0436,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1719,
"unresolvedFailureCount": 636
"total": 1720,
"unresolvedFailureCount": 637
},
"Cambricon_mlu-370-x4|unknown|unknown": {
"attributableFailureCount": 2,
@@ -3344,7 +3344,7 @@
"decisionSuccessRate": 0.2393,
"decisionTotal": 4041,
"failureBreakdown": {
"ambiguous_runtime": 1688,
"ambiguous_runtime": 1689,
"architecture_compatibility": 23,
"backend_operator": 13,
"configuration_launch": 489,
@@ -3362,15 +3362,15 @@
"参数/模板问题": 3672,
"日志缺失": 719
},
"failureCount": 9324,
"failureCount": 9325,
"failureRate": 0.906,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 25,
"successCount": 967,
"successRate": 0.094,
"total": 10291,
"unresolvedFailureCount": 6225
"total": 10292,
"unresolvedFailureCount": 6226
},
"vllm": {
"attributableFailureCount": 4387,
@@ -3448,7 +3448,7 @@
"unresolvedFailureCount": 3
}
},
"generatedAt": "2026-10-31T10:07:49.971384+00:00",
"generatedAt": "2026-10-31T11:08:06.311219+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 139,
@@ -3542,7 +3542,7 @@
"decisionSuccessRate": 0.0689,
"decisionTotal": 1088,
"failureBreakdown": {
"ambiguous_runtime": 297,
"ambiguous_runtime": 298,
"architecture_compatibility": 11,
"context_length": 48,
"framework_architecture_unsupported": 468,
@@ -3556,15 +3556,15 @@
"参数/模板问题": 321,
"日志缺失": 13
},
"failureCount": 1661,
"failureCount": 1662,
"failureRate": 0.9568,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 7,
"successCount": 75,
"successRate": 0.0432,
"total": 1736,
"unresolvedFailureCount": 641
"total": 1737,
"unresolvedFailureCount": 642
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 172,
@@ -4027,17 +4027,17 @@
"unresolvedFailureCount": 17
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 4
"framework_architecture_unsupported": 3
},
"failureCount": 9,
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4049,7 +4049,7 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 9,
"total": 8,
"unresolvedFailureCount": 5
},
"Biren_166m|unknown|text-generation": {
@@ -4097,7 +4097,7 @@
"failureRate": 0.95,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-10-30T05:43:05.595268+00:00",
"lastTerminalAt": "2026-10-31T11:08:06.037498+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4614,15 +4614,15 @@
"unresolvedFailureCount": 1
}
},
"terminalRecords": 17611,
"totalRecords": 17611,
"terminalRecords": 17612,
"totalRecords": 17612,
"totals": {
"attributableFailureCount": 7892,
"decisionFailureRate": 0.8908,
"decisionSuccessRate": 0.1092,
"decisionTotal": 8859,
"failureBreakdown": {
"ambiguous_runtime": 3519,
"ambiguous_runtime": 3520,
"architecture_compatibility": 62,
"attention_backend": 3,
"backend_operator": 136,
@@ -4642,15 +4642,15 @@
"参数/模板问题": 3675,
"日志缺失": 719
},
"failureCount": 16644,
"failureCount": 16645,
"failureRate": 0.9451,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 693,
"successCount": 967,
"successRate": 0.0549,
"total": 17611,
"unresolvedFailureCount": 8059
"total": 17612,
"unresolvedFailureCount": 8060
},
"warnings": [
"GPU Iluvatar_bi-150 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -4699,6 +4699,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17611,
"summarizedRecords": 17612,
"version": 1
}