state: generation 17053 (cycle)

This commit is contained in:
2026-10-31 10:07:53 +00:00
parent b13b0fb372
commit a208ff9e3e
9 changed files with 1004 additions and 1005 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-31T05:24:41.244363+00:00",
"lastSyncTime": "2026-10-31T05:24:41.009215+00:00",
"generatedAt": "2026-10-31T10:07:49.975522+00:00",
"lastSyncTime": "2026-10-31T10:07:49.740586+00:00",
"recentLimit": 300,
"report": {
"agentSummaries": {
@@ -29,7 +29,7 @@
"decisionSuccessRate": 0.0479,
"decisionTotal": 146,
"failureBreakdown": {
"ambiguous_runtime": 56,
"ambiguous_runtime": 57,
"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": 455,
"failureRate": 0.9848,
"failureCount": 456,
"failureRate": 0.9849,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 7,
"successRate": 0.0152,
"total": 462,
"unresolvedFailureCount": 316
"successRate": 0.0151,
"total": 463,
"unresolvedFailureCount": 317
}
},
"architectureCompatibilityBlocks": {
@@ -3224,7 +3224,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 744,
"failureBreakdown": {
"ambiguous_runtime": 212,
"ambiguous_runtime": 213,
"architecture_compatibility": 10,
"attention_backend": 1,
"context_length": 42,
@@ -3236,7 +3236,7 @@
"runtime_memory": 74,
"tokenizer_compatibility": 79
},
"failureCount": 959,
"failureCount": 960,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -3246,8 +3246,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 959,
"unresolvedFailureCount": 212
"total": 960,
"unresolvedFailureCount": 213
},
"hygon_k100-ai|vllm|unknown": {
"attributableFailureCount": 1,
@@ -3378,7 +3378,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 4387,
"failureBreakdown": {
"ambiguous_runtime": 1594,
"ambiguous_runtime": 1595,
"architecture_compatibility": 39,
"attention_backend": 3,
"backend_operator": 111,
@@ -3393,15 +3393,15 @@
"runtime_memory": 99,
"tokenizer_compatibility": 453
},
"failureCount": 6647,
"failureCount": 6648,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 666,
"successCount": 0,
"successRate": 0.0,
"total": 6647,
"unresolvedFailureCount": 1594
"total": 6648,
"unresolvedFailureCount": 1595
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 197,
@@ -3448,7 +3448,7 @@
"unresolvedFailureCount": 3
}
},
"generatedAt": "2026-10-31T05:24:41.238565+00:00",
"generatedAt": "2026-10-31T10:07:49.971384+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 139,
@@ -3853,7 +3853,7 @@
"decisionSuccessRate": 0.0446,
"decisionTotal": 807,
"failureBreakdown": {
"ambiguous_runtime": 339,
"ambiguous_runtime": 340,
"architecture_compatibility": 10,
"attention_backend": 1,
"context_length": 46,
@@ -3868,15 +3868,15 @@
"参数/模板问题": 446,
"日志缺失": 66
},
"failureCount": 1639,
"failureCount": 1640,
"failureRate": 0.9785,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 36,
"successRate": 0.0215,
"total": 1675,
"unresolvedFailureCount": 864
"total": 1676,
"unresolvedFailureCount": 865
}
},
"observedGpuMemoryGiB": {
@@ -4519,15 +4519,15 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 5,
"ambiguous_runtime": 6,
"framework_architecture_unsupported": 1,
"model_load": 2
},
"failureCount": 8,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-10-28T00:26:30.135914+00:00",
"lastTerminalAt": "2026-10-31T10:07:49.740586+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4535,8 +4535,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 5
"total": 9,
"unresolvedFailureCount": 6
}
},
"recentProfileCombinationStats": {},
@@ -4614,15 +4614,15 @@
"unresolvedFailureCount": 1
}
},
"terminalRecords": 17610,
"totalRecords": 17610,
"terminalRecords": 17611,
"totalRecords": 17611,
"totals": {
"attributableFailureCount": 7892,
"decisionFailureRate": 0.8908,
"decisionSuccessRate": 0.1092,
"decisionTotal": 8859,
"failureBreakdown": {
"ambiguous_runtime": 3518,
"ambiguous_runtime": 3519,
"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": 16643,
"failureCount": 16644,
"failureRate": 0.9451,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 693,
"successCount": 967,
"successRate": 0.0549,
"total": 17610,
"unresolvedFailureCount": 8058
"total": 17611,
"unresolvedFailureCount": 8059
},
"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": 17610,
"summarizedRecords": 17611,
"version": 1
}