state: generation 18871 (cycle)

This commit is contained in:
2026-11-01 20:07:16 +00:00
parent c5d30d5d18
commit 24d983368d
9 changed files with 1024 additions and 1024 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-11-01T19:50:21.319845+00:00",
"lastSyncTime": "2026-11-01T19:50:21.043201+00:00",
"generatedAt": "2026-11-01T20:07:12.037874+00:00",
"lastSyncTime": "2026-11-01T20:07:11.761145+00:00",
"recentLimit": 300,
"report": {
"agentSummaries": {
@@ -29,7 +29,7 @@
"decisionSuccessRate": 0.0537,
"decisionTotal": 149,
"failureBreakdown": {
"ambiguous_runtime": 58,
"ambiguous_runtime": 59,
"backend_operator": 5,
"configuration_launch": 33,
"context_length": 5,
@@ -43,15 +43,15 @@
"任务失败_原因未确认": 146,
"参数/模板问题": 114
},
"failureCount": 460,
"failureCount": 461,
"failureRate": 0.9829,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 8,
"successRate": 0.0171,
"total": 468,
"unresolvedFailureCount": 318
"total": 469,
"unresolvedFailureCount": 319
}
},
"architectureCompatibilityBlocks": {
@@ -2871,7 +2871,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 188,
"failureBreakdown": {
"ambiguous_runtime": 4,
"ambiguous_runtime": 5,
"backend_operator": 12,
"framework_architecture_unsupported": 68,
"memory_capacity": 1,
@@ -2881,7 +2881,7 @@
"runtime_memory": 1,
"tokenizer_compatibility": 105
},
"failureCount": 195,
"failureCount": 196,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2891,8 +2891,8 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 195,
"unresolvedFailureCount": 4
"total": 196,
"unresolvedFailureCount": 5
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 810,
@@ -3413,7 +3413,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 197,
"failureBreakdown": {
"ambiguous_runtime": 55,
"ambiguous_runtime": 56,
"backend_operator": 12,
"framework_architecture_unsupported": 68,
"memory_capacity": 10,
@@ -3423,15 +3423,15 @@
"runtime_memory": 1,
"tokenizer_compatibility": 105
},
"failureCount": 255,
"failureCount": 256,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 0,
"successRate": 0.0,
"total": 255,
"unresolvedFailureCount": 55
"total": 256,
"unresolvedFailureCount": 56
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 1,
@@ -3453,7 +3453,7 @@
"unresolvedFailureCount": 3
}
},
"generatedAt": "2026-11-01T19:50:21.312578+00:00",
"generatedAt": "2026-11-01T20:07:12.033121+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 139,
@@ -3799,7 +3799,7 @@
"decisionSuccessRate": 0.0938,
"decisionTotal": 1151,
"failureBreakdown": {
"ambiguous_runtime": 118,
"ambiguous_runtime": 119,
"architecture_compatibility": 13,
"backend_operator": 45,
"context_length": 44,
@@ -3813,15 +3813,15 @@
"任务失败_原因未确认": 8,
"参数/模板问题": 239
},
"failureCount": 1490,
"failureRate": 0.9324,
"failureCount": 1491,
"failureRate": 0.9325,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 82,
"successCount": 108,
"successRate": 0.0676,
"total": 1598,
"unresolvedFailureCount": 365
"successRate": 0.0675,
"total": 1599,
"unresolvedFailureCount": 366
},
"Vastai_va16": {
"attributableFailureCount": 470,
@@ -4276,19 +4276,19 @@
"unresolvedFailureCount": 16
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"attributableFailureCount": 4,
"consecutiveFailures": 4,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 4,
"context_length": 2,
"framework_architecture_unsupported": 1,
"model_load": 2
"model_load": 1
},
"failureCount": 9,
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4300,7 +4300,7 @@
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 9,
"total": 8,
"unresolvedFailureCount": 4
},
"Mthreads_s4000|unknown|text-generation": {
@@ -4386,21 +4386,22 @@
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 12,
"consecutiveFailures": 12,
"consecutivePlatformFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 12,
"failureBreakdown": {
"ambiguous_runtime": 1,
"backend_operator": 1,
"framework_architecture_unsupported": 4,
"platform_storage": 1,
"tokenizer_compatibility": 7
},
"failureCount": 13,
"failureCount": 14,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-10-31T12:05:02.739582+00:00",
"lastTerminalAt": "2026-10-31T12:05:02.739582+00:00",
"lastTerminalAt": "2026-11-01T20:07:11.761145+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -4408,8 +4409,8 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 13,
"unresolvedFailureCount": 0
"total": 14,
"unresolvedFailureCount": 1
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 6,
@@ -4619,15 +4620,15 @@
"unresolvedFailureCount": 1
}
},
"terminalRecords": 17616,
"totalRecords": 17616,
"terminalRecords": 17617,
"totalRecords": 17617,
"totals": {
"attributableFailureCount": 7894,
"decisionFailureRate": 0.8908,
"decisionSuccessRate": 0.1092,
"decisionTotal": 8862,
"failureBreakdown": {
"ambiguous_runtime": 3520,
"ambiguous_runtime": 3521,
"architecture_compatibility": 62,
"attention_backend": 3,
"backend_operator": 136,
@@ -4647,15 +4648,15 @@
"参数/模板问题": 3675,
"日志缺失": 719
},
"failureCount": 16648,
"failureRate": 0.945,
"failureCount": 16649,
"failureRate": 0.9451,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 694,
"successCount": 968,
"successRate": 0.055,
"total": 17616,
"unresolvedFailureCount": 8060
"successRate": 0.0549,
"total": 17617,
"unresolvedFailureCount": 8061
},
"warnings": [
"GPU Iluvatar_bi-150 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -4704,6 +4705,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17616,
"summarizedRecords": 17617,
"version": 1
}