state: generation 18910 (cycle)

This commit is contained in:
2026-11-01 20:51:01 +00:00
parent 0cd8931124
commit cee00e6c93
9 changed files with 942 additions and 939 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-11-01T20:07:12.037874+00:00",
"lastSyncTime": "2026-11-01T20:07:11.761145+00:00",
"generatedAt": "2026-11-01T20:50:57.612596+00:00",
"lastSyncTime": "2026-11-01T20:50:57.358677+00:00",
"recentLimit": 300,
"report": {
"agentSummaries": {
@@ -24,16 +24,16 @@
"unresolvedFailureCount": 3
},
"unknown": {
"attributableFailureCount": 141,
"decisionFailureRate": 0.9463,
"decisionSuccessRate": 0.0537,
"decisionTotal": 149,
"attributableFailureCount": 142,
"decisionFailureRate": 0.9467,
"decisionSuccessRate": 0.0533,
"decisionTotal": 150,
"failureBreakdown": {
"ambiguous_runtime": 59,
"backend_operator": 5,
"configuration_launch": 33,
"context_length": 5,
"framework_architecture_unsupported": 62,
"framework_architecture_unsupported": 63,
"memory_capacity": 1,
"model_load": 17,
"platform_storage": 1,
@@ -43,14 +43,14 @@
"任务失败_原因未确认": 146,
"参数/模板问题": 114
},
"failureCount": 461,
"failureRate": 0.9829,
"failureCount": 462,
"failureRate": 0.983,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 8,
"successRate": 0.0171,
"total": 469,
"successRate": 0.017,
"total": 470,
"unresolvedFailureCount": 319
}
},
@@ -914,18 +914,20 @@
"sunrise_pt-200-x1|vllm|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 2,
"expiresAt": "2026-11-30T12:08:15.546713+00:00",
"evidenceCount": 3,
"expiresAt": "2026-12-01T20:50:57.358677+00:00",
"framework": "vllm",
"latestFailureAt": "2026-10-31T12:08:15.546713+00:00",
"latestFailureAt": "2026-11-01T20:50:57.358677+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5",
"sourceModelIds": [
"prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX",
"togethercomputer/Tev1-0.8B-experimental",
"prithivMLmods/Nexus-9B-CodeCore-Merge"
],
"sourceTaskIds": [
"5008957",
"5520142",
"5008929"
],
@@ -2895,16 +2897,16 @@
"unresolvedFailureCount": 5
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 810,
"attributableFailureCount": 811,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 810,
"decisionTotal": 811,
"failureBreakdown": {
"ambiguous_runtime": 87,
"architecture_compatibility": 13,
"backend_operator": 33,
"context_length": 39,
"framework_architecture_unsupported": 292,
"framework_architecture_unsupported": 293,
"memory_capacity": 113,
"platform_infrastructure": 77,
"platform_storage": 2,
@@ -2912,7 +2914,7 @@
"runtime_memory": 2,
"tokenizer_compatibility": 213
},
"failureCount": 976,
"failureCount": 977,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2922,7 +2924,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 976,
"total": 977,
"unresolvedFailureCount": 87
},
"Sunrise_pt-200-x1|vllm|unknown": {
@@ -3377,17 +3379,17 @@
"unresolvedFailureCount": 6226
},
"vllm": {
"attributableFailureCount": 4389,
"attributableFailureCount": 4390,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4389,
"decisionTotal": 4390,
"failureBreakdown": {
"ambiguous_runtime": 1595,
"architecture_compatibility": 39,
"attention_backend": 3,
"backend_operator": 111,
"context_length": 250,
"framework_architecture_unsupported": 1931,
"framework_architecture_unsupported": 1932,
"memory_capacity": 726,
"model_load": 270,
"platform_infrastructure": 641,
@@ -3397,14 +3399,14 @@
"runtime_memory": 99,
"tokenizer_compatibility": 454
},
"failureCount": 6650,
"failureCount": 6651,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 666,
"successCount": 0,
"successRate": 0.0,
"total": 6650,
"total": 6651,
"unresolvedFailureCount": 1595
},
"vllm_fix_tokenizer": {
@@ -3453,7 +3455,7 @@
"unresolvedFailureCount": 3
}
},
"generatedAt": "2026-11-01T20:07:12.033121+00:00",
"generatedAt": "2026-11-01T20:50:57.607495+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 139,
@@ -3794,16 +3796,16 @@
"unresolvedFailureCount": 338
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 1043,
"attributableFailureCount": 1044,
"decisionFailureRate": 0.9062,
"decisionSuccessRate": 0.0938,
"decisionTotal": 1151,
"decisionTotal": 1152,
"failureBreakdown": {
"ambiguous_runtime": 119,
"architecture_compatibility": 13,
"backend_operator": 45,
"context_length": 44,
"framework_architecture_unsupported": 389,
"framework_architecture_unsupported": 390,
"memory_capacity": 114,
"platform_infrastructure": 79,
"platform_storage": 3,
@@ -3813,14 +3815,14 @@
"任务失败_原因未确认": 8,
"参数/模板问题": 239
},
"failureCount": 1491,
"failureCount": 1492,
"failureRate": 0.9325,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 82,
"successCount": 108,
"successRate": 0.0675,
"total": 1599,
"total": 1600,
"unresolvedFailureCount": 366
},
"Vastai_va16": {
@@ -4120,13 +4122,13 @@
"decisionSuccessRate": 0.5,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 5,
"ambiguous_runtime": 4,
"framework_architecture_unsupported": 1,
"任务失败_原因未确认": 8,
"参数/模板问题": 3
},
"failureCount": 17,
"failureRate": 0.9444,
"failureCount": 16,
"failureRate": 0.9412,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-10-30T20:02:51.541944+00:00",
@@ -4134,11 +4136,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0556,
"successRate": 0.0588,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 18,
"unresolvedFailureCount": 16
"total": 17,
"unresolvedFailureCount": 15
},
"Iluvatar_bi-150|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -4413,22 +4415,22 @@
"unresolvedFailureCount": 1
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 3,
"framework_architecture_unsupported": 4,
"tokenizer_compatibility": 3
},
"failureCount": 7,
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-11-01T19:50:21.043201+00:00",
"lastTerminalAt": "2026-11-01T20:50:57.358677+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4436,7 +4438,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 7,
"total": 8,
"unresolvedFailureCount": 1
},
"Vastai_va16|unknown|text-generation": {
@@ -4620,13 +4622,13 @@
"unresolvedFailureCount": 1
}
},
"terminalRecords": 17617,
"totalRecords": 17617,
"terminalRecords": 17618,
"totalRecords": 17618,
"totals": {
"attributableFailureCount": 7894,
"attributableFailureCount": 7895,
"decisionFailureRate": 0.8908,
"decisionSuccessRate": 0.1092,
"decisionTotal": 8862,
"decisionTotal": 8863,
"failureBreakdown": {
"ambiguous_runtime": 3521,
"architecture_compatibility": 62,
@@ -4634,7 +4636,7 @@
"backend_operator": 136,
"configuration_launch": 489,
"context_length": 408,
"framework_architecture_unsupported": 3153,
"framework_architecture_unsupported": 3154,
"memory_capacity": 1208,
"model_load": 586,
"platform_infrastructure": 652,
@@ -4648,14 +4650,14 @@
"参数/模板问题": 3675,
"日志缺失": 719
},
"failureCount": 16649,
"failureCount": 16650,
"failureRate": 0.9451,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 694,
"successCount": 968,
"successRate": 0.0549,
"total": 17617,
"total": 17618,
"unresolvedFailureCount": 8061
},
"warnings": [
@@ -4705,6 +4707,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17617,
"summarizedRecords": 17618,
"version": 1
}