state: generation 17161 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-10-31T12:05:02.989934+00:00",
|
||||
"lastSyncTime": "2026-10-31T12:05:02.739582+00:00",
|
||||
"generatedAt": "2026-10-31T12:08:15.780820+00:00",
|
||||
"lastSyncTime": "2026-10-31T12:08:15.546713+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"agentSummaries": {
|
||||
@@ -24,16 +24,16 @@
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 139,
|
||||
"decisionFailureRate": 0.9521,
|
||||
"decisionSuccessRate": 0.0479,
|
||||
"decisionTotal": 146,
|
||||
"attributableFailureCount": 140,
|
||||
"decisionFailureRate": 0.9459,
|
||||
"decisionSuccessRate": 0.0541,
|
||||
"decisionTotal": 148,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 58,
|
||||
"backend_operator": 5,
|
||||
"configuration_launch": 33,
|
||||
"context_length": 5,
|
||||
"framework_architecture_unsupported": 61,
|
||||
"framework_architecture_unsupported": 62,
|
||||
"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": 458,
|
||||
"failureRate": 0.9849,
|
||||
"failureCount": 459,
|
||||
"failureRate": 0.9829,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 7,
|
||||
"successRate": 0.0151,
|
||||
"total": 465,
|
||||
"successCount": 8,
|
||||
"successRate": 0.0171,
|
||||
"total": 467,
|
||||
"unresolvedFailureCount": 318
|
||||
}
|
||||
},
|
||||
@@ -914,17 +914,19 @@
|
||||
"sunrise_pt-200-x1|vllm|text-generation|model_type:qwen3_5": {
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectures": [],
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-11-28T09:21:55.734355+00:00",
|
||||
"evidenceCount": 2,
|
||||
"expiresAt": "2026-11-30T12:08:15.546713+00:00",
|
||||
"framework": "vllm",
|
||||
"latestFailureAt": "2026-10-29T09:21:55.734355+00:00",
|
||||
"latestFailureAt": "2026-10-31T12:08:15.546713+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "model_type",
|
||||
"modelType": "qwen3_5",
|
||||
"sourceModelIds": [
|
||||
"togethercomputer/Tev1-0.8B-experimental",
|
||||
"prithivMLmods/Nexus-9B-CodeCore-Merge"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"5520142",
|
||||
"5008929"
|
||||
],
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
@@ -2818,9 +2820,9 @@
|
||||
},
|
||||
"Sunrise_pt-200-x1|unknown|text-generation": {
|
||||
"attributableFailureCount": 38,
|
||||
"decisionFailureRate": 0.2621,
|
||||
"decisionSuccessRate": 0.7379,
|
||||
"decisionTotal": 145,
|
||||
"decisionFailureRate": 0.2603,
|
||||
"decisionSuccessRate": 0.7397,
|
||||
"decisionTotal": 146,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 27,
|
||||
"context_length": 5,
|
||||
@@ -2830,16 +2832,16 @@
|
||||
"参数/模板问题": 237
|
||||
},
|
||||
"failureCount": 310,
|
||||
"failureRate": 0.7434,
|
||||
"failureRate": 0.7416,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 107,
|
||||
"successRate": 0.2566,
|
||||
"successCount": 108,
|
||||
"successRate": 0.2584,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 417,
|
||||
"total": 418,
|
||||
"unresolvedFailureCount": 272
|
||||
},
|
||||
"Sunrise_pt-200-x1|unknown|visual-multi-modal": {
|
||||
@@ -2893,16 +2895,16 @@
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
"attributableFailureCount": 808,
|
||||
"attributableFailureCount": 809,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 808,
|
||||
"decisionTotal": 809,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 87,
|
||||
"architecture_compatibility": 13,
|
||||
"backend_operator": 33,
|
||||
"context_length": 39,
|
||||
"framework_architecture_unsupported": 291,
|
||||
"framework_architecture_unsupported": 292,
|
||||
"memory_capacity": 113,
|
||||
"platform_infrastructure": 77,
|
||||
"platform_storage": 2,
|
||||
@@ -2910,7 +2912,7 @@
|
||||
"runtime_memory": 2,
|
||||
"tokenizer_compatibility": 212
|
||||
},
|
||||
"failureCount": 974,
|
||||
"failureCount": 975,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -2920,7 +2922,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 974,
|
||||
"total": 975,
|
||||
"unresolvedFailureCount": 87
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|unknown": {
|
||||
@@ -3342,9 +3344,9 @@
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 3074,
|
||||
"decisionFailureRate": 0.7607,
|
||||
"decisionSuccessRate": 0.2393,
|
||||
"decisionTotal": 4041,
|
||||
"decisionFailureRate": 0.7605,
|
||||
"decisionSuccessRate": 0.2395,
|
||||
"decisionTotal": 4042,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1689,
|
||||
"architecture_compatibility": 23,
|
||||
@@ -3369,23 +3371,23 @@
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 25,
|
||||
"successCount": 967,
|
||||
"successCount": 968,
|
||||
"successRate": 0.094,
|
||||
"total": 10292,
|
||||
"total": 10293,
|
||||
"unresolvedFailureCount": 6226
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 4387,
|
||||
"attributableFailureCount": 4388,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 4387,
|
||||
"decisionTotal": 4388,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1595,
|
||||
"architecture_compatibility": 39,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 111,
|
||||
"context_length": 250,
|
||||
"framework_architecture_unsupported": 1930,
|
||||
"framework_architecture_unsupported": 1931,
|
||||
"memory_capacity": 726,
|
||||
"model_load": 270,
|
||||
"platform_infrastructure": 641,
|
||||
@@ -3395,14 +3397,14 @@
|
||||
"runtime_memory": 99,
|
||||
"tokenizer_compatibility": 453
|
||||
},
|
||||
"failureCount": 6648,
|
||||
"failureCount": 6649,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 666,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 6648,
|
||||
"total": 6649,
|
||||
"unresolvedFailureCount": 1595
|
||||
},
|
||||
"vllm_fix_tokenizer": {
|
||||
@@ -3451,7 +3453,7 @@
|
||||
"unresolvedFailureCount": 3
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-31T12:05:02.985585+00:00",
|
||||
"generatedAt": "2026-10-31T12:08:15.776364+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 139,
|
||||
@@ -3792,16 +3794,16 @@
|
||||
"unresolvedFailureCount": 338
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"attributableFailureCount": 1041,
|
||||
"decisionFailureRate": 0.9068,
|
||||
"decisionSuccessRate": 0.0932,
|
||||
"decisionTotal": 1148,
|
||||
"attributableFailureCount": 1042,
|
||||
"decisionFailureRate": 0.9061,
|
||||
"decisionSuccessRate": 0.0939,
|
||||
"decisionTotal": 1150,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 118,
|
||||
"architecture_compatibility": 13,
|
||||
"backend_operator": 45,
|
||||
"context_length": 44,
|
||||
"framework_architecture_unsupported": 388,
|
||||
"framework_architecture_unsupported": 389,
|
||||
"memory_capacity": 114,
|
||||
"platform_infrastructure": 79,
|
||||
"platform_storage": 3,
|
||||
@@ -3811,14 +3813,14 @@
|
||||
"任务失败_原因未确认": 8,
|
||||
"参数/模板问题": 239
|
||||
},
|
||||
"failureCount": 1488,
|
||||
"failureRate": 0.9329,
|
||||
"failureCount": 1489,
|
||||
"failureRate": 0.9324,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 82,
|
||||
"successCount": 107,
|
||||
"successRate": 0.0671,
|
||||
"total": 1595,
|
||||
"successCount": 108,
|
||||
"successRate": 0.0676,
|
||||
"total": 1597,
|
||||
"unresolvedFailureCount": 365
|
||||
},
|
||||
"Vastai_va16": {
|
||||
@@ -3984,11 +3986,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 6,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"context_length": 2,
|
||||
"framework_architecture_unsupported": 4
|
||||
},
|
||||
"failureCount": 7,
|
||||
"failureCount": 6,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -4000,8 +4001,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 1
|
||||
"total": 6,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -4362,24 +4363,24 @@
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"任务失败_原因未确认": 8,
|
||||
"参数/模板问题": 4
|
||||
},
|
||||
"failureCount": 12,
|
||||
"failureRate": 0.9231,
|
||||
"failureRate": 0.8571,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-10-30T05:43:05.595353+00:00",
|
||||
"lastTerminalAt": "2026-10-31T12:08:15.546689+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0769,
|
||||
"successCount": 2,
|
||||
"successRate": 0.1429,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 13,
|
||||
"total": 14,
|
||||
"unresolvedFailureCount": 12
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
@@ -4411,22 +4412,22 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
"attributableFailureCount": 4,
|
||||
"consecutiveFailures": 4,
|
||||
"attributableFailureCount": 5,
|
||||
"consecutiveFailures": 5,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 4,
|
||||
"decisionTotal": 5,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"framework_architecture_unsupported": 3,
|
||||
"tokenizer_compatibility": 2
|
||||
},
|
||||
"failureCount": 5,
|
||||
"failureCount": 6,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-10-29T09:21:55.734355+00:00",
|
||||
"lastTerminalAt": "2026-10-31T12:08:15.546713+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4434,7 +4435,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 5,
|
||||
"total": 6,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Vastai_va16|unknown|text-generation": {
|
||||
@@ -4618,13 +4619,13 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17613,
|
||||
"totalRecords": 17613,
|
||||
"terminalRecords": 17615,
|
||||
"totalRecords": 17615,
|
||||
"totals": {
|
||||
"attributableFailureCount": 7892,
|
||||
"attributableFailureCount": 7893,
|
||||
"decisionFailureRate": 0.8908,
|
||||
"decisionSuccessRate": 0.1092,
|
||||
"decisionTotal": 8859,
|
||||
"decisionTotal": 8861,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3520,
|
||||
"architecture_compatibility": 62,
|
||||
@@ -4632,7 +4633,7 @@
|
||||
"backend_operator": 136,
|
||||
"configuration_launch": 489,
|
||||
"context_length": 408,
|
||||
"framework_architecture_unsupported": 3152,
|
||||
"framework_architecture_unsupported": 3153,
|
||||
"memory_capacity": 1208,
|
||||
"model_load": 586,
|
||||
"platform_infrastructure": 652,
|
||||
@@ -4646,14 +4647,14 @@
|
||||
"参数/模板问题": 3675,
|
||||
"日志缺失": 719
|
||||
},
|
||||
"failureCount": 16646,
|
||||
"failureRate": 0.9451,
|
||||
"failureCount": 16647,
|
||||
"failureRate": 0.945,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 694,
|
||||
"successCount": 967,
|
||||
"successRate": 0.0549,
|
||||
"total": 17613,
|
||||
"successCount": 968,
|
||||
"successRate": 0.055,
|
||||
"total": 17615,
|
||||
"unresolvedFailureCount": 8060
|
||||
},
|
||||
"warnings": [
|
||||
@@ -4703,6 +4704,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17613,
|
||||
"summarizedRecords": 17615,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user