state: generation 18922 (cycle)

This commit is contained in:
2026-11-01 21:04:06 +00:00
parent dcdd280db9
commit 7e1d0b80b3
9 changed files with 1038 additions and 1039 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-11-01T21:00:36.353103+00:00",
"lastSyncTime": "2026-11-01T21:00:36.112004+00:00",
"generatedAt": "2026-11-01T21:03:57.528017+00:00",
"lastSyncTime": "2026-11-01T21:03:57.238253+00:00",
"recentLimit": 300,
"report": {
"agentSummaries": {
@@ -24,10 +24,10 @@
"unresolvedFailureCount": 3
},
"unknown": {
"attributableFailureCount": 143,
"decisionFailureRate": 0.947,
"decisionSuccessRate": 0.053,
"decisionTotal": 151,
"attributableFailureCount": 144,
"decisionFailureRate": 0.9474,
"decisionSuccessRate": 0.0526,
"decisionTotal": 152,
"failureBreakdown": {
"ambiguous_runtime": 59,
"backend_operator": 5,
@@ -39,18 +39,18 @@
"platform_storage": 1,
"quantization_compatibility": 1,
"runtime_memory": 1,
"tokenizer_compatibility": 16,
"tokenizer_compatibility": 17,
"任务失败_原因未确认": 146,
"参数/模板问题": 114
},
"failureCount": 463,
"failureRate": 0.983,
"failureCount": 464,
"failureRate": 0.9831,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 8,
"successRate": 0.017,
"total": 471,
"successRate": 0.0169,
"total": 472,
"unresolvedFailureCount": 319
}
},
@@ -2870,10 +2870,10 @@
"unresolvedFailureCount": 1
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 189,
"attributableFailureCount": 190,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 189,
"decisionTotal": 190,
"failureBreakdown": {
"ambiguous_runtime": 5,
"backend_operator": 12,
@@ -2883,9 +2883,9 @@
"platform_storage": 1,
"repository_structure": 1,
"runtime_memory": 1,
"tokenizer_compatibility": 105
"tokenizer_compatibility": 106
},
"failureCount": 197,
"failureCount": 198,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -2895,7 +2895,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 197,
"total": 198,
"unresolvedFailureCount": 5
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -3412,10 +3412,10 @@
"unresolvedFailureCount": 1595
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 198,
"attributableFailureCount": 199,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 198,
"decisionTotal": 199,
"failureBreakdown": {
"ambiguous_runtime": 56,
"backend_operator": 12,
@@ -3425,16 +3425,16 @@
"platform_storage": 1,
"repository_structure": 1,
"runtime_memory": 1,
"tokenizer_compatibility": 105
"tokenizer_compatibility": 106
},
"failureCount": 257,
"failureCount": 258,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 0,
"successRate": 0.0,
"total": 257,
"total": 258,
"unresolvedFailureCount": 56
},
"vllm_tokenizer_patch": {
@@ -3457,7 +3457,7 @@
"unresolvedFailureCount": 3
}
},
"generatedAt": "2026-11-01T21:00:36.348216+00:00",
"generatedAt": "2026-11-01T21:03:57.523913+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 139,
@@ -3798,10 +3798,10 @@
"unresolvedFailureCount": 338
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 1045,
"decisionFailureRate": 0.9063,
"decisionSuccessRate": 0.0937,
"decisionTotal": 1153,
"attributableFailureCount": 1046,
"decisionFailureRate": 0.9064,
"decisionSuccessRate": 0.0936,
"decisionTotal": 1154,
"failureBreakdown": {
"ambiguous_runtime": 119,
"architecture_compatibility": 13,
@@ -3813,18 +3813,18 @@
"platform_storage": 3,
"repository_structure": 114,
"runtime_memory": 3,
"tokenizer_compatibility": 321,
"tokenizer_compatibility": 322,
"任务失败_原因未确认": 8,
"参数/模板问题": 239
},
"failureCount": 1493,
"failureRate": 0.9325,
"failureCount": 1494,
"failureRate": 0.9326,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 82,
"successCount": 108,
"successRate": 0.0675,
"total": 1601,
"successRate": 0.0674,
"total": 1602,
"unresolvedFailureCount": 366
},
"Vastai_va16": {
@@ -4388,24 +4388,24 @@
"unresolvedFailureCount": 12
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 13,
"consecutiveFailures": 13,
"attributableFailureCount": 14,
"consecutiveFailures": 14,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 13,
"decisionTotal": 14,
"failureBreakdown": {
"ambiguous_runtime": 1,
"backend_operator": 1,
"framework_architecture_unsupported": 5,
"platform_storage": 1,
"tokenizer_compatibility": 7
"tokenizer_compatibility": 8
},
"failureCount": 15,
"failureCount": 16,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-10-31T12:05:02.739582+00:00",
"lastTerminalAt": "2026-11-01T21:00:36.112004+00:00",
"lastTerminalAt": "2026-11-01T21:03:57.238253+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -4413,7 +4413,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 15,
"total": 16,
"unresolvedFailureCount": 1
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -4522,18 +4522,18 @@
"unresolvedFailureCount": 16
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 6,
"framework_architecture_unsupported": 1,
"model_load": 2
"model_load": 1
},
"failureCount": 9,
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4545,7 +4545,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 9,
"total": 8,
"unresolvedFailureCount": 6
}
},
@@ -4624,13 +4624,13 @@
"unresolvedFailureCount": 1
}
},
"terminalRecords": 17619,
"totalRecords": 17619,
"terminalRecords": 17620,
"totalRecords": 17620,
"totals": {
"attributableFailureCount": 7896,
"attributableFailureCount": 7897,
"decisionFailureRate": 0.8908,
"decisionSuccessRate": 0.1092,
"decisionTotal": 8864,
"decisionTotal": 8865,
"failureBreakdown": {
"ambiguous_runtime": 3521,
"architecture_compatibility": 62,
@@ -4647,19 +4647,19 @@
"quantization_compatibility": 238,
"repository_structure": 771,
"runtime_memory": 103,
"tokenizer_compatibility": 737,
"tokenizer_compatibility": 738,
"任务失败_原因未确认": 146,
"参数/模板问题": 3675,
"日志缺失": 719
},
"failureCount": 16651,
"failureCount": 16652,
"failureRate": 0.9451,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 694,
"successCount": 968,
"successRate": 0.0549,
"total": 17619,
"total": 17620,
"unresolvedFailureCount": 8061
},
"warnings": [
@@ -4709,6 +4709,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17619,
"summarizedRecords": 17620,
"version": 1
}