state: generation 18856 (cycle)

This commit is contained in:
2026-11-01 19:50:26 +00:00
parent f705d7e2a8
commit 39f92bfd5e
9 changed files with 829 additions and 830 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-31T12:08:15.780820+00:00",
"lastSyncTime": "2026-10-31T12:08:15.546713+00:00",
"generatedAt": "2026-11-01T19:50:21.319845+00:00",
"lastSyncTime": "2026-11-01T19:50:21.043201+00:00",
"recentLimit": 300,
"report": {
"agentSummaries": {
@@ -24,10 +24,10 @@
"unresolvedFailureCount": 3
},
"unknown": {
"attributableFailureCount": 140,
"decisionFailureRate": 0.9459,
"decisionSuccessRate": 0.0541,
"decisionTotal": 148,
"attributableFailureCount": 141,
"decisionFailureRate": 0.9463,
"decisionSuccessRate": 0.0537,
"decisionTotal": 149,
"failureBreakdown": {
"ambiguous_runtime": 58,
"backend_operator": 5,
@@ -39,18 +39,18 @@
"platform_storage": 1,
"quantization_compatibility": 1,
"runtime_memory": 1,
"tokenizer_compatibility": 15,
"tokenizer_compatibility": 16,
"任务失败_原因未确认": 146,
"参数/模板问题": 114
},
"failureCount": 459,
"failureCount": 460,
"failureRate": 0.9829,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 8,
"successRate": 0.0171,
"total": 467,
"total": 468,
"unresolvedFailureCount": 318
}
},
@@ -2895,10 +2895,10 @@
"unresolvedFailureCount": 4
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 809,
"attributableFailureCount": 810,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 809,
"decisionTotal": 810,
"failureBreakdown": {
"ambiguous_runtime": 87,
"architecture_compatibility": 13,
@@ -2910,9 +2910,9 @@
"platform_storage": 2,
"repository_structure": 105,
"runtime_memory": 2,
"tokenizer_compatibility": 212
"tokenizer_compatibility": 213
},
"failureCount": 975,
"failureCount": 976,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2922,7 +2922,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 975,
"total": 976,
"unresolvedFailureCount": 87
},
"Sunrise_pt-200-x1|vllm|unknown": {
@@ -3377,10 +3377,10 @@
"unresolvedFailureCount": 6226
},
"vllm": {
"attributableFailureCount": 4388,
"attributableFailureCount": 4389,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4388,
"decisionTotal": 4389,
"failureBreakdown": {
"ambiguous_runtime": 1595,
"architecture_compatibility": 39,
@@ -3395,16 +3395,16 @@
"platform_storage": 19,
"repository_structure": 506,
"runtime_memory": 99,
"tokenizer_compatibility": 453
"tokenizer_compatibility": 454
},
"failureCount": 6649,
"failureCount": 6650,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 666,
"successCount": 0,
"successRate": 0.0,
"total": 6649,
"total": 6650,
"unresolvedFailureCount": 1595
},
"vllm_fix_tokenizer": {
@@ -3453,7 +3453,7 @@
"unresolvedFailureCount": 3
}
},
"generatedAt": "2026-10-31T12:08:15.776364+00:00",
"generatedAt": "2026-11-01T19:50:21.312578+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 139,
@@ -3794,10 +3794,10 @@
"unresolvedFailureCount": 338
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 1042,
"decisionFailureRate": 0.9061,
"decisionSuccessRate": 0.0939,
"decisionTotal": 1150,
"attributableFailureCount": 1043,
"decisionFailureRate": 0.9062,
"decisionSuccessRate": 0.0938,
"decisionTotal": 1151,
"failureBreakdown": {
"ambiguous_runtime": 118,
"architecture_compatibility": 13,
@@ -3809,18 +3809,18 @@
"platform_storage": 3,
"repository_structure": 114,
"runtime_memory": 3,
"tokenizer_compatibility": 320,
"tokenizer_compatibility": 321,
"任务失败_原因未确认": 8,
"参数/模板问题": 239
},
"failureCount": 1489,
"failureCount": 1490,
"failureRate": 0.9324,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 82,
"successCount": 108,
"successRate": 0.0676,
"total": 1597,
"total": 1598,
"unresolvedFailureCount": 365
},
"Vastai_va16": {
@@ -4412,22 +4412,22 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 3,
"tokenizer_compatibility": 2
"tokenizer_compatibility": 3
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-10-31T12:08:15.546713+00:00",
"lastTerminalAt": "2026-11-01T19:50:21.043201+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4435,7 +4435,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 6,
"total": 7,
"unresolvedFailureCount": 1
},
"Vastai_va16|unknown|text-generation": {
@@ -4619,13 +4619,13 @@
"unresolvedFailureCount": 1
}
},
"terminalRecords": 17615,
"totalRecords": 17615,
"terminalRecords": 17616,
"totalRecords": 17616,
"totals": {
"attributableFailureCount": 7893,
"attributableFailureCount": 7894,
"decisionFailureRate": 0.8908,
"decisionSuccessRate": 0.1092,
"decisionTotal": 8861,
"decisionTotal": 8862,
"failureBreakdown": {
"ambiguous_runtime": 3520,
"architecture_compatibility": 62,
@@ -4642,19 +4642,19 @@
"quantization_compatibility": 238,
"repository_structure": 771,
"runtime_memory": 103,
"tokenizer_compatibility": 736,
"tokenizer_compatibility": 737,
"任务失败_原因未确认": 146,
"参数/模板问题": 3675,
"日志缺失": 719
},
"failureCount": 16647,
"failureCount": 16648,
"failureRate": 0.945,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 694,
"successCount": 968,
"successRate": 0.055,
"total": 17615,
"total": 17616,
"unresolvedFailureCount": 8060
},
"warnings": [
@@ -4704,6 +4704,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17615,
"summarizedRecords": 17616,
"version": 1
}