state: generation 20696 (cycle_no_slots)

This commit is contained in:
2026-11-03 07:51:06 +00:00
parent 631b4c3f92
commit b10e9b52f9
7 changed files with 1058 additions and 1059 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-11-02T03:10:29.104148+00:00",
"lastSyncTime": "2026-11-02T03:10:28.741795+00:00",
"generatedAt": "2026-11-03T07:50:50.039338+00:00",
"lastSyncTime": "2026-11-03T07:50:49.766112+00:00",
"recentLimit": 300,
"report": {
"agentSummaries": {
@@ -24,10 +24,10 @@
"unresolvedFailureCount": 3
},
"unknown": {
"attributableFailureCount": 145,
"decisionFailureRate": 0.9477,
"decisionSuccessRate": 0.0523,
"decisionTotal": 153,
"attributableFailureCount": 146,
"decisionFailureRate": 0.9481,
"decisionSuccessRate": 0.0519,
"decisionTotal": 154,
"failureBreakdown": {
"ambiguous_runtime": 59,
"backend_operator": 5,
@@ -39,18 +39,18 @@
"platform_storage": 1,
"quantization_compatibility": 1,
"runtime_memory": 1,
"tokenizer_compatibility": 17,
"tokenizer_compatibility": 18,
"任务失败_原因未确认": 146,
"参数/模板问题": 114
},
"failureCount": 465,
"failureCount": 466,
"failureRate": 0.9831,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 8,
"successRate": 0.0169,
"total": 473,
"total": 474,
"unresolvedFailureCount": 319
}
},
@@ -2920,10 +2920,10 @@
"unresolvedFailureCount": 5
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 811,
"attributableFailureCount": 812,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 811,
"decisionTotal": 812,
"failureBreakdown": {
"ambiguous_runtime": 87,
"architecture_compatibility": 13,
@@ -2935,9 +2935,9 @@
"platform_storage": 2,
"repository_structure": 105,
"runtime_memory": 2,
"tokenizer_compatibility": 213
"tokenizer_compatibility": 214
},
"failureCount": 977,
"failureCount": 978,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2947,7 +2947,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 977,
"total": 978,
"unresolvedFailureCount": 87
},
"Sunrise_pt-200-x1|vllm|unknown": {
@@ -3402,10 +3402,10 @@
"unresolvedFailureCount": 6226
},
"vllm": {
"attributableFailureCount": 4390,
"attributableFailureCount": 4391,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4390,
"decisionTotal": 4391,
"failureBreakdown": {
"ambiguous_runtime": 1595,
"architecture_compatibility": 39,
@@ -3420,16 +3420,16 @@
"platform_storage": 19,
"repository_structure": 506,
"runtime_memory": 99,
"tokenizer_compatibility": 454
"tokenizer_compatibility": 455
},
"failureCount": 6651,
"failureCount": 6652,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 666,
"successCount": 0,
"successRate": 0.0,
"total": 6651,
"total": 6652,
"unresolvedFailureCount": 1595
},
"vllm_fix_tokenizer": {
@@ -3478,7 +3478,7 @@
"unresolvedFailureCount": 3
}
},
"generatedAt": "2026-11-02T03:10:29.099542+00:00",
"generatedAt": "2026-11-03T07:50:50.035055+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 139,
@@ -3819,10 +3819,10 @@
"unresolvedFailureCount": 338
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 1047,
"decisionFailureRate": 0.9065,
"decisionSuccessRate": 0.0935,
"decisionTotal": 1155,
"attributableFailureCount": 1048,
"decisionFailureRate": 0.9066,
"decisionSuccessRate": 0.0934,
"decisionTotal": 1156,
"failureBreakdown": {
"ambiguous_runtime": 119,
"architecture_compatibility": 13,
@@ -3834,18 +3834,18 @@
"platform_storage": 3,
"repository_structure": 114,
"runtime_memory": 3,
"tokenizer_compatibility": 322,
"tokenizer_compatibility": 323,
"任务失败_原因未确认": 8,
"参数/模板问题": 239
},
"failureCount": 1495,
"failureRate": 0.9326,
"failureCount": 1496,
"failureRate": 0.9327,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 82,
"successCount": 108,
"successRate": 0.0674,
"total": 1603,
"successRate": 0.0673,
"total": 1604,
"unresolvedFailureCount": 366
},
"Vastai_va16": {
@@ -4438,22 +4438,22 @@
"unresolvedFailureCount": 1
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"attributableFailureCount": 8,
"consecutiveFailures": 8,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 4,
"tokenizer_compatibility": 3
"tokenizer_compatibility": 4
},
"failureCount": 8,
"failureCount": 9,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-11-01T20:50:57.358677+00:00",
"lastTerminalAt": "2026-11-03T07:50:49.766112+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4461,7 +4461,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 8,
"total": 9,
"unresolvedFailureCount": 1
},
"Vastai_va16|unknown|text-generation": {
@@ -4550,10 +4550,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 6,
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 1
},
"failureCount": 7,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -4565,8 +4565,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 6
"total": 6,
"unresolvedFailureCount": 5
}
},
"recentProfileCombinationStats": {},
@@ -4644,13 +4644,13 @@
"unresolvedFailureCount": 1
}
},
"terminalRecords": 17621,
"totalRecords": 17621,
"terminalRecords": 17622,
"totalRecords": 17622,
"totals": {
"attributableFailureCount": 7898,
"attributableFailureCount": 7899,
"decisionFailureRate": 0.8908,
"decisionSuccessRate": 0.1092,
"decisionTotal": 8866,
"decisionTotal": 8867,
"failureBreakdown": {
"ambiguous_runtime": 3521,
"architecture_compatibility": 62,
@@ -4667,19 +4667,19 @@
"quantization_compatibility": 238,
"repository_structure": 771,
"runtime_memory": 103,
"tokenizer_compatibility": 738,
"tokenizer_compatibility": 739,
"任务失败_原因未确认": 146,
"参数/模板问题": 3675,
"日志缺失": 719
},
"failureCount": 16653,
"failureCount": 16654,
"failureRate": 0.9451,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 694,
"successCount": 968,
"successRate": 0.0549,
"total": 17621,
"total": 17622,
"unresolvedFailureCount": 8061
},
"warnings": [
@@ -4729,6 +4729,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17621,
"summarizedRecords": 17622,
"version": 1
}