state: generation 15684 (cycle)
This commit is contained in:
@@ -3242,7 +3242,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-25T09:24:06.961999+00:00",
|
||||
"generatedAt": "2026-09-25T09:29:39.585657+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 163,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -396,7 +396,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-25T09:28:33.452207+00:00",
|
||||
"generatedAt": "2026-09-25T09:30:42.361601+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-25T09:28:33.452207+00:00",
|
||||
"catalogUpdatedAt": "2026-09-25T09:30:42.361601+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-25T09:28:35.421086+00:00",
|
||||
"generatedAt": "2026-09-25T09:30:42.361601+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6550,6 +6550,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-25T09:28:33.452207+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-25T09:30:42.361601+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-25T05:14:51.947130+00:00",
|
||||
"lastSyncTime": "2026-09-25T05:14:51.671721+00:00",
|
||||
"generatedAt": "2026-09-25T09:29:39.500166+00:00",
|
||||
"lastSyncTime": "2026-09-25T09:29:37.557613+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -3850,12 +3850,12 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 21,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 20,
|
||||
"ambiguous_runtime": 21,
|
||||
"framework_architecture_unsupported": 20,
|
||||
"memory_capacity": 1,
|
||||
"参数/模板问题": 1
|
||||
},
|
||||
"failureCount": 42,
|
||||
"failureCount": 43,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -3865,8 +3865,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 42,
|
||||
"unresolvedFailureCount": 21
|
||||
"total": 43,
|
||||
"unresolvedFailureCount": 22
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|feature_emb": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -5941,7 +5941,7 @@
|
||||
"decisionSuccessRate": 0.0261,
|
||||
"decisionTotal": 3713,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1560,
|
||||
"ambiguous_runtime": 1561,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 92,
|
||||
@@ -5955,15 +5955,15 @@
|
||||
"tokenizer_compatibility": 415,
|
||||
"参数/模板问题": 50
|
||||
},
|
||||
"failureCount": 6095,
|
||||
"failureCount": 6096,
|
||||
"failureRate": 0.9843,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 869,
|
||||
"successCount": 97,
|
||||
"successRate": 0.0157,
|
||||
"total": 6192,
|
||||
"unresolvedFailureCount": 1610
|
||||
"total": 6193,
|
||||
"unresolvedFailureCount": 1611
|
||||
},
|
||||
"vllm-customized": {
|
||||
"attributableFailureCount": 13,
|
||||
@@ -6113,7 +6113,7 @@
|
||||
"unresolvedFailureCount": 196
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-25T05:14:51.935310+00:00",
|
||||
"generatedAt": "2026-09-25T09:29:39.487405+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 102,
|
||||
@@ -6205,7 +6205,7 @@
|
||||
"decisionSuccessRate": 0.0897,
|
||||
"decisionTotal": 814,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 466,
|
||||
"ambiguous_runtime": 467,
|
||||
"architecture_compatibility": 53,
|
||||
"context_length": 48,
|
||||
"framework_architecture_unsupported": 294,
|
||||
@@ -6218,15 +6218,15 @@
|
||||
"日志缺失": 13,
|
||||
"验证失败": 42
|
||||
},
|
||||
"failureCount": 1564,
|
||||
"failureCount": 1565,
|
||||
"failureRate": 0.9554,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 16,
|
||||
"successCount": 73,
|
||||
"successRate": 0.0446,
|
||||
"total": 1637,
|
||||
"unresolvedFailureCount": 807
|
||||
"total": 1638,
|
||||
"unresolvedFailureCount": 808
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"attributableFailureCount": 60,
|
||||
@@ -11138,9 +11138,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2
|
||||
"ambiguous_runtime": 3
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "gemma2",
|
||||
@@ -11152,8 +11152,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm|text-generation|gemma2|none": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -33517,9 +33517,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
"ambiguous_runtime": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
@@ -33532,8 +33532,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm|text-generation|gemma2|none|34": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -50462,15 +50462,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17010,
|
||||
"totalRecords": 17230,
|
||||
"terminalRecords": 17011,
|
||||
"totalRecords": 17231,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6103,
|
||||
"decisionFailureRate": 0.8635,
|
||||
"decisionSuccessRate": 0.1365,
|
||||
"decisionTotal": 7068,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4385,
|
||||
"ambiguous_runtime": 4386,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 127,
|
||||
@@ -50486,15 +50486,15 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16045,
|
||||
"failureCount": 16046,
|
||||
"failureRate": 0.9433,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 935,
|
||||
"successCount": 965,
|
||||
"successRate": 0.0567,
|
||||
"total": 17010,
|
||||
"unresolvedFailureCount": 9007
|
||||
"total": 17011,
|
||||
"unresolvedFailureCount": 9008
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_mrv-100 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
@@ -50552,6 +50552,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17230,
|
||||
"summarizedRecords": 17231,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user