state: generation 10393 (cycle)
This commit is contained in:
@@ -1783,7 +1783,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T08:24:40.026968+00:00",
|
||||
"generatedAt": "2026-09-20T08:28:03.640396+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 86,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -416,7 +416,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-20T08:27:01.915623+00:00",
|
||||
"generatedAt": "2026-09-20T08:28:11.320456+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-20T08:27:01.915623+00:00",
|
||||
"catalogUpdatedAt": "2026-09-20T08:28:11.320456+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-20T08:27:01.915623+00:00",
|
||||
"generatedAt": "2026-09-20T08:28:11.320456+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6473,6 +6473,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-20T08:27:01.915623+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-20T08:28:11.320456+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-20T08:24:39.967208+00:00",
|
||||
"lastSyncTime": "2026-09-20T08:24:39.658601+00:00",
|
||||
"generatedAt": "2026-09-20T08:28:03.593425+00:00",
|
||||
"lastSyncTime": "2026-09-20T08:28:03.157173+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2205,22 +2205,23 @@
|
||||
"decisionSuccessRate": 0.3043,
|
||||
"decisionTotal": 46,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 25,
|
||||
"model_load": 6,
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 32,
|
||||
"failureRate": 0.6957,
|
||||
"failureCount": 33,
|
||||
"failureRate": 0.7021,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 14,
|
||||
"successRate": 0.3043,
|
||||
"successRate": 0.2979,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 46,
|
||||
"unresolvedFailureCount": 0
|
||||
"total": 47,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
"attributableFailureCount": 695,
|
||||
@@ -4229,7 +4230,7 @@
|
||||
"decisionSuccessRate": 0.0207,
|
||||
"decisionTotal": 3535,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1426,
|
||||
"ambiguous_runtime": 1427,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 84,
|
||||
@@ -4243,15 +4244,15 @@
|
||||
"tokenizer_compatibility": 406,
|
||||
"参数/模板问题": 40
|
||||
},
|
||||
"failureCount": 5792,
|
||||
"failureCount": 5793,
|
||||
"failureRate": 0.9876,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 864,
|
||||
"successCount": 73,
|
||||
"successRate": 0.0124,
|
||||
"total": 5865,
|
||||
"unresolvedFailureCount": 1466
|
||||
"total": 5866,
|
||||
"unresolvedFailureCount": 1467
|
||||
},
|
||||
"vllm-mlu": {
|
||||
"attributableFailureCount": 18,
|
||||
@@ -4363,7 +4364,7 @@
|
||||
"unresolvedFailureCount": 23
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T08:24:39.960094+00:00",
|
||||
"generatedAt": "2026-09-20T08:28:03.586846+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 72,
|
||||
@@ -4424,7 +4425,7 @@
|
||||
"decisionSuccessRate": 0.1237,
|
||||
"decisionTotal": 194,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 130,
|
||||
"ambiguous_runtime": 131,
|
||||
"backend_operator": 4,
|
||||
"context_length": 10,
|
||||
"framework_architecture_unsupported": 112,
|
||||
@@ -4438,15 +4439,15 @@
|
||||
"日志缺失": 62,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 605,
|
||||
"failureRate": 0.9618,
|
||||
"failureCount": 606,
|
||||
"failureRate": 0.9619,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 24,
|
||||
"successRate": 0.0382,
|
||||
"total": 629,
|
||||
"unresolvedFailureCount": 433
|
||||
"successRate": 0.0381,
|
||||
"total": 630,
|
||||
"unresolvedFailureCount": 434
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"attributableFailureCount": 711,
|
||||
@@ -5388,6 +5389,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|cohere2|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "cohere2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|lfm2|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -11480,6 +11504,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|cohere2|none|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
"modelType": "cohere2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|lfm2|none|29": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -18204,15 +18252,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 15767,
|
||||
"totalRecords": 15870,
|
||||
"terminalRecords": 15768,
|
||||
"totalRecords": 15871,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5706,
|
||||
"decisionFailureRate": 0.8614,
|
||||
"decisionSuccessRate": 0.1386,
|
||||
"decisionTotal": 6624,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3719,
|
||||
"ambiguous_runtime": 3720,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 101,
|
||||
@@ -18228,15 +18276,15 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 14849,
|
||||
"failureCount": 14850,
|
||||
"failureRate": 0.9418,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 922,
|
||||
"successCount": 918,
|
||||
"successRate": 0.0582,
|
||||
"total": 15767,
|
||||
"unresolvedFailureCount": 8221
|
||||
"total": 15768,
|
||||
"unresolvedFailureCount": 8222
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_bi-100 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
@@ -18279,13 +18327,13 @@
|
||||
"组合 Ascend_910-b3|vllm_tokenizer_patch|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x4|unknown|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Ascend_910-b4|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_mrv-100|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Ascend_910-b3|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
|
||||
"组合 Ascend_910-b3|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 15870,
|
||||
"summarizedRecords": 15871,
|
||||
"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