state: generation 17948 (cycle)
This commit is contained in:
@@ -3280,7 +3280,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-28T16:09:58.861821+00:00",
|
||||
"generatedAt": "2026-09-28T16:18:42.205285+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 165,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -396,7 +396,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-28T16:17:27.673626+00:00",
|
||||
"generatedAt": "2026-09-28T16:20:11.644618+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-28T16:17:27.673626+00:00",
|
||||
"catalogUpdatedAt": "2026-09-28T16:20:11.644618+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-28T16:17:27.673626+00:00",
|
||||
"generatedAt": "2026-09-28T16:20:11.644618+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6570,6 +6570,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-28T16:17:27.673626+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-28T16:20:11.644618+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-28T12:16:36.344733+00:00",
|
||||
"lastSyncTime": "2026-09-28T12:16:36.062761+00:00",
|
||||
"generatedAt": "2026-09-28T16:18:42.123597+00:00",
|
||||
"lastSyncTime": "2026-09-28T16:18:41.860656+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -3890,12 +3890,12 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 25,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 45,
|
||||
"ambiguous_runtime": 46,
|
||||
"framework_architecture_unsupported": 24,
|
||||
"memory_capacity": 1,
|
||||
"参数/模板问题": 1
|
||||
},
|
||||
"failureCount": 71,
|
||||
"failureCount": 72,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -3905,8 +3905,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 71,
|
||||
"unresolvedFailureCount": 46
|
||||
"total": 72,
|
||||
"unresolvedFailureCount": 47
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|feature_emb": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -5981,7 +5981,7 @@
|
||||
"decisionSuccessRate": 0.0261,
|
||||
"decisionTotal": 3723,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1585,
|
||||
"ambiguous_runtime": 1586,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 93,
|
||||
@@ -5995,15 +5995,15 @@
|
||||
"tokenizer_compatibility": 416,
|
||||
"参数/模板问题": 50
|
||||
},
|
||||
"failureCount": 6132,
|
||||
"failureCount": 6133,
|
||||
"failureRate": 0.9844,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 871,
|
||||
"successCount": 97,
|
||||
"successRate": 0.0156,
|
||||
"total": 6229,
|
||||
"unresolvedFailureCount": 1635
|
||||
"total": 6230,
|
||||
"unresolvedFailureCount": 1636
|
||||
},
|
||||
"vllm-customized": {
|
||||
"attributableFailureCount": 14,
|
||||
@@ -6153,7 +6153,7 @@
|
||||
"unresolvedFailureCount": 197
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-28T12:16:36.331263+00:00",
|
||||
"generatedAt": "2026-09-28T16:18:42.111883+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 102,
|
||||
@@ -6245,7 +6245,7 @@
|
||||
"decisionSuccessRate": 0.0891,
|
||||
"decisionTotal": 819,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 505,
|
||||
"ambiguous_runtime": 506,
|
||||
"architecture_compatibility": 53,
|
||||
"context_length": 48,
|
||||
"framework_architecture_unsupported": 299,
|
||||
@@ -6258,15 +6258,15 @@
|
||||
"日志缺失": 13,
|
||||
"验证失败": 42
|
||||
},
|
||||
"failureCount": 1609,
|
||||
"failureCount": 1610,
|
||||
"failureRate": 0.9566,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 16,
|
||||
"successCount": 73,
|
||||
"successRate": 0.0434,
|
||||
"total": 1682,
|
||||
"unresolvedFailureCount": 847
|
||||
"total": 1683,
|
||||
"unresolvedFailureCount": 848
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"attributableFailureCount": 60,
|
||||
@@ -11500,9 +11500,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 9
|
||||
"ambiguous_runtime": 10
|
||||
},
|
||||
"failureCount": 9,
|
||||
"failureCount": 10,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "llama",
|
||||
@@ -11514,8 +11514,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 9,
|
||||
"unresolvedFailureCount": 9
|
||||
"total": 10,
|
||||
"unresolvedFailureCount": 10
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm|text-generation|llama|none": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -34666,9 +34666,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 5
|
||||
"ambiguous_runtime": 6
|
||||
},
|
||||
"failureCount": 5,
|
||||
"failureCount": 6,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
@@ -34681,8 +34681,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 5
|
||||
"total": 6,
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm|text-generation|llama|none|30": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -51854,15 +51854,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17078,
|
||||
"totalRecords": 17299,
|
||||
"terminalRecords": 17079,
|
||||
"totalRecords": 17300,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6123,
|
||||
"decisionFailureRate": 0.8637,
|
||||
"decisionSuccessRate": 0.1363,
|
||||
"decisionTotal": 7089,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4428,
|
||||
"ambiguous_runtime": 4429,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 128,
|
||||
@@ -51878,15 +51878,15 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16112,
|
||||
"failureCount": 16113,
|
||||
"failureRate": 0.9434,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 938,
|
||||
"successCount": 966,
|
||||
"successRate": 0.0566,
|
||||
"total": 17078,
|
||||
"unresolvedFailureCount": 9051
|
||||
"total": 17079,
|
||||
"unresolvedFailureCount": 9052
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
@@ -51915,7 +51915,6 @@
|
||||
"组合 Kunlunxin_p-800|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 Ascend_910-b4|llamacpp|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|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 Kunlunxin_p-800|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 MetaX_c-500|vllm|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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -51940,10 +51939,11 @@
|
||||
"组合 hygon_k100-ai|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-x4|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 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 Vastai_va16|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 Vastai_va16|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 Kunlunxin_p-800|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": 17299,
|
||||
"summarizedRecords": 17300,
|
||||
"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