state: generation 10966 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-20T22:43:48.315618+00:00",
|
||||
"lastSyncTime": "2026-09-20T22:43:47.754995+00:00",
|
||||
"generatedAt": "2026-09-20T22:57:50.116179+00:00",
|
||||
"lastSyncTime": "2026-09-20T22:57:49.771972+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2950,10 +2950,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"ambiguous_runtime": 2,
|
||||
"framework_architecture_unsupported": 2
|
||||
},
|
||||
"failureCount": 3,
|
||||
"failureCount": 4,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-customized",
|
||||
"pendingCount": 0,
|
||||
@@ -2963,8 +2963,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 1
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
|
||||
"attributableFailureCount": 13,
|
||||
@@ -4973,18 +4973,18 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"ambiguous_runtime": 2,
|
||||
"framework_architecture_unsupported": 2
|
||||
},
|
||||
"failureCount": 3,
|
||||
"failureCount": 4,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 1
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"vllm-mlu": {
|
||||
"attributableFailureCount": 19,
|
||||
@@ -5102,7 +5102,7 @@
|
||||
"unresolvedFailureCount": 38
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T22:43:48.306141+00:00",
|
||||
"generatedAt": "2026-09-20T22:57:50.106858+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 87,
|
||||
@@ -5222,7 +5222,7 @@
|
||||
"decisionSuccessRate": 0.2692,
|
||||
"decisionTotal": 52,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 82,
|
||||
"ambiguous_runtime": 83,
|
||||
"framework_architecture_unsupported": 32,
|
||||
"memory_capacity": 3,
|
||||
"model_load": 1,
|
||||
@@ -5230,15 +5230,15 @@
|
||||
"参数/模板问题": 24,
|
||||
"验证失败": 22
|
||||
},
|
||||
"failureCount": 166,
|
||||
"failureRate": 0.9222,
|
||||
"failureCount": 167,
|
||||
"failureRate": 0.9227,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 14,
|
||||
"successRate": 0.0778,
|
||||
"total": 180,
|
||||
"unresolvedFailureCount": 128
|
||||
"successRate": 0.0773,
|
||||
"total": 181,
|
||||
"unresolvedFailureCount": 129
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"attributableFailureCount": 194,
|
||||
@@ -7415,6 +7415,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-customized|text-generation|granite|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-customized",
|
||||
"modelType": "granite",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -13347,19 +13370,19 @@
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 9,
|
||||
"consecutiveFailures": 9,
|
||||
"attributableFailureCount": 8,
|
||||
"consecutiveFailures": 8,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 9,
|
||||
"decisionTotal": 8,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 6,
|
||||
"framework_architecture_unsupported": 5,
|
||||
"model_load": 1,
|
||||
"runtime_memory": 2
|
||||
},
|
||||
"failureCount": 10,
|
||||
"failureCount": 9,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -13371,7 +13394,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 10,
|
||||
"total": 9,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Biren_166m|vllm|text-generation": {
|
||||
@@ -13435,10 +13458,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"ambiguous_runtime": 2,
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-customized",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -13450,8 +13473,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 1
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -14909,6 +14932,31 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-customized|text-generation|granite|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-customized",
|
||||
"lastTerminalAt": "2026-09-20T22:57:49.771972+00:00",
|
||||
"modelType": "granite",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -19933,6 +19981,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-customized|text-generation|granite|none|33": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-customized",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "granite",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|compressed-tensors|33": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -28411,15 +28483,15 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"terminalRecords": 15993,
|
||||
"totalRecords": 16157,
|
||||
"terminalRecords": 15994,
|
||||
"totalRecords": 16158,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5817,
|
||||
"decisionFailureRate": 0.8619,
|
||||
"decisionSuccessRate": 0.1381,
|
||||
"decisionTotal": 6749,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3818,
|
||||
"ambiguous_runtime": 3819,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 102,
|
||||
@@ -28435,15 +28507,15 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 15061,
|
||||
"failureCount": 15062,
|
||||
"failureRate": 0.9417,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 922,
|
||||
"successCount": 932,
|
||||
"successRate": 0.0583,
|
||||
"total": 15993,
|
||||
"unresolvedFailureCount": 8322
|
||||
"total": 15994,
|
||||
"unresolvedFailureCount": 8323
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_bi-100 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
@@ -28490,12 +28562,12 @@
|
||||
"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 Iluvatar_bi-150|transformers|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 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 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。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 16157,
|
||||
"summarizedRecords": 16158,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user