aws-samples / aws-samples/sample-InferenceBenchmarker
aiperf Total requests fired discrepancy
未关闭
- 主要语言
- Python
- 星标
- 0
- 派生
- 1
- PR 合并指标
- 30 天内没有已合并 PR
描述
misleading when some in-flight requests cancelled for duration bound waves
贡献指南
调研方向
No file or test is named. Start by tracing aiperf's request accounting for duration-bound waves and in-flight cancellations, then identify how “Total requests fired” is calculated. Done means the reported total is no longer misleading when requests are cancelled, with coverage for that scenario.
由索引模型根据 Issue 内容生成。
评估
- 技术栈
- python
- 领域
- performance
- Issue 类型
- 缺陷
- 难度
- 3/5
- 预计耗时
- 1-2 天
- 活跃度
- 冷清
- 描述清晰度
- 需要澄清
- 新手友好度
- 38/100