aws-samples / aws-samples/sample-InferenceBenchmarker
aiperf Total requests fired discrepancy
Open
- Dominant language
- Python
- Stars
- 0
- Forks
- 1
- PR merge metrics
- No merged PRs in 30d
Description
misleading when some in-flight requests cancelled for duration bound waves
Contributor guide
Research direction
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.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- performance
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 38/100