aws-samples / aws-samples/sample-InferenceBenchmarker

aiperf Total requests fired discrepancy

Open
#13 0 comments 0 reactions 0 assignees View on GitHub
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

Open the contributing 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.