Skip to content

Conversation

vMaroon
Copy link
Member

@vMaroon vMaroon commented Sep 21, 2025

Summary

Adding a new benchmark data, used for an llm-d blog.

Signed-off-by: Maroon Ayoub <[email protected]>
@Copilot Copilot AI review requested due to automatic review settings September 21, 2025 14:11
@github-actions github-actions bot requested a review from yankay September 21, 2025 14:11
Copy link
Contributor

@Copilot Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull Request Overview

Adds comprehensive benchmark data for an inference performance study comparing different scheduling strategies (precise, estimated, load, and random) for LLM workloads, including detailed metrics, configurations, and visualizations for a blog post.

  • Adds a complete benchmark report with workload configuration, scheduler configurations, and performance metrics
  • Includes performance comparisons across different QPS levels and scheduling strategies
  • Provides per-pod EPP metrics and visualization references for analysis

Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.

@nilig nilig self-requested a review September 21, 2025 14:21
Copy link
Collaborator

@nilig nilig left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

/lgtm

@vMaroon
Copy link
Member Author

vMaroon commented Sep 21, 2025

/approve

@vMaroon vMaroon merged commit d070ea6 into main Sep 21, 2025
3 checks passed
@vMaroon vMaroon deleted the 73-capacity branch September 21, 2025 14:22
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants