Skip to content

feat: support custom task runner #2407

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 4 commits into from
Dec 8, 2024
Merged

feat: support custom task runner #2407

merged 4 commits into from
Dec 8, 2024

Conversation

zhyncs
Copy link
Member

@zhyncs zhyncs commented Dec 8, 2024

Motivation

Usually, when we run experiments (benchmark or evaluation), we need to do it multiple times, manually starting the server cmd and client cmd each time and collecting results. This work is very procedural and tedious, so it can be semi-automated using scripts. cc @shanyu-sys @yichuan520030910320

Here is a simple example. ref https://github.com/sgl-project/sglang/actions/runs/12224157302

Modifications

Checklist

  • Format your code according to the Contributor Guide.
  • Add unit tests as outlined in the Contributor Guide.
  • Update documentation as needed, including docstrings or example tutorials.

@zhyncs zhyncs merged commit 0f8eb15 into main Dec 8, 2024
3 of 15 checks passed
@zhyncs zhyncs deleted the zhyncs/test branch December 8, 2024 18:29
@zhyncs
Copy link
Member Author

zhyncs commented Dec 8, 2024

ref https://github.com/sgl-project/sglang/actions/runs/12224251746

@zhyncs
Copy link
Member Author

zhyncs commented Dec 8, 2024

TODO(zhyncs):
Make different config.yml files as CI input choices, so we can just write yml and manually trigger the execution of a specific config.
In theory, any group and any server cmd and client cmd can be used. The only things that need to be handled are the dependency installation for the server and the output formatting for the client.
For example, lm_eval, evalplus, etc., and we may want to run different configurations each time. This configurability gives us great flexibility without the need to set up a development environment ourselves.

@zhyncs
Copy link
Member Author

zhyncs commented Dec 8, 2024

In some cases, we only need to display, in other cases, we need to set a threshold for comparison.

@zhyncs zhyncs mentioned this pull request Dec 9, 2024
Closed
3 tasks
timethink pushed a commit to timethink/sglang that referenced this pull request Mar 9, 2025
@zhyncs
feat: support custom task runner (sgl-project#2407)
fe48e11
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@merrymercy merrymercy Awaiting requested review from merrymercy merrymercy is a code owner

@Ying1123 Ying1123 Awaiting requested review from Ying1123

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@zhyncs