Skip to content
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.

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

[Feat] Prefix-aware routing and load balancing #239

Open
wants to merge 9 commits into
base: main
Choose a base branch
from

Conversation

KuntaiDu
Copy link
Collaborator

@KuntaiDu KuntaiDu commented Mar 5, 2025

This PR implements two prefix-aware routing algorithms and a simple load balancing logic in #59 .

This PR introduces two set of abstractions: affinity and endpoint_filter. PTAL and see if you are good with these APIs.

BEFORE SUBMITTING, PLEASE READ THE CHECKLIST BELOW AND FILL IN THE DESCRIPTION ABOVE


  • Make sure the code changes pass the pre-commit checks.
  • Sign-off your commit by using -s when doing git commit
  • Try to classify PRs for easy understanding of the type of changes, such as [Bugfix], [Feat], and [CI].
Detailed Checklist (Click to Expand)

Thank you for your contribution to production-stack! Before submitting the pull request, please ensure the PR meets the following criteria. This helps us maintain the code quality and improve the efficiency of the review process.

PR Title and Classification

Please try to classify PRs for easy understanding of the type of changes. The PR title is prefixed appropriately to indicate the type of change. Please use one of the following:

  • [Bugfix] for bug fixes.
  • [CI/Build] for build or continuous integration improvements.
  • [Doc] for documentation fixes and improvements.
  • [Feat] for new features in the cluster (e.g., autoscaling, disaggregated prefill, etc.).
  • [Router] for changes to the vllm_router (e.g., routing algorithm, router observability, etc.).
  • [Misc] for PRs that do not fit the above categories. Please use this sparingly.

Note: If the PR spans more than one category, please include all relevant prefixes.

Code Quality

The PR need to meet the following code quality standards:

  • Pass all linter checks. Please use pre-commit to format your code. See README.md for installation.
  • The code need to be well-documented to ensure future contributors can easily understand the code.
  • Please include sufficient tests to ensure the change is stay correct and robust. This includes both unit tests and integration tests.

DCO and Signed-off-by

When contributing changes to this project, you must agree to the DCO. Commits must include a Signed-off-by: header which certifies agreement with the terms of the DCO.

Using -s with git commit will automatically add this header.

What to Expect for the Reviews

We aim to address all PRs in a timely manner. If no one reviews your PR within 5 days, please @-mention one of YuhanLiu11
, Shaoting-Feng or ApostaC.

@BrianPark314
Copy link
Contributor

great work, one nitpick comment is that the affinity and endpoint_filter might be better placed under services/routing_service.

Copy link
Collaborator

@gaocegege gaocegege left a comment

Choose a reason for hiding this comment

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

It is a great start, maybe we could implement more intelligent routing logic like https://docs.sglang.ai/router/router.html#cache-aware-load-balancing-router

@KuntaiDu
Copy link
Collaborator Author

KuntaiDu commented Mar 6, 2025

It is a great start, maybe we could implement more intelligent routing logic like https://docs.sglang.ai/router/router.html#cache-aware-load-balancing-router

Yeah we should have it in the future! For now let's have some simple routers that make no assumption on the LLM inference engine.

KuntaiDu added 2 commits March 6, 2025 04:19
Signed-off-by: KuntaiDu <[email protected]>
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.

3 participants