-
Notifications
You must be signed in to change notification settings - Fork 2.8k
[bug] limit bootstrap room to to [0, 2^63 - 1] #8684
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
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Summary of Changes
Hello @slin1237, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!
This pull request resolves a critical KVTransferError
and server hang issue in the Prefill-Decode (PD) router. The problem stemmed from a mismatch in bootstrap_room
value ranges between the Rust-based router and the Python backend. The changes ensure that the Rust component now generates bootstrap_room
values within the expected signed 64-bit range, improving the stability and reliability of the routing mechanism.
Highlights
- Critical Bug Fix: Addressed a critical bug in the Prefill-Decode (PD) router that caused
KVTransferError
and server hangs. This was due to a mismatch in howbootstrap_room
values were generated and expected by different components. - Data Type Compatibility: Ensured that the
bootstrap_room
values generated by the Rust PD router are now limited to the range[0, 2^63 - 1]
. This aligns with the signed 64-bit integer expectation of the Python backend, resolving theKVTransferError
. - New Unit Test: Introduced a new unit test (
test_bootstrap_room_range
) to rigorously verify that generatedbootstrap_room
values consistently fall within the correct[0, 2^63 - 1]
range for both single and batch requests, preventing regressions.
Using Gemini Code Assist
The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.
Invoking Gemini
You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command>
or @gemini-code-assist <command>
. Below is a summary of the supported commands.
Feature | Command | Description |
---|---|---|
Code Review | /gemini review |
Performs a code review for the current pull request in its current state. |
Pull Request Summary | /gemini summary |
Provides a summary of the current pull request in its current state. |
Comment | @gemini-code-assist | Responds in comments when explicitly tagged, both in issue comments and review comments. |
Help | /gemini help |
Displays a list of available commands. |
Customization
To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/
folder in the base of the repository. Detailed instructions can be found here.
Limitations & Feedback
Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments or fill out our survey to provide feedback.
You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.
Footnotes
-
Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code Review
This PR effectively addresses a critical bug by limiting the bootstrap_room
value to the expected range. The changes are well-structured and include a new unit test for validation. I've suggested using i64::MAX
for better readability and maintainability.
c227e9a
to
ea0a609
Compare
Motivation
This PR fixes a critical bug in the PD (Prefill-Decode) router that causes
KVTransferError
and server hangs when routing requests to disaggregated prefill and decode nodes. The error manifests as:The issue occurs because the Rust PD router generates
bootstrap_room
values in the full unsigned 64-bit range (0 to 2^64 - 1), while the Python backend expects signed 64-bit values (0 to 2^63 - 1). This mismatch causes failures whenbootstrap_room
values exceed 2^63 - 1.Modifications
sgl-router/src/routers/pd_types.rs
: Fixed bootstrap_room generation to match Python's expected rangeChecklist