[Misc] Add parallel state node_count function
#20045
Conversation
|
👋 Hi! Thank you for contributing to the vLLM project. 💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels. Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging. To run CI, PR reviewers can either: Add 🚀 |
There was a problem hiding this comment.
Summary of Changes
Hello @njhill, 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 introduces a crucial utility for distributed computing environments within the vllm framework. The newly added node_count function provides a robust and reliable way to ascertain the actual number of physical nodes involved in a distributed job, which is essential for resource management, performance analysis, and understanding the deployment topology.
Highlights
- New Utility Function: I've added a new function,
node_count, tovllm/distributed/parallel_state.py. This function is designed to accurately determine the total number of distinct physical nodes participating in a given distributed process group. - Distributed Node Counting Logic: The
node_countfunction works by having each rank identify the number of other ranks colocated on its node. It then aggregates these local node sizes across all ranks to deduce the total count of unique nodes, supporting bothtorch.distributed.ProcessGroupandStatelessProcessGrouptypes. - Dependency Update: The
collections.defaultdictutility has been imported to facilitate the counting of unique node sizes within the newnode_countfunction.
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 is currently in preview and 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 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. ↩
node_count function
There was a problem hiding this comment.
Code Review
The code introduces a node_count function to determine the number of nodes in a process group, handling both ProcessGroup and StatelessProcessGroup scenarios. The function gathers node sizes from all ranks and counts unique sizes to determine the total number of nodes.
Written with help from claude Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
|
@njhill do we need a force merge? |
|
@WoosukKwon yes, I verified the failures are unrelated OOMs also failing on main (not all tests have completed yet though...) |
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com> Signed-off-by: Will Eaton <weaton@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Signed-off-by: Nick Hill <nhill@redhat.com> Signed-off-by: avigny <47987522+avigny@users.noreply.github.com>
Signed-off-by: Nick Hill <nhill@redhat.com>
Written with help from claude code
For use by #18343