Skip to content

Conversation

@djns99
Copy link

@djns99 djns99 commented Nov 18, 2025

📌 Description

This ports the latest MNNVL A2A communication implementation from TRT-LLM

🔍 Related Issues

#2094

🚀 Pull Request Checklist

Thank you for contributing to FlashInfer! Before we review your pull request, please make sure the following items are complete.

✅ Pre-commit Checks

  • I have installed pre-commit by running pip install pre-commit (or used your preferred method).
  • I have installed the hooks with pre-commit install.
  • I have run the hooks manually with pre-commit run --all-files and fixed any reported issues.

If you are unsure about how to set up pre-commit, see the pre-commit documentation.

🧪 Tests

  • Tests have been added or updated as needed.
  • All tests are passing (unittest, etc.).

Reviewer Notes

@coderabbitai
Copy link
Contributor

coderabbitai bot commented Nov 18, 2025

Important

Review skipped

Draft detected.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

✨ Finishing touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

@djns99 djns99 force-pushed the djns99/update-trtllm-kernels branch 3 times, most recently from e5b5e5d to 5fb452d Compare November 19, 2025 23:39
@djns99 djns99 force-pushed the djns99/update-trtllm-kernels branch from c0d0c04 to 2bac65a Compare November 20, 2025 03:25
@djns99 djns99 force-pushed the djns99/update-trtllm-kernels branch from 710a388 to bd82a2b Compare November 20, 2025 04:18

# Initialize MNNVL memory system
MnnvlMemory.initialize()

Copy link
Contributor

@trevor-m trevor-m Nov 20, 2025

Choose a reason for hiding this comment

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

#1245 adds an optional custom communicator for the MnnvlMemory initialization. This is necessary because sglang/vllm don't use MPI so the previous bootstrapping wouldn't work. We will need to allow users to pass through the custom communicator here as well.

  1. Can you add an arg to this function
config: Optional[MnnvlConfig] = None
  1. Then after MnnvlMemory.initialize(), add
if config:
            MnnvlMemory.set_comm_from_config(mapping, config)  # type: ignore[attr-defined]

I think that should take care of it. Thanks!

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