Skip to content

Conversation

@joshishr
Copy link

Enable CXI provider support in libfabric backend plugin for HPE's Slingshot network.

@copy-pr-bot
Copy link

copy-pr-bot bot commented Nov 25, 2025

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

@github-actions
Copy link

👋 Hi joshishr! Thank you for contributing to ai-dynamo/nixl.

Your PR reviewers will review your contribution then trigger the CI to test your changes.

🚀

@ryanhankins
Copy link

The most recent force commit seems to fix the formatting changes in the checks, so I'm not sure why the checks continue to fail.

// TCP providers don't support FI_MR_VIRT_ADDR and expect offset-based addressing
if (data_rails_[rail_id]->provider_name == "tcp" ||
if (data_rails_[rail_id]->provider_name == "cxi" ||
data_rails_[rail_id]->provider_name == "tcp" ||

Choose a reason for hiding this comment

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

@akkart-aws was there a reason you couldn't just check for FI_MR_VIRT_ADDR directly here?

@brminich
Copy link
Contributor

brminich commented Nov 26, 2025

pls note clang format check errors

@ryanhankins
Copy link

pls note clang format check errors

Thank you for looking at this. I believe the force commit fixed the clang format errors, but it doesn't seem like the Clang Format Check picked up that they were fixed.

@ryanhankins
Copy link

pls note clang format check errors

Far as I can tell, this commit resolved the errors.

image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants