Skip to content

Conversation

@lihaoyang-amd
Copy link

@lihaoyang-amd lihaoyang-amd commented Jun 16, 2025

  1. Integrate quick allreduce to custom allreduce
  2. del oneshot
  3. del test_quick_allreduce and some contents of cuda_communicator.

TODO:
1.We need the full kernel test to guide the chioce of kernel. (include bf16)
2.Check if test_custom_all_reduce.py overrides qr
3.Check the initialization logic of qr and cr
3.fix fp16 err when 2gb

Signed-off-by: Haoyang Li <[email protected]>
@github-actions
Copy link

👋 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 fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

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 ready label to the PR or enable auto-merge.

🚀

Signed-off-by: Haoyang Li <[email protected]>
@lihaoyang-amd lihaoyang-amd marked this pull request as ready for review June 16, 2025 11:13
@ilmarkov ilmarkov merged commit c588abb into neuralmagic:experimental/quick_reduce Jun 16, 2025
4 checks passed
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