MNNVL MoE All-to-All Support#1134
Merged
yzh119 merged 13 commits intoflashinfer-ai:mainfrom Jun 24, 2025
Merged
Conversation
yzh119
reviewed
Jun 11, 2025
Collaborator
Author
|
above issues are all fixed |
yzh119
reviewed
Jun 11, 2025
Collaborator
Author
|
removed and decoupled |
Member
|
The multi-gpu tests are skipped in CI due to the ci resource limit. They pass on my multi-B200 node. Update (Jun 15, 2025): It turns out the MNNVL fabric wasn’t actually being used for data transfers in the multi-gpu tests, so I’ll remove those tests. The MNNVL setup along with the updated multi-GPU and multi-node tests will be added shortly |
5 tasks
yzh119
pushed a commit
that referenced
this pull request
Jun 17, 2025
<!-- .github/pull_request_template.md --> ## 📌 Description Install the python packages for CI docker: mpi4py, pynvml. They will be used for the comm ops. ## 🔍 Related Issues #1145, #1134 ## 🚀 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 - [x] I have installed `pre-commit` by running `pip install pre-commit` (or used your preferred method). - [x] I have installed the hooks with `pre-commit install`. - [x] 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](https://pre-commit.com/). ## 🧪 Tests - [ ] Tests have been added or updated as needed. - [ ] All tests are passing (`unittest`, etc.). ## Reviewer Notes <!-- Optional: anything you'd like reviewers to focus on, concerns, etc. -->
Use trtllm_alltoall.cuh instead of trtllm_alltoall.cu Upd Use pytorch_extension_utils upd upd upd compiled Fix build Register python ops fix Upd Add unittest fix fix fix Add multi-gpu test cases Add cross-gpu test Remove the invalid cross-gpu test add mnnvl (wip) comm module
yzh119
reviewed
Jun 23, 2025
yzh119
approved these changes
Jun 23, 2025
Collaborator
Collaborator
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
📌 Description
Introduce the
MnnvlMemoryandMnnvlMoefrom TensorRT-LLM, for large scale expert parallism. TheMnnvlMoefeatures aMnnvlMemoryworkspace for all-to-all(v) communication operation, aligned to mpi alltoallv interface and functionality.🔍 Related Issues
🚀 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
pre-commitby runningpip install pre-commit(or used your preferred method).pre-commit install.pre-commit run --all-filesand fixed any reported issues.🧪 Tests
unittest, etc.).Reviewer Notes