TransformerEngine icon indicating copy to clipboard operation
TransformerEngine copied to clipboard

Support MLA Context Parallel (CP) exchanging latent KV

Open yuzhongw-nvidia opened this issue 4 months ago • 1 comments

Description

Support MLA CP exchanging latent KV (instead of the complete KV) for ring attention.

Fixes # (issue)

Type of change

  • [ ] Documentation change (change only to the documentation, either a fix or a new content)
  • [ ] Bug fix (non-breaking change which fixes an issue)
  • [ ] New feature (non-breaking change which adds functionality)
  • [ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • [ ] Infra/Build change
  • [ ] Code refactoring

Changes

Please list the changes introduced in this PR:

  • Change A
  • Change B

Checklist:

  • [ ] I have read and followed the contributing guidelines
  • [ ] The functionality is complete
  • [ ] I have commented my code, particularly in hard-to-understand areas
  • [ ] I have made corresponding changes to the documentation
  • [ ] My changes generate no new warnings
  • [ ] I have added tests that prove my fix is effective or that my feature works
  • [ ] New and existing unit tests pass locally with my changes

yuzhongw-nvidia avatar Aug 12 '25 06:08 yuzhongw-nvidia

Hi @yuzhongw-nvidia , thanks for your contribution! It looks like one or more of your commits aren’t signed with a Developer Certificate of Origin (DCO) , type of change, and checklist are not marked. Could you please sign your commits and update the PR? Thank you!

nvMelissa avatar Oct 16 '25 09:10 nvMelissa