Skip to content

[PyTorch] Debug GEMM refactor#1652

Merged
ptrendx merged 4 commits intoNVIDIA:mainfrom
timmoon10:block-scaled-fp8-gemm-tweaks
Apr 8, 2025
Merged

[PyTorch] Debug GEMM refactor#1652
ptrendx merged 4 commits intoNVIDIA:mainfrom
timmoon10:block-scaled-fp8-gemm-tweaks

Conversation

@timmoon10
Copy link
Collaborator

@timmoon10 timmoon10 commented Apr 7, 2025

Description

#1545 introduced some test failures on B200. We also missed some review suggestions for minor stylistic tweaks.

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

  • Fix bug with MXFP8 column strides
  • Review suggestions from @ptrendx

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

Review suggestions from @ptrendx

Signed-off-by: Tim Moon <tmoon@nvidia.com>
@timmoon10 timmoon10 mentioned this pull request Apr 7, 2025
12 tasks
@timmoon10
Copy link
Collaborator Author

/te-ci

@timmoon10 timmoon10 changed the title [PyTorch] Minor stylistic tweaks for block scaled FP8 GEMM [PyTorch] Debug GEMM refactor Apr 8, 2025
@timmoon10
Copy link
Collaborator Author

/te-ci

@phu0ngng
Copy link
Collaborator

phu0ngng commented Apr 8, 2025

LGTM

@ptrendx ptrendx merged commit 9d4e11e into NVIDIA:main Apr 8, 2025
22 of 25 checks passed
wdykas pushed a commit to wdykas/TransformerEngine that referenced this pull request Apr 14, 2025
* Minor stylistic tweaks and typo fixes

Review suggestions from @ptrendx

Signed-off-by: Tim Moon <tmoon@nvidia.com>

* Fix incorrect col strides for MXFP8 matrices

Signed-off-by: Tim Moon <tmoon@nvidia.com>

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Signed-off-by: Tim Moon <tmoon@nvidia.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Signed-off-by: Peter Dykas <wdykas@nvidia.com>
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.

6 participants