emulated nvfp4 support torch._grouped_mm for inference#4314
Merged
Conversation
Contributor
Author
vkuzo
requested review from
danielvegamyhre,
drisspg and
jerryzh168
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/4314
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
This was referenced Apr 22, 2026
vkuzo
commented
Apr 22, 2026
| assert len(orig_size) == 3, "unsupported" | ||
| # only supporting dim0, dim1, dim2 and dim0, dim2, dim1 orders | ||
| new_size = [new_size[0], new_size[2] // 2, new_size[1]] | ||
| new_size = [new_size[0], new_size[1] // 2, new_size[2]] |
Contributor
Author
There was a problem hiding this comment.
the old code was incorrect and untested, this PR fixes it. This function should not reorder the dimensions.
vkuzo
added
the
module: not user facing
jerryzh168
approved these changes
Apr 22, 2026
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary:
Sets up the skeleton for nvfp4 grouped_mm support for inference:
arithmetic bug)
Hooking up real nvfp4 kernel will be in an upcoming PR, to keep things
small.
Test Plan: