mxfp4 and nvfp4: align fp4 packing to PyTorch Core definition #3123
Conversation
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
Contributor
Author
|
Stack from ghstack (oldest at bottom): |
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/3123
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 732b394 with merge base c96f2dd ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
vkuzo
added a commit
that referenced
this pull request
Oct 6, 2025
Summary: Switches fp4 packing from `val0:val1` to `val1:val0`, to align with how `torch.float4_e2m1fn_x2` is defined, and how other frameworks do this. For context, please see the docblock of the `Float4_e2m1fn_x2` object from https://github.com/pytorch/pytorch/pull/148791/files Test Plan: ```bash pytest test/prototype/mx_formats/ -s -x ``` Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: da13f89 ghstack-comment-id: 3373519438 Pull-Request: #3123
meta-cla
bot
added
the
CLA Signed
vkuzo
commented
Oct 6, 2025
vkuzo
commented
Oct 7, 2025
drisspg
approved these changes
Oct 7, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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:
Switches fp4 packing from
val0:val1toval1:val0, to align with howtorch.float4_e2m1fn_x2is defined, and how other frameworks do this.For context, please see the docblock of the
Float4_e2m1fn_x2objectfrom https://github.com/pytorch/pytorch/pull/148791/files
Test Plan:
also, when we save nvfp4 weights in this packing order, we can now use nvfp4 kernels already integrated in vLLM
Reviewers:
Subscribers:
Tasks:
Tags: