[sparse] marlin fixes #2305
Merged
[sparse] marlin fixes #2305
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
Summary: This PR updates sparse-marlin to not use CPU tensors and updates it to be compatible with Int4WeightOnl. Test Plan: ``` pytest test/sparsity/test_marlin.py ``` Reviewers: Subscribers: Tasks: Tags:
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/2305
Note: Links to docs will display an error until the docs builds have been completed. ⏳ No Failures, 1 PendingAs of commit 1d4e73a with merge base 152a8e3 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
jerryzh168
approved these changes
Jun 4, 2025
jerryzh168
reviewed
Jun 4, 2025
Comment on lines
+162
to
+164
| self.scale_and_zero = None | ||
| self.scale = scale | ||
| self.zero_point = zero_point | ||
| self.zero = zero |
There was a problem hiding this comment.
why do we have both scale_and_zero and zero?
There was a problem hiding this comment.
It's to maintain compatibility with https://github.com/pytorch/ao/blob/main/torchao/dtypes/uintx/int4_xpu_layout.py, otherwise the checks fail because the TensorImpl doesn't have this attribute.
liangel-02
pushed a commit
that referenced
this pull request
Aug 25, 2025
* [sparse] marlin fixes Summary: This PR updates sparse-marlin to not use CPU tensors and updates it to be compatible with Int4WeightOnl. Test Plan: ``` pytest test/sparsity/test_marlin.py ``` Reviewers: Subscribers: Tasks: Tags: * ruff check
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 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Outdated suggestions cannot be applied.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:
This PR updates sparse-marlin to not use CPU tensors and updates it to be compatible with Int4WeightOnl.
Test Plan:
Reviewers:
Subscribers:
Tasks:
Tags: