Fix xpu 4bit kernel#1839
Merged
matthewdouglas merged 2 commits intobitsandbytes-foundation:mainfrom Jan 14, 2026
Merged
Conversation
Contributor
Author
|
Hi @matthewdouglas . Would you please review this PR? Thanks! |
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
Member
|
Hi, Because this moves to int64 for indexing, I assume direct uses like this one in Unsloth would need to be updated? |
Contributor
Author
|
Hi @matthewdouglas . I have updated the kernels so they can cast the dtype inside the kernel without api change. Please review the new changes. Thanks! |
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
matthewdouglas
approved these changes
Jan 14, 2026
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
matthewdouglas
merged commit fe784a7
into
bitsandbytes-foundation:main
160 of 162 checks passed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fix XPU 4-bit kernel for odd-sized weights and resolve related test failures.
The original XPU 4-bit kernel did not handle odd weight shapes correctly. This PR fixes the logic and resolves failures in tests such as test_4bit_quant_large.
For
pytest -k "xpu" -ra ./: