fix double compress 8bit precision#1582
Merged
matthewdouglas merged 1 commit intobitsandbytes-foundation:multi-backend-refactorfrom Apr 2, 2025
Merged
fix double compress 8bit precision#1582matthewdouglas merged 1 commit intobitsandbytes-foundation:multi-backend-refactorfrom
matthewdouglas merged 1 commit intobitsandbytes-foundation:multi-backend-refactorfrom
Conversation
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
|
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. |
d180d8e
into
bitsandbytes-foundation:multi-backend-refactor
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Hi @Titus-von-Koeller @matthewdouglas
This PR fixed CPU/XPU double compress (absmax quant to 8bit) precision. To align with cuda implementation, we choose the closest element instead of the smaller number. Please review this PR. Thanks!