CPU: workaround avx512 4bit dequantize accuracy issue for large blocksize#1828
Merged
matthewdouglas merged 1 commit intomainfrom Dec 10, 2025
Merged
CPU: workaround avx512 4bit dequantize accuracy issue for large blocksize#1828matthewdouglas merged 1 commit intomainfrom
matthewdouglas merged 1 commit intomainfrom
Conversation
|
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. |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR fixes 8 failing tests for 4bit dequantization on CPUs with AVX512F support.
There is an accuracy issue for the AVX512 codepath with fp16/fp32 and blocksize 2048 or 4096. This is an unlikely usecase, and as such we can accept to fallback all the way to the slower PyTorch implementation instead of a more complex fallback to a scalar C++ kernel.