Add Windows ARM64 wheel build support with NEON optimization#1959
Merged
matthewdouglas merged 5 commits intoMay 29, 2026
Conversation
| # code. This ensures compatibility across Python versions, as compatibility is | ||
| # dictated by the packaged code itself, not the Python version used for packaging. | ||
| python-version: ["3.10"] | ||
| python-version: ["3.12"] |
Member
There was a problem hiding this comment.
Is this change needed specifically just for WoA? Could we consider making it conditional?
Is there anything we should consider in docs for a minimum Python version for WoA build/runtime requirement?
Contributor
Author
There was a problem hiding this comment.
Yes, for WoA native Python is supported from version 3.11 onwards.
|
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. |
Member
|
@pdeep854 This looks great, thanks! Can you please fix the lint issues with |
matthewdouglas
approved these changes
May 29, 2026
matthewdouglas
merged commit 2177945
into
bitsandbytes-foundation:main
150 of 151 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Add Windows ARM64 wheel support and NEON-based performance optimizations.
Changes
Added Windows ARM64 (.whl) build support
Implemented vectorized 4-bit dequantization
Added NEON-optimized conversions:
BF16 → Float32
Float32 → BF16
Float32 → FP16
Optimized absmax computation for float32 blocks
Optimized norm_to_lut_index to process 4 float values per iteration
Impact
Improves ARM64 performance using NEON SIMD and enables native Windows ARM64 wheel support