cpu: fix ARM NEON nvfp4 dot product on non-dotprod targets#21559
Merged
ggerganov merged 1 commit intoggml-org:masterfrom Apr 14, 2026
Merged
cpu: fix ARM NEON nvfp4 dot product on non-dotprod targets#21559ggerganov merged 1 commit intoggml-org:masterfrom
ggerganov merged 1 commit intoggml-org:masterfrom
Conversation
github-actions
Bot
added
the
ggml
0cc4m
approved these changes
Apr 10, 2026
Contributor
0cc4m
left a comment
0cc4m
left a comment
There was a problem hiding this comment.
I can confirm this fixes the issue on DGX Spark.
Contributor
|
@ggml-org/maintainers Another review needed. |
ngxson
approved these changes
Apr 14, 2026
mengqin
pushed a commit
to mengqin/llama.cpp
that referenced
this pull request
Apr 20, 2026
ArberSephirotheca
pushed a commit
to ArberSephirotheca/llama.cpp
that referenced
this pull request
Apr 21, 2026
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Apr 23, 2026
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
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Overview
Fixes #21462
Fix incorrect nvfp4 vec_dot results on ARM targets without dotprod support. The
ggml_vdotq_s32fallback produces different per-lane grouping than nativevdotq_s32. The total sum is identical but individual lane values differ. Since nvfp4 applies different scales per sub-block using per-lane values, the fallback produces wrong results.Uses native
vdotq_s32directly when dotprod is available (unchanged fast path), and a per-sub-block 8-wide path on non-dotprod targets.Additional information
Related to #21455
Requirements