ggml: aarch64: implement SVE kernels for q3_K_q8_K vector dot#11917
Merged
ggerganov merged 5 commits intoggml-org:masterfrom Feb 20, 2025
Merged
ggml: aarch64: implement SVE kernels for q3_K_q8_K vector dot#11917ggerganov merged 5 commits intoggml-org:masterfrom
ggerganov merged 5 commits intoggml-org:masterfrom
Conversation
github-actions
Bot
added
the
ggml
ggerganov
reviewed
Feb 17, 2025
Member
ggerganov
left a comment
ggerganov
left a comment
There was a problem hiding this comment.
Improve the formatting of the code to be more consistent with the rest of the code. I've given a few hints below.
Contributor
Author
Thank you. Improved the code formatting for consistency. |
ggerganov
approved these changes
Feb 20, 2025
Member
ggerganov
left a comment
ggerganov
left a comment
There was a problem hiding this comment.
Haven't ran any tests myself, so taking a small leap of faith here, assuming you've done all the necessary tests for this change.
ggerganov
reviewed
Feb 20, 2025
ggerganov
reviewed
Feb 20, 2025
ggerganov
reviewed
Feb 20, 2025
Contributor
Author
Thank you! We've done all the necessary tests for this change. |
orca-zhang
pushed a commit
to orca-zhang/llama.cpp
that referenced
this pull request
Feb 26, 2025
…rg#11917) * Added SVE Implementation for Q3_K Kernel in ggml-cpu-quants.c file * Improved Formating of code in ggml-cpu-quants.c file * style : minor fixes * style : less whitespaces * style : ptr spaceing --------- Co-authored-by: vithulep <p.m.vithule1517@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Feb 26, 2025
…rg#11917) * Added SVE Implementation for Q3_K Kernel in ggml-cpu-quants.c file * Improved Formating of code in ggml-cpu-quants.c file * style : minor fixes * style : less whitespaces * style : ptr spaceing --------- Co-authored-by: vithulep <p.m.vithule1517@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Seunghhon
pushed a commit
to Seunghhon/llama.cpp
that referenced
this pull request
Apr 26, 2026
…rg#11917) * Added SVE Implementation for Q3_K Kernel in ggml-cpu-quants.c file * Improved Formating of code in ggml-cpu-quants.c file * style : minor fixes * style : less whitespaces * style : ptr spaceing --------- Co-authored-by: vithulep <p.m.vithule1517@gmail.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
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
3 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.
This PR introduces support for SVE (Scalable Vector Extensions) kernels for the q3_K_q8_K vector dot on the Arm architecture. A similar proposal for SVE support is made in PR #7433 and #11227.
This PR contains the SVE implementation of the vector dot used to compute the Q3_K quantization.
By running a Q3_K quantized model of mistral-7b-v01, on Graviton 3 (Perf 01 XL), Accuracy and Performance are measured.
Performance
The performance enhancement with this PR (SVE) is ~ x1.02 to x1.15 faster than the NEON implementation.
The command used to measure the performance is
Perplexity
I also verified that perplexity matches between the NEON and SVE Implementation.