Repository navigation
sycl: fuse RMS_NORM + MUL - #26015
Merged
ggerganov merged 1 commit intoJul 31, 2026
Merged
Conversation
arthw
reviewed
Jul 27, 2026
arthw
left a comment
Contributor
There was a problem hiding this comment.
With Qwen3.5-4B-Q4_K_M.gguf on B60:
| Test | fa | Base t/s | Primary t/s | Increase Rate (Primary vs Base) |
|---|---|---|---|---|
| pp512 | 0 | 1048.44 | 1056.17 | 0.74% |
| pp512 | 1 | 1048.79 | 1055.80 | 0.67% |
| tg128 | 0 | 80.09 | 81.02 | 1.16% |
| tg128 | 1 | 80.60 | 81.65 | 1.30% |
Titaniumtown
force-pushed
the
pr/sycl-rms-norm-mul-fusion
branch
from
July 28, 2026 22:09
f585fd2 to
75450ee
Compare
Titaniumtown
marked this pull request as ready for review
July 28, 2026 22:10
Contributor
Author
|
Ready for review! |
arthw
reviewed
Jul 29, 2026
Contributor
|
@Titaniumtown, I was wondering what other fusions you have in the works? I was looking at bringing some work we had done earlier up to date and found this PR that already did the RMS_NORM+MUL. I don't want to duplicate effort if you're already working on these ones: |
Contributor
Author
|
@malsbat I have both of those already locally. I can submit PRs for those. |
huaxel
pushed a commit
to huaxel/CachyLLama
that referenced
this pull request
Aug 2, 2026
Contributor
Great, looking forward to those PRs! |
satindergrewal
pushed a commit
to satindergrewal/llama.cpp
that referenced
this pull request
Aug 12, 2026
thecodacus
pushed a commit
to thecodacus/llama.cpp
that referenced
this pull request
Sep 7, 2026
zbrad
pushed a commit
to zbrad/llama.cpp
that referenced
this pull request
Sep 10, 2026
pl752
pushed a commit
to pl752/llama.cpp
that referenced
this pull request
Sep 15, 2026
frostyautumnleaf
pushed a commit
to frostyautumnleaf/llama.cpp
that referenced
this pull request
Oct 5, 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
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
Port of cuda path ggml_cuda_op_rms_norm_fused to SYCL.
Also adds a function
ggml_sycl_can_fusethat can be used in future fusion PRs that I am am working on. This is analogous to the cudaggml_cuda_can_fuse.Additional information
Benchmarked on an Arc B70:
master @ 0278d83:
Patched — master + rms_norm+mul fusion:
Uplift: pp512 +0.54%, pp2048 +0.70%, tg128 +0.47%.
Requirements