SYCL: optimized repeat_back kernel (3× fewer asm instructions, 2× faster)Feature/sycl repeat back opt #16869
Conversation
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
Removed comments to clean up the code.
github-actions
bot
added
ggml
Remove unnecessary blank line before assigning acc to dst_dd.
Contributor
Author
|
Hello @CISC @NeoZhangJianyu, |
NeoZhangJianyu
approved these changes
Nov 3, 2025
Collaborator
NeoZhangJianyu
left a comment
NeoZhangJianyu
left a comment
There was a problem hiding this comment.
It's good job!
Thank you!
gabe-l-hart
added a commit
to gabe-l-hart/llama.cpp
that referenced
this pull request
Nov 3, 2025
* origin/master: (169 commits) opencl: support imrope (ggml-org#16914) fix: Viewing multiple PDF attachments (ggml-org#16974) model-conversion : pass config to from_pretrained (ggml-org#16963) server : add props.model_alias (ggml-org#16943) ggml: CUDA: add head size 72 for flash-attn (ggml-org#16962) mtmd: add --image-min/max-tokens (ggml-org#16921) mtmd: pad mask for qwen2.5vl (ggml-org#16954) ggml : LoongArch fixes (ggml-org#16958) sync: minja (glm 4.6 & minmax m2 templates) (ggml-org#16949) SYCL: optimized repeat_back kernel (3× fewer asm instructions, 2× faster)Feature/sycl repeat back opt (ggml-org#16869) feat(webui): improve LaTeX rendering with currency detection (ggml-org#16508) test-backend-ops : fix segfault in moe-expert-reduce test in support mode and coverage (ggml-org#16936) ci : disable failing riscv cross build (ggml-org#16952) model: add Janus Pro for image understanding (ggml-org#16906) clip : use FA (ggml-org#16837) server : support unified cache across slots (ggml-org#16736) common : move gpt-oss reasoning processing to init params (ggml-org#16937) docs: remove llama_sampler_accept reference in sampling sample usage (ggml-org#16920) CUDA: add FLOOR, CEIL, ROUND, TRUNC unary ops (ggml-org#16917) devops: fix failing s390x docker build (ggml-org#16918) ...
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
This PR replaces the previous SYCL implementation of REPEAT_BACK that I implemented in PR #16734.
The functionality remains identical, but the kernel is now significantly more efficient.
Changes
ggml-sycl/repeat_back.cppwith a vectorized and cache-friendly kernelPerformance
Testing
test-backend-ops -o REPEAT_BACKtests pass on SYCLCompatibility