Skip to content

Conversation

NeoZhangJianyu
Copy link
Collaborator

@NeoZhangJianyu NeoZhangJianyu commented Oct 11, 2025

Fix UT fault cases:

  • count-equal
  • argsort
  • pad
    Update the OP list of SYCL backend.

Make all supported UT cases are passed on Arc770 now.
After this PR is merged, SYCL backend should have a new good base.

I will test all PRs by the UT cases on Arc770 in the future.
Any fault case will block the new PR merge or ask to revert the merged PR.

In the first half year, we focus on the performance and new technology.
The result is not good as we expected.
I think we should focus on the quality firstly:
make a good design base with 100% UT cases.
track the PR quality: 100% offline UT pass rate.
implement all unsupported OPs.
fix the issues reported by users.

@github-actions github-actions bot added documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language labels Oct 11, 2025
@NeoZhangJianyu NeoZhangJianyu merged commit c7be9fe into ggml-org:master Oct 12, 2025
70 of 71 checks passed
gabe-l-hart added a commit to gabe-l-hart/llama.cpp that referenced this pull request Oct 13, 2025
* origin/master: (32 commits)
metal : FA support F32 K and V and head size = 32 (ggml-org#16531)
graph : support cacheless embeddings with FA and iSWA (ggml-org#16528)
opencl: fix build targeting CL 2 (ggml-org#16554)
CUDA: fix numerical issues in tile FA kernel (ggml-org#16540)
ggml : fix build broken with -march=armv9-a on MacOS (ggml-org#16520)
CANN: fix CPU memory leak in CANN backend (ggml-org#16549)
fix: add remark plugin to render raw HTML as literal text (ggml-org#16505)
metal: add support for opt_step_sgd (ggml-org#16539)
ggml : fix scalar path for computing norm (ggml-org#16558)
CANN: Update several operators to support FP16 data format (ggml-org#16251)
metal : add opt_step_adamw and op_sum (ggml-org#16529)
webui: remove client-side context pre-check and rely on backend for limits (ggml-org#16506)
[SYCL] fix UT fault cases: count-equal, argsort, pad OPs (ggml-org#16521)
ci : add Vulkan on Ubuntu with default packages build (ggml-org#16532)
common : handle unicode during partial json parsing (ggml-org#16526)
common : update presets (ggml-org#16504)
ggml : Fix FP16 ELU positive branch (ggml-org#16519)
hparams : add check for layer index in is_recurrent (ggml-org#16511)
ggml: Correct SVE implementation in ggml_vec_dot_f16_unroll (ggml-org#16518)
CUDA: faster tile FA, add oob checks, more HSs (ggml-org#16492)
...
yael-works pushed a commit to yael-works/llama.cpp that referenced this pull request Oct 15, 2025
)

* fix/refactor OP argsort, pad

* fix count-equal op

* update SYCL OP list

* fix format issue

---------

Co-authored-by: Zhang Jianyu <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants