Skip to content

Conversation

ye-NX
Copy link

@ye-NX ye-NX commented Sep 21, 2025

Title: Add SYCL backend support for PAD_REFLECT_1D

Description:
This PR adds a SYCL implementation of the PAD_REFLECT_1D operator:

  • Implements pad_reflect_d1_f32 kernel for F32 tensors.
  • Adds ggml_sycl_op_pad_reflect_d1 launcher and backend dispatch.
  • Verified correctness with test-backend-ops.

This enables reflection padding along the first dimension to run on GPU devices using SYCL, improving operator coverage and reducing CPU fallbacks.

@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 Sep 21, 2025
@ye-NX
Copy link
Author

ye-NX commented Oct 16, 2025

Hi @NeoZhangJianyu and @slaren,
I've opened two related SYCL PRs:

Would appreciate it if you could take a look when you have a moment.
Thanks!

Copy link
Collaborator

@NeoZhangJianyu NeoZhangJianyu left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It's good work!

Thank you!

@NeoZhangJianyu
Copy link
Collaborator

@ye-NX
Please resolve the conflicts!

Thank you!

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.

2 participants