Skip to content

sycl: enable dpcpp nightly builds with oneMKL and oneDNN #13406

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged

Conversation

AD2605
Copy link
Contributor

@AD2605 AD2605 commented May 9, 2025

Currently if one tries to build the SYCL backend of LLaMA with nightly dpcpp with oneDNN and oneMKL libraries included in the release, it disables the oneDNN support because of GPU_VENDOR not being defined, and the CMake errors out with the following error:

CMake Error at ggml/src/ggml-sycl/CMakeLists.txt:112 (target_link_libraries):
  Target "ggml-sycl" links to:

    MKL::MKL_SYCL::BLAS

  but the target was not found.  Possible reasons include:

    * There is a typo in the target name.
    * A find_package call is missing for an IMPORTED target.
    * An ALIAS target is missing.

This is because the MKL's Cmake does not export the MKL_SYCL target when it's a nightly compiler.
This PR enables the same.

@github-actions github-actions bot added ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language labels May 9, 2025
@NeoZhangJianyu NeoZhangJianyu merged commit 1449214 into ggml-org:master May 12, 2025
44 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
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.

6 participants