Skip to content

Add acknowledgment for the xpu-kernels skill / Xe-Forge#627

Draft
jiqing-feng wants to merge 1 commit into
huggingface:mainfrom
jiqing-feng:cpu_skill
Draft

Add acknowledgment for the xpu-kernels skill / Xe-Forge#627
jiqing-feng wants to merge 1 commit into
huggingface:mainfrom
jiqing-feng:cpu_skill

Conversation

@jiqing-feng

Copy link
Copy Markdown
Contributor

Summary

The cpu-kernels skill adapted its overall methodology — the YAML knowledge
base, the benchmark/validation harnesses, and the branching trial-manager
optimization loop — from the existing xpu-kernels skill (built by the Intel
XPU kernels team), which is itself based on Xe-Forge.
This PR adds proper attribution so the original authors get visibility.

Changes

  • kernel-builder/skills/cpu-kernels/SKILL.md
    • Add an Acknowledgments section crediting the xpu-kernels skill and
      Xe-Forge as the origin of the workflow methodology.
    • Add the xpu-kernels skill and Xe-Forge to External Resources.

Notes

The CPU-specific content (AVX2/AVX512 intrinsics, runtime dispatch, brgemm/AMX
integration, NUMA and threading discipline) remains original to this skill; the
acknowledgment is scoped to the shared workflow methodology.

Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
@jiqing-feng jiqing-feng marked this pull request as draft June 10, 2026 01:18
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant