Skip to content

Conversation

ggerganov
Copy link
Member

@ggerganov ggerganov commented Oct 17, 2025

  • Rework matrix-matrix multiplication
  • Use Tensor API when available

TODOs

  • Update mul_mm_id kernel
  • Test on M5

@github-actions github-actions bot added testing Everything test related ggml changes relating to the ggml tensor library for machine learning Apple Metal https://en.wikipedia.org/wiki/Metal_(API) labels Oct 17, 2025
@jeffbolznv
Copy link
Collaborator

Any early performance data?

@ggerganov ggerganov force-pushed the gg/metal-mul-mm-rework branch from 6271c44 to 6726e53 Compare October 18, 2025 14:24
@ggerganov
Copy link
Member Author

@jeffbolznv I think the performance using the tensor API is the same as the old simdgroup-based implementation, but I haven't done detailed analysis yet. I don't have hardware yet to test the actual Neural Accelerators that exist in the new chips and if they would be utilized with these changes.

@ggerganov ggerganov force-pushed the gg/metal-mul-mm-rework branch from 6726e53 to 57fa815 Compare October 20, 2025 13:01
@ggerganov ggerganov marked this pull request as ready for review October 20, 2025 16:30
@ggerganov ggerganov requested a review from slaren as a code owner October 20, 2025 16:30
@ggerganov
Copy link
Member Author

Looking for volunteers with iPhone 17 or MacBook M5 for testing

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Apple Metal https://en.wikipedia.org/wiki/Metal_(API) ggml changes relating to the ggml tensor library for machine learning testing Everything test related

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants