Skip to content
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

Conv 2D CPU Implementation #352

Merged
merged 13 commits into from
Jul 14, 2023
Merged

Conv 2D CPU Implementation #352

merged 13 commits into from
Jul 14, 2023

Conversation

dmille
Copy link
Contributor

@dmille dmille commented Jul 7, 2023

  • Variable padding (p0 and p1)
  • Variable stride (s0 and s1)
  • Variable dilation (d0 and d1)
  • f16 kernel, f32 input tensor
  • Utilizes ggml_vec_dot_f16 (SIMD optimized)

@ggerganov
Copy link
Owner

Thanks! Let's resolve the conflicts and merge

@dmille
Copy link
Contributor Author

dmille commented Jul 11, 2023

@ggerganov Conflicts are resolved!

@ggerganov
Copy link
Owner

Thanks! Will first look to merge #325 and then this one

@dmille
Copy link
Contributor Author

dmille commented Jul 12, 2023

I needed strides of variable length for my project so I went ahead and updated the function to support both dilation and strides.

@dmille dmille marked this pull request as draft July 12, 2023 20:36
@dmille dmille marked this pull request as ready for review July 12, 2023 20:52
@ggerganov ggerganov merged commit a1bd982 into ggerganov:master Jul 14, 2023
2 checks passed
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.

None yet

2 participants