Skip to content

Conversation

rmatif
Copy link
Collaborator

@rmatif rmatif commented May 25, 2025

This PR adds the following ops to OpenCL:

  • GROUP_NORM
  • CONCAT
  • TIMESTEP_EMBEDDING
  • UPSCALE (both nearest and bilinear)
  • UNARY_OP_TANH
  • PAD
  • REPEAT

With these additions, OpenCL now (hopefully) supports all the ops used in stable-diffusion.cpp.

All tests passed using test-backend-ops. Tested on: Adreno 750, 740, 730

Note: I noticed that some im2col and rope tests fail on Adreno 740 and 730. These issues existed prior to this PR and may need to be addressed in the future

@lhez @max-krasnyansky

@github-actions github-actions bot added the ggml changes relating to the ggml tensor library for machine learning label May 25, 2025
@rmatif rmatif force-pushed the new-opencl-kernels branch from dddd1bb to 79a3dc0 Compare May 28, 2025 04:49
@rmatif rmatif closed this May 28, 2025
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
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant