Skip to content

ggml-metal: Clean up files used for embedded build#18705

Merged
ggerganov merged 1 commit intoggml-org:masterfrom
mitmedialab:ggml_metal_fix_embed_target
Jan 14, 2026
Merged

ggml-metal: Clean up files used for embedded build#18705
ggerganov merged 1 commit intoggml-org:masterfrom
mitmedialab:ggml_metal_fix_embed_target

Conversation

@DaAwesomeP
Copy link
Copy Markdown
Contributor

This PR does two things:

  1. Only copy the Metal header files for non-embedded builds. Otherwise these files are unused and never cleaned up.
  2. Use CMAKE_CURRENT_BINARY_DIR for auto-generated files in embedded builds. This places the autogenerated scratch directory in a GGML-specific build directory separate from the application depending on GGML.

When building GGML as a dependency for another project, these files are currently dumped into the main application's build folder.

@DaAwesomeP DaAwesomeP requested a review from ggerganov as a code owner January 9, 2026 00:36
@github-actions github-actions Bot added ggml changes relating to the ggml tensor library for machine learning Apple Metal https://en.wikipedia.org/wiki/Metal_(API) labels Jan 9, 2026
@ggerganov ggerganov merged commit 7d587e5 into ggml-org:master Jan 14, 2026
76 checks passed
dillon-blake pushed a commit to Boxed-Logic/llama.cpp that referenced this pull request Jan 15, 2026
MaheshJakkala pushed a commit to MaheshJakkala/llama.cpp that referenced this pull request Mar 15, 2026
Seunghhon pushed a commit to Seunghhon/llama.cpp that referenced this pull request Apr 26, 2026
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

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants