Enabling building llama.cpp using system libggml #12321
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
llama.cpps's build requires it, too, and we may want to make use of it without add_subdirectory(ggml).
github-actions
bot
added
build
Green-Sky
reviewed
Mar 10, 2025
This facilitates package maintenance for Linux distributions, where the libggml library most likely will be shipped as an individual package upon which a llama.cpp package depends.
ggerganov
approved these changes
Mar 17, 2025
| @@ -1,3 +1,5 @@ | |||
| include("ggml/cmake/common.cmake") | |||
Member
There was a problem hiding this comment.
I think it would be better to have llama.cpp-specific flags instead of reusing the ggml flags like this. But this also works.
Collaborator
Author
There was a problem hiding this comment.
I agree. I didn't know whether the re-use of ggml_get_flags was intentional or not, so I went with the least intrusive option. Well, it can easily be changed once the need arises.
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Mar 19, 2025
* cmake: Factor out compiler flag function from ggml llama.cpps's build requires it, too, and we may want to make use of it without add_subdirectory(ggml). * cmake: Enable building against system ggml This facilitates package maintenance for Linux distributions, where the libggml library most likely will be shipped as an individual package upon which a llama.cpp package depends.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
A llama.cpp build could make use of an already installed libggml using the latter's cmake package. This would be the typical case for Linux distributions.
Note: This requires a ggml build where GGML_BIN_DIR is commented out, see 82d9ca4.
The tests passed but I get a
ModuleNotFoundError(torch) fromconvert_hf_to_gguf.py, which is unexpected. I haven't investigated yet.