This repository was archived by the owner on Sep 9, 2025. It is now read-only.
Build quantize binary in setup.py #7
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
- remove pre-built binaries from git - create a proper sdist with sources - add `setup.py` to compile `quantize` binary for current platform - update to latest release of `llama.cpp` Signed-off-by: Christian Heimes <[email protected]>
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
Last year in March I created and set up
instructlab-quantizein a hurry. I wanted to move the pre-built binary from theinstructlabproject to a separate project. To simplify the build I just stored pre-built binaries in the new project, too. Even thesdistof this project contains binaries instead of sources. I just noticed the problem when I saw an unusual glibc version requirement in our downstream builds.This PR addresses the problem and updates
quantizebinary to latestllama.cpprelease. Now the sdist contains the sources, builds the binary from sources, and creates platform-specificpy3-nonewheels.setup.pyto compilequantizebinary for current platformllama.cpp