Repository navigation
Support llama-cpp-python 0.3.36 with optimized runtime wheels - #9
Merged
Merged
Conversation
da03
changed the title
da03
marked this pull request as ready for review
October 5, 2026 00:07
da03
added a commit
that referenced
this pull request
Oct 5, 2026
Prepare SDK 0.4.11 for the llama-cpp-python 0.3.36 upgrade merged in #9. Bump the package version and add release notes covering macOS runtime wheels and automatic Linux CPU backend selection. Validation: the diff contains only the approved changes to `pyproject.toml` and `CHANGELOG.md`; `git diff --cached --check` passed.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Allow llama-cpp-python 0.3.36 while retaining Python 3.8–3.14 support. Build Intel and Apple Silicon wheels targeting macOS 11, plus Apple Silicon wheels with BLAS for macOS 14+. Keep Windows and manylinux 2.17 Linux wheels.
Linux wheels select among 14 CPU backends with OS-state and AMX permission checks. Fix GCC 11 AMX initialization and route Q6_K away from AMX based on benchmark results.
Validation: all 24 runtime-wheel jobs and 43 SDK CI jobs passed. Linux Standard and Compact inference and prefix-cache save/reload passed with automatic backend selection and forced x64.