- Test your changes:
- Execute the full CI locally on your machine before publishing
- Verify that the perplexity and the performance are not affected negatively by your changes (use
llama-perplexityandllama-bench) - If you modified the
ggmlsource, run thetest-backend-opstool to check whether different backend implementations of theggmloperators produce consistent results (this requires access to at least two differentggmlbackends) - If you modified a
ggmloperator or added a new one, add the corresponding test cases totest-backend-ops
- Consider allowing write access to your branch for faster reviews, as reviewers can push commits directly
- If your PR becomes stale, don't hesitate to ping the maintainers in the comments
- Squash-merge PRs
- Use the following format for the squashed commit title:
<module> : <commit title> (#<issue_number>). For example:utils : fix typo in utils.py (#1234) - Optionally pick a
<module>from here: https://github.com/ggerganov/llama.cpp/wiki/Modules - Consider adding yourself to CODEOWNERS
- Avoid adding third-party dependencies, extra files, extra headers, etc.
- Always consider cross-compatibility with other operating systems and architectures
- Avoid fancy-looking modern STL constructs, use basic
forloops, avoid templates, keep it simple - There are no strict rules for the code style, but try to follow the patterns in the code (indentation, spaces, etc.). Vertical alignment makes things more readable and easier to batch edit
- Clean-up any trailing whitespaces, use 4 spaces for indentation, brackets on the same line,
void * ptr,int & a - Naming usually optimizes for common prefix (see ggerganov/ggml#302 (comment))
- Tensors store data in row-major order. We refer to dimension 0 as columns, 1 as rows, 2 as matrices
- Matrix multiplication is unconventional:
C = ggml_mul_mat(ctx, A, B)means$C^T = A B^T \Leftrightarrow C = B A^T.$
The Github issues, PRs and discussions contain a lot of information that can be useful to get familiar with the codebase. For convenience, some of the more important information is referenced from Github projects: