sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-03-17 16:44:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

general: CONTRIBUTING.md - guidelines for quantization schemes (#19762)

Browse Source 
* Guidelines for quantization schemes

* Update CONTRIBUTING.md

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* Change required precision from Q8 to FP16/BF16

* Update CONTRIBUTING.md

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* Update CONTRIBUTING.md

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* Update CONTRIBUTING.md

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* Update CONTRIBUTING.md

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>

* Update CONTRIBUTING.md [no ci]

* Update CONTRIBUTING.md [no ci]

---------

Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
This commit is contained in:
Piotr Wilkin (ilintar)
2026-03-13 12:21:33 +01:00
committed by GitHub
parent 73c9eb8ced
commit 2948e6049a
1 changed files with 12 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
CONTRIBUTING.md
View File

@@ -38,6 +38,11 @@ Before submitting your PR:
- Avoid combining unrelated changes in a single PR
- For intricate features, consider opening a feature request first to discuss and align expectations
- When adding support for a new model or feature, focus on **CPU support only** in the initial PR unless you have a good reason not to. Add support for other backends like CUDA in follow-up PRs
- In particular, adding new data types (extension of the `ggml_type` enum) carries with it a disproportionate maintenance burden. As such, to add a new quantization type you will need to meet the following *additional* criteria *at minimum*:
- convert a small model to GGUF using the new type and upload it to HuggingFace
- provide [perplexity](https://github.com/ggml-org/llama.cpp/tree/master/tools/perplexity) comparisons to FP16/BF16 (whichever is the native precision) as well as to types of similar size
- provide KL divergence data calculated vs. the FP16/BF16 (whichever is the native precision) version for both the new type as well as types of similar size
- provide [performance data](https://github.com/ggml-org/llama.cpp/tree/master/tools/llama-bench) for the new type in comparison to types of similar size on pure CPU
- Consider allowing write access to your branch for faster reviews, as reviewers can push commits directly
- If you are a new contributor, limit your open PRs to 1.