ggml-org/llama.cpp

llama : refactor the llm.build_xxx functions

Geschlossen

#5.239 geöffnet am 31.01.2024

 (3 Kommentare) (3 Reaktionen) (0 zugewiesene Personen)C++ (21.786 Forks)batch import
good first issuerefactoringroadmap

Repository-Metriken

Stars
 (124.222 Sterne)
PR-Merge-Metriken
 (Durchschn. Merge 6T 8h) (389 gemergte PRs in 30 T)

Beschreibung

Now that we support a large amount of architectures, we can clearly see the patterns when constructing the compute graphs - i.e. optional biases, different norm types, QKV vs Q+K+V, etc.

We should deduplicate the copy-paste portions in functions such as llm.build_llama(), llm.build_falcon(), etc.

The advantage of the current code is that it is easy to look into the graph of a specific architecture. When we refactor this, we will lose this convenience to some extend. So we should think about making this refactoring in such a way that we don't completely obscure which parts of the graph belong to which architectures

Open for ideas and suggestions how to do this best

Contributor Guide