8000 common/llama: align structures for reduce cacheline size on 64bit platforms by GermanAizek · Pull Request #13710 · ggml-org/llama.cpp · GitHub
[go: up one dir, main page]
Skip to content

common/llama: align structures for reduce cacheline size on 64bit platforms#13710

Open
GermanAizek wants to merge 1 commit intoggml-org:masterfrom
GermanAizek:align-64bit

Commits

Commits on May 22, 2025
0