]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: b964876)
ggml : Parallelize quant LUT init (#23595)
authorJeff Bolz <redacted>
Mon, 25 May 2026 07:15:46 +0000 (02:15 -0500)
committerGitHub <redacted>
Mon, 25 May 2026 07:15:46 +0000 (10:15 +0300)
commit826539ce590fe294642db0acd54ea5e0a2fcd739
tree04e58b3825194b3539964f6bf23022ffc7a5a819tree
parentb96487645cb902551bdefb905e29261d0b0971bfcommit | diff
ggml : Parallelize quant LUT init (#23595)

- Use OpenMP to parallelize iq2xs_init_impl and iq3xs_init_impl.
- Move the OpenMP detection from ggml-cpu to ggml-base.
- Update OpenMP dependencies in ggml-config.cmake.in.
ggml/cmake/ggml-config.cmake.in diff | blob | history
ggml/src/CMakeLists.txt diff | blob | history
ggml/src/ggml-cpu/CMakeLists.txt diff | blob | history
ggml/src/ggml-quants.c diff | blob | history
Packaging of ggml-org/llama.cpp