]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: f121705)
Enable Fused-Multiply-Add (FMA) and F16C/CVT16 vector extensions on MSVC (#375)
authoranzz1 <redacted>
Tue, 28 Mar 2023 19:44:29 +0000 (22:44 +0300)
committerGitHub <redacted>
Tue, 28 Mar 2023 19:44:29 +0000 (22:44 +0300)
commit5a5f8b1501fbb34367225544010ddfc306d6d2fe
treeab77116dc4b03350ecdf3b9b00b7ff46b0b4b0c5tree
parentf1217055eaedfc7214be93d98e529cae89830430commit | diff
Enable Fused-Multiply-Add (FMA) and F16C/CVT16 vector extensions on MSVC (#375)

* Enable Fused-Multiply-Add (FMA) instructions on MSVC

__FMA__ macro does not exist in MSVC

* Enable F16C/CVT16 vector extensions on MSVC

__F16C__ macro does not exist in MSVC, but is implied with AVX2/AVX512

* MSVC cvt intrinsics

* Add __SSE3__ macro for MSVC too because why not

even though it's not currently used for anything when AVX is defined
ggml.c diff | blob | history
Packaging of ggml-org/llama.cpp