]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
ggml : AVX512 gemm for Q4_0_8_8 (#9532)
authorSrihari-mcw <redacted>
Mon, 23 Sep 2024 14:06:38 +0000 (19:36 +0530)
committerGitHub <redacted>
Mon, 23 Sep 2024 14:06:38 +0000 (17:06 +0300)
commit1e7b9299c6ccb5bbc55d3db7cfa9b51f3ab09b59
tree878c88efec1a382810b670de49d44feb5f7a206f
parent37f8c7b4c97784496cfd91040d55fa22f50b1d57
ggml : AVX512 gemm for Q4_0_8_8 (#9532)

* AVX512 version of ggml_gemm_q4_0_8x8_q8_0

* Remove zero vector parameter passing

* Rename functions and rearrange order of macros

* Edit commments

* style : minor adjustments

* Update x to start from 0

---------

Co-authored-by: Georgi Gerganov <redacted>
ggml/src/ggml-aarch64.c