]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
ggml : AVX512 gemm for Q4_0_8_8 (llama/9532)
authorSrihari-mcw <redacted>
Mon, 23 Sep 2024 14:06:38 +0000 (19:36 +0530)
committerGeorgi Gerganov <redacted>
Tue, 24 Sep 2024 10:04:37 +0000 (13:04 +0300)
commit3e2f8e370ad3d2c7024d285ddde56014cf0b79ab
treec109a8ef5a67e99da9c63068f9f532e772945f6d
parent64f30f362597c427889446484b8f6a9176f14601
ggml : AVX512 gemm for Q4_0_8_8 (llama/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>
src/ggml-aarch64.c