ik_llama_opt/ggml
Kawrakow b44d05dbe0 q6_0: Slightly faster Zen4/AVX2 (#78)
* Faster q6_0 on AVX2

PP-512 goes up by 3.4%.

* q6_0: this is slightly better

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-10-02 18:09:47 +03:00
..
cmake Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
include Fused unary(x)*y (#70) 2024-10-02 17:05:56 +03:00
src q6_0: Slightly faster Zen4/AVX2 (#78) 2024-10-02 18:09:47 +03:00
.gitignore Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
CMakeLists.txt Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00