Kawrakow f17d0d72f5 Performance improvements for legacy quants on ARM_NEON (#37) ...

* WIP: trying to improve legacy quants

* WIP: trying to improve legacy quants

With this commit PP-512 for LlaMA-3.1-8B goes from
72 t/s to 87.2 t/s for q4_0, and from 61.5 t/s to 73.9 t/s
for q4_1, so 20+% improvement for both.

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

2024-09-04 07:24:04 +03:00

..

cmake

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

include

Faster Gemma2 (#27)

2024-08-27 17:40:59 +03:00

src

Performance improvements for legacy quants on ARM_NEON (#37)

2024-09-04 07:24:04 +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