Iwan Kawrakow 4941c043bb Improve gemv for bf16_r16 ...

It is better to process one "row" at a time and to have
4 accumulators. I guess, this allows better interleving of
load and fmadd instructions. We get ~10% better performance
for 1 thread, and fully saturate memory bandwidth at 2 threads
with a ~3.5% better performance (4.4 vs 4.25 t/s for L3-8B).

2025-01-23 08:29:48 +02:00

..

cmake

Merge mainline llama.cpp (#3)

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

include

CPU Flash Attention improvements (#172)

2025-01-15 18:19:22 +02:00

src

Improve gemv for bf16_r16

2025-01-23 08:29:48 +02:00

.gitignore

Merge mainline llama.cpp (#3)

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

CMakeLists.txt

Move to c++17 projectwide (#80)

2024-10-04 14:43:26 +03:00