Iwan Kawrakow b02fd4ee38 iq2_bn_r4: Experimenting on NEON ...

The matrix x vvector multiplication is erratic.
iq2_bn_r4 is faster at 1, 2, and 4 threads, but
saturates to a lower t/s at 8 threads compared to
iq2_bn. iq2_bn actually manages 99 t/s at 8 threads
and not 93 as I wrore in the last commit. iq2_bn_r4
performance has huge fluctuations at 4 and 8 threads.

2024-12-05 18:52:38 +01:00

..

cmake

Merge mainline llama.cpp (#3)

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

include

Adding iq2_bn_r4

2024-12-05 15:18:33 +02:00

src

iq2_bn_r4: Experimenting on NEON

2024-12-05 18:52:38 +01:00

.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