Iwan Kawrakow c24ad0d1e7 iq4_xxs: Zen4 ...

I noticed that iq4_xs is wrong on Zen4 (and possibly AVX2).
Again the same mistake of packing int32_t back to int16_t,
which overflows occasionally (just occasionally, that's why the
result doesn't look completely wrong, so I didn't notice).

2024-10-08 19:40:26 +03:00

..

cmake

Merge mainline llama.cpp (#3)

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

include

iq4_k_xxs: basics

2024-10-08 10:52:53 +03:00

src

iq4_xxs: Zen4

2024-10-08 19:40:26 +03:00

.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