ik_llama_opt/ggml
Kawrakow 6123e1700b IQ4_NL kv-cache on the CPU (Zen4/AVX2/ARM_NEON) (#74)
* Be able to use IQ4_NL for KV cache on AVX2/Zen4

* Be able to use IQ4_NL for KV cache on ARM_NEON

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-10-01 14:46:40 +03:00
..
cmake Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
include Adding SWIGLU unary op (#65) 2024-09-28 13:37:25 +03:00
src IQ4_NL kv-cache on the CPU (Zen4/AVX2/ARM_NEON) (#74) 2024-10-01 14:46:40 +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