ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-21 05:34:08 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
7874e4425ff3e9bc7cca78e2e176448ee4e43e81
ik_llama.cpp/ggml
History
Kawrakow 7874e4425f AVX2 Flash Attention 2 (#50) 
* AVX2 Flash Attention: add ability to use Q8_0 for kv-cache

* AVX2 Flash Attention: add ability to use Q4_0 for kv-cache

* AVX2 Flash Attention: add ability to use Q4_1 for kv-cache

* Fix Zen4

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-09-11 19:55:42 +03:00
..
cmake
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
include
Adding IQ1_TN - 1.6875 bpw for TriLM ternary models (#44)
2024-09-09 14:56:34 +03:00
src
AVX2 Flash Attention 2 (#50)
2024-09-11 19:55:42 +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