ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-04 19:10:03 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
92adf7e6df7deec1cc1df601f89726d5e3062901
ik_llama.cpp/ggml
History
Iwan Kawrakow 92adf7e6df Experimenting with flash attention on Zen4 
This version outperforms no-FA at 8k tokens, but then
performance becomes the same at 16k and worse at 32k.
2024-08-30 07:38:54 +03:00
..
cmake
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
include
Fused soft cap and SIMD-ified GeLU (#9)
2024-08-20 17:15:47 +03:00
src
Experimenting with flash attention on Zen4
2024-08-30 07:38:54 +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