ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-26 16:14:10 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
30b89f0cf9053ee5a88d166eff746a09738d9202
ik_llama.cpp/ggml
History
Iwan Kawrakow 30b89f0cf9 Experimenting with flash attention on Zen4 
Slightly (~1%) better by keeping qkv accumulators
on the stack and only storing the final result into
the qkv tensor.
2024-08-30 09:21:37 +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 09:21:37 +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