ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-28 10:21:48 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
23ee1ac1b8868724253ee8b6554288dd1e4a5632
ik_llama.cpp/ggml
History
Kawrakow 23ee1ac1b8 Attempt to improve FlashMLA on the CPU (#277) 
* Fix it for nth > rk2

* Handle rk2%nth_k != 0

* Cleanup

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-23 07:28:21 +01:00
..
cmake
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
include
SER - Smart Expert Reduction (#239)
2025-03-02 13:47:38 +02:00
src
Attempt to improve FlashMLA on the CPU (#277)
2025-03-23 07:28:21 +01:00
.gitignore
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
CMakeLists.txt
Compile time option to use bf16 for qunts without MMQ kernels (#261)
2025-03-18 07:37:10 +01:00