ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-24 23:24:13 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
73c28dbef4face700f89ffee765068594603ea70
ik_llama.cpp/ggml
History
Kawrakow 5cc15d0ecf CUDA MoE improvements (#923) 
* Use mmq_id in mul_mat_id

* Better

* Also use it in the fused up+gate op

* Better -no-fmoe TG on CUDA

Still much slower than -fmoe, but abot 20-25% faster than what
we had before.

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-11-09 11:34:33 +02:00
..
cmake
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
include
CUDA: set compute parameters via command line arguments (#910)
2025-11-07 07:11:23 +02:00
src
CUDA MoE improvements (#923)
2025-11-09 11:34:33 +02:00
.gitignore
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
CMakeLists.txt
Disable CUDA fusion by default for now (#903)
2025-11-05 10:58:12 +02:00