ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-01-26 17:20:01 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
c23a17b6feaa456173190205925cb581cd74d624
ik_llama.cpp/ggml
History
Kawrakow c23a17b6fe cuda: use better block sizes for rms_norm (#845) 
* cuda: use better block sizes for rms_norm

* Minor

* Remove forgotten printf

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-10-21 08:12:48 +03:00
..
cmake
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
include
Grouped expert routing (CPU only) (#836)
2025-10-16 14:57:02 +03:00
src
cuda: use better block sizes for rms_norm (#845)
2025-10-21 08:12:48 +03:00
.gitignore
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
CMakeLists.txt
Set default value of GGML_SCHED_MAX_COPIES to 1 (#751)
2025-09-02 07:04:39 +02:00