ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-20 22:49:31 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
ik/deepseek_opt
ik_llama.cpp/ggml
History
Iwan Kawrakow aae817e50b DeepSeek TG optimizations for TG 
* Fuse concat and copy into K cache
* Avoid ggml_cont() when n_token = 1

Combined effect: about +2% in TG performance with full GPU offload
2025-11-09 07:54:05 +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
DeepSeek TG optimizations for TG
2025-11-09 07:54:05 +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