Iwan Kawrakow df066ced5e Seems to be working on CUDA ...

For a dense model we get 2-3% speedup for PP and ~0.6% for TG.

2025-08-30 12:09:54 +03:00

..

cmake

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

include

Fused up+gate+unary for regular (not MoE) FFN - CPU

2025-08-30 12:09:54 +03:00

src

Seems to be working on CUDA

2025-08-30 12:09:54 +03:00

.gitignore

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

CMakeLists.txt

Enable CUDA graphs for MoE models + GPT-OSS support (#689)

2025-08-15 09:18:07 +03:00