ik_llama_opt/ggml
Kawrakow d55e98519f CUDA: prompt processing optimizations for MoE models (#739)
* Skip the row id computation for the ffn_down op

Sadly, almost negligible performance gain.

* Also this doesn't do much

* Also this barely moves the needle

* This is slightly better

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-08-30 12:09:41 +03:00
..
cmake Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
include AVX512+AVXVNNI GEMM implementation for quants using Q8_K for activations (#710) 2025-08-22 06:27:07 +03:00
src CUDA: prompt processing optimizations for MoE models (#739) 2025-08-30 12:09:41 +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