ik_llama_opt/ggml
Kawrakow a3f6ee27cc DeepSeek CUDA Flash Attention (#241)
* WIP CUDA FA with Dk != Dv

* WIP

* CUDA FA WIP - It actually works!

No TG yet, but for PP I can run FA with fp16 cache and it gets
the same answer.

* CUDA FA WIP - it now works for Q8_0 + Q8_0 for KV cache

* CUDA FA WIP - TG, not working yet.

* CUDA FA with Dk != Dv: it works now for DeepSeek

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-05 07:27:49 +02:00
..
cmake Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
include SER - Smart Expert Reduction (#239) 2025-03-02 13:47:38 +02:00
src DeepSeek CUDA Flash Attention (#241) 2025-03-05 07:27:49 +02:00
.gitignore Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
CMakeLists.txt FA: Add option to build all FA kernels (#197) 2025-02-09 18:59:33 +02:00