ik_llama_opt/ggml
Kawrakow 6719288bf0 Flash MLA (CPU only) (#240)
* FlashMLA - it finally works (on the CPU)

* FlashMLA: allow for f16 and bf16 cache in addition to q8_0

* It works with ggml FA, not with iqk FA

* WIP

* FlashMLA: it now works with iqk

I had forgotten to divide the Q stride by sizeof(float) and
that's why, very cobfusingly, it was working for TG but not for PP.

* WIP

* FlashMLA: that should be it for now

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-03-03 15:17:51 +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 Flash MLA (CPU only) (#240) 2025-03-03 15:17:51 +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