ik_llama_opt/ggml
Kawrakow 18f5bb47d8 Add support for bf16 to iqk_mul_mat (#39)
* WIP: adding BF16 support to iqk_mul_mat

* Minor

* Improve TG speed (when not memory bound)

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2024-09-05 07:48:27 +03:00
..
cmake Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
include Faster Gemma2 (#27) 2024-08-27 17:40:59 +03:00
src Add support for bf16 to iqk_mul_mat (#39) 2024-09-05 07:48:27 +03:00
.gitignore Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
CMakeLists.txt Merge mainline - Aug 12 2024 (#17) 2024-08-12 15:14:32 +02:00