ik_llama_opt/ggml
Kawrakow 73742c5db9
mtmd: be able to use alternative types for the K*Q multiplication (#1567)
* mtmd: allow using types other than f32 for K*Q

* Do not cast q if kq_type is quantized

* Fix formatting

* More formatting
2026-04-02 08:04:05 +02:00
..
cmake Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
include Better barrier (#1456) 2026-03-19 07:33:00 +01:00
src mtmd: be able to use alternative types for the K*Q multiplication (#1567) 2026-04-02 08:04:05 +02:00
.gitignore Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
CMakeLists.txt Enable all CPU-backend FA supported quants by default (#1549) 2026-03-29 14:36:09 +02:00