ik_llama_opt/ggml
Kawrakow 3e70d984dd MMQ implementation for IQ4_KS_R4 and IQ5_KS_R4 (#493)
* MMQ for iq4_ks_r4

* MMQ for iq5_ks_r4

* Add forgotten file

* Another forgotten file

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-06-05 08:31:20 +03:00
..
cmake Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
include Trellis quants with CPU inference (#441) 2025-05-23 09:17:52 +03:00
src MMQ implementation for IQ4_KS_R4 and IQ5_KS_R4 (#493) 2025-06-05 08:31:20 +03:00
.gitignore Merge mainline llama.cpp (#3) 2024-07-27 07:55:01 +02:00
CMakeLists.txt Option to enable disable the IQK CPU FA kernels (#429) 2025-05-17 11:21:58 +03:00