ik_llama.cpp/ggml
Kawrakow 0976467845
CUDA GEMM and GEMV for IQ4_KS_R4 and IQ5_KS_R4 (#462)
* CUDA: iq4_ks_r4 GEMV and GEMM

* CUDA: iq5_ks_r4 GEMV and GEMM

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
2025-05-27 08:37:44 +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 CUDA GEMM and GEMV for IQ4_KS_R4 and IQ5_KS_R4 (#462) 2025-05-27 08:37:44 +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