ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-25 07:34:10 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
bdc882bfac5251e94dd896b9356db45b68dc03dd
ik_llama.cpp/ggml
History
Iwan Kawrakow bdc882bfac Moving 4D gemm logic from ggml.c to iqk_mul_mat.cpp 
This allows us to optimize TG performance for GQA models.
E.g., for IQ4_XS L3-8B with 8k TG-64 goes from 8.6 to 10.26 t/s.
2025-02-14 18:03:19 +02:00
..
cmake
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
include
Use Q8_K_128 for IQ1_S_R4 and IQ1_M_R4 matrix multiplications (#194)
2025-02-09 09:14:52 +02:00
src
Moving 4D gemm logic from ggml.c to iqk_mul_mat.cpp
2025-02-14 18:03:19 +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