ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-26 09:29:27 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
78411343cc14210b3a311176a11352edc51ee26d
ik_llama.cpp/ggml
History
Iwan Kawrakow 78411343cc New iq4_kt: AVX2 dot product finally works 
We get 13.6 t/s vs 8.4 t/s with the f16 trellis and f32 arithmetic.
Still somewhat slower than other quants, but no longer pathetic.
2025-06-18 15:34:27 +03:00
..
cmake
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
include
Fix non rpc build error (#506)
2025-06-08 17:27:00 +03:00
src
New iq4_kt: AVX2 dot product finally works
2025-06-18 15:34:27 +03:00
.gitignore
Merge mainline llama.cpp (#3)
2024-07-27 07:55:01 +02:00
CMakeLists.txt
Better strategy for GPU offload (#520)
2025-06-12 19:25:11 +03:00