ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-09 13:30:17 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
a0ba58e9b977ae13bf47d08b12745ee4325fe015
ik_llama.cpp/ggml
History
Iwan Kawrakow a0ba58e9b9 iq2_kt and iq3_kt work with new int trellis 
Much slower than the fp16 based trellis. I guess, Apple doesn't
have int8_t SIMD on the M2-Max GPU.
2025-06-20 10:47:22 +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
iq2_kt and iq3_kt work with new int trellis
2025-06-20 10:47:22 +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