Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-16 07:08:28 +01:00
Code Issues Packages Projects Releases Wiki Activity
3420909dff
llama.cpp/ggml/src/ggml-cpu/amx
History
Diego Devesa 3420909dff
ggml : automatic selection of best CPU backend (#10606) 
* ggml : automatic selection of best CPU backend

* amx : minor opt

* add GGML_AVX_VNNI to enable avx-vnni, fix checks
2024-12-01 16:12:41 +01:00
..
amx.cpp ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
amx.h ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00
common.h ggml : automatic selection of best CPU backend (#10606) 2024-12-01 16:12:41 +01:00
mmq.cpp ggml : automatic selection of best CPU backend (#10606) 2024-12-01 16:12:41 +01:00
mmq.h ggml : move AMX to the CPU backend (#10570) 2024-11-29 21:54:58 +01:00