cturan/llama.cpp @ 2a24c8caa6d10a7263ca317fa7cb64f0edc72aae

miroir de https://github.com/cturan/llama.cpp

Nico Bosshard e3f6fd56b1 ggml : dynamic ggml_sched_max_splits based on graph_size (#9047)		il y a 1 an
..
cmake	f3f65429c4 llama : reorganize source code + improve CMake (#8006)	il y a 1 an
include	06943a69f6 ggml : move rope type enum to ggml.h (#8949)	il y a 1 an
src	e3f6fd56b1 ggml : dynamic ggml_sched_max_splits based on graph_size (#9047)	il y a 1 an
.gitignore	17eb6aa8a9 vulkan : cmake integration (#8119)	il y a 1 an
CMakeLists.txt	5fd89a70ea Vulkan Optimizations and Fixes (#8959)	il y a 1 an