cturan/llama.cpp @ b549a1bbefb2f1fbb8b558bac1f2ae7967e60964

kopia lustrzana https://github.com/cturan/llama.cpp

Chen Xi b549a1bbef [SYCL] fix the mul_mat_id ut issues (#8427)		1 rok temu
..
cmake	f3f65429c4 llama : reorganize source code + improve CMake (#8006)	1 rok temu
include	0f1a39f343 ggml : add AArch64 optimized GEMV and GEMM Q4 kernels (#5780)	1 rok temu
src	b549a1bbef [SYCL] fix the mul_mat_id ut issues (#8427)	1 rok temu
CMakeLists.txt	6b2a849d1f ggml : move sgemm sources to llamafile subfolder (#8394)	1 rok temu
ggml_vk_generate_shaders.py	3fd62a6b1c py : type-check all Python scripts with Pyright (#8341)	1 rok temu