cturan/llama.cpp @ fd123cfead49eb32e386e26b8ef7a6d41554dda5

0cc4m fd123cfead Vulkan: Default to 1GB allocations instead of 4GB to avoid fragmentation and driver issues (#12434)		10 месяцев назад
..
cmake	374101fd74 cmake : enable building llama.cpp using system libggml (#12321)	10 месяцев назад
include	7dfad387e3 llama: Add support for RWKV v7 architecture (#12412)	10 месяцев назад
src	fd123cfead Vulkan: Default to 1GB allocations instead of 4GB to avoid fragmentation and driver issues (#12434)	10 месяцев назад
.gitignore	17eb6aa8a9 vulkan : cmake integration (#8119)	1 год назад
CMakeLists.txt	8acdacb3ea opencl: use OpenCL C standard supported by the device (#12221)	10 месяцев назад