Inicio Explorar Axuda
Iniciar sesión
cturan
/
llama.cpp
réplica de https://github.com/cturan/llama.cpp
1
0
Fork 0
Ficheiros Incidencias 0 Wiki
Árbore: 7c7f3b7f43
Ramas Etiquetas
llama.cpp
/
ggml
/
src
/
ggml-vulkan
cmdr2 0cbee131ad cuda/vulkan: specify fp32-only support for some operations in supports_op (ggml/1129) hai 11 meses
..
cmake 1d8504338e fix: ggml: fix vulkan-shaders-gen build (#10448) hai 1 ano
vulkan-shaders 438a83926a vulkan: add specific MMV kernels for IQ2 and IQ3 quants + optimizations (#11595) hai 11 meses
CMakeLists.txt 1d8504338e fix: ggml: fix vulkan-shaders-gen build (#10448) hai 1 ano
ggml-vulkan.cpp 0cbee131ad cuda/vulkan: specify fp32-only support for some operations in supports_op (ggml/1129) hai 11 meses