1
0
Ruben Ortlam 7f459c98e7 vulkan: use fewer FA rows for small cache runs (#18280) 1 сар өмнө
..
cmake 9a96389544 ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 5 сар өмнө
include b1f3a6e5db llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653) 1 сар өмнө
src 7f459c98e7 vulkan: use fewer FA rows for small cache runs (#18280) 1 сар өмнө
.gitignore 17eb6aa8a9 vulkan : cmake integration (#8119) 1 жил өмнө
CMakeLists.txt ce734a8a2f ggml-hexagon: Implement true Q8_0 quantization on Hexagon NPU for more accurate mixed-precision matmul operations (#17977) 1 сар өмнө