| .. |
|
cmake
|
9a96389544
ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094)
|
5 meses atrás |
|
include
|
b1f3a6e5db
llama: automatically set parameters not set by the user in such a way that maximizes GPU utilization (#16653)
|
1 mês atrás |
|
src
|
10b4f82d44
Added comments explaining thread block size selection logic based on row count and column size, derived from historical commit context (#18212)
|
3 semanas atrás |
|
.gitignore
|
17eb6aa8a9
vulkan : cmake integration (#8119)
|
1 ano atrás |
|
CMakeLists.txt
|
ce734a8a2f
ggml-hexagon: Implement true Q8_0 quantization on Hexagon NPU for more accurate mixed-precision matmul operations (#17977)
|
4 semanas atrás |
Aadeshveer Singh
10b4f82d44
Added comments explaining thread block size selection logic based on row count and column size, derived from historical commit context (#18212)