vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

move QK_WARP_SIZE to presets.hpp

Browse source
This commit is contained in:
luoyu-intel 2024-07-03 13:33:48 +08:00
parent d7cf5f5abb
commit ac8a4bd9d5
2 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

1
ggml/src/ggml-sycl/dmmv.cpp
View file

@ -3,7 +3,6 @@
#include "dequantize.hpp"
#include "presets.hpp"
int constexpr QK_WARP_SIZE = 32;
static void convert_f16(const void * vx, const int ib, const int iqs, dfloat2 & v){
const sycl::half *x = (const sycl::half *)vx;

1
ggml/src/ggml-sycl/presets.hpp
View file

@ -62,4 +62,5 @@ static_assert(K_QUANTS_PER_ITERATION == 1 || K_QUANTS_PER_ITERATION == 2, "K_QUA
#define MUL_MAT_SRC1_COL_STRIDE 128
#define QK_WARP_SIZE 32
#endif // GGML_SYCL_PRESETS_HPP