move QK_WARP_SIZE to presets.hpp

luoyu-intel · luoyu-intel · commit ac8a4bd9d5ac · 2024-07-05T10:48:29.000+08:00
diff --git a/ggml/src/ggml-sycl/dmmv.cpp b/ggml/src/ggml-sycl/dmmv.cpp
@@ -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;
diff --git a/ggml/src/ggml-sycl/presets.hpp b/ggml/src/ggml-sycl/presets.hpp
@@ -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

Original file line number	Diff line number	Diff line change
`@@ -62,4 +62,5 @@ static_assert(K_QUANTS_PER_ITERATION == 1 \|\| K_QUANTS_PER_ITERATION == 2, "K_QUA`
`62`	`62`
`63`	`63`	`#define MUL_MAT_SRC1_COL_STRIDE 128`
`64`	`64`
	`65`	`+#define QK_WARP_SIZE 32`
`65`	`66`	`#endif // GGML_SYCL_PRESETS_HPP`