|
@@ -12,9 +12,6 @@
|
|
|
#include <vector>
|
|
#include <vector>
|
|
|
#include <map>
|
|
#include <map>
|
|
|
#include <array>
|
|
#include <array>
|
|
|
-#include "ggml-cuda.h"
|
|
|
|
|
-#include "ggml.h"
|
|
|
|
|
-#include "ggml-backend-impl.h"
|
|
|
|
|
|
|
|
|
|
#if defined(GGML_USE_HIPBLAS)
|
|
#if defined(GGML_USE_HIPBLAS)
|
|
|
#include <hip/hip_runtime.h>
|
|
#include <hip/hip_runtime.h>
|
|
@@ -118,6 +115,11 @@
|
|
|
|
|
|
|
|
#endif // defined(GGML_USE_HIPBLAS)
|
|
#endif // defined(GGML_USE_HIPBLAS)
|
|
|
|
|
|
|
|
|
|
+// ggml-cuda need half type so keep ggml headers include at last
|
|
|
|
|
+#include "ggml-cuda.h"
|
|
|
|
|
+#include "ggml.h"
|
|
|
|
|
+#include "ggml-backend-impl.h"
|
|
|
|
|
+
|
|
|
#define CUDART_HMAX 11070 // CUDA 11.7, min. ver. for which __hmax and __hmax2 are known to work (may be higher than needed)
|
|
#define CUDART_HMAX 11070 // CUDA 11.7, min. ver. for which __hmax and __hmax2 are known to work (may be higher than needed)
|
|
|
|
|
|
|
|
#define CC_PASCAL 600
|
|
#define CC_PASCAL 600
|