cuda : fix compile error in jetson platform (llama/4975)

* cuda: fix compile error in jetson platform

* cuda: update comment in ggml-cuda.cu

* cuda: update ggml-cuda.cu comment

diff --git a/ggml-cuda.cu b/ggml-cuda.cu
index b2211d858c23aad6b8c1fe79a96f38b9c684afe5..ec3837fb88d14888c905fac7eea32ebe7c1a1c10 100644 (file)
--- a/ggml-cuda.cu
+++ b/ggml-cuda.cu
@@ -12,9 +12,6 @@
 #include <vector>
 #include <map>
 #include <array>
-#include "ggml-cuda.h"
-#include "ggml.h"
-#include "ggml-backend-impl.h"
 
 #if defined(GGML_USE_HIPBLAS)
 #include <hip/hip_runtime.h>
@@ -118,6 +115,11 @@
 
 #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 CC_PASCAL     600