[Offload] Use newer CUDA API functions when dynamically loaded (#93057)

Summary:
CUDA does its versioning by putting a redirection in the header so the
API functions remain the same while the symbol changes. These weren't
being used for some functions that required it in the dynamic cuda
version.

These functions have newer verisons that should be used. These are
fairly old as far as I'm aware so we should be able to sweep backward
compatibility under the rug.

Author: jhuber6

offload/plugins-nextgen/cuda/dynamic_cuda/cuda.h

@@ -16,6 +16,15 @@
 #include <cstddef>
 #include <cstdint>
 
+#define cuDeviceTotalMem cuDeviceTotalMem_v2
+#define cuModuleGetGlobal cuModuleGetGlobal_v2
+#define cuMemGetInfo cuMemGetInfo_v2
+#define cuMemAlloc cuMemAlloc_v2
+#define cuMemFree cuMemFree_v2
+#define cuMemAllocHost cuMemAllocHost_v2
+#define cuDevicePrimaryCtxRelease cuDevicePrimaryCtxRelease_v2
+#define cuDevicePrimaryCtxSetFlags cuDevicePrimaryCtxSetFlags_v2
+
 typedef int CUdevice;
 typedef uintptr_t CUdeviceptr;
 typedef struct CUmod_st *CUmodule;