complied error in complying the kernel code file

[fyyfang]

C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.6\include\sm_32_intrinsics.hpp(123): error: asm operand type size(8) does not match type/size implied by constraint 'r'
static __declspec(device) __inline unsigned short __ldg(const unsigned short *ptr) { unsigned short ret; asm volatile ("ld.global.nc.u16 %0, [%1];" : "=h"(ret) : "r" (ptr)); return ret; }
^

Error limit reached.
100 errors detected in the compilation of "D:/java/TEXTDATA/src/GPU/kernels/JCudaVectorAddKernel.cu".
Compilation terminated.

[bottler]

This appears to be unrelated to pytorch3d.