Unable to build shap with GPU support on Windows 10

I am trying to install the latest version of SHAP (0.45.0) with CUDA support to utilise GPUTree, on a Windows 10 machine installed with Visual Studio 2022 (version 17.9.6) with "Desktop development with C++ workload", CMake version 3.29.2 and CUDA Toolkit version 12.4.1. I have ensured that the cl.exe's path is there in the Path environment variable. Also, CUDA_PATH and CUDA_PATH_V12_4 are also defined properly. I created a venv environment with Python 12.0.0. As per the documentation available at https://shap.readthedocs.io/en/latest/example_notebooks/api_examples/explainers/GPUTree.html I cloned the SHAP repository and ran python setup.py install --user to build SHAP with CUDA support. However, I am getting errors like the below and the build is not successful (Finished processing dependencies for shap==0.0.0).

(shap_gpu) C:\Users\mimi\shap>python setup.py install --userAttempting to build SHAP: with_binary=True, with_cuda=True (Attempt 1)NVCC ==>  C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\bin\nvcc.exeCompiling cuda extension, calling nvcc with arguments:['C:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v12.4\\bin\\nvcc.exe', '-allow-unsupported-compiler', 'shap/cext/_cext_gpu.cu', '-lib', '-o', 'build/_cext_gpu.lib', '-Xcompiler', '/MD', '--include-path', 'C:\\Users\\mimi\\AppData\\Local\\Programs\\Python\\Python312\\Include', '--std', 'c++14', '--expt-extended-lambda', '--expt-relaxed-constexpr', '-gencode=arch=compute_60,code=sm_60', '-gencode=arch=compute_70,code=sm_70', '-gencode=arch=compute_75,code=sm_75', '-gencode=arch=compute_75,code=compute_75', '-gencode=arch=compute_80,code=sm_80']_cext_gpu.cuC:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\include\cuda_fp16.hpp(1890): error: asm operand type size(8) does not match type/size implied by constraint 'r'      asm ("ld.global.nc.b32 %0, [%1];"  : "=r"(*(reinterpret_cast<unsigned int *>(&(ret)))) : "r"(ptr));                                                                                               ^C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\include\cuda_fp16.hpp(1896): error: asm operand type size(8) does not match type/size implied by constraint 'r'      asm ("ld.global.nc.b16 %0, [%1];"  : "=h"(*(reinterpret_cast<unsigned short *>(&(ret)))) : "r"(ptr));                                                                                                 ^C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\include\cuda_fp16.hpp(1902): error: asm operand type size(8) does not match type/size implied by constraint 'r'      asm ("ld.global.cg.b32 %0, [%1];"  : "=r"(*(reinterpret_cast<unsigned int *>(&(ret)))) : "r"(ptr));                                                                                               ^C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\include\cuda_fp16.hpp(1908): error: asm operand type size(8) does not match type/size implied by constraint 'r'      asm ("ld.global.cg.b16 %0, [%1];"  : "=h"(*(reinterpret_cast<unsigned short *>(&(ret)))) : "r"(ptr));                                                                                                 ^C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\include\cuda_fp16.hpp(1914): error: asm operand type size(8) does not match type/size implied by constraint 'r'      asm ("ld.global.ca.b32 %0, [%1];"  : "=r"(*(reinterpret_cast<unsigned int *>(&(ret)))) : "r"(ptr));                                                                                               ^C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\include\cuda_fp16.hpp(1920): error: asm operand type size(8) does not match type/size implied by constraint 'r'      asm ("ld.global.ca.b16 %0, [%1];"  : "=h"(*(reinterpret_cast<unsigned short *>(&(ret)))) : "r"(ptr));                                                                                                 ^C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\include\cuda_fp16.hpp(1926): error: asm operand type size(8) does not match type/size implied by constraint 'r'      asm ("ld.global.cs.b32 %0, [%1];"  : "=r"(*(reinterpret_cast<unsigned int *>(&(ret)))) : "r"(ptr));                                                                                               ^C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\include\cuda_fp16.hpp(1932): error: asm operand type size(8) does not match type/size implied by constraint 'r'      asm ("ld.global.cs.b16 %0, [%1];"  : "=h"(*(reinterpret_cast<unsigned short *>(&(ret)))) : "r"(ptr));                                                                                                 ^C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.4\include\cuda_fp16.hpp(1938): error: asm operand type size(8) does not match type/size implied by constraint 'r'      asm ("ld.global.lu.b32 %0, [%1];"  : "=r"(*(reinterpret_cast<unsigned int *>(&(ret)))) : "r"(ptr) : "memory");

I was expecting successful installation of SHAP package with CUDA support. Instead the building resulted in numerous errors. Please help to resolve the issue.