Fix CUDA 12.5 build issue (#1273)

pythonInterface.cpp depends on ops.cuh
which in turn depends on some thrust headers.
It is defined as a C++ compilation unit
which is problematic  becuase thrift doesn't guarantee
compatibility with a host compiler.

This is starting to cause issues with CUDA 12.5.
There is no dependency on the thrust headers,
which means they can be removed without other consequences.

csrc/kernels.cu

@@ -12,8 +12,6 @@
 #include <cub/block/block_reduce.cuh>
 #include <cub/cub.cuh>
 #include <math_constants.h>
-#include <thrust/host_vector.h>
-#include <thrust/device_vector.h>
 #include <mma.h>
 
 

csrc/ops.cuh

@@ -19,10 +19,6 @@
 #include <vector>
 #include <functional>
 
-#include <thrust/host_vector.h>
-#include <thrust/device_vector.h>
-
-
 
 #define CUDA_CHECK_RETURN(value) {                      \
   cudaError_t _m_cudaStat = value;                    \