[AMD][CI/Build][Bugfix] Guarding CUDA specific functions by ifndef ROCM (#21766)

Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>

csrc/quantization/compressed_tensors/int8_quant_kernels.cu

 #include <ATen/cuda/CUDAContext.h>
 #include <torch/all.h>
 
-#include "../per_token_group_quant_8bit.h"
+#ifndef USE_ROCM
+  #include "../per_token_group_quant_8bit.h"
+#endif
 
 #include <cmath>
 
@@ -339,10 +341,12 @@ void dynamic_scaled_int8_quant(
       });
 }
 
+#ifndef USE_ROCM
 void per_token_group_quant_int8(const torch::Tensor& input,
                                 torch::Tensor& output_q,
                                 torch::Tensor& output_s, int64_t group_size,
                                 double eps, double int8_min, double int8_max) {
   per_token_group_quant_8bit(input, output_q, output_s, group_size, eps,
                              int8_min, int8_max);
-}
\ No newline at end of file
+}
+#endif