[sgl-kernel/cpu] support w8a8 int8 model for arm cpu (#16045)

skip gpu test as this one is not related to gpu backend.

sgl-kernel/csrc/cpu/gemm_int8.cpp

@@ -473,6 +473,7 @@ at::Tensor int8_scaled_mm_cpu(
   return out;
 }
 
+#ifndef __aarch64__
 // fused `per_token_quant_int8_cpu` and `int8_scaled_mm_cpu`
 at::Tensor int8_scaled_mm_with_quant(
     at::Tensor& mat1,
@@ -539,3 +540,4 @@ at::Tensor int8_scaled_mm_with_quant(
   });
   return out;
 }
+#endif  // #ifndef __aarch64__