diff --git a/paddle/operators/multiplex_op.cc b/paddle/operators/multiplex_op.cc
index 78263da2fbf843f6a5af2ba95aa0b219a7523b52..d275fa5cbbfbf4a949d7bb16c3acc598543ba000 100644
--- a/paddle/operators/multiplex_op.cc
+++ b/paddle/operators/multiplex_op.cc
@@ -119,7 +119,13 @@ REGISTER_OPERATOR(multiplex, ops::MultiplexOp, ops::MultiplexOpMaker,
 REGISTER_OPERATOR(multiplex_grad, ops::MultiplexGradOp);
 REGISTER_OP_CPU_KERNEL(
     multiplex,
-    ops::MultiplexCPUKernel<paddle::platform::CPUDeviceContext, float>);
+    ops::MultiplexCPUKernel<paddle::platform::CPUDeviceContext, float>,
+    ops::MultiplexCPUKernel<paddle::platform::CPUDeviceContext, double>,
+    ops::MultiplexCPUKernel<paddle::platform::CPUDeviceContext, int>,
+    ops::MultiplexCPUKernel<paddle::platform::CPUDeviceContext, int64_t>);
 REGISTER_OP_CPU_KERNEL(
     multiplex_grad,
-    ops::MultiplexGradCPUKernel<paddle::platform::CPUDeviceContext, float>);
+    ops::MultiplexGradCPUKernel<paddle::platform::CPUDeviceContext, float>,
+    ops::MultiplexGradCPUKernel<paddle::platform::CPUDeviceContext, double>,
+    ops::MultiplexGradCPUKernel<paddle::platform::CPUDeviceContext, int>,
+    ops::MultiplexGradCPUKernel<paddle::platform::CPUDeviceContext, int64_t>);
diff --git a/paddle/operators/multiplex_op.cu b/paddle/operators/multiplex_op.cu
index 4372dc2c65ec7c0f28e46cd070ea471701ce8304..546e6e7a24d3653e9904706eac51c1b833f51463 100644
--- a/paddle/operators/multiplex_op.cu
+++ b/paddle/operators/multiplex_op.cu
@@ -90,7 +90,13 @@ namespace ops = paddle::operators;
 
 REGISTER_OP_CUDA_KERNEL(
     multiplex,
-    ops::MultiplexGPUKernel<paddle::platform::CUDADeviceContext, float>);
+    ops::MultiplexGPUKernel<paddle::platform::CUDADeviceContext, float>,
+    ops::MultiplexGPUKernel<paddle::platform::CUDADeviceContext, double>,
+    ops::MultiplexGPUKernel<paddle::platform::CUDADeviceContext, int>,
+    ops::MultiplexGPUKernel<paddle::platform::CUDADeviceContext, int64_t>);
 REGISTER_OP_CUDA_KERNEL(
     multiplex_grad,
-    ops::MultiplexGradGPUKernel<paddle::platform::CUDADeviceContext, float>);
+    ops::MultiplexGradGPUKernel<paddle::platform::CUDADeviceContext, float>,
+    ops::MultiplexGradGPUKernel<paddle::platform::CUDADeviceContext, double>,
+    ops::MultiplexGradGPUKernel<paddle::platform::CUDADeviceContext, int>,
+    ops::MultiplexGradGPUKernel<paddle::platform::CUDADeviceContext, int64_t>);