TensorRT context consume mush memory on Orin

I modified a superGLue model for a image matching project and the tensorRT engine works well ,the superGlue trt engine’s result is correct. but the problem is that the engine counsume too much memory! my device is Orin with 32GB memory. the superGLue engine context consume 24G+ memory !!!. on my other x64 server with GPU A6000, the engine only need 9GB memory. that’s a big problem. please help me, thanks a lot.

orin enviroment:
CUDA 11.4
cudnn 8.3.2
TensorRT 8.4.0

x64 server with GPU A6000:
CUDA 11.1
cudann 8.2.1
TensorRT 8.2.1

Dear @yixinvs1115,
Could you confirm if you have DRIVE AGX Orin or Jetson AGX Orin platform?

my device is Jetson AGX Origin

Dear @yixinvs1115,
Please post Jetson AGX Orin related issues at Jetson AGX Orin - NVIDIA Developer Forums for attention.