Centerpoint Int8 quantization and deployment

[zxxzxy]

Thanks for your work! I'm trying to quantize Int8 Centerpoint to accelerate my model on Orin. However the qat code provided only support fp16 quantize and trt model transfer. Could you please give me some advertise on how to quantize the model to Int8 and how to convert the int8 model to .engine. Also is it possible for me to use DLA to accelerate the model , any good tutorial for that?

Thanks a lot