how to fuse QuantizeLinear Node with my custom op when convert onnx to trtengine

[AnnaTrainingG]

how to fuse QuantizeLinear Node with my custom op when convert onnx to trtengine
I find that the QuantizeLinear will be called like:

it cost long time, How to fuse it with my custom kernel before QuantizeLinear node. the compute in QuantizeLinear is what ?
like:
my_custom_op - Q -- DQ --- Conv. fuse to => my_custom_op_with_Q --- (DQ_Conv)

[lix19937]

First , you need use --best to check whether your model fusion case match your expected goal.
Then, fusion the scale in your plugin.