Luo shiyong

have you solove this question? i had met same problem

i try to ignore the concat amax fusion process and success to get onnx partrial_quant model, but it can not convert to tensorrt model,


i also want know how to remove the qdq node and get a cache file ,in onnx_utils.py just through"node.output[0] == node_name" so how it works ? "hi, directly build quantized...