I’m trying to implement a lowering of pytorch’s quantize_per_tensor  to TOSA.
quantize_per_tensor is specified  using round , which is specified to “round half to even”.
I seem to be unable to find a TOSA operator with “round half to even” behavior" (CAST seems to be “round toward zero”), so I cannot get an accurate lowering.
 Sorry, can only put two links as a new user
 Quantization — PyTorch master documentation (glaringlee.github.io)
 torch.round — PyTorch 1.13 documentation