anijain2305 commented on a change in pull request #4977: [Torch, QNN] Add
support for quantized models via QNN
URL: https://github.com/apache/incubator-tvm/pull/4977#discussion_r386563528
##########
File path: python/tvm/relay/frontend/pytorch.py
##########
@@ -146,6 +149,10 @@ def _impl(inputs, input_types):
def _relu():
def _impl(inputs, input_types):
data = inputs[0]
+ if input_types[0] == "quint8":
+ assert len(inputs) == 3, "Input quant param not found in op inputs"
+ input_zero_point = _expr.const(inputs[2])
Review comment:
Do you want to add a datatype "int32" here?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
