You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2022/06/21 17:34:16 UTC
[GitHub] [tvm] AndrewZhaoLuo commented on a diff in pull request #11700: [QNN] Add hardswish int8 impl using table lookup
AndrewZhaoLuo commented on code in PR #11700:
URL: https://github.com/apache/tvm/pull/11700#discussion_r902891338
##########
python/tvm/relay/frontend/qnn_torch.py:
##########
@@ -987,6 +983,21 @@ def hardsigmoid(x):
dequantized_hswish, output_scale, output_zero_point, out_dtype="uint8"
)
+ def _impl_int8(inputs):
+ output_scale = _expr.const(inputs[1])
+ output_zero_point = _expr.const(inputs[2])
+ input_scale = _expr.const(inputs[3])
+ input_zero_point = _expr.const(inputs[4])
+ return relay.qnn.op.hardswish(
+ input[0], input_scale, input_zero_point, output_scale, output_zero_point
Review Comment:
this should be `inputs[0]` not `input[0]`
--
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.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org