masahi commented on code in PR #13578:
URL: https://github.com/apache/tvm/pull/13578#discussion_r1043841295
##########
python/tvm/relay/transform/fake_quantization_to_integer.py:
##########
@@ -502,6 +502,33 @@ def register_binary_qnn(op_name, op):
def binary(expr, type_map):
left, right, left_t, right_t, out_t = get_binary_types(expr, type_map)
+
+ if (
+ approx_equal(left_t.scale, right_t.scale)
Review Comment:
But right, this code path is only meant for catching 32 bit `add` used as
bias addition. I'll update the condition to catch only this case.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
