zhaoyang-star commented on code in PR #12116:
URL: https://github.com/apache/tvm/pull/12116#discussion_r925302150
##########
python/tvm/relay/qnn/op/qnn.py:
##########
@@ -1179,7 +1179,7 @@ def batch_matmul(x, y, x_zero_point, y_zero_point,
x_scale, y_scale, out_dtype="
reg.register_pattern("qnn.dequantize", OpPattern.OPAQUE)
-def leaky_relu(x, alpha, scale, zero_point):
+def leaky_relu(x, alpha, scale, zero_point, output_scale, output_zero_point):
Review Comment:
Done
##########
src/relay/qnn/op/leaky_relu.cc:
##########
@@ -32,8 +32,8 @@ namespace qnn {
bool QnnLeakyReluRel(const Array<Type>& types, int num_inputs, const Attrs&
attrs,
const TypeReporter& reporter) {
- // Expected Types: data, scale, zero_point
- ICHECK_EQ(types.size(), 4);
+ // Expected Types: data, scale, zero_point, output_scale, output_zero_point,
out_type
Review Comment:
Done
--
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]
