masahi commented on a change in pull request #8622:
URL: https://github.com/apache/tvm/pull/8622#discussion_r681286198
##########
File path: python/tvm/relay/frontend/pytorch.py
##########
@@ -1445,7 +1445,7 @@ def linear(self, inputs, input_types):
# 0 - input
# 1 - weight
bias = inputs[2]
- mm_out = self.matmul(inputs[:2], input_types[:2])
+ mm_out = self.matmul([inputs[0], _op.transpose(inputs[1], axes=(1,
0))], input_types[:2])
Review comment:
Yes, see my comment in the discuss thread above. Until PT 1.8,
`nn.Linear` converts to `aten::addmm`, so this code path never hit unless users
explicitly call something that converts to `aten::linear`. Since PT 1.9,
`nn.Linear` converts to `aten::linear`, so this becomes a major issue.
--
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]
