mbaret commented on pull request #5689:
URL: https://github.com/apache/incubator-tvm/pull/5689#issuecomment-635665317
It's not really the case that old merge composite explicitly 'lifts'
constant nodes if they're vars, in old merge composite vars indicate inputs to
the pattern (so they
mbaret commented on pull request #5689:
URL: https://github.com/apache/incubator-tvm/pull/5689#issuecomment-635650558
Try changing w in the pattern to a relay.const rather than a var.
This is an automated message from the
mbaret commented on pull request #5689:
URL: https://github.com/apache/incubator-tvm/pull/5689#issuecomment-635640183
```
%2 = fn (%input: Tensor[(1, 224, 224, 3), uint8], Composite="qnn_conv2d") ->
Tensor[(1, 224, 224, 64), uint8] {
%0 = qnn.conv2d(%input,
mbaret commented on pull request #5689:
URL: https://github.com/apache/incubator-tvm/pull/5689#issuecomment-635633008
Thanks for the PR so soon! Is there an example of how partition works on a
constant match? In particular, does the constant remain propagated into the
body?
On a
