tqchen commented on code in PR #16757:
URL: https://github.com/apache/tvm/pull/16757#discussion_r1536660431
##########
python/tvm/relax/frontend/nn/exporter.py:
##########
@@ -121,7 +122,6 @@ def _effects() -> typing.List[typing.Tuple[str,
core.Effect]]:
outputs = _emit_effect_init(self.builder, effects)
self.builder.emit_func_output(outputs, params=[])
for method_name, method_spec in zip(spec.method_names,
spec.method_specs):
- params = _params() # Re-initialize so symbolic shapes not
shared across methods
Review Comment:
i also agree that the original logic was simpler. The intermediate
computation sharing was a mechanism that we would like to introduce, would be
good to discuss alternative ways to achieve the same goal. E.g. defining a
seperate parameter mapping function explicitly rather than having things
implicitly
--
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]
