I think your change it correct, but I'd like to defer to @altanh , he's the one
that implemented this variadic template.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/dfpatternrewritecomposer-addrewrite-with-additional-args-raises-compile-error/12323/2)
to respond.
You are receiving
Hi @lhutton1. That was the intention (it's somewhat safer to do a dataflow
transformation without access to recursion at all), but MixedMode* was
introduced well after TVM became a mature project, and it seems like most
people prefer using the MixedModMutator directly, since the API is closer
Okay, I'm remembering how this works. The issue here comes in the definition of
the domination pattern. In your pattern, the nodes I've circled in green count
as part of the domination, they're in a direct line between conv2d and relu,
but the second inputs to add and multiply are taking data
Ooh, I haven't debugged a problem like this with the pattern matcher in like a
year. :smiley: I thought it was stable. This looks like a bug.
I have some freetime today, I'll try to reproduce and debug.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/question-on-fuzzy-path-matching-mat
https://github.com/apache/tvm/pull/7754
Also managed to fix partitioning Functions with fuzzy bodies :D Skipping that
test has been bothering me for a while.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/pattern-language-matching-a-tuple-with-variable-size/9497/7)
to respond.
You a
https://tvm.apache.org/docs/langref/relay_pattern.html
Docs are here. If you have more detail about what you'd like to do, we might be
able to point you at something more specific.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/relay-analysing-of-relay-graph-and-clone-subggraphs/9482/
[quote="jmatai1, post:5, topic:9307"]
```
if call.op.name =="add":
# save this call for return!
self.return_values.append(call)
super().visit_call(call)
```
[/quote]
:point_down:
```
post = super().visit_call(call)
if post.op.name =="add":
return this `super().visit_call(call)`
---
[Visit
Topic](https://discuss.tvm.apache.org/t/changing-return-of-relay-function-or-irmodule/9307/6)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.ap
Try this:
```
new_body = self.visit(fn.body)
print("Visited all", new_body)
return_values_to_function = relay.Tuple([new_body] + self.return_values)
func = relay.Function(fn.params, return_values_to_function,
fn.ret_type, fn.type_params, fn.attrs)
```
---
[V
When you construct a relay Function, you can wrap multiple output variables in
relay.Tuple and return that as the output of the Function.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/changing-return-of-relay-function-or-irmodule/9307/2)
to respond.
You are receiving this because yo
Ooh, good catch, sorry for this. I mostly left that check in as a debug tool
for developing passes, but you're right, the partitioned graph won't match
anymore if we're doing more specific things, like matching on names, or
possibly matching on types. I think maybe we should just remove the ch
Like a pattern that exists across multiple functions? Yes, we'll need a
FunctionPattern.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/how-to-match-the-pattern-of-a-function-in-relay/8283/21)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe f
The way the API is written, the matcher doesn't traverse you're input graph, it
will return false unless the exact node you supply matches the pattern.
The partition and rewriting functions, however, will traverse the relay
expression, go into functions, and find the match inside your function
@comaniac sounds good, we'll see who gets there first :)
---
[Visit
Topic](https://discuss.tvm.apache.org/t/how-to-match-the-pattern-of-a-function-in-relay/8283/11)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](h
I'm happy to add it, but it will be a couple of days before I can get to it.
Any one else interested in adding the node and some matching tests?
---
[Visit
Topic](https://discuss.tvm.apache.org/t/how-to-match-the-pattern-of-a-function-in-relay/8283/7)
to respond.
You are receiving this b
It will definitely go inside the function to match patterns, but you're right,
we don't have a Function Pattern right now, we should probably add one.
This seems to be a function created by the FuseOps pass. Typically we'd do
pattern rewriting/partitioning before that, maybe there's a simpler
@jwfromm and I did ONNX LSTM a few months ago, and decided to unroll because
the rest of the ONNX importer only support static shapes. We've recently fix
that, and Josh recently implemented ONNX Loop using relay's recursive while
function. We could probably use that experience to go back and t
17 matches
Mail list logo
