I believe those parameters have been changed.
https://github.com/facebookexperimental/tvm/commit/f55609b4a19ed7166d9b4dbbee4acd48af3697ac#diff-671adc633fba88046d0863b931de9c75e57627706387f1cf98a207616ee62e27
Unfortunately the tutorial hasn't been updated to reflect this as of now.
---
[Vis
Thanks for your quick response and fix!
---
[Visit
Topic](https://discuss.tvm.apache.org/t/mergecomposite-error-when-defining-custom-pattern/8505/5)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.t
This is certainly interesting. I think the behavior depends on the
debug/release and whether the symbol is inlined. This is indeed a problem that
we can see in a few places. The simplest thing is to re-assign a local var
before use
---
[Visit
Topic](https://discuss.tvm.apache.org/t/ci-c-
https://tvm.apache.org/docs/api/python/relay/nn.html#tvm.relay.nn.dense
Can someone explain to me what `units` is supposed to represent here? I'm
implementing my own `nn.dense` function to be lowered from Relay IR, and I'm
unsure what this attribute is supposed to be used for. For context, my
So if you look at :
https://github.com/apache/incubator-tvm/blob/main/src/runtime/micro/micro_session.cc
You can see that there is a : static constexpr const size_t
kReceiveBufferSizeBytes = 128;
which is declared but not defined and used directly below as an argument which
leads to linking
Make sense. PR filed:
https://github.com/apache/incubator-tvm/pull/6958
---
[Visit
Topic](https://discuss.tvm.apache.org/t/mergecomposite-error-when-defining-custom-pattern/8505/4)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails
I think so, we only compile with std=c++14, so it should fail on new things
that are in c++17
---
[Visit
Topic](https://discuss.tvm.apache.org/t/ci-c-standard-for-the-tvm-project/8508/2)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these
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
This is an interesting case and thanks for pointing out. I investigated it a
bit and identified that this is not the problem of MergeComposite but the
pattern partition. Specifically, you can reproduce this problem by replacing
`assert test_pattern.match(r) # True` with `assert test_pattern.pa
Hi All,
I had a go at it implementing the some of the discussed changes :
https://github.com/apache/incubator-tvm/pull/6950.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/external-modules-in-utvm/7993/13) to
respond.
You are receiving this because you enabled mailing list mode.
To
Hi @582990,
Every operator of a convolutional networks is implemented through one or more
strategies (strategy=compute+schedule). Every strategy needs to be tuned and
represents a "task". If a strategy defines no knobs, the tuning of that
strategy will be a nop.
To reduce the number of task
Are we using c++ std14 or std17 for the tvm project ?
>From what I can tell, it looks like std14.
If so, is the CI expected to fail on C++17 only features ?
cc : @tqchen
---
[Visit
Topic](https://discuss.tvm.apache.org/t/ci-c-standard-for-the-tvm-project/8508/1)
to respond.
You are rec
Hi,
I want to define a custom pattern, and then use the MergeComposite function,
but I met some problem.
The pattern I defined is a sequence of nested ops including reshape,add,...My
question is that why I got error when passing the is_var pattern to the
callback of is_op, but it is fine wi
13 matches
Mail list logo
