@ZihengJiang @tqchen @jroesch @MarisaKirisame @yidawang @zheng-da @ajtulloch
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/issues/3731#issuecomment-519361871
### Motivation
With new sparse operators being added to TVM on a weekly basis, we would like
to propose a change that would address the lack of expressiveness in sparse
tensors of the current relay type system.
Currently, we represent a CSR matrix with `namedtuple("CSR", ["data",
"indices
I'm trying to add my own OP in relay.
Here is an existing function, but I can't understand it. Does anyone give me
some hints?(tvm/src/relay/op/vision/nms.cc)
bool GetValidCountRel(const Array& types,
int num_inputs,
const Attrs& attrs,
[quote="MarisaKirisame, post:6, topic:3595"]
upstream
[/quote]
Awesome！！！
Thanks very much！！！:+1:
---
[Visit
Topic](https://discuss.tvm.ai/t/relay-concatenate-downcast-from-relay-reftype-to-relay-tensortype-failed/3595/8)
to respond.
You are receiving this because you enabled mailing lis
> - [ ] graph level automated optimization
Does it mean traditional fusion / layout transform, or more recent graph
substitution like [this paper](https://www.sysml.cc/doc/2019/22.pdf)? If the
later one, I would like to port my onnx implementation to TVM.
--
You are receiving this because you
@Ruinhuang see https://github.com/dmlc/tvm/pull/3729.
---
[Visit
Topic](https://discuss.tvm.ai/t/relay-concatenate-downcast-from-relay-reftype-to-relay-tensortype-failed/3595/7)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [c
@Ruinhuang I fixed it in add_grad, will upstream rn.
---
[Visit
Topic](https://discuss.tvm.ai/t/relay-concatenate-downcast-from-relay-reftype-to-relay-tensortype-failed/3595/6)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [cl
maybe I'm missing some context. would you mind give an example?
---
[Visit
Topic](https://discuss.tvm.ai/t/discussion-adding-a-function-to-relay-module-automatically-triggers-infertype/3643/2)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from t
TVMError:
Error(s) have occurred. The program has been annotated with them:
In `main`:
v0.0.3
fn (%input: Tensor[(2, 3), float32], %input1: Tensor[(3, 3), float32]) ->
(Tensor[(5, 3), float32], (Tensor[(2, 3), float32], Tensor[(3, 3), float32])) {
%0 = fn () -> () {
