This PR adds @MarisaKirisame to the reviewer list of TVM. He has been
contributing to Relay IR, passes, and ADT.
- [Commits](https://github.com/dmlc/tvm/commits?author=MarisaKirisame)
- [Code
Review](https://github.com/dmlc/tvm/pulls?utf8=%E2%9C%93&q=reviewed-by%3AMarisaKirisame)
- [Community En
I would like to know whether dynamic shapes are already supported in a
planned way. I am not familiar with other deep learning frameworks, but without
dynamic shapes, many OP of TF cannot be added, which leads to TVM's narrow
choice of models and lack of generality.
I seem to see some dyn
After I added a new OP in the project when I run the op test wrote by myself,
the error comes out.
I double-checked the params, the data type is right, I don't know why this
error happens.
tvm._ffi.base.TVMError: Traceback (most recent call last):
[bt] (2)
/usr/local/lib/python3.6/
Looks like you passed in a float value into where we expect an integer
---
[Visit
Topic](https://discuss.tvm.ai/t/tvmerror-check-failed-type-code-kdlint-2-vs-0-expected-int-but-get-float/3703/2)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from
I defined my OP in fun(expr, expr, int, int, double, double), and I passed the
params in with corresponding type and shape. Is there any hint for me how to
debug it?
---
[Visit
Topic](https://discuss.tvm.ai/t/tvmerror-check-failed-type-code-kdlint-2-vs-0-expected-int-but-get-float/3703/3)