When I run the example as the blog
says.[https://tvm.apache.org/2020/06/04/tinyml-how-tvm-is-taming-tiny](https://tvm.apache.org/2020/06/04/tinyml-how-tvm-is-taming-tiny)I
can't find directory'device' in tvm/micro,therefore I am not able to import
the moudles as the example says.What should I
relay has support for recursion, pattern matching, conditional. with them you
can define lstm.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/how-to-use-relay-control-flow/8243/5)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these ema
your
https://tvm.apache.org/docs/tutorials/micro/micro_tflite.html#sphx-glr-tutorials-micro-micro-tflite-py
-- micro_tflite.ipynb is incomplete
even adding
!pip install tflite==2.1.0 --user
!pip install tvm
!set PYTHONPATH to /usr/local/lib/python3.6/dist-packages/tvm-1.0.0.dist-info
that we
Could you please share your ios project for study?
---
[Visit Topic](https://discuss.tvm.apache.org/t/tvm-ios-deployment/1977/8) to
respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.apache.org/email/u
Hi,
I've been looking at [Bring Your Own Codegen to
TVM](https://tvm.apache.org/docs/dev/relay_bring_your_own_codegen.html) and
understand how it interacts with the TVM C++ Runtime.
Any suggestions or pointers on making a custom codegen work with the TVM C
Runtime?
Thanks!
Ajay
---
[Vi
The output is expected. The API `list_tags` lists the existing tags that have
been registered to the system, not the target used in the current scope - in
this case, I believe you are looking for Target.current().
If the document of list_tags is confusing, would you like to send a PR to
clari
When I use target.list_tags(), It always says cuda. I have however set cuda
flag off while making tvm and in the code I've written target='llvm'. What is
the possible cause of this?

---
[Visit
Topic]
Does auto-tune work for you? It seems that I have similar error
---
[Visit
Topic](https://discuss.tvm.apache.org/t/relay-cuda-error-invalid-value-occurs-when-testing-conv2d-grad/4022/6)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these em