OK! Thank you for reply.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/how-to-run-module-with-hexagon-simulator-sim-dev/7946/4)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.apache.org/em
@asdlalala make sure and check out the [new GPU auto-scheduler tutorial
PR](https://github.com/apache/incubator-tvm/pull/6512) that @merrymercy just
put up. It still doesn't support full models yet to my knowledge (full
integration with Relay is coming next) but this should enable you to optim
First of all, I would like to thank the TVM developers for the implementation
of 3d operations such as 3D convolutions. This feature is very much appreciated
by 3D CNN users like me.
I am contacting you because of the lack of support for group convolutions. For
example, if you try to import a
Yes, @FrozenGene is correct. At the moment, only offload is suported (via
`pipeline` attribute). Running entire models is on our roadmap, but there
aren't any specific dates when this functionality will be available.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/how-to-run-module-w
If i remember correctly, we still not support relay e2e on hexagon, right?
@kparzysz
---
[Visit
Topic](https://discuss.tvm.apache.org/t/how-to-run-module-with-hexagon-simulator-sim-dev/7946/2)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from
I try to execute tvm graph with hexagon sim! But I get some error!
I have change
`set(USE_HEXAGON_DEVICE sim) `
`set(USE_HEXAGON_SDK /home/wang/Qualcomm/Hexagon_SDK/3.5.2)`
```python
with tvm.transform.PassContext(opt_level=1):
with tvm.target.hexagon("v60", hvx=128) as target:
