mshr-h opened a new issue, #17183:
URL: https://github.com/apache/tvm/issues/17183
### Environment
- TVM@3c7adf
- PyTorch v2.3.1
### Steps to reproduce
repro
```python
import torch
import torch.fx
from tvm.relax.frontend.torch import from_fx
def main():
class PermuteTest(torch.nn.Module):
def __init__(self):
super().__init__()
def forward(self, x):
x = torch.permute(x, (0, 2, 3, 1))
return x
model = PermuteTest()
x = torch.randn(2, 3, 5, 7)
graph_module = torch.fx.symbolic_trace(model)
with torch.no_grad():
mod = from_fx(graph_module, [(x.shape, "float32")])
if __name__ == "__main__":
main()
```
### Triage
Please refer to the list of label tags
[here](https://github.com/apache/tvm/wiki/Issue-Triage-Labels) to find the
relevant tags and add them below in a bullet format (example below).
* needs-triage
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
