Anton
Anton
Tried running it locally and now I have this weird log with `matmul` example, which I didn't have on Lambda node with H100. Same log gets produced with changes in...
I ran the code and got a similar error message. Correct me if I'm wrong: I think the problem is in how Torch‑MLIR’s FxImporter (and underlying TorchDynamo integration) currently handles...
@JibAxelera I think it should be in the scope of torch-mlir, since semantically your code above is acceptable for PyTorch. I wouldn't mind implementing this feature myself.
This sounds interesting - I would like to implement it. Can this issue be assigned to me?
I had a similar problem with setting up WSL - the problem turned out to be that the mlir_venv and Ubuntu were referencing different `PYTHONPATH` ? In other words, WSL...