Kushagra-88 comments

Repositories
Issues
Comments

Results 2 comments of


                                            Kushagra-88

[Bug] Constant folding cannot process onnx model correctly: InternalError: Check failed: pb->value != 0 (0 vs. 0) : Divide by zero

For relax.build() to work properly, it expects the model to be lowered to TensorIR before compilation. Before calling relax.build(), add this transformation: tvm_model = relax.transform.LowerToTensorIR()(tvm_model) It should work.

Does `torch_mlir.compile` exist now?

I am facing the same issue.. Is there something i am missing?