-
### 🐛 Describe the bug
Here, I ran into this issue trying to export a module with same Tensor in input example for multiple inputs - it seems export() does generate a graph where those inputs are not…
-
### What happened?
For the given IR
```
module {
func.func @main_graph(%arg0: !torch.vtensor, %arg1: !torch.vtensor, %arg2: !torch.vtensor, %arg3: !torch.vtensor, %arg4: !torch.vtensor, %arg5:…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and found no similar bug report.
### Ultralytics YOLO Component
Expo…
-
### What happened?
The following depthwise convolution op (ingested from an onnx model) seems to generate outputs through IREE on cpu differing substantially from the results generated from onnxrunti…
-
Dear all
once again I'm facing an issue when trying to export @heyoeyo's implementation of image_encoder to onnx. I'm using tracing-based exporter, since I wasn't successful with TorchScript and Dy…
-
### What happened?
for the given IR
```mlir
module {
func.func @torch_jit(%arg0: !torch.vtensor, %arg1: !torch.vtensor, %arg2:!torch.vtensor, %arg3:!torch.vtensor, %arg4:!torch.vtensor, %arg5:…
-
### What happened?
for the given IR
```mlir
module {
func.func @main_graph(%arg0: !torch.vtensor, %arg1: !torch.vtensor, %arg2: !torch.vtensor, %arg3: !torch.vtensor, %arg4:!torch.vtensor, %ar…
-
The error message I received when applying `SmoothQuant` to the VIT model is as follows:
`ValueError: Number of values does not match tensor's size. Expected 1, but it is 3072. `
A reproducible co…
-
### Request description
The current onnx-specific intake logic in [PluginRegistration.cpp](https://github.com/iree-org/iree/blob/e2a352c06d41a7e63e892c98c6df350a5d8d16c4/compiler/plugins/input/Torch/…
-
For the given IR, I am getting following error
```
model.torch_onnx.mlir:21:13: error: 'linalg.generic' op inferred input/output operand #1 has shape's dimension #0 to be 12288, but found 512
…