-
Hi, converting a model that uses `nn.RMSNorm` does not work:
```python
class RMSNormModel(nn.Module):
def __init__(self):
super().__init__()
self.norm = nn.RMSNorm(3, 0.1)…
-
internal xref: https://fb.workplace.com/groups/1075192433118967/permalink/1516427078995498/
repro:
```
import torch
@torch.compile
def f(x, y):
return torch.index_select(x, 0, y)
x = …
-
env:
torch.__version__ = 2.0.1+cu118
onnx.__version__ = '1.16.0'
command:
python cosyvoice/bin/export_onnx.py --model_dir $dir
error logs:
/root/miniconda3/envs/cosyvoice/lib/python3.8/site-pac…
-
We currently "fudge" autograd.Function by running through the forward as if it was the function and rely on the differentiation of that to work.
(This is not good when there is `.detach()` or some su…
-
## Summary
I think there is an issue with the support of "torch.where" within "compile_torch_model".
Torch.where is expecting a bool tensor for the "condition" parameter, while "compile_torch_mode…
-
### 🐛 Describe the bug
torch.export.export fails to trace through a binary operator.
Here is the failing code
```python
import torch
class MyTensor:
def __init__(self, tensor):
…
-
I found from onnxruntime-directml==1.15, mask outputs are diffrent and incorrect between directml and onnxruntime.
I used detectron2 Mask r-cnn.
In python onnxruntime-directml==1.14.1 is ok, and in…
-
## ❓ Question
I'm trying to run the `examples/dynamo/vgg16_fp8_ptq.y` example but got following error:
```
Traceback (most recent call last):
File "/home/wh/generative_action/SynHSI/vgg_quat.p…
-
If you try to use these classes in a differentiable manner (i.e. backward passes during training), and on GPU - they will both fail with errors like the following:
```
File "/home/crow/repos/praxi…
-
Can you please share .onnx file , because I obtain this error :
`Traceback (most recent call last):
File "/home/ubuntu/Desktop/loftr2onnx-main/convert_to_onnx.py", line 102, in
main()
…