-
Building CUDA layers fails with the following error when running `python setup.py install` from inside the `pointnet2` directory:
```
running install
running bdist_egg
running egg_info
creating…
-
**torch-mlir version**: 20230705.890
**pytorch version**: 2.1.0.dev20230704+cpu
The following pytorch model compilation failed
```python
import torch
import torch_mlir
class Model(torch.…
-
untimeError: 0INTERNAL ASSERT FAILED at "/opt/conda/conda-bld/pytorch_1634272178570/work/torch/csrc/jit/ir/alias_analysis.cpp":584, please report a bug to PyTorch. We don't have an op for aten::leaky_…
-
**Describe the issue**:
I use TaylorFOWeightPruner to prune mT5_base model, but the errors happened when speed up model.
pruner = TaylorFOWeightPruner(attention_pruned_model, ffn_config_list, evalua…
-
/home/cv/TensorRT-8.4.1.5.Linux.x86_64-gnu.cuda-11.6.cudnn8.4/TensorRT-8.4.1.5/include/NvInfer.h:3281:22: note: declared here
class TRT_DEPRECATED IRNNv2Layer : public ILayer
…
-
## Bug Description
When replacing the view nodes with reshape nodes, the metadata of the original view nodes, are assigned to the reshape nodes in the wrong order.
For example, assume we have 2…
-
### Describe the issue
When I run a seq2seq model, it returned errors:
/home/ypd-24-stu-9/anaconda3/envs/Ort/lib/python3.9/site-packages/onnxruntime/training/ortmodule/_training_manager.py:190: Us…
-
fft_r2c does not support dynamic shapes:
```python
import torch
class STFTModel(torch.nn.Module):
def __init__(self):
super().__init__()
self._window = torch.hann_windo…
-
### 🐛 Describe the bug
PyTorch dispacthing non core ATen ops in .compile mode for torch ops.
Same non core ATen ops are observed as part of our backend.
**List of non core ATen ops observed are:…
-
### Discussion
- [X] Yes, and I still want to report a bug
### What type of Synergy user are you?
Customer
### Support ticket number (for customers)
Ticket \#182960
### Product name
…