-
`aten.constant_pad_nd.default` currently does not support lowering to `ttnn.pad` if its input rank > 4
Throws `TT_THROW Tensor rank is greater than 4`
btw, there's no rank > 4 case in models, so I th…
-
# ComfyUI Error Report
## Error Details
- **Node Type:** Echo_Sampler
- **Exception Type:** NotImplementedError
- **Exception Message:** Could not run 'torchvision::nms' with arguments from the 'C…
-
Tuning checkpoint from ./dfine_l_obj365_e25.pth
Load model.state_dict, {'missed': ['decoder.denoising_class_embed.weight'], 'unmatched': ['decoder.enc_score_head.weight', 'decoder.enc_score_head.bias…
-
### 🐛 Describe the bug
Under specific inputs, `reflection_pad1d` triggered a crash.
```python
import torch
self = torch.full((9, 7, 9, 9,), 1e+13, dtype=torch.double)
padding = [-1, -1]
torch.…
-
should be handled more gracefully
```
(garak) leon@blade:~/dev/garak$ python3 -m garak -m huggingface -n gpt2 -p dan
garak LLM security probe v0.9.post4 ( https://github.com/leondz/garak ) at 202…
-
Exporting the operator 'aten::scaled_dot_product_attention' to ONNX opset version 18 is not supported.
-
Hi,
I just upgraded to executorch 0.4 and ran my code which previously failed as described in
https://github.com/pytorch/executorch/issues/1350
Now it fails with
```ConstraintViolationError```…
-
### 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
Trai…
-
## ❓ Questions and Help
2024-03-08 21:33:06,932 maskrcnn_benchmark INFO: Using 1 GPUs
2024-03-08 21:33:06,932 maskrcnn_benchmark INFO: AMP_VERBOSE: False
DATALOADER:
ASPECT_RATIO_GROUPING: True
…
-
### 🐛 Describe the bug
CPU time as below,
```
override aten::sum 2.52% 24.765ms 4.07% 39.978ms 60.849us
non-override aten::sum 4.49% …