-
### š Describe the bug
```
import torch
model = torch.nn.EmbeddingBag(num_embeddings=49157, embedding_dim=32, mode="sum")
a = torch.tensor([[39906]]).long()
example_args = (a,)
model_eval = moā¦
-
### Describe the issue
The CPU implementation of LayerNormalization occasionally produces `nan` when computing the square root of variance. This occurs when the input variance is extremely small, pā¦
-
### Describe the issue
### Observation
A lot of CMake configuration given back to `build.py` file.
https://github.com/microsoft/onnxruntime/blob/main/tools/ci_build/build.py#L1000-L1099
Final assetsā¦
mc-nv updated
1 month ago
-
### Describe the issue
Just saw this error on our logs, I've to investigate how to reproduce:
[E:onnxruntime:, sequential_executor.cc:516 ExecuteKernel] Non-zero status code returned while runningā¦
-
### Describe the issue
When trying to benchmark bert model with latest ZenDNN release, I'm facing the similar degradation issue with this issue: https://github.com/amd/ZenDNN-onnxruntime/issues/5. Anā¦
-
### Describe the issue
the CXX wrapper cause sanitizer error and segfault...
this is cause many unexpected behaviors until I enabled the address sanitizer.
### Urgency
Yes since I'm blocked on aā¦
DxUr updated
4 months ago
-
### š Describe the bug
I am trying to convert the well renowned [LAMA Inpainting](https://github.com/advimman/lama) model to ONNX via the new dynamo_export, as earlier these fft_rfftn were not suppā¦
-
Hello,
I'm trying to figure out how to use the trt_int8_use_native_calibration_table option, but I can't find any examples or documentation that explain how to do so.
I generated a TensorRT INTā¦
-
### Describe the issue
This line assumes that there are at least 256 thread per thread block:
if (tid < 256) H[tid] = 0;
https://github.com/microsoft/onnxruntime/blob/main/onnxruntime/core/prā¦
-
### Describe the issue
I have been customizing yolov8 in order to port on hardware. I customised SPFF block in yolov8 architecture:- I have changed the shape of maxpool layer from 5*5 to 3*3 shape.ā¦