-
# Issue Description
Document.ActiveView is not updating after switching views and re-Running scripts.
![image](https://github.com/DynamoDS/Dynamo/assets/22381084/366ea1ed-c32a-4380-aebf-ca47202df01c…
-
# Issue Description
Please fill in the following information to help us reproduce the issue:
## Dynamo version
Dynamo: `2.16.2.5624`
## Operating system
OS: `Microsoft Windows NT 10.0.22631.0…
-
Currently up at ISI and need a version up and available at TACC
-
### 🐛 Describe the bug
Seems like we need automatic dynamic to kick for strides. Or maybe skip strides when size is 1?
```
import torch
@torch.compile(backend="eager")
def fn(x, y):
…
-
# Issue Description
Please fill in the following information to help us reproduce the issue:
## Dynamo version
Dynamo: `2.16.2.5624`
## Operating system
OS: `Microsoft Windows NT 10.0.22631.0…
-
### 🐛 Describe the bug
When attempting to save the inputs to a graph that supports dynamic shapes, torch.save throws a runtime error because it is attempting to call numel() on tensor with symbolic s…
yaxan updated
9 hours ago
-
### 🐛 Describe the bug
Following creates two triton kernels instead of one. In fact the `buf0` is unused.
```python
import torch, itertools
n = 200
a = torch.randn((n, n, n), device='cuda')
…
-
### 🐛 Describe the bug
Usage of "out" syntax in torch APIs like `torch.ge(it, a, out=b)` will cause a crash in TorchDynamo when both of the following conditions hold:
1. Those torch APIs are ins…
-
# Issue Description
Please fill in the following information to help us reproduce the issue: Join 5 parameter of element. The element around 20 k
## Dynamo version
Dynamo: `2.19.3.6394`
## Op…
-
According to [this table](https://huggingface.co/docs/transformers/main/en/quantization/overview#when-to-use-what), `quanto` supposedly works with `torch.compile`. However, I get dynamo errors when tr…