-
Code:
```python
torch._dynamo.config.suppress_errors = True
self.pipe = OotdPipeline.from_pretrained(
MODEL_PATH,
unet_garm=unet_garm,
unet_vton=unet_vton,
vae=vae,
torch…
-
### Your current environment
```text
PyTorch version: 2.3.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04.3 LTS (x86_64)
GCC vers…
-
Hi,
I'm using the "new" app from the store (thanks for getting it there!) at the moment but the same happened with the one I installed with the developer mode. My LG C9 is running the latest WebOS …
zsohu updated
6 months ago
-
### 🐛 Describe the bug
Using ```torch.sigmoid``` on a tensor of negative complex numbers result in nan for cpu. For sigmoid, large negative numbers should result in 0, which it does in the cuda versi…
-
### Describe the bug
I have a movie file with the following information (from MediaInfo). It is direct playing to AppleTV. The issue I am having is the TV is going to a black screen approximately e…
-
### Your current environment
PyTorch version: 2.1.2+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
OS: Debian GNU/Linux 11 (bullseye) (x86_64)
GCC…
-
### Describe the bug
My benchmark code is here: https://github.com/chsasank/device-benchmarks. Installed IPEX version 2.1.40+xpu and reran benchmarks now
```
(ipex) sasank@arc-reactor:~/device-be…
-
### 🐛 Describe the bug
```
import torch
import torch.nn.functional as F
def test_log_softmax(device):
print(f"Testing on {device}")
input_tensor = torch.randn(3, 4, 5, device=device)…
-
### Motivation: Why do you think this is important?
when we pass df to and from flyte tasks - is there any native way to ask Flyte to do sampling as its reading and writing the data?
eg i sometimes …
-
I'm trying to use rrweb to record user sessions and replay them back at a later time. Unfortunately, when replaying the application, certain elements are repeated an enormous number of times, covering…