-
### Bug description
If I register a `float64` tensor to a buffer in the `__init__` function of a `LightningModule` like so:
```py
self.register_buffer("testing_variable", torch.tensor([1,2,3], …
-
### 🐛 Describe the bug
I have more details in [this colab notebook](https://colab.research.google.com/drive/1lf8RjX2p5F4E3MzN_blbRICughqHkSJP?usp=sharing), but the issue has to do with a specific seq…
-
!pip install --upgrade pip setuptools wheel
# Update the package list
!apt-get update
# Install build tools and other dependencies
!apt-get install -y build-essential cmake pkg-config
!apt-get …
-
### 🐛 Describe the bug
CamemBert float32 static shape default wrapper multiple threads inductor_max_autotune backend accuracy failure
```
Traceback (most recent call last):
File "/workspace/pyto…
-
### Bug description
Got
**RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:1 and cuda:0! (when checking argument for argument index in method wrapp…
-
### 🐛 Describe the bug
I am following this example to perform inference on TorchServe with a torch-tensorrt model: https://github.com/pytorch/serve/tree/master/examples/torch_tensorrt
I am using a…
-
### 🐛 Describe the bug
I am not sure this is a bug but it is a major performance issue and there seems to be no suitable issue category for that.
Torch dataloaders are the natural entry point fo…
-
### 🐛 Describe the bug
My repro:
```
import torch
from torch._subclasses.fake_tensor import FakeTensorMode
from torch.utils._mode_utils import no_dispatch
fake_mode = FakeTensorMode()
with …
-
### 🐛 Describe the bug
While Dynamically post-training quantized the following linear model:
```python
class Net(nn.Module):
def __init__(self):
super().__init__()
self.layer = n…
-
### Your current environment
```text
Collecting environment information...
WARNING 09-19 10:19:04 _custom_ops.py:14] Failed to import from vllm._C with ModuleNotFoundError("No module named 'vllm.…