-
# ❓ Questions and Help
Hi guys,
Thanks a lot for the amazing work. I am trying to use `xformers` on CLIP, following the `timm` tutorial I've put together the following code
```python
MODEL_NAM…
-
# 🌟 New model addition
My teammates and I (including @ice-americano) would like to use efficient self attention methods such as Linformer, Performer and Nystromformer
## Model description
The…
-
From https://github.com/pytorch/pytorch/pull/133065#issuecomment-2288701447 . Basically, there was a noticeable performance drop on the inference side after bumping up the HF pin, [dashboard](https://…
-
Hi, This repository helped me a lot. thank you
By the way, I have a question.
Is there a way to do attention only certain parts of the image?
In other words, is there a way to specify the part …
-
# 🐛 Bug
The documentation says one thing that doesn't match the equivalent code:
[equivalent code](https://github.com/facebookresearch/xformers/blob/97cc81f5e4aef5af7202791bd75a7e3fb5a1762e/xfor…
-
Hello,
As per [this line](https://github.com/aqlaboratory/openfold/blob/main/openfold/model/evoformer.py#L649), when neither Deepspeed nor LMA is selected, the custom memory-efficient [kernel](http…
-
### Describe the issue
Hello,
I am encountering an unexpected performance issue while using the MInference library with the Qwen/Qwen2-7B-Instruct model. I have followed the example provided in ru…
-
### 🚀 The feature, motivation and pitch
I'm working on ensembling multiple UNet with the method mentioned in [MODEL ENSEMBLING
](https://pytorch.org/tutorials/intermediate/ensembling.html). This met…
-
WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:
PyTorch 2.3.0+cu121 with CUDA 1201 (you have 2.4.0+cu121)
Python 3.10.14 (you have 3.10.12)
Please rei…
-
> The experimental results under different lengths demonstrate that BurstAttention offers significant advantages for processing long sequences compared with these competitive baselines, especially ten…