-
### Search before asking
- [x] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and found no similar bug report.
### YOLOv8 Component
Integrations, Other
###…
-
Hi. Thanks for the great work.
Why is the pos_enc in cross-attention only used for the keys, and not the queries? (see config files)
```
pos_enc_at_cross_attn_keys: true
pos_enc_at_c…
-
This issue is to track the new design required for flash-attention on bottom-up optimization pipeline.
## Status
The most of the optimization passes has been finished and been checked in llvm-targ…
-
First, give a thumbs up to your work. But I have a question. The paper mentions decomposing cross attention into space and channels. What is the difference between these two and why is it called space…
-
Hey folks, I have no time to maintain this library. If anyone wants to take over, I'm ready to give commit access.
One condition: a pull request solving a bug or adding a feature. Send a meaningful…
gch1p updated
2 weeks ago
-
I wrote a helper that allows someone to use CuDNN attention within Pytorch seamlessly.
```python
import cudnn
import torch
import math
# export CUDNN_FRONTEND_LOG_FLIE=fe.log
# export CUDNN_…
-
I am requesting that you merge with the upstream flash-attention repo, in order to garner community engagement and improving integration and distribution.
This separation is a major blocker to AMD …
-
https://github.com/ParadoxZW/LLaVA-UHD-Better/blob/main/llava_uhd/adapt_llava.py#L136-L138
这里由于The first token is for CLS,是不是需要把
```python
m[:w * h] = True
```
改成
```python
m[:w * h+1] = …
-
-
### Describe the bug
> RuntimeError: The size of tensor a (154) must match the size of tensor b (2304) at non-singleton dimension 1
### Reproduction
```python
# StableDiffusion3Pipeline
pipe.enab…