-
### Feature request
PagedAttention has been a mainstream optimization technology for generation task based on LLMs. It has been supported by a lot of server engines, e.g., [vllm](https://github.co…
-
### Checklist
- [X] The issue exists after disabling all extensions
- [X] The issue exists on a clean installation of webui
- [ ] The issue is caused by an extension, but I believe it is caused b…
-
Hello! @JunzheJosephZhu It's an excellent work of multimodal robot learning.
I'm confused about how to normalize the attention scores across all modalities. I would appreciate it if you could prov…
-
We are building [Refiners](https://github.com/finegrain-ai/refiners), an open source, PyTorch-based framework made to easily train and run adapters on top of foundational models. Just wanted to let yo…
-
Thank you for sharing such a nice work.
I have some questions.
(1) What is the meaning of self.pre_assign_attn? Has it been described in the paper?
https://github.com/NVlabs/GroupViT/blob/b4ef51b8a…
-
Every extension works fine except this one, its just the default webui code i didnt change anything
```
/notebooks/stable-diffusion-webui
Patching transformers to fix kwargs errors.
Dreambooth A…
-
**Describe the bug**
Model I am using (trocr-base-stage1.pt, trocr-base-printed.pt etc. TrOCR pretained models):
The problem arises when using:
pic_inference.py
A clear and concise descriptio…
-
I want to quantize model from [open-flamingo](https://github.com/mlfoundations/open_flamingo) or https://github.com/open-mmlab/Multimodal-GPT (open-flamingo v1) before lora training,
https://github…
-
Here is a black box and I want to change its color to red,
but changing color al…
-
```
import math
import pytest
import torch
import triton
import triton.language as tl
# from triton.runtime.interpreter import TensorHandle
@triton.jit
def _fwd_kernel2(
Q,
K…