Skip to content

Issues: facebookresearch/xformers

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

289 Open 288 Closed
289 Open 288 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

memory_efficient_attention faster than flash attention 2 backend?
#1180 opened Dec 19, 2024 by asahni04
[AMD GPU] NotImplementedError: No operator found for memory_efficient_attention_forward with inputs
#1175 opened Dec 15, 2024 by Looong01
3
Does Xformers offer any extra speed over PyTorch anymore? And why is my Xformers file so big?
#1174 opened Dec 14, 2024 by Mescalamba
3
xformers on nvidia jetson orin agx
#1173 opened Dec 12, 2024 by obliviate1230
3
More precise Errors and logger warnings for failing to import triton
#1170 opened Dec 3, 2024 by b-burton
1
visual studio 2022,cuda 12.4 ,but it still can't build the wheel, and return this
#1161 opened Nov 22, 2024 by zslefour
2
Incompatibility Between xformers FA3 Torch Custom op Wrapper and recent flashattn_hopper_cuda
#1159 opened Nov 21, 2024 by ohwi
1
5
Generalize SwiGLU related python code
#1158 opened Nov 21, 2024 by warpuv
1
need to release xformers-0.0.28.post3.whl with manylinux2014_x86_64 os version.
#1155 opened Nov 19, 2024 by controlRun
1
Customization of BlockDiagonalMask or LowerTriangularMask
#1147 opened Nov 13, 2024 by kc334
build without flash attn?
#1145 opened Nov 7, 2024 by sipie800
1
How to install to aarch64
#1142 opened Nov 4, 2024 by gongchangsui
1
vllm 0.6.3 createLLM error TypeError: autotune() got an unexpected keyword argument 'use_cuda_graph' on windows
#1138 opened Oct 30, 2024 by xiezhipeng-git
4
incorrect causal mask in global attention
#1135 opened Oct 22, 2024 by davidqqq
1
1
Cant use powershell command to build for Nightly PyTorch on Win - filename too long
#1132 opened Oct 22, 2024 by Mescalamba
5
Is there an efficient way to use memory_efficient_attention with a causal mask that has a small rectangle of zeros?
#1131 opened Oct 22, 2024 by arilato
1
xformers 0.0.20 memoery efficient attent cutalss backward non deterministic
#1128 opened Oct 13, 2024 by Bavesh-B
xformers.sparse.utils._coo_to_csr is incorrect when n > m
#1125 opened Oct 11, 2024 by francois-rozet
Incorrect attention output with SparseCS mask
#1124 opened Oct 10, 2024 by francois-rozet
1
Add support for CUDNN attention via CUDNN_FRONTEND Python API?
#1123 opened Oct 10, 2024 by Skylion007
[Bug] Unexpected behavior of memory_efficient_attention with BlockDiagonalMask
#1122 opened Oct 10, 2024 by xiangxu-google
1
Does memory efficient attention cutlass kernel support various seq len inputs for q/k/v + tensor bias?
#1120 opened Oct 4, 2024 by ShijunK
Why xformers 0.0.28.post1 doesn't have pre-compiled wheel for Windows?
#1118 opened Oct 1, 2024 by FurkanGozukara
8
I tried upgrade visual studio,cuda 12.4 and 12.6,but it still can't build the wheel,and return this
#1117 opened Sep 29, 2024 by neutronslime
5
scaled_dot_product_attention output is different from memory_efficient_attention
#1114 opened Sep 25, 2024 by aenoca
1
ProTip! Find all open issues with in progress development work with linked:pr.