Skip to content

Issues: thu-ml/SpargeAttn

Beta
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

20 Open 32 Closed
20 Open 32 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
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Support LM decoding
#59 opened Jun 5, 2025 by Cecilwang
Flux Error
#58 opened May 28, 2025 by wavetao2010
Unable to Generate Videos with CogVideoX1.5-5b + SparseAttn (Output is Fully Black)
#55 opened May 11, 2025 by rickyxie2004
I have some questions on evaluate/modify_model/modify_hunyuan.py
#54 opened May 7, 2025 by Crazek-CZA
2
FLUX Hyperparameter
#53 opened May 4, 2025 by riDuxd
3
how long does it take to tune flux model without parallel?
#50 opened Apr 28, 2025 by Crazek-CZA
12
Speed up warm up
#49 opened Apr 28, 2025 by yinfan98
3
cannot install correctly
#48 opened Apr 25, 2025 by artetaout
8
Discrepancies in SparseAttentionMeansim Results
#47 opened Apr 23, 2025 by tobygh
2
[Feedback] Test Results
#36 opened Apr 9, 2025 by Ethkuil
2
RuntimeError when enable usp + sparse_attn in wan2.1
#34 opened Apr 7, 2025 by Eigensystem
Tried WAN video but the quality loss was severe
#33 opened Apr 3, 2025 by Popping-Lock
13
Hilbert Curve implementation
#32 opened Apr 1, 2025 by jzhang38
1
HunyuanVideo pre-tuned hyper-parameters
#29 opened Mar 28, 2025 by aliabougazia
1
Has it been adaptedto Deepseek MLA
#28 opened Mar 28, 2025 by darrenyao87
triton error
#27 opened Mar 27, 2025 by Leonisux
2
Hi Want to tune it for my video Model for Image to Video Usecase.
#24 opened Mar 20, 2025 by nighting0le01
4
Support For Qwen Model?
#23 opened Mar 19, 2025 by vefalun
1
Do you have any use cases for the StableVideoDiffusion Pipeline in diffusers? It's very necessary. Can you provide them
#21 opened Mar 13, 2025 by xu15031483273
1
support for flux
#2 opened Feb 27, 2025 by algorithmconquer
9
ProTip! Adding no:label will show everything without a label.