Skip to content

Issues: thu-ml/SageAttention

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

37 Open 95 Closed
37 Open 95 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

Sage Attention vs Flash Attention Speed Comparison with Wan 2.1 - Sage Attention is 37% Faster - 720p - 14b model - tested on Windows Python VENV - no WSL
#150 opened Mar 25, 2025 by FurkanGozukara
2
qk_int_sv_f8_cuda_sm90 kernel failed to run on H20
#149 opened Mar 25, 2025 by SimonSongg
4
SageAttention fails to work on RTX 50xx series GPU (e.g. 5090) despite clean venv install
#148 opened Mar 24, 2025 by Teskun
53
I've built Windows wheels
#146 opened Mar 24, 2025 by woct0rdho
1
Is there a C++ callable API available?
#145 opened Mar 24, 2025 by Popping-Lock
1
Can't build wheels - No module named 'torch' .venv Comfy UI- Windows 10
#142 opened Mar 20, 2025 by AdamGman
12
Low accuracy for qk int8 pv fp16 kernel
#141 opened Mar 19, 2025 by SimonSongg
6
Support on CUDA 11.4
#140 opened Mar 18, 2025 by SimonSongg
2
The StableVideoDiffusionPipeline in diffusers has no acceleration effect
#139 opened Mar 14, 2025 by xu15031483273
1
Unsupported CUDA architecture: sm75 with RTX 2080 Ti
#137 opened Mar 13, 2025 by De-M-oN
6
About bench
#136 opened Mar 13, 2025 by jamescsq47
1
Error when trying to install SageAttention - distutils._msvccompiler has no attribute '_get_vc_env'
#132 opened Mar 10, 2025 by Eshinio
4
SageAttention2 will support qo len != kv len with causal?
#131 opened Mar 10, 2025 by yongchaoding
1
Could you please tell me how to solve this problem?
#129 opened Mar 6, 2025 by sywud
1
About masked acceleration
#127 opened Mar 4, 2025 by Harry-Miral
6
Circular Import when using sageattn
#126 opened Mar 3, 2025 by MercuryB1
1
UnicodeDecodeError when trying to build SageAttention
#122 opened Feb 27, 2025 by gzzhongqi
9
Any precompiled wheels for Windows Python 3.10 or 3.11 or 3.12 venv?
#116 opened Feb 22, 2025 by FurkanGozukara
1
sliding window attention enhancement New feature or request
#114 opened Feb 20, 2025 by matthijsvk
1
Compile SageAttention CUDA 12.8, TORCH 2.7.0 - Blackwell
#107 opened Feb 12, 2025 by alisson-anjos
13
sageattn_qk_int8_pv_fp16_cuda black output with pv_accum fp16, results in black screen in opensora
#93 opened Jan 22, 2025 by nighting0le01
10
Error installing SageAttention2 on Ubuntu
#81 opened Dec 26, 2024 by tahseensheik
2
can not install on rtx 6000 passive - turing compute
#78 opened Dec 25, 2024 by Nemesis-the-Warlock
2
Compilation with full CUDA graphs (without breaks) enhancement New feature or request
#74 opened Dec 20, 2024 by bm-synth
18
SageAttention support for vLLM？
#71 opened Dec 16, 2024 by Zachary-ai-engineer
ProTip! Type g i on any issue or pull request to go back to the issue listing page.