Pinokio
Feed
Apps
Remote
Create
App
github-com-thu-ml-spargeattn
x
Search
Download Pinokio
Switch to dark mode
Sign in
Create account
Join
Switch to dark mode
Sign in
Create account
Join
SpargeAttn
Share
github.com/thu-ml/spargeattn
Updated 8mo ago
[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
Follow
1
Loading project owner…
Projects using this repository
No references listed yet.
Check-ins
0
Feed
Dev
Check-ins
(0)
Community
Search this app
Sort by
Recent activity
Newest
Top: Past day
Top: Past week
Top: Past month
Top: Past year
Top: All
Create post
Ask or share about SpargeAttn…
Loading...
Feed
Apps
Create
Remote
Recent commits
reduce repo size
Jintao Zhang
9 months ago
ae5b629
Add new article reference for SpargeAttention2
Jintao Zhang
9 months ago
6fb72d6
fix cuda launch error on devices < sm89
whx1003
11 months ago
bfd980b
Merge pull request #62 from t0saki/main
Jintao Zhang
11 months ago
d097a13
Modify CogVideoX model path in inference example
jt-zhang
11 months ago
c01e14e
Please use `spas_sage2_attn_meansim_topk_cuda` and `block_sparse_sage2_attn_cuda` APIs
Jintao Zhang
11 months ago
9906f67
fix sm90 pad_size
whx1003
11 months ago
01c4b48
Please use `spas_sage2_attn_meansim_topk_cuda` and `block_sparse_sage2_attn_cuda` APIs
Jintao Zhang
11 months ago
2e6e89e
Please use `spas_sage2_attn_meansim_topk_cuda` and `block_sparse_sage2_attn_cuda` APIs
Jintao Zhang
11 months ago
62532ec
Please use `spas_sage2_attn_meansim_topk_cuda` and `block_sparse_sage2_attn_cuda` API
Jintao Zhang
11 months ago
baf8739