spatten
[HPCA'21] SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning
mit-han-lab/spatten
View on GitHub ↗[HPCA'21] SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning
spatten grew +0.7% in the last 30 days, ranks 218th of 303 in Inference Optimization, last commit 788 days ago.
Star trajectory
115 days tracked2026-07-02142 stars today2026-10-25
Momentum
+0.7% in 30d, below the Inference Optimization median of +1.5%.
Maintenance
Last commit 788 days ago, staler than the median of 15d.
How it compares in Inference Optimization
spatten
142
stars
+0.7% 30d
commit 788 days ago
Inference Optimization median
257
stars
+1.5% 30d
commit ~15d ago
Leader · supertonic
13.8k
stars
-0.2% 30d
commit 45 days ago
Ranked 218th of 303 by stars.
- Language
- Scala
- License
- MIT License
- Contributors
- 1
- Forks
- 12
- Watchers
- 7
- Open issues
- 2
- Releases
- 0
- Created
- 2023-10-28
- Stars this week
- +0
You've seen where spatten stands today.
Get the moves before everyone else: the 5 Inference Optimization repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.