rigl
End-to-end training of sparse deep neural networks with little-to-no performance loss.
google-research/rigl
View on GitHub ↗End-to-end training of sparse deep neural networks with little-to-no performance loss.
rigl grew +0.6% in the last 30 days, ranks 50th of 103 in Pretraining & Training, last commit 1,367 days ago.
Star trajectory
115 days tracked2026-07-02340 stars today2026-10-25
Momentum
+0.6% in 30d, above the Pretraining & Training median of +0.0%.
Maintenance
Last commit 1,367 days ago, staler than the median of 163d.
How it compares in Pretraining & Training
rigl
340
stars
+0.6% 30d
commit 1,367 days ago
Pretraining & Training median
316
stars
+0.0% 30d
commit ~163d ago
Leader · maxtext
2.4k
stars
+0.9% 30d
commit today
Ranked 50th of 103 by stars.
- Language
- Python
- License
- Apache License 2.0
- Contributors
- 14
- Forks
- 50
- Watchers
- 14
- Open issues
- 0
- Releases
- 0
- Created
- 2019-11-25
- Stars this week
- +2
You've seen where rigl stands today.
Get the moves before everyone else: the 5 Pretraining & Training repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.