FlexGen
Running large language models on a single GPU for throughput-oriented scenarios.
FMInference/FlexGen
View on GitHub ↗Running large language models on a single GPU for throughput-oriented scenarios.
FlexGen grew -0.0% in the last 30 days, ranks 9th of 92 in Distributed Inference, last commit 725 days ago.
Star trajectory
120 days tracked2026-06-259.3k stars today2026-10-23
Momentum
-0.0% in 30d, below the Distributed Inference median of +1.4%.
Maintenance
Last commit 725 days ago, staler than the median of 7d.
How it compares in Distributed Inference
FlexGen
9.3k
stars
-0.0% 30d
commit 725 days ago
Distributed Inference median
415.5
stars
+1.4% 30d
commit ~7d ago
Leader · exo
48k
stars
+0.8% 30d
commit 9 days ago
Ranked 9th of 92 by stars.
- Language
- Python
- License
- Apache License 2.0
- Contributors
- 19
- Forks
- 588
- Watchers
- 11
- Open issues
- 52
- Releases
- 0
- Created
- 2023-02-15
- Stars this week
- -1
You've seen where FlexGen stands today.
Get the moves before everyone else: the 5 Distributed Inference repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.