vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
vllm-project/vllm
View on GitHub ↗A high-throughput and memory-efficient inference and serving engine for LLMs
vllm grew +2.9% in the last 30 days, ranks 1st of 318 in Production Serving & Deployment, actively maintained, last commit today.
Star trajectory
121 days tracked2026-06-2595.3k stars today2026-10-24
Momentum
+2.9% in 30d, above the Production Serving & Deployment median of +1.1%.
Maintenance
Last commit today, fresher than the median of 3.5d.
How it compares in Production Serving & Deployment
vllm
95.3k
stars
+2.9% 30d
commit today
Production Serving & Deployment median
317
stars
+1.1% 30d
commit ~3.5d ago
Category leader
95.3k
stars
- 30d
you lead
Ranked 1st of 318 by stars.
- Language
- Python
- License
- Apache License 2.0
- Contributors
- 3,867
- Forks
- 23.9k
- Watchers
- 612
- Open issues
- 2.7k
- Releases
- 108
- Created
- 2023-02-09
- Stars this week
- +1.3k
You've seen where vllm stands today.
Get the moves before everyone else: the 5 Production Serving & Deployment repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.