vllm-project/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

94.0k

Stars

23.5k

Forks

80.2

Radar Score

Rising

Momentum

Star History

Sep 25 → Oct 17

92.7k ★+1.3k in period94.0k ★

Radar Score History

Aug 21 → Oct 17

80.9now 80.2

Scoring Breakdown

Impact99.5

Velocity71.6

Health61.1

Growth Metrics

7-Day Stars

+540

30-Day Stars

+1.3k

Acceleration

1.27x

Language

Python

Why it ranks

Exceptional momentum — gaining stars far faster than almost everything else tracked.

LLM Frameworks · inference engineTop 2% globally+540 stars / 7d+1.3k stars / 30d

Trend signal: Strong momentum with 540 new stars this week. Above-average growth velocity. High developer adoption with 319 new forks this week. Active in the LLM Frameworks category.

View on GitHub