← Back to rankings
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
⭐ 85,562
Stars
19,051
Forks
1,958
Open Issues
72.5
Velocity Score
Language: Python
License: Apache-2.0
Last commit: about 2 hours ago
Score Breakdown
40.0
Recency (40%)
9.8
Health (10%)
19.7
Authority (20%)
3.0
Cross-list (30%)
72.5