vllm
v0.33.0rc3A high-throughput and memory-efficient inference and serving engine for LLMs
- Maintenance
- Active11334 commits in 3 months · bus factor 14
- License
- Apache-2.0Permissive · OSI-approved
- Security
- 30 advisories7 high, 22 medium, 1 low
- Supported versions
- No scheduleendoflife.date does not track this project
97k stars · 24.8k forks · 10.4k open issues · last release 13 days ago · data checked 4 hours ago
Tour
Nobody has run vllm for a tour yet. A tour starts the project in a container, walks through it in a browser and records each step with a screenshot.