GitHub repository
vllm-project/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Repository metrics
- Stars · Nov 15, 2026
- 96,938
- Stars · Oct 18, 2026
- 94,007
- Stars change
- +2,931
- Current rank
- 154
- Previous rank
- 157
- Rank change
- +3
Language PythonForks 13,515gptllmpytorchmodel-servingtransformerllm-servinginferencellama
Source: GitHubLB snapshots.