vLLM
一种高吞吐量且内存高效的推理与服务引擎，专为大型语言模型（LLMs）设计。「A high-throughput and memory-efficient inference and serving engine for LLMs」
Main metrics
Overview
| Name With Owner | vllm-project/vllm |
|---|---|
| Primary Language | Python |
| Program language | (Language Count: 8) |
| Platform | |
| License: | Apache License 2.0 |
| Release Count | 87 |
| Last Release Name | v0.11.0rc6 (Posted on ) |
| First Release Name | submission (Posted on ) |
| Created At | 2023-02-09 11:23:20 |
| Pushed At | 2025-10-03 11:29:45 |
| Last Commit At | |
| Stargazers Count | 59377 |
| Watchers Count | 440 |
| Fork Count | 10502 |
| Commits Count | 10099 |
| Has Issues Enabled | |
| Issues Count | 11131 |
| Issue Open Count | 1868 |
| Pull Requests Count | 10022 |
| Pull Requests Open Count | 1170 |
| Pull Requests Close Count | 3195 |
| Has Wiki Enabled | |
| Is Archived | |
| Is Fork | |
| Is Locked | |
| Is Mirror | |
| Is Private |
