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 | 75 |
| Last Release Name | v0.10.1.1 (Posted on ) |
| First Release Name | submission (Posted on ) |
| Created At | 2023-02-09 11:23:20 |
| Pushed At | 2025-08-22 10:07:24 |
| Last Commit At | |
| Stargazers Count | 56020 |
| Watchers Count | 430 |
| Fork Count | 9572 |
| Commits Count | 8803 |
| Has Issues Enabled | |
| Issues Count | 10336 |
| Issue Open Count | 1804 |
| Pull Requests Count | 8723 |
| Pull Requests Open Count | 1011 |
| Pull Requests Close Count | 2717 |
| Has Wiki Enabled | |
| Is Archived | |
| Is Fork | |
| Is Locked | |
| Is Mirror | |
| Is Private |
