vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
Installation
To install this package, run one of the following:
Usage Tracking
0.10.2
0.10.1
0.10.0
0.9.2
0.8.3
5 / 8 versions selected
Downloads (Last 6 months): 0
Description
Easy, fast, and cheap LLM serving for everyone
About
Summary
A high-throughput and memory-efficient inference and serving engine for LLMs
Last Updated
Jan 11, 2026 at 10:24
License
Apache-2.0 AND BSD-3-Clause
Total Downloads
17.0K
Supported Platforms
linux-64
linux-aarch64
macOS-arm64
Documentation
https://vllm.readthedocs.io/en/latest/