About
A high-throughput and memory-efficient inference and serving engine for LLMs
https://vllm.readthedocs.io
Apache License 2.0
Languages
Language:Python 80.4%Language:Cuda 14.0%Language:C++ 3.9%Language:CMake 0.8%Language:Shell 0.5%Language:Dockerfile 0.2%Language:C 0.1%Language:Jinja 0.1%