vllm-project/vllm

vLLM

High-throughput LLM serving.

Open sourceActiveAn ops project

“A high-throughput and memory-efficient inference and serving engine for LLMs” — from the project

The license, in plain English

License
Apache 2.0 · OSI-approved
Use it at work?
Yes — use it anywhere, including in commercial products.
Share your changes?
No. Keep the copyright notice and you’re done.

Our reading, not legal advice — the repository’s LICENSE file is the source of truth.

Alternatives