Run a lightweight version of a language model for fast text generation and processing.
From the README
pip install git+https://github.com/GeeeekExplorer/nano-vllm.git
- 🚀 Fast offline inference - Comparable inference speeds to vLLM
- 📖 Readable codebase - Clean implementation in ~ 1,200 lines of Python code
- ⚡ Optimization Suite - Prefix caching, Tensor Parallelism, Torch compilation, CUDA graph, etc.
Excerpts from the project README on GitHub. Copyright and licensing remain with the respective authors.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeNano vLLM
nano-vllm has 15.2k stars on GitHub. It has been forked 2.5k times. nano-vllm is written mainly in Python. It has been in active development since 2025. nano-vllm is available under the MIT license. Its main topics are deep-learning, inference, llm, nlp.
What is nano-vllm?
Nano vLLM
Is nano-vllm open source?
nano-vllm is an open-source project. It is released under the MIT license.
Is nano-vllm free?
Yes. nano-vllm is free and open source — you can use, modify and self-host it.
What license does nano-vllm use?
nano-vllm is available under the MIT license.
What language is nano-vllm written in?
nano-vllm is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/geeeekexplorer-nano-vllm.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.