
vLLM
High-throughput LLM inference and serving engine
vLLM is an open-source library for fast LLM serving with PagedAttention, continuous batching and an OpenAI-compatible server.
vLLM compared with similar tools
| Product | Price | Open source | Self-host | Platforms |
|---|---|---|---|---|
| vLLM | Free | Yes | Yes | Linux, Self-hosted |
| LiteLLM | Free plan | Yes | Yes | Self-hosted, API |
| llama.cpp | Free | Yes | Yes | Mac, Windows, Linux |
| LocalAI | Free | Yes | Yes | Self-hosted, Linux, Mac |
| Ollama | Free plan | – | Yes | Mac, Windows, Linux |
| Open WebUI | Free plan | Yes | Yes | Self-hosted, Web |
| Dify | Free plan | Yes | Yes | Web, Self-hosted |
Similar to vLLM
Open WebUI
Self-hosted chat interface for local and cloud LLMs
Open WebUI is an extensible web UI for Ollama and OpenAI-compatible APIs with RAG, multi-user accounts and tools.
Free plan · Self-hosted, Web · Website ↗
Questions
Is vLLM free?
vLLM is free.
Is vLLM open source?
Yes, vLLM is open source.
Can vLLM be self-hosted?
Yes, you can run vLLM on your own server.
What platforms does vLLM run on?
vLLM is available for Linux, Self-hosted.
What are some alternatives to vLLM?
Similar indie products include LiteLLM, llama.cpp, LocalAI, Ollama and 4 more.
Is this your product? Submit an update.