vLLM
High-throughput LLM inference engine with PagedAttention for efficient GPU memory usage
vLLM is an open-source inference and serving engine for Large Language Models, originally developed at UC Berkeley. It uses PagedAttention to manage GPU memory efficiently, achieving up to 24x higher throughput compared to Hugging Face Transformers. It supports most popular open-source models including Llama, Mixtral, DeepSeek, and multimodal models like LLaVA. vLLM includes both a fast inference engine and a production-ready OpenAI-compatible serving server, making it a popular choice for self-hosted LLM deployments.
Pricing: Free
vLLM Alternatives
Explore 25 products in the Frameworks & Stacks category. View all vLLM alternatives.
GPT4All
Desktop app and Python SDK for running open-source LLMs locally on any device
Jan
Open-source desktop app for running LLMs locally with a clean GUI
llama.cpp
LLM inference in C/C++ with broad hardware support and aggressive quantization
Google ADK
Open-source agent development kit from Google for building multi-agent systems
Also listed in
Is your product missing?