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 79 products in the Inference APIs category. View all vLLM alternatives.
IONOS AI Model Hub
OpenAI-compatible API for open-weight LLMs and image models, hosted in IONOS EU data centers
Opper
EU-hosted AI gateway serving 300+ models through one OpenAI-compatible API
CheapestInference
Flat-rate unlimited inference on open-weight models, sold in daily 8-hour windows
Lyceum
EU-hosted inference cloud for open-source models, OpenAI-compatible
Also listed in
Work on vLLM? Feature it at the top of Inference APIs.
Is your product missing?