What is vLLM?
vLLM is an open-source engine for serving large language models with high throughput and efficient memory use. It supports many open models across different hardware, uses PagedAttention and continuous batching, and offers an OpenAI-compatible API for developers and teams deploying models.
Key facts
- Pricing
- Open source
- Category
- Coding
- Website
- https://vllm.ai/
- Listing updated
- Nov 11, 2026
vLLM FAQ
What is vLLM?
vLLM is an open-source engine for serving large language models with high throughput and efficient memory use. It supports many open models across different hardware, uses PagedAttention and continuous batching, and offers an OpenAI-compatible API for developers and teams deploying models.
What does vLLM cost?
vLLM pricing is listed as Open source.