Capabilities and tasks
Fast inference serving for large language models
Publisher source ↗vLLM
Fast inference serving for large language models
CodingCompany overview
Fast inference serving for large language models
- Maintainer
- vLLM projectOfficial source ↗
- Original author(s)
- Woosuk Kwon and original paper contributorsOfficial source ↗
- Project since
- 2023Official source ↗
- Listed?
- N/A
Free use
Free on your own device; hardware required
Publisher source ↗Official pricing
Local software free; cloud billed separately
Publisher source ↗Models and capabilities
Serving compatible large language models
Publisher source ↗Countries, regions and access
Self-hosted / local software; cloud and model rules separate
Publisher source ↗Commercial rights
The publisher software license has conditions. Model and cloud-service rights are separate.
Publisher source ↗Payment methods
- No software payment for the self-hosted/open-source editionPublisher source ↗
- Cloud hosting, compute and model API costs are billed separatelyPublisher source ↗
Developer API pricing and web plans
Self-hosted core has no vendor fee per request; GPU, hosting and connected model APIs cost separately.
Web or product subscription (not an API-call fee)
Local software free; cloud billed separately
Publisher source ↗