vLLM
Project record
Maintained by PyTorch Foundation (hosted project)78, vLLM core maintainers (project Technical Steering Committee)4
vLLM is an open-source inference and serving engine for large language models, originally built around the PagedAttention memory-management technique. It was developed in UC Berkeley's Sky Computing Lab, and UC Berkeley contributed it to the PyTorch Foundation in 2025.27
- Repository: Repository (external site: github.com)
- Documentation: Documentation (external site: docs.vllm.ai)
- License: LICENSE (external site: github.com)
- Release notes: Releases (external site: github.com)
Availability and license
Public materials checklist
| Item | Status | Notes and evidence |
|---|---|---|
| Source codeIs the source code publicly readable? | Public | 1 |
| DocumentationIs user documentation published? | Public | 5 |
| InstallationAre installation instructions or packages publicly available? | Public | Installation guides are published per hardware platform.5 |
| Supported platformsAre supported operating systems or hardware documented? | Public | Installation docs cover NVIDIA CUDA, AMD ROCm, and Intel XPU GPUs, x86, ARM AArch64, Apple silicon, and IBM Z CPUs. Other accelerators are supported through out-of-tree hardware plugins.5 |
| Release statusAre versioned releases published? | Public | Versioned releases are published on GitHub.6 |
What it is useful for
Serving language and multimodal models through an OpenAI-compatible API server, including distributed inference across multiple accelerators.2
Organization context
U.S. eligibility
Eligible · basis: U.S.-governed project
vLLM is a PyTorch Foundation-hosted project, contributed by the University of California, Berkeley. Per the Foundation, hosted projects are governed and administered under its governance model. The PyTorch Foundation is hosted by the Linux Foundation, whose privacy policy gives a contact mailing address in San Francisco, California. vLLM's governance document says its core maintainers serve as the Technical Steering Committee under Linux Foundation project governance, and that committer status belongs to individuals, not companies.7894
Sources
This listing is not an endorsement, a safety assessment, or a federal approval.