Llaminar documentation

Llaminar runs language models on CPUs, NVIDIA GPUs, AMD GPUs, and combinations of them across one or more machines.

This documentation site is just getting started. For installation and serving examples, use the Quickstart on GitHub.

Releases and test results

The release archive contains release notes, HTTP end-to-end test certificates, and benchmark certificates for both the AVX512 and AVX2 images. Each release page links to the exact image digests and downloadable reports behind its results.

New releases appear here automatically after publication. General user guides will follow.