Home

Aphrodite Engine

Caution

This wiki is deprecated. Please refer to the official documentation website instead!

Aphrodite Engine is designed for serving LLMs at scale, based on vLLM. It supports the majority of HuggingFace models, including Llama, Mistral, and Mixtral.

Aphrodite also supports multiple weight quantization methods for not-at-scale (and at-scale!) use-cases. Please see this page for details.