PygmalionAI's large-scale inference engine
pygmalion.chat

It is designed to serve as the inference endpoint for the PygmalionAI website, and to allow serving the Pygmalion models to a large number of users with blazing fast speeds (thanks to vLLM's Paged Attention).

AlpinDale a409431c40 feat: draft for cuda kernels 1 year ago
aphrodite a409431c40 feat: draft for cuda kernels 1 year ago
assets fefbf029c9 revert previous commit 1 year ago
kernels a409431c40 feat: draft for cuda kernels 1 year ago
.gitignore b6804de3c7 chore: add pycache to gitignore 1 year ago
LICENSE fefbf029c9 revert previous commit 1 year ago
README.md fefbf029c9 revert previous commit 1 year ago
requirements.txt fefbf029c9 revert previous commit 1 year ago

README.md

Aphrodite - The Pygmalion Backend

Work in Progress

aphrodite

Aphrodite is the backend service for PygmalionAI, built on top of FastChat, vLLM, SkyPilot, and more.

Currently a work in progress, not remotely functional.